CN118350735A - Digital twinning-based fresh storage logistics online monitoring system and monitoring method - Google Patents
Digital twinning-based fresh storage logistics online monitoring system and monitoring method Download PDFInfo
- Publication number
- CN118350735A CN118350735A CN202410448214.9A CN202410448214A CN118350735A CN 118350735 A CN118350735 A CN 118350735A CN 202410448214 A CN202410448214 A CN 202410448214A CN 118350735 A CN118350735 A CN 118350735A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- fresh
- information
- product
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000007405 data analysis Methods 0.000 claims abstract description 46
- 238000013507 mapping Methods 0.000 claims abstract description 12
- 238000003066 decision tree Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 16
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 238000013480 data collection Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000004519 manufacturing process Methods 0.000 claims description 9
- 238000001237 Raman spectrum Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 238000013138 pruning Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 abstract description 7
- 238000013068 supply chain management Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 235000013311 vegetables Nutrition 0.000 description 2
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0833—Tracking
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a digital twinning-based fresh storage logistics on-line monitoring system and a digital twinning-based fresh storage logistics monitoring method, which belong to the technical field of fresh storage logistics management, wherein the system comprises a data acquisition unit and a digital twinning model unit, and the data acquisition unit is connected with the digital twinning model unit through a virtual-real mapping unit; the data acquisition unit is used for acquiring real-time data of fresh products in the warehouse logistics, and comprises a fixed data acquisition module arranged in fresh warehouse equipment and a mobile data acquisition module arranged on the fresh products, wherein the fixed data acquisition module and the mobile data acquisition module are both connected with the virtual-real mapping unit; the digital twin model unit comprises a heterogeneous data analysis module for unifying data formats, the heterogeneous data analysis module is connected with a fresh-keeping data module and a fresh-keeping product description module, the fresh-keeping product description module is connected with a prediction early-warning module and a quality tracing module, and the prediction early-warning module, the quality tracing module and the fresh-keeping data module are all connected with a database. By adopting the digital twin-based fresh storage logistics online monitoring system and the digital twin-based fresh storage logistics online monitoring method, the whole process of fresh products is monitored and predicted, the loss is effectively reduced, the management efficiency is improved, and effective support is provided for fresh product supply chain management.
Description
Technical Field
The invention belongs to the technical field of fresh storage logistics management, and particularly relates to a digital twin-based fresh storage logistics online monitoring system and a digital twin-based fresh storage logistics online monitoring method.
Background
With the development of economy and the improvement of the living standard of people, the demand for fresh products is continuously increased, and the storage logistics management of the fresh products becomes a concern. The traditional warehouse logistics management mode generally depends on manual operation and paper document recording, and has the conditions of non-real-time information, inaccurate data and high transportation loss rate. These problems result in inefficiency of the agricultural product supply chain, serious waste of resources, and even possibly influence on quality and safety of the product. To solve these problems, a more advanced and efficient warehouse logistics management method is needed.
Disclosure of Invention
The invention aims to provide a digital twinning-based fresh storage logistics online monitoring system and a digital twinning-based fresh storage logistics online monitoring method, which solve the technical problems.
In order to achieve the purpose, the invention provides a digital twinning-based fresh storage logistics online monitoring system which comprises a data acquisition unit and a digital twinning model unit, wherein the data acquisition unit is connected with the digital twinning model unit through a virtual-real mapping unit;
The data acquisition unit is used for acquiring real-time data of fresh products in the warehouse logistics, and comprises a fixed data acquisition module arranged in fresh warehouse equipment and a mobile data acquisition module arranged on the fresh products, wherein the fixed data acquisition module and the mobile data acquisition module are both connected with the virtual-real mapping unit;
The digital twin model unit comprises a heterogeneous data analysis module for unifying data formats, the heterogeneous data analysis module is connected with a fresh-keeping data module and a fresh-keeping product description module, the fresh-keeping product description module is connected with a prediction early-warning module and a quality tracing module, and the prediction early-warning module, the quality tracing module and the fresh-keeping data module are all connected with a database.
Preferably, the fixed data acquisition module comprises a first sensor assembly, a scanner for identifying information identification tags on fresh products and a first camera or a first Raman spectrum detector for acquiring appearance states and running conditions of the fresh products;
The mobile data acquisition module comprises a positioning device, a second sensor assembly arranged on the transportation equipment, and a second camera or a second Raman spectrum detector for acquiring the appearance state and the running condition of the fresh product;
The first sensor assembly and the second sensor assembly comprise a temperature sensor, a humidity sensor and an olfactory sensor, the first sensor assembly further comprises a pressure sensor, the pressure sensor is used for detecting the temperature, the humidity and the freshness index of the storage environment of the fresh product, and the freshness index comprises an odor index detected by the olfactory sensor and an activity index detected by the pressure sensor and obtained by detecting pressure change;
the first sensor assembly, the first camera, the scanner, the positioning device, the second sensor assembly and the second camera are all connected with the heterogeneous data analysis module.
Preferably, the fresh data module comprises a product form identification sub-module, a sensor data sub-module and a position tracking data sub-module;
The product form recognition sub-module, the sensor data sub-module and the position tracking data sub-module are all connected with the heterogeneous data analysis module;
The fresh product description module comprises a product information description sub-module, a position information description sub-module and a state monitoring sub-module which are respectively used for constructing a product information model, a position information model and a state information model;
the product information description submodule is connected with the sensor data submodule and is used for receiving basic information of fresh products, wherein the basic information comprises product types, batch numbers, production dates and expiration dates;
The position information description sub-module is connected with the position tracking data sub-module and is used for receiving the position information of the fresh product, wherein the position information comprises a production place, a current position, a transportation path and a destination;
The state monitoring submodule is connected with the sensor data submodule and is used for receiving state information of fresh products, wherein the state information comprises temperature, humidity and freshness indexes.
Preferably, the databases include a time series database, a document database, a relational database, and a blockchain.
The monitoring method based on the digital twin-based fresh storage logistics online monitoring system comprises the following specific steps:
step S1: establishing connection between a data acquisition unit and a digital twin model unit and between the digital twin model unit and a virtual-real mapping unit;
Step S2: collecting data of fresh products in real time in the processes of materials and storage and transmitting the collected data to a heterogeneous data analysis module;
The method comprises the steps that in the transportation process, transportation temperature, humidity, position and smell data of fresh products are collected through a mobile data collection module, and the collected data are transmitted to a heterogeneous data analysis module to be converted into a digital data format;
When fresh products are delivered to a storage facility, an information identification tag is identified and recorded through a scanner, appearance state and movement condition information of the fresh products are collected through a first camera in a fixed data collection module, freshness indexes of storage environment and the fresh products are collected through a first sensor assembly, and basic information and image information carried by the information identification tag are transmitted to a heterogeneous data analysis module to be converted into a digital data format;
Step S3: the heterogeneous data analysis module analyzes the received original data to form a unified standard data format, the unified standard data format is transmitted to the digital twin description module, the information of the fresh product is updated, the real-time data information of the fresh product is displayed through the digital twin model, the data is stored in the database, and data support is provided for the prediction early warning module and the quality tracing module;
step S4: the prediction and early warning module performs feature extraction and analysis on the acquired data, predicts and analyzes the data acquired in real time, identifies potential abnormal conditions or risk events, and sends out corresponding early warning signals;
and the quality tracing module retrieves related data information from the database according to the query requirement of the user, and displays and gathers the queried quality tracing information so as to be convenient for the user to check and analyze.
Preferably, the real-time position data of the fresh product is collected through the positioning device, the positioning device adopts a GPS (global positioning system) positioner, the real-time position information is transmitted to the heterogeneous data analysis module, the heterogeneous data analysis module analyzes the data to form a unified standard data format and transmits the unified standard data format to the position tracking data sub-module, and the position information description sub-module is used for updating the position data.
Preferably, the first sensor assembly and the second sensor assembly are used for transporting and storing environment monitoring data, the first sensor assembly is used for detecting pressure change data through the pressure sensor to obtain liveness index data, the environment monitoring data and the liveness index data are transmitted to the heterogeneous data analysis module, the heterogeneous data analysis module is used for analyzing the data to form a unified standard data format and transmitting the unified standard data format to the sensor data sub-module, and the state monitoring sub-module is used for updating environment information and liveness index data stored in fresh products.
Preferably, the first camera and the second camera collect the appearance state and movement condition data of the product, the appearance state and movement condition data are transmitted to the heterogeneous data analysis module, the heterogeneous data analysis module analyzes the image to form a unified standard data format and transmits the unified standard data format to the product form identification sub-module, and the form information of the fresh product is updated through the product information description sub-module.
Preferably, the prediction and early warning module predicts and early warns according to the updated data in the digital twin description module, and predicts and early warns by a decision tree method, and the specific process is as follows:
Step S41: data acquisition, namely acquiring updated monitoring data in the fresh product warehouse logistics process, wherein the monitoring data comprise temperature, humidity, images, liveness indexes and product positions;
step S42: preprocessing data, namely preprocessing the acquired data, detecting whether missing values, abnormal values and repeated values exist or not, filling the missing values, and eliminating the abnormal values and the repeated values;
step S43: dividing the processed data set into a training set and a testing set;
Step S44: constructing a decision tree prediction model, and training and testing through a training set and a testing set;
Step S45: and predicting the data acquired in real time through the trained and tested decision tree model, formulating an early warning strategy according to the prediction result, and sending out a corresponding early warning signal to prompt related personnel to take corresponding measures when the prediction result shows that an abnormal situation occurs.
Preferably, in step S44, the specific process of constructing the decision tree prediction model is as follows:
First, a root node is selected: selecting corresponding characteristics from the training set as root nodes according to the fresh product types;
Then, the dataset is split: splitting training set data into different subsets according to the selected characteristics, wherein each subset has different values corresponding to root nodes, and a branch structure of a decision tree is constructed by continuously dividing the data sets;
Then, recursively split: recursively repeating the splitting process for each subset until a stop condition is met, such as reaching a maximum depth, the number of samples contained by the node being less than a threshold, or the node being less than a threshold of unreliability; constructing a decision tree model of a completion foundation;
then, simplifying the basic model, and deleting nodes and branches through pruning measurement;
and finally, generating a decision rule according to the simplified decision tree model.
Therefore, the digital twin-based fresh storage logistics online monitoring system and the digital twin-based fresh storage logistics online monitoring method have the following beneficial effects:
(1) The real-time monitoring and predicting method in the fresh product storage logistics process is provided based on the Internet of things technology, the digital twin technology, the big data analysis technology and the predicting algorithm, and the technical problem of insufficient information timeliness and accuracy in the fresh product storage logistics process is solved.
(2) Various data including information such as position, temperature, humidity, vibration, freshness index and the like in the fresh product storage logistics process are collected in real time by utilizing the Internet of things technology, and a virtual logistics model is constructed by utilizing the digital twin technology, so that the monitoring process is more real-time and accurate.
(3) The virtual logistics model is constructed by utilizing the digital twin technology, so that the logistics process can be better simulated and optimized, and a new thought and method are provided for logistics management of fresh product storage.
(4) The collected data is comprehensively analyzed and predicted, so that the situation in the logistics process can be more comprehensively known, corresponding early warning and adjustment suggestions are provided, and the transportation loss rate is effectively reduced.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a block diagram of an on-line monitoring system for fresh warehouse logistics based on digital twinning;
FIG. 2 is a diagram showing the data acquisition layout of fresh aquatic products according to the present invention;
FIG. 3 is a diagram of an on-line monitoring system for fresh warehouse logistics based on digital twinning in the present invention;
FIG. 4 is a view showing the monitoring of fresh product state in the digital twin model of the present invention.
Detailed Description
Examples
In the description of the present invention, it should be noted that, directions or positional relationships indicated by terms such as "upper", "lower", "inner", "outer", etc., are directions or positional relationships based on those shown in the drawings, or those that are conventionally put in use, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements to be referred to must have a specific direction, be constructed and operated in a specific direction, and thus should not be construed as limiting the present invention. In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, the terms "disposed," "mounted," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in FIG. 1, the digital twinning-based fresh storage logistics online monitoring system comprises a data acquisition unit and a digital twinning model unit, wherein the data acquisition unit is connected with the digital twinning model unit through a virtual-real mapping unit. The virtual-real mapping unit can be a PLC or a singlechip device and is used for establishing the connection between the physical entity space and the digital twin model space.
Fig. 2 is a layout diagram of data collection of fresh aquatic products according to the present invention, fig. 3 is a layout diagram of an online monitoring system of fresh storage logistics based on digital twinning according to the present invention, wherein the data collection unit is used for collecting real-time data of fresh products in the storage logistics, and comprises a fixed data collection module arranged in fresh storage equipment and a mobile data collection module arranged on the fresh products, and the fixed data collection module and the mobile data collection module are both connected with the virtual-real mapping unit. The fixed data acquisition module comprises a first sensor component, a scanner for identifying information identification tags (RFID tags in the embodiment, including one-dimensional codes, two-dimensional codes, single product tags, outer box tags and the like) on fresh products, unique identification codes for identifying the fresh products, transportation paths and position information for identifying and tracking the fresh products, and a first camera or a first Raman spectrum detector for acquiring appearance states and running conditions of the fresh products. The mobile data acquisition module comprises a positioning device, a second sensor assembly arranged on the transportation equipment, and a second camera or a second Raman spectrum detector for acquiring the appearance state and the running condition of the fresh product. The first sensor assembly and the second sensor assembly each comprise a temperature sensor, a humidity sensor and an olfactory sensor, and the first sensor assembly further comprises a pressure sensor (which can be replaced by a vibration sensor) for detecting the temperature, the humidity and the freshness index of the storage environment of the fresh product, wherein the freshness index comprises an odor index detected by the olfactory sensor and an activity index obtained by the pressure sensor for detecting pressure change. The types and the number of specific sensors can be increased according to actual needs, the types of the sensors are selected according to the characteristics of aquatic products, in fig. 2, the aquatic products comprise living bodies and non-living bodies, carbon dioxide and oxygen sensors are also required to be added for living body detection, and detection sensors of microorganisms, TVB-N and endogenous enzymes are required to be added for non-living body detection. The first sensor assembly, the first camera, the scanner, the positioning device, the second sensor assembly and the second camera are all connected with the heterogeneous data analysis module.
The digital twin model unit comprises a heterogeneous data analysis module for unifying data formats, the heterogeneous data analysis module is connected with a fresh-keeping data module and a fresh-keeping product description module, the fresh-keeping product description module is connected with a prediction early-warning module and a quality tracing module, and the prediction early-warning module, the quality tracing module and the fresh-keeping data module are all connected with a database. The fresh data module comprises a product form identification sub-module, a sensor data sub-module and a position tracking data sub-module, and the product form identification sub-module, the sensor data sub-module and the position tracking data sub-module are all connected with the heterogeneous data analysis module. The fresh product description module comprises a product information description sub-module, a position information description sub-module and a state monitoring sub-module which are respectively used for constructing a product information model, a position information model and a state information model. The product information description submodule is connected with the sensor data submodule and is used for receiving basic information of fresh products, wherein the basic information comprises product types, batch numbers, production dates and expiration dates. The position information description sub-module is connected with the position tracking data sub-module and is used for receiving the position information of the fresh product, wherein the position information comprises a production place, a current position, a transportation path and a destination. The state monitoring submodule is connected with the sensor data submodule and is used for receiving state information of fresh products, wherein the state information comprises temperature, humidity and freshness indexes. Databases include a timing database, a document database, a relational database, and a blockchain.
The monitoring method based on the digital twin-based fresh storage logistics online monitoring system is characterized by comprising the following specific steps:
step S1: establishing connection between a data acquisition unit and a digital twin model unit and between the digital twin model unit and a virtual-real mapping unit;
Step S2: collecting data of fresh products in real time in the processes of materials and storage and transmitting the collected data to a heterogeneous data analysis module;
The method comprises the steps that in the transportation process, transportation temperature, humidity, position and smell data of fresh products are collected through a mobile data collection module, and the collected data are transmitted to a heterogeneous data analysis module to be converted into a digital data format;
When fresh products are delivered to a storage facility, an information identification tag is identified and recorded through a scanner, appearance state and movement condition information of the fresh products are collected through a first camera in a fixed data collection module, freshness indexes of storage environment and the fresh products are collected through a first sensor assembly, and basic information and image information carried by the information identification tag are transmitted to a heterogeneous data analysis module to be converted into a digital data format;
Step S3: the heterogeneous data analysis module analyzes the received original data to form a unified standard data format, the unified standard data format is transmitted to the digital twin description module, the information of the fresh product is updated, the real-time data information of the fresh product is displayed through the digital twin model, the data is stored in the database, and data support is provided for the prediction early warning module and the quality tracing module;
step S4: the prediction and early warning module performs feature extraction and analysis on the acquired data, predicts and analyzes the data acquired in real time, identifies potential abnormal conditions or risk events, and sends out corresponding early warning signals;
The quality tracing module retrieves related data information from a database according to the query requirement of a user, and traces the whole processes of production, processing, transportation and the like of the product to determine the source and the production process of the product, and the queried quality tracing information is displayed and summarized for the user to check and analyze.
The prediction and early warning information is presented in a visual mode, so that a user can intuitively know the possible problems in the storage logistics process of the fresh products, and timely take measures to adjust and process.
The real-time position data of the fresh products are collected through the positioning device, the positioning device adopts a GPS (global positioning system) positioner, the real-time position information is transmitted to the heterogeneous data analysis module, the heterogeneous data analysis module analyzes the data to form a unified standard data format and transmits the unified standard data format to the position tracking data sub-module, and the position information is updated through the position information description sub-module.
The first sensor assembly and the second sensor assembly are used for transporting and storing environment monitoring data, the first sensor assembly is used for detecting pressure change data through a pressure sensor to obtain liveness index data, the environment monitoring data and the liveness index data are transmitted to the heterogeneous data analysis module, the heterogeneous data analysis module is used for analyzing the data to form a unified standard data format and transmitting the unified standard data format to the sensor data sub-module, and the state monitoring sub-module is used for updating environment information and liveness index data stored in fresh products.
The first camera and the second camera acquire the appearance state and movement condition data of the product and transmit the appearance state and movement condition data to the heterogeneous data analysis module, the heterogeneous data analysis module analyzes the image to form a unified standard data format and transmits the unified standard data format to the product form identification sub-module, and the form information of the fresh product is updated through the product information description sub-module.
In the embodiment, the data transmission format is a Json format, the communication protocol is an MQTT, and the acquired real-time environment data is updated into the digital twin model space through the digital twin description module so as to maintain the accuracy and real-time performance of environment information in the model.
The prediction and early warning module predicts and early warns according to the updated data in the digital twin description module, and predicts and early warns through a decision tree method, and the specific process is as follows:
Step S41: data acquisition, namely acquiring updated monitoring data in the fresh product warehouse logistics process, wherein the monitoring data comprise temperature, humidity, images, liveness indexes and product positions;
step S42: preprocessing data, namely preprocessing the acquired data, detecting whether missing values, abnormal values and repeated values exist or not, filling the missing values, and eliminating the abnormal values and the repeated values;
step S43: dividing the processed data set into a training set and a testing set;
Step S44: and constructing a decision tree prediction model, and training and testing through a training set and a testing set.
The concrete process of constructing the decision tree prediction model is as follows:
First, a root node is selected: and selecting corresponding characteristics from the training set according to the fresh product type as a root node. The selected feature should be the feature that most effectively classifies the data into different categories or predicts the target variable.
Then, the dataset is split: according to the selected characteristics, the training set data are split into different subsets, each subset has different values corresponding to the root node, and a branch structure of a decision tree is constructed by continuously dividing the data sets.
Then, recursively split: recursively repeating the splitting process for each subset until a stop condition is met, such as reaching a maximum depth, the number of samples contained by the node being less than a threshold, or the node being less than a threshold of unreliability; and constructing a decision tree model of the completion foundation.
The base model is then simplified, and nodes and branches are pruned by pruning measurements. After the decision tree is built, a situation may occur in which the model performs well on the training set, but poorly on the test set. In order to improve the generalization capability of the model, a pruning strategy can be adopted, unnecessary nodes and branches are deleted, and the complexity of the model is simplified.
And finally, generating a decision rule according to the simplified decision tree model. For interpreting the predictive process of the model. These rules can help the user understand the decision logic of the model and formulate the corresponding pre-warning strategy accordingly.
And simultaneously evaluating the decision tree model. The evaluation procedure was as follows:
firstly, predicting samples in a test set by using a constructed decision tree model to obtain a prediction result;
Then, the predicted result and the actual result are compared: and comparing the prediction result of the model with the real labels in the test set to evaluate the accuracy of the model.
And then calculating performance indexes, and calculating indexes such as accuracy, recall rate, F1 score and the like of the model according to the prediction result and the actual result so as to comprehensively evaluate the prediction effect of the model.
Accuracy rate: the ratio of the number of correct samples of the model prediction to the total number of samples is represented by the following calculation formula:
Wherein TP (True Positives) denotes the true case number, TN (True Negatives) denotes the true case number, FP (False Positives) denotes the false positive case number, and FN (False Negatives) denotes the false negative case number.
Recall rate: the proportion of the positive example predicted correctly by the model to the total positive example is expressed, and the proportion is also called recall ratio, and the calculation formula is as follows:
F1 fraction: the index of the accuracy rate and the recall rate is comprehensively considered, and is a harmonic average value of the accuracy rate and the recall rate, and the calculation formula is as follows:
then, the evaluation result is interpreted: analyzing the performance index obtained by calculation, explaining the performance of the model in the prediction and early warning process, and evaluating the advantages and disadvantages of the model.
Finally, the model parameters are adjusted: according to the evaluation result, parameters of the model can be adjusted or a construction method of the model can be improved so as to improve the performance of the model.
Step S45: and predicting the data acquired in real time through the trained and tested decision tree model, formulating an early warning strategy according to the prediction result, and sending out a corresponding early warning signal to prompt related personnel to take corresponding measures when the prediction result shows that an abnormal situation occurs.
As shown in fig. 4, taking fresh aquatic products and vegetables as examples (the first row and the second row in fig. 4 respectively), the color state of the fresh aquatic products and vegetables is monitored by the digital twin real-time monitoring system for fresh agricultural products, and in fig. 4, from left to right, the first image is a physical image of the fresh products, and in order to record the quality and state of the fresh products, various data including information on color, shape, texture and the like are acquired. The second graph is used for creating a virtual product model, simulating the change condition of fresh products under different environmental conditions, and not only comprises the appearance characteristics of the products, but also comprises environmental factors such as temperature, humidity and the like and other activity indexes. The third and the fourth diagrams record the state change of the fresh products in the storage and transportation process, mainly pay attention to the color state of the products, and can continuously monitor the color of the fresh products through a real-time monitoring system so as to discover any abnormal change in time. Environmental parameters such as temperature, humidity and the like and other liveness indexes can be recorded, and more comprehensive data support is provided for early warning.
Various data including information such as product position, temperature, humidity, vibration, freshness index and the like in the fresh product storage logistics process are collected in real time by utilizing the Internet of things technology, and a virtual logistics model is constructed by utilizing a digital twin technology, so that real-time monitoring and early warning of fresh products are realized. Meanwhile, the data are analyzed and predicted by combining a big data analysis technology and a prediction algorithm, the whole processes of production, processing, transportation and the like of the product are traced, and timely early warning and adjustment suggestions are provided for the problems in the logistics process.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention and not for limiting it, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the invention can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the invention.
Claims (10)
1. Digital twinning-based fresh storage logistics online monitoring system is characterized in that: the system comprises a data acquisition unit and a digital twin model unit, wherein the data acquisition unit is connected with the digital twin model unit through a virtual-real mapping unit;
The data acquisition unit is used for acquiring real-time data of fresh products in the warehouse logistics, and comprises a fixed data acquisition module arranged in fresh warehouse equipment and a mobile data acquisition module arranged on the fresh products, wherein the fixed data acquisition module and the mobile data acquisition module are both connected with the virtual-real mapping unit;
The digital twin model unit comprises a heterogeneous data analysis module for unifying data formats, the heterogeneous data analysis module is connected with a fresh-keeping data module and a fresh-keeping product description module, the fresh-keeping product description module is connected with a prediction early-warning module and a quality tracing module, and the prediction early-warning module, the quality tracing module and the fresh-keeping data module are all connected with a database.
2. The digital twinning-based fresh warehouse logistics online monitoring system as claimed in claim 1, wherein: the fixed data acquisition module comprises a first sensor assembly, a scanner for identifying information identification tags on fresh products and a first camera or a first Raman spectrum detector for acquiring the appearance state and the running condition of the fresh products;
The mobile data acquisition module comprises a positioning device, a second sensor assembly arranged on the transportation equipment, and a second camera or a second Raman spectrum detector for acquiring the appearance state and the running condition of the fresh product;
The first sensor assembly and the second sensor assembly comprise a temperature sensor, a humidity sensor and an olfactory sensor, the first sensor assembly further comprises a pressure sensor, the pressure sensor is used for detecting the temperature, the humidity and the freshness index of the storage environment of the fresh product, and the freshness index comprises an odor index detected by the olfactory sensor and an activity index detected by the pressure sensor and obtained by detecting pressure change;
the first sensor assembly, the first camera, the scanner, the positioning device, the second sensor assembly and the second camera are all connected with the heterogeneous data analysis module.
3. The digital twinning-based fresh warehouse logistics online monitoring system as claimed in claim 2, wherein: the fresh data module comprises a product form identification sub-module, a sensor data sub-module and a position tracking data sub-module;
The product form recognition sub-module, the sensor data sub-module and the position tracking data sub-module are all connected with the heterogeneous data analysis module;
The fresh product description module comprises a product information description sub-module, a position information description sub-module and a state monitoring sub-module which are respectively used for constructing a product information model, a position information model and a state information model;
the product information description submodule is connected with the sensor data submodule and is used for receiving basic information of fresh products, wherein the basic information comprises product types, batch numbers, production dates and expiration dates;
The position information description sub-module is connected with the position tracking data sub-module and is used for receiving the position information of the fresh product, wherein the position information comprises a production place, a current position, a transportation path and a destination;
The state monitoring submodule is connected with the sensor data submodule and is used for receiving state information of fresh products, wherein the state information comprises temperature, humidity and freshness indexes.
4. The digital twinning-based fresh warehouse logistics online monitoring system as claimed in claim 1, wherein: databases include a timing database, a document database, a relational database, and a blockchain.
5. A method for monitoring a digital twin-based fresh storage logistics online monitoring system according to any one of claims 1-4, which is characterized by comprising the following specific steps:
step S1: establishing connection between a data acquisition unit and a digital twin model unit and between the digital twin model unit and a virtual-real mapping unit;
Step S2: collecting data of fresh products in real time in the processes of materials and storage and transmitting the collected data to a heterogeneous data analysis module;
The method comprises the steps that in the transportation process, transportation temperature, humidity, position and smell data of fresh products are collected through a mobile data collection module, and the collected data are transmitted to a heterogeneous data analysis module to be converted into a digital data format;
When fresh products are delivered to a storage facility, an information identification tag is identified and recorded through a scanner, appearance state and movement condition information of the fresh products are collected through a first camera in a fixed data collection module, freshness indexes of storage environment and the fresh products are collected through a first sensor assembly, and basic information and image information carried by the information identification tag are transmitted to a heterogeneous data analysis module to be converted into a digital data format;
Step S3: the heterogeneous data analysis module analyzes the received original data to form a unified standard data format, the unified standard data format is transmitted to the digital twin description module, the information of the fresh product is updated, the real-time data information of the fresh product is displayed through the digital twin model, the data is stored in the database, and data support is provided for the prediction early warning module and the quality tracing module;
step S4: the prediction and early warning module performs feature extraction and analysis on the acquired data, predicts and analyzes the data acquired in real time, identifies potential abnormal conditions or risk events, and sends out corresponding early warning signals;
and the quality tracing module retrieves related data information from the database according to the query requirement of the user, and displays and gathers the queried quality tracing information so as to be convenient for the user to check and analyze.
6. A method of monitoring according to claim 5, wherein: the real-time position data of the fresh products are collected through the positioning device, the positioning device adopts a GPS (global positioning system) positioner, the real-time position information is transmitted to the heterogeneous data analysis module, the heterogeneous data analysis module analyzes the data to form a unified standard data format and transmits the unified standard data format to the position tracking data sub-module, and the position information is updated through the position information description sub-module.
7. A method of monitoring according to claim 6, wherein: the first sensor assembly and the second sensor assembly are used for transporting and storing environment monitoring data, the first sensor assembly is used for detecting pressure change data through a pressure sensor to obtain liveness index data, the environment monitoring data and the liveness index data are transmitted to the heterogeneous data analysis module, the heterogeneous data analysis module is used for analyzing the data to form a unified standard data format and transmitting the unified standard data format to the sensor data sub-module, and the state monitoring sub-module is used for updating environment information and liveness index data stored in fresh products.
8. A method of monitoring according to claim 7, wherein: the first camera and the second camera acquire the appearance state and movement condition data of the product and transmit the appearance state and movement condition data to the heterogeneous data analysis module, the heterogeneous data analysis module analyzes the image to form a unified standard data format and transmits the unified standard data format to the product form identification sub-module, and the form information of the fresh product is updated through the product information description sub-module.
9. A method of monitoring according to claim 8, wherein: the prediction and early warning module predicts and early warns according to the updated data in the digital twin description module, and predicts and early warns through a decision tree method, and the specific process is as follows:
Step S41: data acquisition, namely acquiring updated monitoring data in the fresh product warehouse logistics process, wherein the monitoring data comprise temperature, humidity, images, liveness indexes and product positions;
step S42: preprocessing data, namely preprocessing the acquired data, detecting whether missing values, abnormal values and repeated values exist or not, filling the missing values, and eliminating the abnormal values and the repeated values;
step S43: dividing the processed data set into a training set and a testing set;
Step S44: constructing a decision tree prediction model, and training and testing through a training set and a testing set;
Step S45: and predicting the data acquired in real time through the trained and tested decision tree model, formulating an early warning strategy according to the prediction result, and sending out a corresponding early warning signal to prompt related personnel to take corresponding measures when the prediction result shows that an abnormal situation occurs.
10. A method of monitoring according to claim 9, wherein: in step S44, the specific process of constructing the decision tree prediction model is as follows:
First, a root node is selected: selecting corresponding characteristics from the training set as root nodes according to the fresh product types;
Then, the dataset is split: splitting training set data into different subsets according to the selected characteristics, wherein each subset has different values corresponding to root nodes, and a branch structure of a decision tree is constructed by continuously dividing the data sets;
Then, recursively split: recursively repeating the splitting process for each subset until a stop condition is met, such as reaching a maximum depth, the number of samples contained by the node being less than a threshold, or the node being less than a threshold of unreliability; constructing a decision tree model of a completion foundation;
then, simplifying the basic model, and deleting nodes and branches through pruning measurement;
and finally, generating a decision rule according to the simplified decision tree model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410448214.9A CN118350735A (en) | 2024-04-15 | 2024-04-15 | Digital twinning-based fresh storage logistics online monitoring system and monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410448214.9A CN118350735A (en) | 2024-04-15 | 2024-04-15 | Digital twinning-based fresh storage logistics online monitoring system and monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118350735A true CN118350735A (en) | 2024-07-16 |
Family
ID=91813261
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410448214.9A Pending CN118350735A (en) | 2024-04-15 | 2024-04-15 | Digital twinning-based fresh storage logistics online monitoring system and monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118350735A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118505908A (en) * | 2024-07-17 | 2024-08-16 | 浪潮智慧供应链科技(山东)有限公司 | Storage data visualization method and system based on digital twinning |
-
2024
- 2024-04-15 CN CN202410448214.9A patent/CN118350735A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118505908A (en) * | 2024-07-17 | 2024-08-16 | 浪潮智慧供应链科技(山东)有限公司 | Storage data visualization method and system based on digital twinning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220137612A1 (en) | Transformer fault diagnosis and positioning system based on digital twin | |
| CN116796907A (en) | Water environment dynamic monitoring system and method based on Internet of things | |
| CN116519895B (en) | Water quality on-line monitoring analysis management system based on big data platform | |
| CN118350735A (en) | Digital twinning-based fresh storage logistics online monitoring system and monitoring method | |
| Gutiérrez et al. | On the use of information fusion techniques to improve information quality: Taxonomy, opportunities and challenges | |
| CN115660291B (en) | Plant disease occurrence and potential occurrence identification and evaluation method and system | |
| CN116308958A (en) | Carbon emission online detection and early warning system and method based on mobile terminal | |
| CN117010915A (en) | Carbon emission target identification and monitoring system based on Internet of things technology | |
| CN110993096A (en) | Sepsis early warning device, equipment and storage medium | |
| CN118235723B (en) | Cow intelligent monitoring platform and device based on wisdom pasture | |
| CN118200950B (en) | Method and system for inspecting telecommunication base station | |
| CN117974343A (en) | Aquaculture control method, intelligent device and storage medium | |
| CN117764413A (en) | Accurate carbon emission accounting algorithm based on machine learning | |
| CN110911011A (en) | Sepsis early warning device, equipment and storage medium | |
| CN115099332A (en) | Radar data real-time processing method and system based on mixed forest | |
| CN103136439B (en) | Plant illness discrimination method and system thereof | |
| CN118012977B (en) | AI and GIS fusion-based two-dimensional multi-mode data processing method | |
| CN118312726B (en) | Ground penetrating radar data real-time evaluation method and system, and training method and system | |
| CN118503893B (en) | Time sequence data anomaly detection method and device based on space-time characteristic representation difference | |
| CN117688452B (en) | Food pesticide residue detection and early warning method and system based on neural network | |
| CN112464896B (en) | Physical and mental state analysis system based on student behaviors | |
| CN118940055A (en) | Data analysis-based Chinese bee honeycomb honey baume degree data processing system and method | |
| CN112305184B (en) | Sewage treatment multi-fault diagnosis system and method | |
| Umar et al. | Smart Ontology-Based System for Recommending Practices in Melon Cultivation | |
| Salinas-Buestán et al. | Predictive Model Proposal in Telemetry Using Machine Learning Techniques to Anticipate Water Degradation in Aquaculture |
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 |