CN118469268B - Digital factory consumable management system and method - Google Patents
Digital factory consumable management system and method Download PDFInfo
- Publication number
- CN118469268B CN118469268B CN202410944237.9A CN202410944237A CN118469268B CN 118469268 B CN118469268 B CN 118469268B CN 202410944237 A CN202410944237 A CN 202410944237A CN 118469268 B CN118469268 B CN 118469268B
- Authority
- CN
- China
- Prior art keywords
- numerical control
- cutter
- production
- tool
- control tool
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims description 42
- 238000004519 manufacturing process Methods 0.000 claims abstract description 99
- 238000012423 maintenance Methods 0.000 claims abstract description 49
- 238000007726 management method Methods 0.000 claims abstract description 31
- 238000012544 monitoring process Methods 0.000 claims abstract description 28
- 238000013531 bayesian neural network Methods 0.000 claims abstract description 17
- 238000005520 cutting process Methods 0.000 claims description 46
- 230000002159 abnormal effect Effects 0.000 claims description 26
- 238000012216 screening Methods 0.000 claims description 16
- 238000005299 abrasion Methods 0.000 claims description 14
- 230000006978 adaptation Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 abstract description 13
- 239000002699 waste material Substances 0.000 abstract description 7
- 230000009467 reduction Effects 0.000 abstract description 3
- 230000008439 repair process Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 27
- 238000013528 artificial neural network Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 15
- 238000012549 training Methods 0.000 description 15
- 238000010606 normalization Methods 0.000 description 12
- 210000002569 neuron Anatomy 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000005284 excitation Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013077 scoring method Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000003801 milling Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Automation & Control Theory (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Fuzzy Systems (AREA)
- Computational Mathematics (AREA)
- Manufacturing & Machinery (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Probability & Statistics with Applications (AREA)
Abstract
The invention discloses a digital factory consumable management system and a digital factory consumable management method, which particularly relate to the technical field of digital cutter management, wherein a multi-sensor is arranged on a digital machine tool to monitor the use state of the digital cutter in real time, a fuzzy Bayesian neural network model constructed according to monitoring data predicts the replacement time point of the digital cutter, so that more accurate cutter replacement time prediction is provided, resource waste and production efficiency reduction caused by too early or too late replacement of the cutter are avoided, when a cutter replacement prompt signal is generated, the completion degree of a current production link and state information of an inventory cutter are combined, the optimal digital cutter is intelligently selected for replacement, the optimal allocation and utilization of digital cutter resources are realized, continuous interruption of production is avoided, the replaced digital cutter is scanned and put in storage in an image mode, and the maintenance sequence of the cutter is determined according to scanned image information and the importance degree of the digital cutter, so that the maintenance and repair flow of the cutter is optimized.
Description
Technical Field
The invention relates to the technical field of numerical control tool management, in particular to a consumable management system and method for a digital factory.
Background
Digital factory consumable management refers to a process of managing consumables (e.g., raw materials, parts, tools, etc.) within a factory using digital technology and an informatization system. The management method generally relates to technologies such as Internet of things (sensor equipment), big data analysis, artificial intelligence and the like to achieve targets such as real-time monitoring, inventory optimization, supply chain coordination, predictive maintenance and the like of consumable materials, wherein numerical control tool management is an important component part in a consumable management system of a digital factory, and the main purpose of the management method is to effectively manage various numerical control tools used by the factory so as to ensure full utilization, maintenance and update of the numerical control tools in the production process.
At present, when obvious faults occur to numerical control cutters in management of the numerical control cutters which are in production operation, a worker performs cutter replacement operation, when obvious faults occur to the numerical control cutters and then replacement is performed, extra production stopping time is increased, and because the worker cannot adapt the state (wear degree and the like) of stock cutters to the corresponding production link completion degree, if the cutter with the lower wear degree is replaced in the higher production completion degree, occupation and waste of cutter resources can be caused, and if the cutter with the lower wear degree is replaced in the lower production completion degree, the numerical control cutters can be replaced frequently, so that continuous production interruption can be caused.
In order to solve the above-mentioned defect, a technical scheme is provided.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks of the prior art, embodiments of the present invention provide a digital factory consumable management system and method, so as to solve the above-mentioned problems in the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
A digital factory consumable management method comprises the following steps:
Step S1, installing multiple sensors on a numerical control machine tool, and monitoring the use state of the numerical control tool in real time and storing monitoring data in a database;
S2, calling the use state data of the numerical control tool from a database, constructing a fuzzy Bayesian neural network model according to the use state data of the numerical control tool, predicting the replacement time point of the numerical control tool, and generating a replacement prompt signal of the numerical control tool at the replacement time point;
Step S3, when a replacement prompt signal of the numerical control cutter is generated, selecting the optimal stock cutter to replace by combining the production completion degree of the current link and the state information of the stock cutter;
And S4, performing image scanning on the replaced numerical control tool, and determining the maintenance sequence of the numerical control tool according to the scanned image information and the importance degree of the numerical control tool.
In a preferred embodiment, in step S2, a fuzzy bayesian neural network model is constructed according to the usage status data of the numerical control tool to predict the replacement time point of the numerical control tool, and the method further includes the steps of:
step S201, obtaining sample data to determine input and output variables;
Acquiring various data of temperature, vibration and current of the numerical control tool during working, wherein the data are used as input variables, and the replacement time of the numerical control tool is used as output variables;
step S202, establishing a fuzzy Bayesian neural network model;
Step S203, the trained model is applied to predict the numerical control tool in real time when the actual working time of the numerical control tool is greater than or equal to the predicted numerical control tool replacement time point, and a numerical control tool replacement prompt signal is generated.
In a preferred embodiment, in step S3, when the replacement prompt signal of the numerical control tool is generated, the production completion degree of the current link is quantified by the link completion progress value in combination with the state information of the stock tool including the tool edge wear ratio, the cutting speed deviation abnormality coefficient, and the average adaptation completion degree.
In a preferred embodiment, an inventory cutter screening model is built according to the link completion progress value, the cutter edge wear ratio, the cutting speed deviation abnormal coefficient and the average adaptation completion degree, and the inventory cutter screening index is obtained by weighted summation calculation；
Screening existing stock knives according to the stock knife screening model and obtaining the best stock knife adapted to the current production completion, best stock knife = max (ZU).
In a preferred embodiment, in step S4, the replaced nc tool is scanned in an image, and the maintenance sequence of the nc tool is determined according to scanned image information and the importance level of the nc tool, wherein the image information includes the tool edge moire duty ratio, and the importance level of the nc tool is quantified by the number of production links.
In a preferred embodiment, a numerical control cutter maintenance model is established according to the cutter edge different grain ratio and the number of production links, and the numerical control cutter maintenance coefficient is obtained through weighted summation calculation;
And evaluating the same batch of replaced numerical control cutters according to the numerical control cutter maintenance model, sequencing the numerical control cutters from large to small according to the numerical control cutter maintenance coefficient generated by each numerical control cutter, generating a numerical control cutter maintenance table, and determining the maintenance sequence of the numerical control cutters.
In a preferred embodiment, a consumable management system of a digital factory comprises a digital control cutter monitoring module, a data prediction module, a replacement decision module and a maintenance management module, wherein signal connection exists among the modules;
the numerical control tool monitoring module is used for installing a plurality of sensors on the numerical control machine tool, monitoring the use state of the numerical control tool in real time and storing monitoring data in a database;
The data prediction module is used for retrieving the use state data of the numerical control tool from the database, constructing a fuzzy Bayesian neural network model according to the use state data of the numerical control tool, predicting the replacement time point of the numerical control tool, and generating a replacement prompt signal of the numerical control tool at the replacement time point;
The replacement decision module is used for selecting the optimal stock cutter to replace by combining the production completion degree of the current link and the state information of the stock cutter when a replacement prompt signal of the numerical control cutter is generated;
and the maintenance management module is used for carrying out image scanning on the replaced numerical control cutter and determining the maintenance sequence of the numerical control cutter according to the scanned image information and the importance degree of the numerical control cutter.
The invention has the technical effects and advantages that:
1. According to the invention, the use state of the numerical control tool is monitored in real time by installing the multiple sensors on the numerical control machine tool, and the replacement time point of the numerical control tool is predicted according to the fuzzy Bayesian neural network model constructed by the monitoring data, so that more accurate tool replacement time prediction is provided. The method has the advantages that the method can guide the tool replacement decision of a production site more effectively, avoid the resource waste and the production efficiency reduction caused by too early or too late tool replacement, intelligently select the optimal numerical control tool to replace by combining the completion degree of the current production link and the state information of the stock tools when the tool replacement prompt signal is generated, improve the production efficiency, realize the optimal allocation and utilization of the numerical control tool resources, reduce the resource waste, carry out image scanning and warehousing on the replaced numerical control tool, determine the maintenance sequence of the tool according to the scanned image information and the importance degree of the numerical control tool, optimize the maintenance and repair flow of the tool, prolong the service life of the tool and reduce the maintenance cost.
Drawings
For the convenience of those skilled in the art, the present invention will be further described with reference to the accompanying drawings;
FIG. 1 is a schematic diagram of the method of embodiment 1 of the present invention;
fig. 2 is a schematic diagram of the system in embodiment 2 of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
FIG. 1 shows a method for managing consumable parts in a digital factory, which comprises the following steps:
Step S1, installing multiple sensors on a numerical control machine tool, and monitoring the use state of the numerical control tool in real time and storing monitoring data in a database;
S2, calling the use state data of the numerical control tool from a database, constructing a fuzzy Bayesian neural network model according to the use state data of the numerical control tool, predicting the replacement time point of the numerical control tool, and generating a replacement prompt signal of the numerical control tool at the replacement time point;
Step S3, when a replacement prompt signal of the numerical control cutter is generated, selecting the optimal stock cutter to replace by combining the production completion degree of the current link and the state information of the stock cutter;
S4, performing image scanning on the replaced numerical control tool, and determining the maintenance sequence of the numerical control tool according to scanned image information and the importance degree of the numerical control tool;
In step S1, firstly, a plurality of sensors are installed on the numerically controlled machine tool, wherein the sensors are arranged and installed according to the monitoring requirement and are used for monitoring the use state of the numerically controlled tool in real time, the types of the sensors include, but are not limited to, temperature sensors, vibration sensors, current sensors and the like, and each sensor has a specific monitoring function as follows:
Temperature sensor: monitoring the temperature change of the numerical control tool in the working process, wherein the abnormal temperature change can indicate the problems of abrasion, abnormal processing conditions and the like of the numerical control tool;
vibration sensor: monitoring vibration change conditions of the numerical control tool during working, wherein abnormal vibration change can represent uneven abrasion or unstable processing conditions of the numerical control tool;
a current sensor: measuring the current consumption condition of the numerical control tool during working, wherein abnormal current change can indicate the increase of friction between the numerical control tool and a workpiece or the increase of abrasion of the numerical control tool;
the monitoring of the sensor is used for collecting all working state data of the numerical control cutter in real time, wherein the working state data comprise temperature, vibration and current data in working, and the data of all the monitored working states are transmitted to a database for storage after being collected;
step S2, the use state data of the numerical control tool is called from a database, a fuzzy Bayesian neural network model is constructed according to the use state data of the numerical control tool to predict the replacement time point of the numerical control tool, and the method further comprises the following steps:
step S201, obtaining sample data to determine input and output variables;
Acquiring various data of temperature, vibration and current of the numerical control tool during working, wherein the data are used as input variables, and the replacement time of the numerical control tool is used as output variables;
It should be noted that, the replacement time point of the nc tool may be obtained by subtracting the time point of the obvious fault of the nc tool from the pre-time threshold range, where the pre-time threshold range is set by those skilled in the art comprehensively considering the actual production requirement, the time spent by the staff to replace the nc tool, and the screening time of the nc tool.
Sample data acquisition is carried out on the data detected by the sensor, wherein the sample data acquisition is historical monitoring data of one year in a database and comprises 365 groups of sample data;
Eighty percent of the collected sample data was used as training data and twenty percent was used as test sample data.
In order to avoid overlarge neural network errors and prevent local neurons from reaching an oversaturated state, carrying out normalization processing on sample data so that the sample data are between 0 and 1, and obtaining an original output value by adopting inverse normalization processing on network output vectors; the normalization formula of the sample data is as followsIn which, in the process,For the normalized sample data,As the ratio of the original sample data to the minimum value of the original sample data,The ratio of the maximum value of the original sample data to the minimum value of the original sample data is set;
obtaining a training sample set through normalization processing, namely WhereinThe data of the temperature is represented and,The vibration data is represented as such,The current data is represented by a graph of the current,Indicating a replacement time point of the numerical control tool, wherein n is n=365 which is 365 groups of data acquired;
step S202, establishing a fuzzy Bayesian neural network model;
The neural network model for predicting the numerical control tool replacement time point consists of an input layer, an hidden layer and an output layer; the input layer consists of temperature data, vibration data and current data 1 group data, 15 neuron nodes are all arranged, and the hidden layer is determined by an empirical formula; the output layer is used for controlling the replacement time point of the cutter as a prediction result; the hidden layer is determined by an empirical formula, which is Wherein G is the number of neurons of the hidden layer, h is the number of neurons input by the input layer, m is the number of neurons output by the output layer, a is an empirical parameter, usually an adjustment factor or constant, used for finely adjusting the number of nodes of the hidden layer on the basis of an empirical formula, and the value range of a is a constant between 1 and 10;
Establishing the fuzzy Bayesian neural network prediction model, and determining an excitation function, a training function, a learning function and a neural network performance index of the model; excitation function selection sigmod functions, i.e. The training function selects trainlm functions, the learning function selects Bayes functions, and the neural network performance index is: Where n is the number of samples, i.e., 365 sets of sample data collected, The input vector is represented as such,The weight component is represented by a number of components,The desired output target value, i= {1,2, 3..n }.
The pre-training process comprises the following steps: setting a training target and training step number through a pre-training function trainlm, training error precision, and selecting the optimal hidden layer neuron number according to the result;
creating a forward neural network:
net= newff (PR, [ S1, S2..sn 1], { TF1, tf2..tfn 1}, BTF, BLF, PF) wherein the vector elements range from 1 to N1; net is the creation of a new neural network; PR is a matrix formed by the maximum value and the minimum value of network input elements; [ S1, S2..SN 1] represents the number of neurons of the hidden layer and the output layer of the network; { TF1, tf2..tfn1 } represents the hidden layer and output layer excitation functions, sigmod functions; the BTF is a training function of the network and is trainlm functions; BLF is a weight learning function of the network and is a Bayesian function; PF is a performance function, defaulting to a "mse" function;
Creating a set of neural network weights: the set of weights affecting the computational accuracy and generalization ability of the neural network is denoted by ω, i.e Wherein, the method comprises the steps of, wherein,Representing weight components, n is the acquired 365 sets of data, i.e., n=365;
Creating a weight judgment set: and (3) fuzzifying the weight of the neural network by adopting an improved expert scoring method, scoring the neural network without communication by the expert, sorting the scoring results from large to small, negotiating by the expert from head to tail, scoring again, reordering, and the like until scoring is finished. The evaluation set being denoted by V, i.e Wherein, the method comprises the steps of, wherein,The importance degree of the weight component is represented, and n is acquired 365 groups of data, namely n=365;
expert scoring: blurring the weight of the neural network by adopting an expert scoring method;
defuzzification: deblurring by adopting a weighted average method to obtain the prior probability of the weight of the neural network, wherein the formula is In which, in the process,Representing the prior probability of the weights of the neural network,The number of the judges is indicated,Indicating that the judge makes possible judging results, n is acquired 365 groups of data, namely n=365;
Determining a likelihood function: assuming a desired output target value Is generated under Gaussian white noise, and likelihood function isWherein, the method comprises the steps of, wherein,As a normalization factor, gamma is a super parameter; Representing an error function; the posterior probability of the weight is determined as (prior probability formula likelihood function)/sample distribution constant, and the specific expression is as follows Where i= (1, 2, 3,) n, j= (1, 2, 3,) n,As a function of the error,P (D) represents a sample distribution constant;
Randomly selecting a training sample set D to learn and train a fuzzy Bayesian neural network prediction model, determining each weight of an input layer, an implicit layer and an output layer by using fuzzy knowledge and Bayesian functions, and judging whether the actual output and the expected output of the output layer meet the performance index requirement of the neural network or not by using training sample data; if the requirement is not met, the number of neurons of an implicit layer is properly changed, the weights of the input layer, the implicit layer and the output layer are determined again by fuzzy knowledge and Bayesian functions, and whether the actual output and the expected output of the output layer meet the performance index requirement of the neural network or not is judged again by training sample data (the specific performance indexes comprise accuracy, recall rate, F1 value and the like); if the requirement is met, finishing training, otherwise continuing training until the performance index requirement of the neural network is met; thus, a trained model is obtained.
Step S203, predicting the numerical control tool which is being produced in real time by applying the trained model, if the actual working time of the numerical control tool is greater than or equal to the predicted numerical control tool replacement time point, generating a numerical control tool replacement prompt signal, and carrying out early warning before obvious faults occur on the numerical control tool to prompt workers to deploy the numerical control tool replacement in advance;
when the replacement prompt signal of the numerical control tool is generated, because the staff' S seniority is different, the state (such as the wear degree, etc.) of the stock tool cannot be adapted to the corresponding production link completion degree, which may cause occupation and waste of tool resources or continuous interruption of production, in step S3, the best stock tool is selected for replacement by combining the production completion degree of the current link and the state information of the stock tool, and the method further comprises the following steps:
The production completion degree refers to the current completion progress of the production link for which the numerical control cutter needs to be replaced is responsible, and the production completion degree is calculated by the completion progress value of the link Quantified, its calculation expression is as followsWhereinIndicating the number of workpieces which are finished in the production link and are responsible for the numerical control tool to be replaced,Indicating the total number of work pieces required to be completed in the production link for which the numerical control tool needs to be replaced. The higher the production completion degree, namely the larger the link completion progress value, the numerical control cutter with relatively higher abrasion degree and relatively poorer state should be preferentially considered for replacement, and the lower the production completion degree, namely the smaller the link completion progress value, the numerical control cutter with relatively lower abrasion degree and relatively better state should be preferentially considered for replacement;
It should be noted that, in the process of calculating the link completion progress value, the following steps are performed 、Including but not limited to the number of workpieces, e.g., link completion time, etc.;
state information of stock cutter through cutter edge abrasion duty ratio Coefficient of cutting speed deviation abnormalityAverage adaptation completionTo measure; it should be noted that, the state information of the stock cutter includes, but is not limited to, the cutter edge wear ratio, the cutting speed deviation anomaly coefficient, and the average adaptation completion;
The cutter blade abrasion ratio refers to the ratio between the current cutter blade size and the original standard size of the stock cutter, is used for quantifying the abrasion degree of the cutter blade of the stock, measures the size of the cutter blade of the stock by using a proper measuring tool (such as a micrometer or a microscope), and can measure the width or the thickness of the cutter blade for a straight cutter; for a rotating tool (e.g., milling cutter), the diameter or radius of the cutting edge can be measured, and the original size of the tool can be obtained from a tool specification table, and the wear ratio of the cutting edge of the tool can be calculated by the following expression WhereinIndicating the measured dimensions of the cutting edge of the tool,Representing the original size;
The cutting speed deviation abnormal coefficient is an index for measuring abnormal conditions of the cutting speed of the stock cutter in the historical production task, can be calculated and obtained according to the historical use data of the stock cutter, is used for evaluating the stability and reliability of the stock cutter in the production task and reflecting the state of the stock cutter, and the lower the cutting speed abnormal coefficient is, the better the state of the stock cutter is, and is more suitable for the production task with lower production completion degree;
The acquisition logic of the cutting speed deviation abnormality coefficient is as follows:
Acquiring cutting speed data of the stock cutter in historical production tasks, wherein the cutting speed data comprises a set value of cutting speed in each production task and a measured value of actual cutting speed, calculating a cutting speed deviation value according to the set value and the measured value, and marking the cutting speed deviation value as ; Calculating an average cutting speed deviation value from the cutting speed deviation valueThe expression is as followsWherein p represents the order number of cutting speed deviation values at each production task, p= {1,2,., q }, q being a positive integer; the cutting speed deviation value standard deviation BZ is calculated from the average cutting speed deviation value, expressed as followsThe cutting speed deviation abnormality coefficient is calculated from the average cutting speed deviation value and the standard deviation of the cutting speed deviation value, expressed as follows；
The average adaptation completion is used for measuring the use condition of the stock cutter required to be replaced in the historical production task, and can be calculated and obtained from the use record of the historical production task, and the expression is as follows: wherein A production progress value indicating that the stock cutter can complete from the start of production to the time of failure in the historical production task is expressed as follows，Indicating the number of workpieces that the inventory knife has completed from the start of production to the time of failure in the historical production tasks,Showing the total number of work pieces required to be completed in a production link of an inventory cutter in a historical production task, wherein z represents the sequence number of the production progress value of each production task of the inventory cutter in the historical production task, and z= {1, 2., b }, and b is a positive integer;
screening the inventory cutters according to the current production completion degree and the state information of the inventory cutters, and selecting the optimal inventory cutters suitable for different production completion degrees, wherein the inventory cutters are specifically as follows:
The obtained link completion progress value, cutter edge abrasion ratio, cutting speed deviation abnormal coefficient and average adaptation completion degree are mapped to intervals [0,1] by adopting linear normalization, and the formula is as follows: . In the method, in the process of the invention, For the values after normalization, collectdata is the value of the original data point that needs normalization, minValue is the smallest value in the dataset, and MaxValue is the largest value in the dataset.
It should be noted that, the normalization formula given in this embodiment is a general formula, and the process of normalizing the obtained link completion progress value, the cutter edge wear ratio, the cutting speed deviation abnormal coefficient, and the average adaptation completion degree is consistent with the general formula, which is not related to the data information obtained by the consumable management system of the digital factory, and is not described herein.
Establishing an inventory cutter screening model according to the link completion progress value, the cutter edge abrasion duty ratio, the cutting speed deviation abnormal coefficient and the average adaptation completion degree, and generating an inventory cutter screening index ZU according to the following expressionWhereinRespectively representThe specific numerical value of the weight factor of (2) can be set according to the actual situation;
the weight factor is The method is used for balancing the influence of the abrasion ratio of the cutting edge of the cutter, the deviation of the cutting speed from an abnormal coefficient and the average adaptation completion degree on the selection of the final stock cutter.
Screening existing stock knives according to the stock knife screening model and obtaining the best stock knife adapted to the current production completion, best stock knife = max (ZU).
When the optimal stock cutter is selected, the state of the selected stock cutter is updated, and the selected stock cutter is marked as 'to be claimed', so that the accuracy of stock data is ensured;
Sending a notification to the relevant staff via a communication system (such as an email, an internal message platform, a short message or a broadcast system) inside the factory, wherein the notification contains detailed information (such as type, specification, position and the like) of the stock cutter, and the time limit and the place of the claim, and ensuring that the selected stock cutter is taken out of the stock and placed in a designated claim area before the staff arrives;
When the staff arrives, guiding the staff to complete the claim process, and registering the claim information of the inventory cutter, wherein the claim information comprises the name of the claim, the claim date and the like;
After the success of the claim, the staff performs the replacement operation on the numerical control tool to be replaced, uses the image scanning equipment to scan the replaced numerical control tool in detail, and determines the maintenance sequence of the numerical control tool according to the scanned image information and the importance degree of the numerical control tool, and specifically comprises the following steps:
The image information includes the cutter edge different grain ratio ；
The cutter edge abnormal grain ratio is used for measuring the proportion degree of abnormal grains appearing on the replaced numerical control cutter edge to the whole edge length, and in the numerical control cutter, due to long-time use or improper processing conditions, the cutter edge can appear abnormal grains, and the abnormal grains can influence the performance and service life of the cutter. Therefore, by detecting the duty cycle of the tool edge profile, it is possible to help determine the health status of the tool and the maintenance sequence. The different mark duty ratio of the edge of the cutter can be calculated by the following formulaWhereinThe length of the total abnormal grain is represented,Representing the total length of the tool edge;
It should be noted that the abnormal line detection of the edge of the cutter includes the following steps: preprocessing the image, including denoising, enhancing contrast, sharpening edges and the like, so as to improve the visibility of abnormal lines; and detecting abnormal lines of the numerical control cutter in the image by using an edge detection algorithm, identifying abnormal line areas by checking the characteristics of pixel values, edge continuity, shape, size and the like, and extracting the characteristics of the identified abnormal line areas, namely the lengths of the edge abnormal lines.
The importance degree of the numerical control cutter is calculated by the number of production linksThe number of production links is the number of production links which are responsible for the index control cutter in the whole production task, namely the numerical control cutter possibly takes charge of a plurality of production links in the whole production task, and the more the number of production links which are responsible for the numerical control cutter is, namely the higher the importance degree of the numerical control cutter is, the higher the priority of the maintenance of the numerical control cutter is, and the number of production links which are responsible for the numerical control cutter in the whole production task can be obtained from a production task plan.
Carrying out linear normalization on the obtained different grain duty ratio of the edge of the cutter and the number of production links;
It should be noted that, the linear normalization of the different grain ratio of the edge of the cutter and the number of production links is consistent with the linear normalization method of the completion progress value of the links, the abrasion ratio of the cutting edge of the cutter, the deviation abnormal coefficient of the cutting speed and the average adaptation completion degree, and no description is repeated here;
establishing a numerical control cutter maintenance model according to the different grain occupation ratio of the cutter edge and the number of production links to generate a numerical control cutter maintenance coefficient The expression according to the method is as followsWhereinThe weight factors respectively representing the different grain duty ratio of the edge of the cutter and the number of production links, and the specific numerical value can be set according to the actual situation; evaluating the same batch of replaced numerical control cutters according to a numerical control cutter maintenance model, sequencing the numerical control cutters from large to small according to the numerical control cutter maintenance coefficient generated by each numerical control cutter, generating a numerical control cutter maintenance table, and determining the maintenance sequence of the numerical control cutters;
the numerical control tool maintenance table is characterized in that the higher the numerical control tool is, the higher the maintenance priority is;
the numerical control cutter after maintenance needs to be stored again and warehoused comprises the following steps:
Before storage and warehousing, thoroughly cleaning and checking the maintained numerical control cutter, and removing greasy dirt and sundries on the surface;
Marking the maintained numerical control cutter, and recording related information including the model number, the maintenance date and the like of the cutter, wherein the information is beneficial to subsequent tracing and management;
Placing the maintained numerical control cutter into a warehouse according to a set storage position, and marking each storage position by using a label or a number so as to facilitate subsequent searching and management;
recording the storage information of the maintained numerical control cutter, wherein the storage information comprises the information of the number, the model, the storage date, the storage position and the like of the cutter;
Updating and maintaining the inventory information of the digital cutters according to the recorded digital control cutter warehousing information, and timely updating the inventory quantity and the position information to ensure the accuracy and the instantaneity of the inventory data;
According to the invention, the use state of the numerical control tool is monitored in real time by installing the multiple sensors on the numerical control machine tool, and the replacement time point of the numerical control tool is predicted according to the fuzzy Bayesian neural network model constructed by the monitoring data, so that more accurate tool replacement time prediction is provided. The method has the advantages that the method can guide the tool replacement decision of a production site more effectively, avoid the resource waste and the production efficiency reduction caused by too early or too late tool replacement, intelligently select the optimal numerical control tool to replace by combining the completion degree of the current production link and the state information of the stock tools when the tool replacement prompt signal is generated, improve the production efficiency, realize the optimal allocation and utilization of the numerical control tool resources, reduce the resource waste, carry out image scanning and warehousing on the replaced numerical control tool, determine the maintenance sequence of the tool according to the scanned image information and the importance degree of the numerical control tool, optimize the maintenance and repair flow of the tool, prolong the service life of the tool and reduce the maintenance cost.
Example 2
The embodiment is an introduction to a consumable management system of a digital factory, as shown in fig. 2, which comprises a numerical control cutter monitoring module, a data prediction module, a replacement decision module and a maintenance management module, wherein signal connection exists between the modules;
the numerical control tool monitoring module is used for installing a plurality of sensors on the numerical control machine tool, monitoring the use state of the numerical control tool in real time and storing monitoring data in a database;
The data prediction module is used for retrieving the use state data of the numerical control tool from the database, constructing a fuzzy Bayesian neural network model according to the use state data of the numerical control tool, predicting the replacement time point of the numerical control tool, and generating a replacement prompt signal of the numerical control tool at the replacement time point;
The replacement decision module is used for selecting the optimal stock cutter to replace by combining the production completion degree of the current link and the state information of the stock cutter when a replacement prompt signal of the numerical control cutter is generated;
and the maintenance management module is used for carrying out image scanning on the replaced numerical control cutter and determining the maintenance sequence of the numerical control cutter according to the scanned image information and the importance degree of the numerical control cutter.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the system and method described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems and methods may be implemented in other ways.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (5)
1. A digital factory consumable management method is characterized in that: the method comprises the following steps:
Step S1, installing multiple sensors on a numerical control machine tool, and storing the monitored use state data of the numerical control tool in a database, wherein the multiple sensors are used for monitoring the use state of the numerical control tool in real time;
S2, calling the use state data of the numerical control tool from a database, constructing a fuzzy Bayesian neural network model according to the use state data of the numerical control tool, predicting the replacement time point of the numerical control tool, and generating a replacement prompt signal of the numerical control tool at the replacement time point;
Step S3, when a replacement prompt signal of the numerical control cutter is generated, selecting the optimal stock cutter to replace by combining the production completion degree of the current link and the state information of the stock cutter;
S4, performing image scanning on the replaced numerical control tool, and determining the maintenance sequence of the numerical control tool according to scanned image information and the importance degree of the numerical control tool;
In step S3, the production completion degree refers to the current completion progress of the production link for which the numerical control tool needs to be replaced;
The state information of the stock cutter comprises the abrasion duty ratio of the cutting edge of the cutter Coefficient of cutting speed deviation abnormalityAverage adaptation completion；
The production completion degree is a link completion progress valueQuantified, its calculation expression is as followsWhereinIndicating the number of workpieces which are finished in the production link and are responsible for the numerical control tool to be replaced,Indicating the total number of work pieces required to be completed in the production link for which the numerical control tool needs to be replaced;
according to the progress value of link completion Duty ratio of tool edge wearCoefficient of cutting speed deviation abnormalityAverage adaptation completionEstablishing an inventory cutter screening model, and obtaining an inventory cutter screening index through weighted summation calculation；
The tool edge wear ratio can be calculated by the following expressionWhereinIndicating the measured dimensions of the cutting edge of the tool,Representing the original size;
according to the average cutting speed deviation value Calculating the cutting speed deviation abnormality coefficient from the cutting speed deviation value standard deviation BZThe expression is as follows; Wherein the average cutting speed deviation value is calculated according to the cutting speed deviation valueThe expression is as followsThe cutting speed deviation value is marked asP represents the order number of the cutting speed deviation values at each production task, p= {1,2,., q }, q being a positive integer; the cutting speed deviation value standard deviation BZ is calculated from the average cutting speed deviation value, expressed as follows；
Average adaptation completionThe method is used for measuring the use condition of the stock cutter required to be replaced in the historical production task, and the expression is as follows: wherein A production progress value indicating that the stock cutter can complete from the start of production to the time of failure in the historical production task is expressed as follows，Indicating the number of workpieces that the inventory knife has completed from the start of production to the time of failure in the historical production tasks,The method comprises the steps that the total number of work pieces required to be completed in a production link of an inventory cutter in a historical production task is represented, z represents the sequence number of production progress values of each production task of the inventory cutter in the historical production task, z= {1, 2., b }, and b is a positive integer;
establishing an inventory cutter screening model according to the link completion progress value, the cutter edge abrasion ratio, the cutting speed deviation abnormal coefficient and the average adaptation completion degree, and generating an inventory cutter screening index ZU;
the expression is as follows WhereinRespectively representWeight factors of (2); screening existing stock knives according to the stock knife screening model and obtaining the best stock knife adapted to the current production completion, best stock knife = max (ZU).
2. The digital factory consumable management method according to claim 1, wherein: in step S2, a fuzzy bayesian neural network model is constructed according to the usage state data of the numerical control tool to predict the replacement time point of the numerical control tool, and the method further includes the following steps:
step S201, obtaining sample data to determine input and output variables;
Acquiring various data of temperature, vibration and current of the numerical control tool during working, wherein the data are used as input variables, and the replacement time of the numerical control tool is used as output variables;
step S202, establishing a fuzzy Bayesian neural network model;
Step S203, the trained model is applied to predict the numerical control tool in real time when the actual working time of the numerical control tool is greater than or equal to the predicted numerical control tool replacement time point, and a numerical control tool replacement prompt signal is generated.
3. The digital factory consumable management method according to claim 1, wherein: in step S4, performing image scanning on the replaced numerical control cutter, and determining the maintenance sequence of the numerical control cutter according to scanned image information and the importance degree of the numerical control cutter, wherein the image information comprises the cutter edge different grain duty ratio, and the importance degree of the numerical control cutter is quantized by the number of production links;
The different grain duty ratio of the edge of the cutter is calculated as the expression WhereinThe length of the total abnormal grain is represented,Representing the total length of the tool edge;
the importance degree of the numerical control cutter is calculated by the number of production links Quantitative number of production linksThe number of production links for which the cutter is responsible in the whole production task is controlled by index.
4. A digital factory consumable management method according to claim 3, wherein: according to the different grain duty ratio of the edge of the cutter and the number of production linksEstablishing a numerical control tool maintenance model to generate a numerical control tool maintenance coefficientThe expression is as followsWhereinWeight factors respectively representing the different grain duty ratio of the edge of the cutter and the number of production links;
And evaluating the same batch of replaced numerical control cutters according to the numerical control cutter maintenance model, sequencing the numerical control cutters from large to small according to the numerical control cutter maintenance coefficient generated by each numerical control cutter, generating a numerical control cutter maintenance table, and determining the maintenance sequence of the numerical control cutters.
5. A digital factory consumable management system for implementing a digital factory consumable management method according to any one of claims 1-4, characterized in that: the system comprises a numerical control cutter monitoring module, a data prediction module, a replacement decision module and a maintenance management module, wherein the modules are connected by signals;
the numerical control tool monitoring module is used for installing a plurality of sensors on the numerical control machine tool, monitoring the use state of the numerical control tool in real time and storing monitoring data in a database;
The data prediction module is used for retrieving the use state data of the numerical control tool from the database, constructing a fuzzy Bayesian neural network model according to the use state data of the numerical control tool, predicting the replacement time point of the numerical control tool, and generating a replacement prompt signal of the numerical control tool at the replacement time point;
The replacement decision module is used for selecting the optimal stock cutter to replace by combining the production completion degree of the current link and the state information of the stock cutter when a replacement prompt signal of the numerical control cutter is generated;
and the maintenance management module is used for carrying out image scanning on the replaced numerical control cutter and determining the maintenance sequence of the numerical control cutter according to the scanned image information and the importance degree of the numerical control cutter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410944237.9A CN118469268B (en) | 2024-07-15 | 2024-07-15 | Digital factory consumable management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410944237.9A CN118469268B (en) | 2024-07-15 | 2024-07-15 | Digital factory consumable management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118469268A CN118469268A (en) | 2024-08-09 |
| CN118469268B true CN118469268B (en) | 2024-09-27 |
Family
ID=92168992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410944237.9A Active CN118469268B (en) | 2024-07-15 | 2024-07-15 | Digital factory consumable management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118469268B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111830915A (en) * | 2020-06-10 | 2020-10-27 | 清华大学 | Multi-stage hierarchical automatic cutter selection method and system for numerical control machining system |
| CN114742798A (en) * | 2022-04-13 | 2022-07-12 | 武汉科技大学 | Disc shear tool changing time prediction system and method based on shear blade wear detection |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11179636A (en) * | 1997-12-18 | 1999-07-06 | Toshiba Mach Co Ltd | Replacement timing decision system for tool |
| CN114781081A (en) * | 2022-04-11 | 2022-07-22 | 广东工业大学 | Cutter configuration method considering cutter service life |
| CN115062674B (en) * | 2022-07-28 | 2022-11-22 | 湖南晓光汽车模具有限公司 | Tool arrangement and tool changing method and device based on deep learning and storage medium |
| CN116204774A (en) * | 2022-12-14 | 2023-06-02 | 中国航空工业集团公司金城南京机电液压工程研究中心 | Cutter abrasion stability prediction method based on hierarchical element learning |
-
2024
- 2024-07-15 CN CN202410944237.9A patent/CN118469268B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111830915A (en) * | 2020-06-10 | 2020-10-27 | 清华大学 | Multi-stage hierarchical automatic cutter selection method and system for numerical control machining system |
| CN114742798A (en) * | 2022-04-13 | 2022-07-12 | 武汉科技大学 | Disc shear tool changing time prediction system and method based on shear blade wear detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118469268A (en) | 2024-08-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6356304B2 (en) | Maintenance recommendation system based on maintenance effectiveness estimation | |
| US5251144A (en) | System and method utilizing a real time expert system for tool life prediction and tool wear diagnosis | |
| CN116629577A (en) | Intelligent supply chain management system based on big data | |
| CN118154174B (en) | Intelligent operation and maintenance cloud platform for industrial equipment | |
| CN112200327B (en) | MES equipment maintenance early warning method and system | |
| CN107403279B (en) | Oil transfer pump working condition self-adaptive state early warning system and method | |
| Becherer et al. | Intelligent choice of machine learning methods for predictive maintenance of intelligent machines | |
| CN117152119A (en) | Profile flaw visual detection method based on image processing | |
| CN110570013A (en) | Single-station online wave period data prediction diagnosis method | |
| CN116523442A (en) | Production process digital management system and method for paint | |
| Koops | Optimized maintenance decision-making—A simulation-supported prescriptive analytics approach based on probabilistic cost-benefit analysis | |
| CN113723637B (en) | Economic repair level analysis method and system for ship repair system | |
| CN118469268B (en) | Digital factory consumable management system and method | |
| CN113191506B (en) | Aperiodic condition-based maintenance method considering equipment detection uncertainty | |
| KR102474332B1 (en) | Prediction method of machine health stability in smart factory system, and recording medium thereof | |
| CN117893100A (en) | Construction method of quality evaluation data updating model based on convolutional neural network | |
| CN117592682A (en) | Supply chain risk monitoring method and system based on real-time audit data flow analysis system | |
| CN111798069A (en) | Machine learning-based complex equipment spare part management method and system | |
| Mateo Casalí et al. | An industry maturity model for implementing Machine Learning operations in manufacturing | |
| CN118364418B (en) | Intelligent corrosion resistance detection method and system for bearing pedestal | |
| CN117408742B (en) | User screening method and system | |
| CN118024035B (en) | Machine learning-based polishing solution replacement early warning method and device | |
| CN118730932B (en) | Portable intelligent analysis method for food ingredients | |
| CN112488432B (en) | Equipment health assessment method, storage device and terminal | |
| Yang et al. | Change-point estimation for repairable systems combining bootstrap control charts and clustering analysis: Performance analysis and a case study |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |