CN118088923B - Safety monitoring method and system based on hydrogen storage and transportation - Google Patents
Safety monitoring method and system based on hydrogen storage and transportation Download PDFInfo
- Publication number
- CN118088923B CN118088923B CN202410442713.7A CN202410442713A CN118088923B CN 118088923 B CN118088923 B CN 118088923B CN 202410442713 A CN202410442713 A CN 202410442713A CN 118088923 B CN118088923 B CN 118088923B
- Authority
- CN
- China
- Prior art keywords
- data
- hydrogen storage
- hydrogen
- safety monitoring
- sample set
- 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
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 title claims abstract description 228
- 239000001257 hydrogen Substances 0.000 title claims abstract description 228
- 229910052739 hydrogen Inorganic materials 0.000 title claims abstract description 228
- 238000003860 storage Methods 0.000 title claims abstract description 146
- 238000012544 monitoring process Methods 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004364 calculation method Methods 0.000 claims abstract description 38
- 230000008859 change Effects 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000002372 labelling Methods 0.000 claims abstract description 24
- 238000007781 pre-processing Methods 0.000 claims abstract description 21
- 238000013500 data storage Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 15
- 230000035772 mutation Effects 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 210000002569 neuron Anatomy 0.000 claims description 11
- 230000004913 activation Effects 0.000 claims description 10
- 238000010606 normalization Methods 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 7
- 230000000737 periodic effect Effects 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 230000002068 genetic effect Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000006356 dehydrogenation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000010304 firing Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000001915 proofreading effect Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C13/00—Details of vessels or of the filling or discharging of vessels
- F17C13/02—Special adaptations of indicating, measuring, or monitoring equipment
- F17C13/025—Special adaptations of indicating, measuring, or monitoring equipment having the pressure as the parameter
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C13/00—Details of vessels or of the filling or discharging of vessels
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C13/00—Details of vessels or of the filling or discharging of vessels
- F17C13/02—Special adaptations of indicating, measuring, or monitoring equipment
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C13/00—Details of vessels or of the filling or discharging of vessels
- F17C13/02—Special adaptations of indicating, measuring, or monitoring equipment
- F17C13/026—Special adaptations of indicating, measuring, or monitoring equipment having the temperature as the parameter
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C13/00—Details of vessels or of the filling or discharging of vessels
- F17C13/12—Arrangements or mounting of devices for preventing or minimising the effect of explosion ; Other safety measures
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C2223/00—Handled fluid before transfer, i.e. state of fluid when stored in the vessel or before transfer from the vessel
- F17C2223/01—Handled fluid before transfer, i.e. state of fluid when stored in the vessel or before transfer from the vessel characterised by the phase
- F17C2223/0107—Single phase
- F17C2223/0123—Single phase gaseous, e.g. CNG, GNC
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C2250/00—Accessories; Control means; Indicating, measuring or monitoring of parameters
- F17C2250/04—Indicating or measuring of parameters as input values
- F17C2250/0404—Parameters indicated or measured
- F17C2250/043—Pressure
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17C—VESSELS FOR CONTAINING OR STORING COMPRESSED, LIQUEFIED OR SOLIDIFIED GASES; FIXED-CAPACITY GAS-HOLDERS; FILLING VESSELS WITH, OR DISCHARGING FROM VESSELS, COMPRESSED, LIQUEFIED, OR SOLIDIFIED GASES
- F17C2250/00—Accessories; Control means; Indicating, measuring or monitoring of parameters
- F17C2250/04—Indicating or measuring of parameters as input values
- F17C2250/0404—Parameters indicated or measured
- F17C2250/0439—Temperature
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Filling Or Discharging Of Gas Storage Vessels (AREA)
Abstract
The invention discloses a safety monitoring method and a system based on hydrogen storage and transportation, which belong to the technical field of hydrogen safety monitoring and comprise the following steps: s1, acquiring parameter information of a hydrogen storage container based on a sensor to obtain hydrogen storage container information data; s2, preprocessing the hydrogen storage container information data to obtain a calculation data set; s3, constructing a sample set based on a public data storage library, and marking the pressure change characteristic and the temperature gradient characteristic of the sample set to obtain a marked sample set; s4, constructing a first multi-layer perceptron structure, and training an optimal multi-layer perceptron structure based on the labeling sample set to obtain a hydrogen safety monitoring model; s5, taking the calculated data set as input, based on the hydrogen safety monitoring model, obtaining a hydrogen safety monitoring prediction result and monitoring the hydrogen storage and transportation safety. The method and the device have the advantages that the early warning capability and the safety capability under the condition of hydrogen storage and transportation are improved, and the monitoring response is timely and accurate, so that the comprehensiveness and the accuracy are improved.
Description
Technical Field
The invention relates to the technical field of hydrogen safety monitoring, in particular to a safety monitoring method and system based on hydrogen storage and transportation.
Background
With the rapid development of the hydrogen energy industry, many challenges are faced in the fields of hydrogen energy manufacturing, storage and transportation and the like. The high-pressure gaseous hydrogen storage is the most mature and most commonly used hydrogen storage technology, has the characteristics of lower cost, low energy consumption, easiness in dehydrogenation, wider working conditions and the like, mainly adopts 4 types of I-type, II-type, III-type and IV-type gas cylinders made of different materials as hydrogen storage containers, stores gaseous hydrogen in a high-pressure compression mode, has small hydrogen molecules, is easy to leak in the storage and use process, has a firing point of only 585 ℃, and explodes when the content of the hydrogen in the air is within the range of 4-75 percent and meets open fire, so that the leakage of the hydrogen is required to be monitored in the use process of the hydrogen.
The current safety monitoring for hydrogen storage is mainly based on descriptive analysis of data, lacks the capability of predicting possible future occurrence events, and cannot early warn safety risks in advance. Meanwhile, the current monitoring method may have delay, and potential safety hazards and abnormal conditions cannot be captured in time, so that monitoring response is not timely.
Disclosure of Invention
Aiming at the problems of low early warning safety risk capability and untimely monitoring response caused by the lack of effective hydrogen storage and transportation safety monitoring means in the prior art, the invention provides a safety monitoring method and a safety monitoring system based on hydrogen storage and transportation, which are used for preprocessing information data of a hydrogen storage container to obtain a calculation data set; the method comprises the steps of obtaining a sample set, marking the sample set, constructing and improving a multi-layer perceptron, training the optimal multi-layer perceptron based on the marked sample set, obtaining a hydrogen safety monitoring model, inputting a calculation data set into the hydrogen safety monitoring model for calculation, and monitoring the hydrogen storage and transportation safety by the obtained hydrogen safety monitoring prediction result, so that the early warning capability and the safety capability under the condition of hydrogen storage and transportation are improved, the state and the characteristics of a hydrogen storage and transportation system can be comprehensively perceived, and the monitoring response is timely and accurate, thereby improving the monitoring comprehensiveness and accuracy.
In order to solve the technical problems, the invention provides a safety monitoring method based on hydrogen storage and transportation, which comprises the following steps:
S1, acquiring parameter information of a hydrogen storage container based on a sensor to obtain hydrogen storage container information data;
s2, preprocessing the hydrogen storage container information data to obtain a calculation data set;
S3, constructing a sample set based on a public data storage library, and marking the pressure change characteristic and the temperature gradient characteristic of the sample set to obtain a marked sample set;
S4, constructing a first multi-layer perceptron structure, and training an optimal multi-layer perceptron structure based on the labeling sample set to obtain a hydrogen safety monitoring model;
And S5, taking the calculated data set as input, acquiring a hydrogen safety monitoring prediction result based on the hydrogen safety monitoring model, and monitoring the hydrogen storage and transportation safety based on the hydrogen safety monitoring prediction result.
Preferably, the step S1 includes the steps of:
S11, acquiring first information data and second information data of a hydrogen storage container based on a first sensor and a second sensor;
And S12, integrating the first information data and the second information data to obtain hydrogen storage container information data.
Preferably, the S2 includes:
S21, analyzing the hydrogen storage container information data to obtain data attributes;
S22, performing correlation calculation on the hydrogen storage container information data based on the data attribute to obtain hydrogen storage container correlation data;
S23, classifying the hydrogen storage container information data through a Tanh activation function based on the hydrogen storage container relativity data to obtain classification data;
s24, performing proofreading and normalization operation on the classified data to generate a calculation data set.
Preferably, the step S24 includes the steps of:
S241, checking and layering the classified data to obtain layered classified data;
s242, carrying out data processing on the hierarchical classification data and transmitting the hierarchical classification data to a target data warehouse;
S243, carrying out standard deviation normalization processing on the target data warehouse to obtain normalized data so as to obtain a calculation data set.
Preferably, the step S3 includes the steps of:
S31, constructing a sample set by acquiring a public data storage library;
S32, analyzing the time sequence of the sample set according to the data attribute to obtain a pressure change periodic characteristic and a pressure change trend so as to obtain a pressure change characteristic;
s33, counting the temperature gradients at different positions in the hydrogen storage container information data according to the data attributes to obtain temperature gradient characteristics;
And S34, labeling the pressure change characteristics and the temperature gradient characteristics in the sample set to obtain a labeled sample set.
Preferably, the step S4 includes the steps of:
S41, constructing a group of first multi-layer perceptron structures, training and evaluating the first multi-layer perceptron structures through labeling sample sets, and obtaining fitness values of each individual and second multi-layer perceptron structures;
s42, based on the fitness value, selecting a second multi-layer sensor structure as a parent to perform cross operation, and obtaining a first child individual, wherein the cross operation is multi-point cross;
s43, performing mutation operation on the first offspring individuals to generate second offspring individuals;
s44, integrating the second offspring individuals with the second multi-layer sensor structure to obtain a multi-layer sensor population;
S45, sequentially performing cross operation and mutation operation on the multi-layer perceptron population until the maximum iteration number is reached, and outputting a final population;
s46, selecting an individual with the highest fitness in the final population as an optimal multi-layer sensor structure;
And S47, training the optimal multi-layer sensor structure based on the labeling sample set to obtain a hydrogen safety monitoring model.
Preferably, the mutation operation includes changing a neuron connection weight, modifying an activation function, and adjusting the number of neurons.
Preferably, the step S5 includes the steps of:
S51, taking the calculated data set as input, and obtaining a hydrogen safety monitoring prediction result based on a hydrogen safety monitoring model;
s52, analyzing a hydrogen safety monitoring prediction result to obtain a potential safety hazard prediction result and an abnormal condition prediction result;
And S53, monitoring the hydrogen storage and transportation safety based on the potential safety hazard prediction result and the abnormal condition prediction result.
The invention also provides a safety monitoring system based on hydrogen storage and transportation:
The safety monitoring system based on hydrogen storage and transportation comprises a data acquisition module, a sample set processing module, a preprocessing module, a model construction module and a result generation module;
the data acquisition module acquires parameter information of the hydrogen storage container through a sensor so as to obtain hydrogen storage container information data; the preprocessing module is used for preprocessing the hydrogen storage container information data to obtain a calculation data set; the sample set processing module obtains a sample set through a public data storage library, marks the pressure change characteristics and the temperature gradient characteristics of the sample set, and obtains a marked sample set; the model construction module is used for constructing a first multi-layer perceptron structure and training the optimal multi-layer perceptron structure based on the labeling sample set to obtain a hydrogen safety monitoring model; the result generation module is used for inputting the calculation data set into the hydrogen safety monitoring model for calculation to obtain a hydrogen safety monitoring prediction result, and monitoring the hydrogen storage and transportation safety based on the hydrogen safety monitoring prediction result.
The invention has the beneficial effects that:
1. The scheme comprises the steps of preprocessing hydrogen storage container information data to obtain a calculation data set; the method comprises the steps of obtaining a sample set, marking the sample set, constructing and improving a multi-layer perceptron, training the optimal multi-layer perceptron based on the marked sample set, obtaining a hydrogen safety monitoring model, inputting a calculation data set into the hydrogen safety monitoring model for calculation, and monitoring the hydrogen storage and transportation safety by the obtained hydrogen safety monitoring prediction result, so that the early warning capability and the safety capability under the condition of hydrogen storage and transportation are improved, the state and the characteristics of a hydrogen storage and transportation system can be comprehensively perceived, and the monitoring response is timely and accurate, thereby improving the monitoring comprehensiveness and accuracy.
2. According to the scheme, the sensor is used for collecting the parameter information of the hydrogen storage container, and can monitor key parameters of the hydrogen storage container, such as hydrogen concentration, pressure, temperature and the like, in real time, so that the safety and stability of the hydrogen storage process are ensured, the sensor is suitable for changes and uncertainties in different environments, and the flexibility and adaptability of the system are improved. Through real-time data acquisition, the sensor can timely find potential safety hazards such as hydrogen leakage, pressure abnormality and the like, and further corresponding early warning and handling measures are adopted to prevent accidents.
3. According to the scheme, the hydrogen storage container information data is preprocessed, so that the error, abnormal or repeated data can be corrected or deleted, and the accuracy and consistency of the data are ensured. This aids in the accuracy and reliability of subsequent analysis. The preprocessing process may include feature extraction and selection that helps extract important information from the raw data for hydrogen storage vessel performance and safety assessment. These features can be used as input for subsequent analysis to improve the pertinence and effectiveness of the analysis.
4. According to the scheme, the sample set is constructed by acquiring the public data storage library, so that the variety and the number of samples can be enriched, more comprehensive support is provided for subsequent data analysis and model training, and meanwhile, the data in the public data storage library are usually subjected to strict screening and auditing, so that the method has higher quality and reliability. The data is used as a sample set, so that the accuracy and the reliability of data analysis can be improved, and the analysis result deviation caused by the data quality problem can be reduced.
5. The scheme marks the sample set through the pressure change characteristic and the temperature gradient characteristic, so that the multi-layer sensor structure can accurately identify and understand the key information. These features are critical to the performance analysis and safety assessment of hydrogen storage vessels. By using these features as inputs to the model, the model can learn better about the intrinsic rules and patterns of the data, thereby improving the accuracy of predictions and classification.
6. According to the scheme, the multi-layer perceptron structure is constructed, the hydrogen safety monitoring model is obtained, multidimensional characteristics including various monitoring indexes such as pressure, temperature and humidity can be learned at the same time, the state and the characteristics of the hydrogen storage and transportation system can be comprehensively perceived, and the monitoring comprehensiveness and accuracy are improved. Meanwhile, the multi-layer sensor structure has strong feature extraction capability, which is beneficial to improving the performance of the model, so that the potential safety hazard can be identified more accurately.
7. According to the scheme, the hydrogen storage and transportation safety is monitored through the hydrogen safety monitoring model, and a comprehensive safety monitoring and early warning system can be provided. These data can be used to analyze and evaluate the trend and frequency of hydrogen leakage, providing a reference basis for improved safety measures. Meanwhile, regular model detection and calibration work can ensure normal operation and accuracy of equipment, potential faults can be found and removed in time, and reliability and stability of the safety monitoring system are improved.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures.
Fig. 1 is a flow chart of a safety monitoring method based on hydrogen storage and transportation.
Fig. 2 is a schematic diagram of a safety monitoring system based on hydrogen storage and transportation according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings and examples, it being understood that the detailed description herein is merely a preferred embodiment of the present invention, which is intended to illustrate the present invention, and not to limit the scope of the invention, as all other embodiments obtained by those skilled in the art without making any inventive effort fall within the scope of the present invention.
Example 1: as shown in fig. 1, the safety monitoring method based on hydrogen storage and transportation comprises the following steps:
S1, acquiring parameter information of a hydrogen storage container based on a sensor to obtain hydrogen storage container information data.
Specifically, S1 includes the steps of:
S11, acquiring first information data and second information data of a hydrogen storage container based on a first sensor and a second sensor;
And S12, integrating the first information data and the second information data to obtain hydrogen storage container information data.
According to the embodiment, the sensor is used for collecting the parameter information of the hydrogen storage container, and the sensor can monitor key parameters of the hydrogen storage container, such as hydrogen concentration, pressure, temperature and the like, in real time, so that the safety and stability of the hydrogen storage process are ensured, the sensor is suitable for changes and uncertainties in different environments, and the flexibility and adaptability of the system are improved. Through real-time data acquisition, the sensor can timely find potential safety hazards such as hydrogen leakage, pressure abnormality and the like, and further corresponding early warning and handling measures are adopted to prevent accidents.
It is understood that the first sensor and the second sensor may be a pressure sensor, a temperature sensor, a gesture sensor, etc., and the first information data and the second information data may be pressure data, temperature data, gesture data, etc., and the pressure data, the temperature data, the gesture data, etc. are integrated to obtain hydrogen storage container information data.
S2, preprocessing the hydrogen storage container information data to obtain a calculation data set.
Specifically, S2 includes the steps of:
s21, analyzing the hydrogen storage container information data to obtain data attributes;
S22, performing correlation calculation on the hydrogen storage container information data based on the data attribute to obtain hydrogen storage container correlation data;
S23, classifying the hydrogen storage container information data through a Tanh activation function based on the hydrogen storage container relativity data to obtain classification data;
S24, performing correction and normalization operation on the classified data to generate a calculation data set.
Specifically, S24 includes the steps of:
s241, checking and layering the classified data to obtain layered classified data;
s242, carrying out data processing on the hierarchical classification data and transmitting the hierarchical classification data to a target data warehouse;
S243, carrying out standard deviation normalization processing on the target data warehouse to obtain normalized data so as to obtain a calculation data set.
In this embodiment, by preprocessing the hydrogen storage container information data, erroneous, abnormal or repeated data can be corrected or deleted, thereby ensuring the accuracy and consistency of the data. This aids in the accuracy and reliability of subsequent analysis. The preprocessing process may include feature extraction and selection that helps extract important information from the raw data for hydrogen storage vessel performance and safety assessment. These features can be used as input for subsequent analysis to improve the pertinence and effectiveness of the analysis.
S3, constructing a sample set based on the public data storage library, and marking the pressure change characteristic and the temperature gradient characteristic of the sample set to obtain a marked sample set.
Specifically, S3 includes the steps of:
S31, constructing a sample set by acquiring a public data storage library;
s32, analyzing the time sequence of the sample set according to the data attribute to obtain a pressure change periodic characteristic and a pressure change trend so as to obtain a pressure change characteristic;
s33, counting the temperature gradients at different positions in the hydrogen storage container information data according to the data attributes to obtain temperature gradient characteristics;
and S34, labeling the pressure change characteristic and the temperature gradient characteristic in a sample set to obtain a labeled sample set.
In the embodiment, the sample set is constructed by acquiring the public data storage library, so that the variety and the number of samples can be enriched, more comprehensive support is provided for subsequent data analysis and model training, and meanwhile, the data in the public data storage library is usually subjected to strict screening and auditing, so that the quality and the reliability are higher. The data is used as a sample set, so that the accuracy and the reliability of data analysis can be improved, and the analysis result deviation caused by the data quality problem can be reduced.
The key information can be more accurately identified and understood by marking the pressure change characteristics and the temperature gradient characteristics in the sample set. These features are critical to the performance analysis and safety assessment of hydrogen storage vessels. By using these features as inputs to the model, the model can learn better about the intrinsic rules and patterns of the data, thereby improving the accuracy of predictions and classification.
And S4, constructing a first multi-layer perceptron structure, and training the optimal multi-layer perceptron structure based on the labeling sample set to obtain a hydrogen safety monitoring model.
Specifically, S4 includes the steps of:
s41, constructing a group of first multi-layer perceptron structures, training and evaluating the first multi-layer perceptron structures through the labeling sample set, and obtaining the fitness value of each individual and a second multi-layer perceptron structure;
S42, based on the fitness value, selecting a second multi-layer sensor structure as a parent to perform cross operation, and obtaining a first child individual, wherein the cross operation is multi-point cross;
s43, performing mutation operation on the first offspring individuals to generate second offspring individuals;
S44, integrating the second offspring individuals with a second multi-layer sensor structure to obtain a multi-layer sensor population;
s45, sequentially performing cross operation and mutation operation on the multi-layer perceptron population until the maximum iteration number is reached, and outputting a final population;
S46, selecting an individual with the highest fitness in the final population as an optimal multi-layer sensor structure;
And S47, training the optimal multi-layer sensor structure based on the labeling sample set to obtain a hydrogen safety monitoring model.
Specifically, the mutation operation includes changing the neuron connection weight, modifying the activation function, and adjusting the number of neurons.
In the embodiment, the multi-dimensional characteristics including various monitoring indexes such as pressure, temperature and humidity can be learned simultaneously by constructing the multi-layer sensor structure and obtaining the hydrogen safety monitoring model, so that the state and the characteristics of the hydrogen storage and transportation system can be comprehensively sensed, and the monitoring comprehensiveness and accuracy are improved. Meanwhile, the multi-layer sensor structure has strong feature extraction capability, which is beneficial to improving the performance of the model, so that the potential safety hazard can be identified more accurately. The convergence speed and the precision of the model are improved through optimization methods such as a genetic algorithm, a gradient descent algorithm and the like.
It will be appreciated that the genetic algorithm is an optimization algorithm based on population searching that is capable of finding the optimal solution in the entire solution space, rather than being limited to localized areas. This makes genetic algorithms particularly suitable for dealing with complex and nonlinear problems. Genetic algorithms can be executed in parallel, which enables superior solutions to be searched out more quickly in a multi-processor or distributed environment. In addition, the genetic algorithm is easy to be mixed with other technologies and has expansibility.
And S5, taking the calculated data set as input, acquiring a hydrogen safety monitoring prediction result based on the hydrogen safety monitoring model, and monitoring the hydrogen storage and transportation safety based on the hydrogen safety monitoring prediction result.
Specifically, S5 includes the steps of:
S51, taking the calculated data set as input, and obtaining a hydrogen safety monitoring prediction result based on a hydrogen safety monitoring model;
S52, analyzing the hydrogen safety monitoring prediction result to obtain a potential safety hazard prediction result and an abnormal condition prediction result;
And S53, monitoring the hydrogen storage and transportation safety based on the potential safety hazard prediction result and the abnormal condition prediction result.
In this embodiment, the hydrogen safety monitoring model monitors the safety of hydrogen storage and transportation, and can provide a comprehensive safety monitoring and early warning system. These data can be used to analyze and evaluate the trend and frequency of hydrogen leakage, providing a reference basis for improved safety measures. Meanwhile, regular model detection and calibration work can ensure normal operation and accuracy of equipment, potential faults can be found and removed in time, and reliability and stability of the safety monitoring system are improved.
The invention also provides a safety monitoring system based on hydrogen storage and transportation: the safety monitoring system based on hydrogen storage and transportation comprises a data acquisition module, a sample set processing module, a preprocessing module, a model construction module and a result generation module; the data acquisition module acquires parameter information of the hydrogen storage container through a sensor so as to obtain hydrogen storage container information data; the preprocessing module is used for preprocessing the hydrogen storage container information data to obtain a calculation data set; the sample set processing module obtains a sample set through a public data storage library, marks the pressure change characteristics and the temperature gradient characteristics of the sample set, and obtains a marked sample set; the model construction module is used for constructing a first multi-layer perceptron structure and training the optimal multi-layer perceptron structure based on the labeling sample set to obtain a hydrogen safety monitoring model; the result generation module is used for inputting the calculation data set into the hydrogen safety monitoring model for calculation to obtain a hydrogen safety monitoring prediction result, and monitoring the hydrogen storage and transportation safety based on the hydrogen safety monitoring prediction result.
The embodiment obtains a calculation data set by preprocessing hydrogen storage container information data; the method comprises the steps of obtaining a sample set, marking the sample set, constructing and improving a multi-layer perceptron, training the optimal multi-layer perceptron based on the marked sample set, obtaining a hydrogen safety monitoring model, inputting a calculation data set into the hydrogen safety monitoring model for calculation, and monitoring the hydrogen storage and transportation safety by the obtained hydrogen safety monitoring prediction result, so that the early warning capability and the safety capability under the condition of hydrogen storage and transportation are improved, the state and the characteristics of a hydrogen storage and transportation system can be comprehensively perceived, and the monitoring response is timely and accurate, thereby improving the monitoring comprehensiveness and accuracy.
Further, embodiment 2 is an expansion of the content of embodiment 1, specifically as follows: as shown in fig. 1, the present embodiment provides a method for monitoring safety of hydrogen storage, which includes:
With the advancement of energy conversion, hydrogen has received increasing attention as a clean and efficient energy source. In the aspect of monitoring the hydrogen storage container, the embodiment provides a method based on a sensor and machine learning, and aims to improve the safety of hydrogen storage application.
Acquiring parameter information of the hydrogen storage container based on the sensor to obtain data of the hydrogen storage container;
Preprocessing data of a hydrogen storage container to obtain a data set to be calculated;
A sample set is obtained, and the pressure change characteristic and the temperature gradient characteristic of the sample set are marked to obtain a marked sample set;
constructing and improving a multi-layer perceptron, and training the improved multi-layer perceptron based on the labeling sample set to obtain a hydrogen monitoring model;
And inputting the data set to be calculated into the hydrogen monitoring model for calculation to obtain a predicted result for hydrogen storage and operation, and monitoring the safety for hydrogen storage and transportation based on the predicted result for hydrogen storage and operation.
First, the present embodiment uses sensors to collect key parameters of the hydrogen storage container in real time, including pressure, temperature, etc. These parameters are important basis for evaluating the state of the hydrogen storage container, and the operation state of the hydrogen storage container can be known in real time through the data acquired by the sensor.
The collected data needs to be preprocessed to eliminate interference factors such as noise, abnormal values and the like, and the data quality is improved. The preprocessed data is used as a data set to be calculated, and a basis is provided for subsequent analysis and modeling.
In order to construct the hydrogen monitoring model, this embodiment needs to obtain a sample set, and label the pressure change feature and the temperature gradient feature of the sample set. The labeling process requires accurate classification and labeling of each feature in the sample set based on expertise to form a labeled sample set.
In constructing the model, the present embodiment selects a multilayer perceptron (MLP) as the base model. The MLP is a common neural network model, has good nonlinear mapping capability, and is suitable for processing complex pattern recognition problems. The multi-layer sensor has excellent adaptability and generalization capability, and can process unseen data and make accurate predictions. This means that the hydrogen safety monitoring model can be applied to different environments and conditions and is not limited to the range covered by the training data. This generalization capability makes the model more reliable and efficient in practical applications.
Based on the labeling sample set, the embodiment trains the improved MLP to obtain a hydrogen monitoring model. In the training process, the embodiment adopts an optimization method such as a gradient descent algorithm and the like so as to improve the convergence speed and the precision of the model.
By training the multi-layer perceptron, the connection weights can be automatically adjusted to optimize the predictive performance. This means that the model can be continually learned and refined to better accommodate changes in the hydrogen environment. The optimization capability is helpful to improve the accuracy and reliability of the model, so that the model can better ensure the safety of hydrogen. In order to improve the performance of the model, the embodiment improves the MLP, including adjusting the network structure, optimizing parameters, and the like.
Finally, the embodiment inputs the calculation data set into the hydrogen monitoring model for calculation, and obtains the predicted result of hydrogen storage operation. The prediction results can provide important information about the safety of the hydrogen storage container for the embodiment, help the embodiment to find potential safety hazards in time and take corresponding measures for precaution.
According to a further optimized scheme, parameter information of the hydrogen storage container is acquired based on the sensor, and the process for obtaining data of the hydrogen storage container comprises the following steps:
Deploying a pressure sensor and a temperature sensor to the delivery port and the outside of the hydrogen storage container to obtain pressure data and temperature data; acquiring pose data of a hydrogen storage container through a pose sensor; and integrating the pressure data, the temperature data and the pose data to obtain the data of the hydrogen storage container.
Further optimizing scheme, preprocessing the data of the hydrogen storage container, and obtaining the data set to be calculated comprises the following steps:
analyzing the data of the hydrogen storage container to obtain data attributes; performing correlation calculation on the data of the hydrogen storage container based on the data attribute to obtain correlation data of the hydrogen storage container; classifying the data of the hydrogen storage container based on the relativity data of the hydrogen storage container and the Tanh activation function to obtain classification data; and (5) performing correction and normalization on the classified data to obtain a data set to be calculated.
Further optimizing the scheme, performing correction and normalization on the classified data, and obtaining the data set to be calculated comprises the following steps:
Checking consistency of the classified data, and layering the data; carrying out data conversion and data cleaning on the layered data, carrying out data loading on the processed data, and transmitting the data to a target data warehouse; and carrying out standard deviation normalization processing on the data stored in the target data warehouse to obtain normalized data.
Further optimizing the scheme, obtaining a sample set, marking the pressure change characteristic and the temperature gradient characteristic of the sample set, and obtaining the marked sample set comprises the following steps:
Analyzing the time sequence of the sample set based on the data attribute to obtain a pressure change periodic characteristic and a pressure change trend, and integrating the pressure change periodic characteristic and the pressure change trend to obtain a pressure change characteristic; based on the data attribute, counting the temperature gradients at different positions in the sample set to obtain a temperature gradient characteristic; and feeding back the pressure change characteristics and the temperature gradient characteristics to the sample set for marking, so as to obtain a marked sample set.
Further optimizing scheme, constructing and improving the multi-layer perceptron, training the improved multi-layer perceptron based on the labeling sample set, and obtaining the hydrogen monitoring model comprises the following steps:
Constructing a group of initial multi-layer perceptron structures, training the group of initial multi-layer perceptron structures through a labeling sample set, and evaluating performance to obtain fitness values of each individual and the trained multi-layer perceptron structures; selecting a part of trained multi-layer perceptron structure as a parent to carry out cross operation based on the fitness value of each individual to obtain a newly generated child individual, wherein the cross operation is multi-point cross; performing mutation operation on the newly generated offspring individuals to generate processed offspring individuals; integrating the treated offspring individuals with the trained multi-layer perceptron structure to obtain a new multi-layer perceptron population; sequentially performing cross operation and mutation operation on the new multi-layer perceptron population until the maximum iteration number is reached, and outputting to obtain a final population; and selecting the individual with the highest fitness in the final population as the optimal multi-layer sensor structure.
The method comprises the following specific steps:
s1, randomly generating a group of initial multi-layer perceptron structures, wherein the initial values comprise initial values of parameters such as neuron number, layer number, activation function and the like.
S2, training each individual (namely each multi-layer perceptron structure) by using the training data set, and evaluating the performance of the individual on the verification set or the cross verification set. This performance index is typically classification accuracy, regression error, etc.
S3, selecting a part of individuals as father of the next generation according to a certain selection strategy (such as roulette selection, tournament selection and the like) according to the fitness value of each individual.
S4, randomly selecting a pair of individuals from the selected father, and performing cross operation to generate new offspring individuals. The interleaving operation may be a single point interleaving, a multi-point interleaving, or the like.
S5, carrying out mutation operation with a certain probability on the newly generated offspring individuals so as to increase the diversity of the population. The mutation operation may be to change the neuron connection weight, modify the activation function, adjust the number of neurons, and the like.
S6, replacing the newly generated offspring individuals with a part of individuals in the original population to form a new population.
S7, repeating the steps 2-6 until stopping conditions (such as maximum iteration times, a certain threshold value of adaptability and the like) are reached.
S8, after iteration is stopped, selecting an individual with the highest fitness from the final population as an optimal multi-layer sensor structure.
S9, training the optimal individual again by using the training data set so as to further improve the performance of the optimal individual.
And training the optimal multi-layer perceptron structure based on the labeling sample set to obtain a hydrogen monitoring model.
Further optimization schemes, the process of mutating newly generated offspring individuals includes, but is not limited to, changing neuron connection weights, modifying activation functions, and adjusting the number of neurons.
Further optimizing scheme, inputting the data set to be calculated into the hydrogen monitoring model for calculation, and obtaining the predicted result of hydrogen storage operation comprises the following steps:
inputting the data set to be calculated into a hydrogen monitoring model for calculation, and generating a hydrogen safety monitoring prediction result; explaining the hydrogen safety monitoring prediction result to obtain a potential safety hazard prediction result and an abnormal condition prediction result; and monitoring the safety for hydrogen storage and transportation based on the potential safety hazard prediction result and the abnormal condition prediction result.
Further, embodiment 3 is a detailed description (principle, etc.) of the effect, purpose or certain feature of embodiment 1, as shown in fig. 2, in this embodiment, a safety monitoring system for hydrogen storage and transportation is provided, including:
The data acquisition module is used for acquiring parameter information of the hydrogen storage container based on the sensor to obtain data of the hydrogen storage container;
The pretreatment module is used for carrying out pretreatment on the data of the hydrogen storage container to obtain a data set to be calculated;
the sample set processing module is used for acquiring a sample set, marking the pressure change characteristic and the temperature gradient characteristic of the sample set, and acquiring a marked sample set;
The model construction module is used for constructing and improving the multi-layer perceptron, training the improved multi-layer perceptron based on the labeling sample set and obtaining a hydrogen monitoring model;
the result generation module is used for inputting the data set to be calculated into the hydrogen monitoring model for calculation, obtaining a predicted result for hydrogen storage and use, and monitoring the safety for hydrogen storage and use based on the predicted result for hydrogen storage and use.
The above embodiments are preferred embodiments of the present invention, and are not intended to limit the scope of the present invention, which includes but is not limited to the embodiments, and equivalent changes in shape, structure, and method according to the present invention are all within the scope of the present invention.
Claims (5)
1. The safety monitoring method based on hydrogen storage and transportation is characterized by comprising the following steps of:
S1, acquiring parameter information of a hydrogen storage container based on a sensor to obtain hydrogen storage container information data;
s2, preprocessing the hydrogen storage container information data to obtain a calculation data set;
S21, analyzing the hydrogen storage container information data to obtain data attributes;
S22, performing correlation calculation on the hydrogen storage container information data based on the data attribute to obtain hydrogen storage container correlation data;
S23, classifying the hydrogen storage container information data through a Tanh activation function based on the hydrogen storage container relativity data to obtain classification data;
s24, performing correction and normalization operation on the classified data to generate a calculation data set;
S241, checking and layering the classified data to obtain layered classified data;
s242, carrying out data processing on the hierarchical classification data and transmitting the hierarchical classification data to a target data warehouse;
S243, carrying out standard deviation normalization processing on the target data warehouse to obtain normalized data so as to obtain a calculation data set;
S3, constructing a sample set based on a public data storage library, and marking the pressure change characteristic and the temperature gradient characteristic of the sample set to obtain a marked sample set;
S31, constructing a sample set by acquiring a public data storage library;
S32, analyzing the time sequence of the sample set according to the data attribute to obtain a pressure change periodic characteristic and a pressure change trend so as to obtain a pressure change characteristic;
s33, counting the temperature gradients at different positions in the hydrogen storage container information data according to the data attributes to obtain temperature gradient characteristics;
S34, labeling the pressure change characteristics and the temperature gradient characteristics in a sample set to obtain a labeled sample set;
S4, constructing a first multi-layer perceptron structure, and training an optimal multi-layer perceptron structure based on the labeling sample set to obtain a hydrogen safety monitoring model;
S41, constructing a group of first multi-layer perceptron structures, training and evaluating the first multi-layer perceptron structures through labeling sample sets, and obtaining fitness values of each individual and second multi-layer perceptron structures;
s42, based on the fitness value, selecting a second multi-layer sensor structure as a parent to perform cross operation, and obtaining a first child individual, wherein the cross operation is multi-point cross;
s43, performing mutation operation on the first offspring individuals to generate second offspring individuals;
s44, integrating the second offspring individuals with the second multi-layer sensor structure to obtain a multi-layer sensor population;
S45, sequentially performing cross operation and mutation operation on the multi-layer perceptron population until the maximum iteration number is reached, and outputting a final population;
s46, selecting an individual with the highest fitness in the final population as an optimal multi-layer sensor structure;
s47, training the optimal multi-layer sensor structure based on the labeling sample set to obtain a hydrogen safety monitoring model;
And S5, taking the calculated data set as input, acquiring a hydrogen safety monitoring prediction result based on the hydrogen safety monitoring model, and monitoring the hydrogen storage and transportation safety based on the hydrogen safety monitoring prediction result.
2. The safety monitoring method based on hydrogen storage and transportation according to claim 1, wherein S1 comprises the steps of:
S11, acquiring first information data and second information data of a hydrogen storage container based on a first sensor and a second sensor;
And S12, integrating the first information data and the second information data to obtain hydrogen storage container information data.
3. The safety monitoring method based on hydrogen storage and transportation according to claim 1, wherein:
the mutation operation includes changing the neuron connection weight, modifying the activation function, and adjusting the number of neurons.
4. The safety monitoring method based on hydrogen storage and transportation according to claim 1, wherein S5 comprises the steps of:
S51, taking the calculated data set as input, and obtaining a hydrogen safety monitoring prediction result based on a hydrogen safety monitoring model;
s52, analyzing a hydrogen safety monitoring prediction result to obtain a potential safety hazard prediction result and an abnormal condition prediction result;
And S53, monitoring the hydrogen storage and transportation safety based on the potential safety hazard prediction result and the abnormal condition prediction result.
5. A safety monitoring system based on hydrogen storage and transportation, which is suitable for the safety monitoring method based on hydrogen storage and transportation according to any one of claims 1-4, and is characterized in that:
The safety monitoring system based on hydrogen storage and transportation comprises a data acquisition module, a sample set processing module, a preprocessing module, a model construction module and a result generation module;
The data acquisition module acquires parameter information of the hydrogen storage container through a sensor so as to obtain hydrogen storage container information data;
The preprocessing module is used for preprocessing the hydrogen storage container information data to obtain a calculation data set;
the sample set processing module obtains a sample set through a public data storage library, marks the pressure change characteristics and the temperature gradient characteristics of the sample set, and obtains a marked sample set;
The model construction module is used for constructing a first multi-layer perceptron structure and training the optimal multi-layer perceptron structure based on the labeling sample set to obtain a hydrogen safety monitoring model;
The result generation module is used for inputting the calculation data set into the hydrogen safety monitoring model for calculation to obtain a hydrogen safety monitoring prediction result, and monitoring the hydrogen storage and transportation safety based on the hydrogen safety monitoring prediction result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410442713.7A CN118088923B (en) | 2024-04-12 | 2024-04-12 | Safety monitoring method and system based on hydrogen storage and transportation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410442713.7A CN118088923B (en) | 2024-04-12 | 2024-04-12 | Safety monitoring method and system based on hydrogen storage and transportation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118088923A CN118088923A (en) | 2024-05-28 |
| CN118088923B true CN118088923B (en) | 2024-10-25 |
Family
ID=91147802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410442713.7A Active CN118088923B (en) | 2024-04-12 | 2024-04-12 | Safety monitoring method and system based on hydrogen storage and transportation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118088923B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA622848A (en) * | 1961-06-27 | W. Cameron Jack | Gas generating method and apparatus | |
| CN111947022A (en) * | 2020-06-30 | 2020-11-17 | 同济大学 | Filling method for vehicle-mounted hydrogen storage bottle of fuel cell vehicle |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7216040B2 (en) * | 2005-04-11 | 2007-05-08 | Air Products And Chemicals, Inc. | Intelligent network of hydrogen supply modules |
| US11703186B2 (en) * | 2020-06-01 | 2023-07-18 | Daniel McNicholas | Safe transportation system operations including fueling, transfer and charging |
| CN113724880A (en) * | 2021-11-03 | 2021-11-30 | 深圳先进技术研究院 | Abnormal brain connection prediction system, method and device and readable storage medium |
| FR3130047B1 (en) * | 2021-12-08 | 2023-11-03 | Commissariat Energie Atomique | Method and device for controlling a system using an artificial neural network based on continuous learning |
| CN116045203A (en) * | 2022-12-29 | 2023-05-02 | 陕西燃气集团富平能源科技有限公司 | Hydrogen storage and transportation safety monitoring system and monitoring method thereof |
| CN116150693A (en) * | 2022-12-30 | 2023-05-23 | 南斗六星系统集成有限公司 | Hydrogen fuel cell engine safety evaluation method, device, equipment and storage medium |
| CN116242611A (en) * | 2023-01-05 | 2023-06-09 | 上海电机学院 | Motor bearing fault diagnosis method |
| CN116447514A (en) * | 2023-04-12 | 2023-07-18 | 江苏大学 | Hydrogen storage tank intelligent early warning device and method |
-
2024
- 2024-04-12 CN CN202410442713.7A patent/CN118088923B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA622848A (en) * | 1961-06-27 | W. Cameron Jack | Gas generating method and apparatus | |
| CN111947022A (en) * | 2020-06-30 | 2020-11-17 | 同济大学 | Filling method for vehicle-mounted hydrogen storage bottle of fuel cell vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118088923A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lavin et al. | Evaluating real-time anomaly detection algorithms--the Numenta anomaly benchmark | |
| CN110309886A (en) | The real-time method for detecting abnormality of wireless sensor high dimensional data based on deep learning | |
| Nkonyana et al. | Performance evaluation of data mining techniques in steel manufacturing industry | |
| CN113762329A (en) | Method and system for constructing state prediction model of large rolling mill | |
| CN116737510B (en) | Data analysis-based intelligent keyboard monitoring method and system | |
| CN117972580B (en) | Remote monitoring method and system for aviation obstruction lights | |
| CN117785858A (en) | Big data-based information data management method and system | |
| CN117390499A (en) | Be applied to multiple sample detecting system that food pesticide remained and detected | |
| CN111767657B (en) | Nuclear power system fault diagnosis method and system | |
| CN117708669A (en) | Multi-source data-based adaptive probability neural network high-voltage cable state evaluation method | |
| CN117032165A (en) | Industrial equipment fault diagnosis method | |
| Chernov et al. | Intelligent decision support for power grids using deep learning on small datasets | |
| US20230221684A1 (en) | Explaining Machine Learning Output in Industrial Applications | |
| CN118246744A (en) | Risk assessment method and system for construction site of extra-long tunnel | |
| CN116204825A (en) | Production line equipment fault detection method based on data driving | |
| CN118088923B (en) | Safety monitoring method and system based on hydrogen storage and transportation | |
| Bond et al. | A hybrid learning approach to prognostics and health management applied to military ground vehicles using time-series and maintenance event data | |
| CN118152355A (en) | Log acquisition management method and system | |
| CN117763341A (en) | Internet hazardous chemical substance safety production monitoring platform constructed by utilizing big data technology | |
| Wang et al. | Health state assessment of industrial equipment driven by the fusion of digital twin model and intelligent algorithm | |
| CN116311739A (en) | Multi-sensor fire detection method based on long-short-term memory network and environment information fusion | |
| CN115598459A (en) | Power failure prediction method for 10kV feeder line fault of power distribution network | |
| Das et al. | Unbalanced Fault Classification Using Active Learning in Synthetic Fiber Manufacturing Process | |
| CN118536048B (en) | Switch cabinet insulation state monitoring and management system | |
| CN118053218B (en) | Method, device and system for detecting computer board card |
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 |