Dangerous chemical substance transportation tank car safety state detection method and system based on digital twinning technology

Abstract

The invention discloses a method and a system for detecting the safety state of a hazardous chemical substance transportation tank truck based on a digital twinning technology. The system comprises a data acquisition module, a data processing module, a risk assessment module, a digital twinning module and a decision support module. And the data acquisition module can acquire data in various aspects in the transportation process of the tank car. An intelligent assessment algorithm is built in the risk assessment module, and risk diagnosis can be carried out based on the four aspects of people, vehicles, goods and rings. And the digital twin module integrates the digital model and dynamic data to realize visual management of a transportation tank truck structure, a risk evolution process and a coupling relationship among the sub-models. And the decision support module is used for providing decision support for operators in combination with the current situation and historical data. According to the data-model-knowledge-driven multi-domain performance evaluation solution provided by the invention, the safety and reliability of the transportation process can be effectively improved.

Description

Technical Field

[0001] The present invention belongs to the field of hazardous chemicals transportation monitoring, and specifically relates to a method and system for detecting the safety status of hazardous chemicals transport tank trucks based on digital twin technology. Background Art

[0002] With the rapid development of my country's industrial economy, the demand for hazardous chemicals is increasing, and the transportation of hazardous chemicals has gradually occupied an important position in modern industrial and economic activities. However, due to the inherent danger of hazardous chemicals, accidents often occur during the transportation of hazardous chemicals. Each hazardous chemical transportation accident may cause casualties, property losses and environmental pollution, which in turn affects the stability and sustainable development of society. Therefore, how to improve the safety of hazardous chemical transportation has become a common concern of the industry and society.

[0003] At present, with the increase in transportation volume, the substantial expansion of road transportation mileage, and the increasingly complex transportation conditions, transportation accidents involving the transportation of hazardous chemicals have also gradually increased. However, due to the uneven professional quality of practitioners, the probability of accidents has greatly increased. Therefore, in order to analyze the internal and external factors affecting the occurrence of accidents and take targeted measures, it is particularly important to establish a suitable safety status assessment method and monitoring system for hazardous chemical tankers. However, most technologies now focus on a single link or use related means to achieve full-process data monitoring during the transportation of hazardous chemicals. However, there is a lack of accurate perception of the status of hazardous chemical tankers during transportation and early warning of real-time evolution of risks. In addition, existing technologies still face limitations in data accuracy, real-time and system stability in practical applications.

[0004] Therefore, this patent proposes a digital twin system for detecting the safety status of hazardous chemical transport tank trucks. The system aims to establish a multi-layer structure tree that can truly depict the operation of the tank truck by adding spatial relationships, constraint relationships and other associations to parts and components, and assemble and integrate them into a digital twin model of complex equipment. Based on the intelligent early warning algorithm, the operating status of the hazardous chemical transport tank truck is risk assessed and visualized, forming a data-model-knowledge driven multi-domain performance evaluation solution that can effectively ensure the safety and reliability of the transportation process. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for detecting the safety status of a hazardous chemicals transport tanker based on digital twin technology, so as to solve the deficiencies of the above-mentioned prior art.

[0006] To achieve the above objectives, the present invention provides a method for detecting the safety status of a hazardous chemicals transport tanker based on digital twin technology, comprising:

[0007] Step 1: The data acquisition module is used to collect the multi-factor perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemicals tank trucks. The data includes: vehicle speed, acceleration, roll angle, tank temperature, tank pressure, tank liquid level, driver's driving behavior, relative speed of front and rear vehicles, relative distance, weather conditions, and road area;

[0008] Step 2: Preprocess the collected data through the data preprocessing module, the preprocessing includes: cleaning, missing value filling, outlier processing, classification operations, and transmit the processed data to the risk assessment module;

[0009] Step 3: construct a risk assessment and early warning model through an intelligent assessment algorithm, use the preprocessed data to input the initial risk assessment and early warning model and train it to obtain a trained risk assessment and early warning model, wherein the risk assessment and early warning model includes a primary risk assessment module and an overall risk assessment module;

[0010] Step 4: Obtain real-time multi-factor perception data of "people-vehicle-cargo-environment" of hazardous chemicals transport tankers, and identify and warn of various unsafe conditions in the operation of hazardous chemicals transport tankers through risk assessment and early warning models, so as to evaluate the safety status of the four dimensions of people-vehicle-cargo-environment of hazardous chemicals transport tankers;

[0011] Step 5: Construct a digital twin module, based on the data output of the risk assessment and early warning model, display the structure, risk evolution process, parameter details and coupling relationship between sub-models of the digital twin tank truck model in a three-dimensional interactive manner, and issue early warnings for safety risks in the operation status of hazardous chemicals tank trucks, so as to realize data-model-knowledge driven intelligent early warning;

[0012] Step 6: Combining the current situation with historical data, based on the model output and intelligent state representation of the digital twin module, predict possible failures or dangerous events in advance, provide decision support operations for operators, and ensure the safety and reliability of the transportation process.

[0013] Furthermore, the data acquisition module is used to collect multi-factor perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemicals tank trucks, including:

[0014] The multi-factor perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemicals tank trucks is derived from the vehicle monitoring data of hazardous chemicals tank trucks and the hazardous chemicals monitoring data;

[0015] Collect various unsafe conditions of hazardous chemicals tank trucks in operation;

[0016] Among them, the various unsafe conditions include abnormalities of the hazardous chemicals transport tanker, abnormal status of hazardous chemicals, abnormal status of the driver of the hazardous chemicals transport tanker, and interference from the surrounding environment;

[0017] The abnormalities of the hazardous chemicals transport tanker vehicles include: fatigue failure of key parts of the tanker vehicles, tanker vehicle rollover, and tanker vehicle collision threats;

[0018] The abnormal state of hazardous chemicals includes abnormal reactions in four aspects: liquid level in the tank, pressure in the tank, temperature in the tank, and gas concentration;

[0019] The abnormal state of the driver of the hazardous chemicals transport tanker includes monitoring the driver's dangerous driving behavior, including monitoring the driver's driving behavior, the number of times the driver blinks and yawns;

[0020] The surrounding environment interference is obtained by monitoring weather conditions in different scenarios, including road accidents in fog, rain, snow, temperature, and wind speed scenarios.

[0021] Furthermore, in step 4, the safety status of the hazardous chemicals transport tanker in four dimensions of personnel, vehicle, cargo and environment is evaluated, including:

[0022] First, use the primary risk assessment module to conduct a first-level risk status assessment on the four dimensions of people, vehicles, cargo and environment. Then use the overall risk assessment module to integrate people, vehicles, cargo and environment together through the fuzzy comprehensive evaluation method for a second-level assessment.

[0023] Furthermore, the primary risk assessment module is used to conduct a first-level risk status assessment on the four dimensions of people-vehicle-cargo-environment, including: judging the driver's behavior using a visual detection algorithm for the safety status of the person, and the dangerous behaviors include: making phone calls, yawning, drinking water, playing with mobile phones, and nodding sleepily, and outputting the first-level risk status assessment factor of the "person";

[0024] In view of the safety status of the tank truck, firstly, the classification thresholds are set for the speed, acceleration and tank inclination of the tank truck in different scenes and locations to make a preliminary assessment of the vehicle status of the tank truck itself; then, a secondary assessment is made through the relative speed and relative distance of the front and rear vehicles collected by data to obtain the current status of the tank truck; at the same time, based on the relationship between mileage and stress cycle number, by combining the fatigue strength index and fatigue strength coefficient in the SN curve and the concept of cumulative damage in Miner theory, an early warning model for the fatigue life of components estimated by mileage is constructed; combined with the above algorithm, the first-level risk status assessment factor of the "vehicle" is output;

[0025] The safety status of hazardous chemicals in hazardous chemicals transport tankers can be derived from their temperature, pressure, and liquid level. The temperature and pressure are predicted by using the LSTM neural network, and the status of hazardous chemicals is evaluated based on the predicted data using the threshold method. At the same time, the first-level risk status assessment factor of the relevant goods is output.

[0026] Furthermore, the use of LSTM neural network to predict temperature and pressure includes:

[0027] Construct a two-layer LSTM neural network; the input layer is composed of time vectors of characteristic parameters such as temperature, pressure, vehicle speed, liquid level, tank inclination, etc.; the first layer is the LSTM layer, in which multiple memory units are set, and one part is used to process input data, and the other part is used to obtain the memory layer from the previous layer; the second layer is the dropout layer, which is used to randomly discard the output of the previous layer to reduce the risk of overfitting; the third layer is the second LSTM layer, which is used to continue processing the output of the previous layer, further extract features and generate new outputs; the fourth layer is the second dropout layer, which will randomly discard the output again to ensure the generalization ability of the network; the last layer is the fully connected layer, which calculates the output of the previous layer through linear transformation and finally generates a prediction result vector of multiple categories;

[0028] Among them, the mean square error (MSE) is selected as the loss function during the training of the primary risk assessment module, and the Adam optimizer is used for optimization to prevent overfitting of the model and improve the stability of training;

[0029] The threshold method is used to perform graded judgment based on the predicted data. When the predicted value reaches the first-level warning threshold, the current state is output. If it reaches the second-level warning threshold, it is judged again through the same temperature difference comparison method, temperature change rate and temperature deviation.

[0030] Furthermore, the overall risk assessment module uses a fuzzy comprehensive evaluation method to integrate people, vehicles, goods and environment for secondary evaluation, including:

[0031] A double-layer fuzzy evaluation model is constructed, and the characteristic data of the hazardous chemicals transport tank truck are studied to establish an index evaluation system. The factor set can be expressed as:

[0032] U={u1,u2,u3...,u n}, where u1, u2, u3, …u n Indicates the evaluation factor;

[0033] The influence of each factor in the factor set on the safety status of the tank truck can be divided into five levels: poor, slightly poor, medium, slightly better, and good; the level set of any factor can be expressed as:

[0034] u i = {u i1 ,u i2 ,u i3 ,u i4 ,u i5},(i=1,2,3...,n), where u i1 、u i2 、u i3 、u i4 、u i5 Indicates the evaluation level under the corresponding evaluation factor;

[0035] A weight is set for each factor, expressed as:

[0036] A={a1,a2,a3...,a n}

[0037] and Among them, a1, a2, a3..., a n Indicates the weight corresponding to each factor;

[0038] The fuzzy evaluation level obtained by the first-level fuzzy comprehensive evaluation method is:

[0039] V = {v1, v2, v3, v4, v5}, where v1, v2, v3, v4, v5 represent the fuzzy evaluation levels of each factor;

[0040] By calculating a factor u of the factor set U i Evaluate and obtain V for each evaluation level j The membership degree r ij ,Right now:

[0041] r ij = {r i1 ,r i2 ,r i3 ,r i4 ,r i5},(i=1,2,3...,n)

[0042] Establish a comprehensive evaluation matrix:

[0043] The factor weight set A and the comprehensive evaluation matrix R are obtained, and the fuzzy comprehensive evaluation set B is obtained through the generalized fuzzy synthesis operator *: B = A*R = (b1, b2, b3, ..., b n )

[0044] A multi-level evaluation method is used for comprehensive evaluation. Assuming that the subset can be divided into m factors, the corresponding factor set is:

[0045] U2={ui1 ,u i2 ,u i3 ...,u im},(i=1,2,3...,n), where u i1 ,u i2 ,u i3 ...,u im Indicates the evaluation level under the corresponding evaluation factor;

[0046] Its factor weight set is:

[0047] A2={a i1 ,a i2 ,a i3 ...,a im},(i=1,2,3,...,n), where, a i1 ,a i2 ,a i3 ...,a in Indicates the weight corresponding to each factor;

[0048] By establishing the second-level comprehensive evaluation matrix, we can obtain the second-level comprehensive evaluation set:

[0049] B i =A i *R i =(b i1 ,b i2 ,b i3 ,...,b in ), where i = 1, 2, 3, 4, ..., n;

[0050] The first-level comprehensive evaluation result is used as input, and the fuzzy synthesis operation is performed again to obtain the final comprehensive evaluation result;

[0051] Once the fuzzy evaluation model is established, the risk evaluation level of hazardous chemicals transport tank trucks is output in the form of a membership function, where the degree of influence of each factor on the safety status of the tank truck can be divided into five levels, namely: poor, slightly poor, medium, slightly better, and good.

[0052] Furthermore, the construction of the digital twin module in step 5 includes:

[0053] Construct the three-dimensional display module, data transmission module, model correction module, and early warning module in sequence;

[0054] The three-dimensional display module is used to display the digital model of the hazardous chemicals transport tanker, and to construct a response model describing the behavior characteristics of the tanker by considering the behavioral coupling relationship between various components;

[0055] The data transmission module is used to input the data collected by the data collection module and the results of the risk assessment module on various aspects into the model correction module;

[0056] The model correction module corrects the model displayed by the three-dimensional display module through the received data, and constructs various parameters and objective functions to make the model output results as close to the physical results as possible. Its goal is to ensure the accuracy of the model so that it can better adapt to different application requirements and conditions; the early warning module is based on preset safety thresholds and logical rules. When an indicator change beyond the normal range is detected, the corresponding alarm mechanism is immediately triggered to warn of various states of the hazardous chemicals transport tanker to remind the driver and background supervisory personnel.

[0057] As a further improvement method of the present invention:

[0058] Optionally, the present invention also provides a safety status detection system for hazardous chemicals transport tankers based on digital twin technology, characterized in that: the system includes a data acquisition module, a data processing module, a risk assessment module, a digital twin module and a decision support module;

[0059] A data acquisition module is used to collect multi-factor perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemicals tank trucks through the data acquisition module. The data includes: vehicle speed, acceleration, roll angle, tank temperature, tank pressure, tank liquid level, driver's driving behavior, relative speed of front and rear vehicles, relative distance, weather conditions, and road area;

[0060] The data processing module is used to pre-process the collected data through the data pre-processing module, wherein the pre-processing includes: cleaning, missing value filling, outlier processing, classification operations, and transmitting the processed data to the risk assessment module;

[0061] A risk model building module is used to build a risk assessment and early warning model through an intelligent assessment algorithm, use the preprocessed data to input the initial risk assessment and early warning model and perform training to obtain a trained risk assessment and early warning model, wherein the risk assessment and early warning model includes a primary risk assessment module and an overall risk assessment module;

[0062] The risk assessment module is used to obtain real-time multi-factor perception data of "people-vehicle-cargo-environment" of hazardous chemicals transport tankers, and identify and warn of various unsafe conditions in the operation of hazardous chemicals transport tankers through risk assessment and early warning models, so as to evaluate the safety status of the four dimensions of people-vehicle-cargo-environment of hazardous chemicals transport tankers;

[0063] The digital twin module is used to display the structure, risk evolution process, parameter details and coupling relationship between sub-models of the digital twin tank truck model in a three-dimensional interactive manner based on the data output of the risk assessment and early warning model, and to warn of the safety risks of the operation status of the hazardous chemicals tank truck, so as to realize data-model-knowledge driven intelligent early warning;

[0064] The decision support module is used to combine the current situation with historical data, based on the model output and intelligent state representation of the digital twin module, to predict possible failures or dangerous events in advance, provide decision support operations for operators, and ensure the safety and reliability of the transportation process.

[0065] As a further improvement method of the present invention:

[0066] Optionally, the present invention also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method for detecting the safety status of a hazardous chemical transport tank truck based on digital twin technology when executing the computer program.

[0067] As a further improvement method of the present invention:

[0068] Optionally, the present invention also provides a computer storage medium, which stores a computer program, characterized in that when the computer program is executed by a processor, the steps of the method for detecting the safety status of a hazardous chemicals transport tanker based on digital twin technology are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A flow chart of a state detection method provided by an embodiment of the present invention

[0070] Figure 2 The intelligent early warning algorithm structure of the tank truck safety status provided by an embodiment of the present invention

[0071] Figure 3 A neural network structure diagram provided for an embodiment of the present invention

[0072] Figure 4 A fuzzy evaluation model structure diagram provided for an embodiment of the present invention

[0073] Figure 5 A membership function diagram provided by an embodiment of the present invention

[0074] Figure 6 Schematic diagram of the digital twin module structure provided by an embodiment of the present invention

[0075] Figure 7 Schematic diagram of a safety status detection system module provided by an embodiment of the present invention

[0076] Figure 8 A schematic diagram of a device structure provided in accordance with an embodiment of the present invention

[0077] In the figure: 1 electronic device, 10 processor, 11 memory, 12 program, 13 communication interface.

[0078] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0079] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0080] The embodiment of the present application provides a method for detecting the safety status of a hazardous chemical transport tanker based on digital twin technology. The execution subject of the method includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc., and the platform communicating with the server involves multiple micro-monitoring service platforms.

[0081] Embodiment 1:

[0082] A safety status detection method for hazardous chemicals transport tanker based on digital twin technology, such as Figure 1 As shown, the following steps are included:

[0083] S1: The data acquisition module is used to collect the multi-factor perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemicals tank trucks. The data include: vehicle speed, acceleration, roll angle, tank temperature, tank pressure, tank liquid level, driver's driving behavior, relative speed of front and rear vehicles, relative distance, weather conditions, and road area.

[0084] Specifically, the data acquisition module is used to collect various data during the transportation process of the hazardous chemicals transport tanker, and the data collected by the data acquisition module will be transmitted to the data processing module for various pre-processing operations.

[0085] S2: Preprocess the collected data through the data preprocessing module, wherein the preprocessing includes: cleaning, missing value filling, outlier processing, classification operations, and the processed data is transmitted to the risk assessment module.

[0086] Specifically, the data processing module is used to clean, fill in missing values, process outliers, and classify the data collected by the data acquisition module, and then transmit the processed data to the risk assessment module.

[0087] S3: Construct a risk assessment and early warning model through an intelligent assessment algorithm, use the preprocessed data to input the initial risk assessment and early warning model and train it to obtain a trained risk assessment and early warning model, wherein the risk assessment and early warning model includes a primary risk assessment module and an overall risk assessment module.

[0088] S4: Obtain real-time multi-factor perception data of "people-vehicle-cargo-environment" of hazardous chemicals transport tank trucks, and identify and warn of various unsafe conditions in the operation of hazardous chemicals transport tank trucks through risk assessment and early warning models, so as to evaluate the safety status of the four dimensions of people-vehicle-cargo-environment of hazardous chemicals transport tank trucks.

[0089] S5: Construct a digital twin module, based on the data output of the risk assessment and early warning model, to display the structure, risk evolution process, parameter details and coupling relationship between sub-models of the digital twin tank truck model in a three-dimensional interactive manner, and issue early warnings for the safety risks of the operating status of hazardous chemicals tank trucks, so as to realize data-model-knowledge driven intelligent early warning.

[0090] S6: Combining the current situation with historical data, based on the model output and intelligent state representation of the digital twin module, predict possible failures or dangerous events in advance, provide decision support operations for operators, and ensure the safety and reliability of the transportation process.

[0091] like Figure 2 The structure of the intelligent early warning algorithm for the safety status of the tank truck is shown. The intelligent early warning algorithm model includes: a sequence input layer, a neural network layer, and a regression output layer; wherein, the feature vector is input into the sequence input layer to obtain a time series feature input vector, which is transmitted to the neural network layer, and the neural network layer includes multiple LSTM neural network structures, and the pre-result input vector is obtained after multi-dimensional time series processing.

[0092] First, use the primary risk assessment module to conduct a first-level risk status assessment on the four dimensions of people, vehicles, cargo and environment. Then use the overall risk assessment module to integrate people, vehicles, cargo and environment together through the fuzzy comprehensive evaluation method for a second-level assessment.

[0093] Specifically, with respect to a person’s safety status, visual detection algorithms can be used to judge the driver’s behavior. Dangerous behaviors include: making phone calls, yawning, drinking water, playing with mobile phones, and nodding sleepily, and output the first-level risk status assessment factor for the “person”.

[0094] In view of the safety status of the tank truck, we first set classification thresholds for the tank truck speed, acceleration, and tank inclination in different scenarios and locations to make a preliminary assessment of the tank truck's own vehicle status; then, we make a secondary assessment based on the relative speed and relative distance of the front and rear vehicles collected through data to obtain the tank truck's current status; at the same time, based on the relationship between mileage and the number of stress cycles, by combining the fatigue strength index and fatigue strength coefficient in the SN curve, and the concept of cumulative damage in Miner theory, we construct an early warning model for component fatigue life estimated by mileage; combined with the above algorithm, we output the first-level risk status assessment factor of the "vehicle".

[0095] The safety status of hazardous chemicals in hazardous chemicals transport tankers can be derived from their temperature, pressure, and liquid level. The temperature and pressure are predicted by using the LSTM neural network, and the status of hazardous chemicals is evaluated based on the predicted data using the threshold method. At the same time, the first-level risk status assessment factor of the relevant goods is output.

[0096] The data of the hazardous chemicals storage environment and the data of the hazardous chemicals themselves that have been preprocessed are input into the LSTM model for training to obtain training results; the error reverse analysis is performed on the training results, and the training parameters of the LSTM prediction model are adjusted based on the reverse analysis to obtain a trained LSTM prediction model.

[0097] Construct a two-layer LSTM neural network; its structure is as follows Figure 3 As shown in the figure, the input layer is composed of time vectors of characteristic parameters such as temperature, pressure, vehicle speed, liquid level, and tank inclination; the first layer is an LSTM layer, in which multiple memory units are set, and one part is used to process input data, and the other part is used to obtain the memory layer from the previous layer; the second layer is a dropout layer, which is used to randomly discard the output of the previous layer to reduce the risk of overfitting; the third layer is the second LSTM layer, which is used to continue processing the output of the previous layer, further extract features and generate new outputs; the fourth layer is the second dropout layer, which will randomly discard the output again to ensure the generalization ability of the network; the last layer is a fully connected layer, which calculates the output of the previous layer through linear transformation and finally generates a prediction result vector of multiple categories.

[0098] Among them, the mean square error (MSE) is selected as the loss function during the training of the primary risk assessment module, and the Adam optimizer is used for optimization to prevent overfitting of the model and improve the stability of training.

[0099] The threshold method is used to perform graded judgment based on the predicted data. When the predicted value reaches the first-level warning threshold, the current state is output. If it reaches the second-level warning threshold, it is judged again through the same temperature difference comparison method, temperature change rate and temperature deviation.

[0100] The overall risk assessment module uses a fuzzy comprehensive evaluation method to integrate people, vehicles, cargo and environment for secondary evaluation, including:

[0101] Place Figure 4 The fuzzy evaluation model structure diagram is shown. A double-layer fuzzy evaluation model is constructed, and the characteristic data of the hazardous chemicals transport tank truck are studied to establish an index evaluation system. The factor set can be expressed as:

[0102] U={u1,u2,u3...,u n}, where u1, u2, u3, …u n Indicates the evaluation factor;

[0103] The influence of each factor in the factor set on the safety status of the tank truck can be divided into five levels: poor, slightly poor, medium, slightly better, and good; the level set of any factor can be expressed as:

[0104] u i = {u i1 ,u i2 ,u i3 ,u i4 ,u i5},(i=1,2,3...,n), where u i1 、u i2 、u i3 、u i4 、u i5 Indicates the evaluation level under the corresponding evaluation factor;

[0105] A weight is set for each factor, expressed as:

[0106] A={a1,a2,a3...,a n}

[0107] and Among them, a1, a2, a3..., a n Indicates the weight corresponding to each factor;

[0108] The fuzzy evaluation level obtained by the first-level fuzzy comprehensive evaluation method is:

[0109] V = {v1, v2, v3, v4, v5}, where v1, v2, v3, v4, v5 represent the fuzzy evaluation levels of each factor;

[0110] like Figure 5 The membership function diagram is shown. By factor u on the factor set U i Evaluate and obtain V for each evaluation level j The membership degree r ij ,Right now:

[0111] r ij = {r i1 ,r i2 ,r i3 ,r i4 ,r i5},(i=1,2,3...,n)

[0112] Establish a comprehensive evaluation matrix:

[0113] The factor weight set A and the comprehensive evaluation matrix R are obtained, and the fuzzy comprehensive evaluation set B is obtained through the generalized fuzzy synthesis operator "*": B = A*R = (b1, b2, b3, ..., b n )

[0114] A multi-level evaluation method is used for comprehensive evaluation. Assuming that the subset can be divided into m factors, the corresponding factor set is:

[0115] U2={u i1 ,u i2 ,u i3 ...,u im},(i=1,2,3...,n), where u i1 ,u i2 ,u i3 ...,u im Indicates the evaluation level under the corresponding evaluation factor;

[0116] Based on the above, the factor weight set can be:

[0117] A2={a i1 ,a i2 ,a i3 ...,a im},(i=1,2,3,...,n), where, a i1 ,a i2 ,a i3 ...,a in Indicates the weight corresponding to each factor;

[0118] By establishing the second-level comprehensive evaluation matrix, we can obtain the second-level comprehensive evaluation set:

[0119] B i =A i *R i =(b i1 ,b i2 ,b i3 ,...,b in ), where i = 1, 2, 3, 4, ..., n;

[0120] The first-level comprehensive evaluation result is used as input, and the fuzzy synthesis operation is performed again to obtain the final comprehensive evaluation result;

[0121] Once the fuzzy evaluation model is established, the risk evaluation level of hazardous chemicals transport tank trucks is output in the form of a membership function, where the degree of influence of each factor on the safety status of the tank truck can be divided into five levels, namely: poor, slightly poor, medium, slightly better, and good.

[0122] Furthermore, the specific steps are as follows:

[0123] First, the multi-source heterogeneous data of hazardous chemical tank trucks are collected and integrated through data acquisition devices to create comprehensive hazardous chemical tank truck status and operation information. Key features are extracted from the original data, including vehicle status, driver behavior, hazardous chemical status, environmental factors, etc. At the same time, these features will be used as input vectors for intelligent algorithms.

[0124] Furthermore, a digital model is built for the hazardous chemicals transport tank truck, including information such as the hazardous chemicals tank truck's geometry, structure, performance, and behavior status. It can also receive data from the physical tank truck in real time to maintain virtual-real dynamic consistency with the physical object.

[0125] Furthermore, based on deep learning technology, an intelligent early warning algorithm model is designed to assess the risk level of the status of hazardous chemicals transport tankers.

[0126] The intelligent early warning algorithm model can conduct risk assessment on four aspects: people-vehicle-cargo-environment.

[0127] The risk assessment of people is achieved through visual recognition algorithms, which can learn from the driver's risk data set to achieve risk assessment of the driver's dangerous driving.

[0128] In terms of the safety status of the tank truck, we first set classification thresholds for the speed, acceleration, and tank inclination of the tank truck in different scenarios and locations to make a preliminary assessment of the vehicle status of the tank truck itself. Then, we make a secondary assessment based on the relative speed and relative distance of the front and rear vehicles collected from the data to obtain the current status of the tank truck. At the same time, based on the relationship between mileage and the number of stress cycles, we combine the fatigue strength index and fatigue strength coefficient in the SN curve, as well as the concept of cumulative damage in Miner theory, to build an early warning model for component fatigue life estimated by mileage.

[0129] The safety status of hazardous chemicals in hazardous chemical transport tankers can be derived from the temperature, pressure, and liquid level of hazardous chemicals. Specifically, the temperature and pressure are predicted by using the LSTM neural network, and the status of hazardous chemicals is evaluated using the threshold method based on the predicted data.

[0130] Furthermore, for road interference, the status is evaluated by obtaining data and accident information released by the National Meteorological Information Center and the Transportation Bureau. Specific road interference can be divided into various adverse weather conditions, such as rain, snow, fog, sand, etc., as well as congested roads, construction areas, accident areas, etc. The risk probability of each interference is given by combining big data analysis technology and fuzzy comprehensive evaluation method.

[0131] Furthermore, the status of hazardous chemicals transport tank trucks is evaluated by combining the four aspects of people-vehicle-cargo-environment, and the fuzzy comprehensive evaluation method is used to conduct risk assessment.

[0132] Once the fuzzy evaluation model is established, the risk evaluation level of hazardous chemicals transport tank trucks is output in the form of a membership function, where the degree of influence of each factor on the safety status of the tank truck can be divided into five levels, namely: poor, slightly poor, medium, slightly better, and good.

[0133] Furthermore, the status of hazardous chemicals tankers is monitored in real time, including personnel behavior, vehicle status, cargo conditions, and surrounding environment. Based on the output of the intelligent algorithm, these states are intelligently characterized to complete the visualization of risk intelligent early warning. At the same time, the digital model is corrected to make the model output results as close to the physical results as possible.

[0134] First, the physical model of the tank truck is collected or directly read through the device to obtain the data of the target model. Based on the information such as geometric feature parameters and physical properties, the geometric model and physical model are constructed. In view of the complexity and data size of the tank truck model, it is necessary to perform lightweight data processing and convert the OBJ format model into GLTF format to improve the efficient browsing and interaction of the model, so as to better adapt to the limitations of computer equipment resource performance;

[0135] Then, the vehicle data of hazardous chemicals transport tank trucks, hazardous chemicals data, meteorological data and road data obtained by the data acquisition module are stored in a standard format, and data cleaning, noise and outlier removal and other operations are performed to finally establish a big data collection system library.

[0136] Furthermore, the multi-source heterogeneous data is integrated to create comprehensive hazardous chemicals tanker status and operation information. Key features are extracted from the raw data, including vehicle status, driver behavior, hazardous chemicals status, environmental factors, etc. These features will be used as input vectors for intelligent algorithms.

[0137] Furthermore, based on deep learning technology, an intelligent early warning algorithm model is designed to assess the risk level of the status of hazardous chemicals transport tankers.

[0138] The intelligent early warning algorithm model can conduct risk assessment on four aspects: people, vehicles, cargo, and environment. First, the intelligent early warning algorithm is used to conduct a primary risk status assessment on the four aspects of people, vehicles, cargo, and environment, and then the fuzzy comprehensive evaluation method is used to integrate people, vehicles, cargo, and environment for secondary assessment.

[0139] Regarding the safety status of "people", the visual detection algorithm is used to judge the driver's behavior. Dangerous behaviors include: making phone calls, yawning, drinking water, playing with mobile phones, and nodding sleepily, and the first-level risk status assessment factor of the "person" is output.

[0140] Regarding the safety status of the tank truck, firstly, the classification thresholds are set for the tank truck speed, acceleration, and tank inclination angle in different scenarios and locations to make a preliminary assessment of the vehicle status of the tank truck itself; then a secondary assessment is made through the relative speed and relative distance of the front and rear vehicles collected through data to obtain the current status of the tank truck; at the same time, based on the relationship between mileage and the number of stress cycles, by combining the fatigue strength index and fatigue strength coefficient in the SN curve, and the concept of cumulative damage in Miner theory, an early warning model for the fatigue life of components estimated by mileage is constructed; combined with the above algorithm, the first-level risk status assessment factor of the "vehicle" is output.

[0141] The safety status of hazardous chemicals in hazardous chemicals transport tankers can be derived from the temperature, pressure, and liquid level of hazardous chemicals. Specifically, the temperature and pressure are predicted by using the LSTM neural network, and the status of hazardous chemicals is evaluated based on the predicted data using the threshold method, and the first-level risk status assessment factor of the "cargo" is output at the same time. The specific steps are as follows:

[0142] In order to achieve accurate prediction of LSTM neural network, a two-layer neural network is built. The overall network structure is as follows: Figure 2 , 3 As shown:

[0143] The input layer is composed of time vectors of characteristic parameters such as temperature, pressure, vehicle speed, liquid level, tank inclination, etc. The first layer is an LSTM layer, in which multiple memory units are set, and one part is used to process input data, and the other part is used to obtain the memory layer from the previous layer; the second layer is a dropout layer, the purpose of which is to randomly discard the output of the previous layer to reduce the risk of overfitting; the third layer is the second LSTM layer, the purpose of which is to continue processing the output of the previous layer, further extract features and generate new outputs; the fourth layer is the second dropout layer, which will randomly discard the output again to ensure the generalization ability of the network; the last layer is a fully connected layer, which calculates the output of the previous layer through linear transformation and finally generates a prediction result vector of multiple categories. At the same time, the mean square error (MSE) is selected as the loss function during the training process, and in order to prevent the model from overfitting and improve the stability of the training, the Adam optimizer is used for optimization.

[0144] Furthermore, the threshold method is used to perform graded evaluation based on the predicted data. When the predicted value reaches the first-level warning threshold, the current state is output. If it reaches the second-level warning threshold (the first-level warning value is greater than the second-level warning value), it is judged again through the same temperature difference comparison method, temperature change rate and temperature deviation.

[0145] For environmental factors, the status is evaluated by obtaining data and accident information released by the National Meteorological Information Center and the Transportation Bureau. Specific road interference can be divided into various adverse weather conditions, such as rain, snow, fog, sand, etc., as well as congested roads, construction areas, accident areas, etc. By combining big data analysis technology and fuzzy comprehensive evaluation method, the first-level risk status assessment factor of the relevant "environment" is output.

[0146] Then, the expert knowledge base is combined to conduct risk assessment on the status of hazardous chemicals transport tankers in four aspects: people, vehicles, cargoes, and environment. By using the fuzzy comprehensive evaluation method, the following is constructed. Figure 4 The double-layer fuzzy evaluation structure shown in the figure has the following specific steps:

[0147] Based on the characteristic data of the hazardous chemicals transport tanker, an index evaluation system is established, and the evaluation factors are u1, u2, u3, ...u n , then its factor set can be expressed as:

[0148] U={u1,u2,u3...,u n}

[0149] The influence of each factor in the factor set on the safety status of the tank truck can be divided into five levels: poor, slightly poor, medium, slightly better, and good. The level set of any factor can be expressed as:

[0150] u i= {u i1 ,u i2 ,u i3 ,u i4 ,u i5}(i=1,2,3...,n)

[0151] In addition, for each factor, we also need to set its weight, which can be expressed as follows:

[0152] A={a1,a2,a3...,a n}

[0153] and

[0154] And its fuzzy evaluation level is:

[0155] V={v1,v2,v3,v4,v5}

[0156] This is called the first-level fuzzy comprehensive evaluation method. By evaluating a factor ui in the factor set U, V of each evaluation level is obtained. j The membership degree r ij ,Right now:

[0157] r ij = {r i1 ,r i2 ,r i3 ,r i4 ,r i5}(i=1,2,3...,n)

[0158] Thus, a comprehensive evaluation matrix can be established:

[0159]

[0160] Through the above process, we can get the factor weight set A and the comprehensive evaluation matrix R. Selecting the generalized fuzzy synthesis operator "*", we can get the fuzzy comprehensive evaluation set B:

[0161] B=A*R=(b1,b2,b3,...,b n )

[0162] But usually the first-level fuzzy evaluation is not accurate enough. To overcome this shortcoming, a multi-level evaluation method should be used for comprehensive evaluation. If its subset can be divided into m factors, then the corresponding factor set is:

[0163] U2={u i1 ,u i2 ,u i3 ...,u im}(i=1,2,3...,n)

[0164] Based on the above, the factor weight set can be:

[0165] A2={a i1 ,a i2 ,a i3 ...,a im}(i=1,2,3,...,n)

[0166] Thus, the second-level comprehensive evaluation matrix can be established, and the second-level comprehensive evaluation set can be obtained:

[0167] B i =A i *R i =(b i1 ,b i2 ,b i3 ,...,b in )

[0168] Where i = 1, 2, 3, 4..., n, and then the first-level comprehensive evaluation result is taken as input, and the fuzzy synthesis operation is performed again to obtain the final comprehensive evaluation result.

[0169] Once the fuzzy evaluation model is established, the risk evaluation level of hazardous chemicals transport tank trucks is output in the form of a membership function, where the degree of influence of each factor on the safety status of the tank truck can be divided into five levels, namely: poor, slightly poor, medium, slightly better, and good.

[0170] Furthermore, after evaluating the status of hazardous chemicals transport tank trucks, digital twin technology and systems driven by digital models are built through WebGL technology and microservice architecture, and a digital twin driving platform for hazardous chemicals transport tank trucks is established. The digital models of many existing roads and oil and gas station buildings are integrated into the digital twin system as the basic framework, and the details of different types of stations and the characteristics of different levels of roads are incorporated in various ways to depict the system outline. In terms of system dynamics, with the help of high-speed communication technology, dynamic GIS data is used as the base map, and the dynamic data collected by existing sensors is integrated at key locations to build a dynamic information layer for vehicles and personnel. The specific steps can be as follows:

[0171] First, import the models of various components of the hazardous chemicals transport tanker into the web system.

[0172] Secondly, the numerous components of hazardous chemicals transport tank trucks are spatially correlated with various influencing factors. Through the multi-scale twin model, the multi-scale relationship from part level to component level to complex equipment level can be described, and the vertical, parallel and tangent spatial relationships between component models can be analyzed. A multi-layer structure tree is established to effectively describe the relationship between each scale.

[0173] After that, the digital twin model is verified for consistency with the actual tank truck model, and the model output results are made as close as possible to the physical results through data connection. Then, based on the above-mentioned early warning algorithm model, the risk status of the hazardous chemical transport tank truck is output, and based on the corresponding risk status, different states are displayed on the digital twin model of the hazardous chemical transport tank truck.

[0174] Finally, the status of the hazardous chemicals tanker is presented, including personnel behavior, vehicle status, cargo conditions, and surrounding environment. Based on the output of the intelligent algorithm, these states are intelligently characterized to assess risk factors. Based on the model output and intelligent status characterization, the system will perform intelligent early warning operations.

[0175] The digital twin module is divided into a three-dimensional display module, a data transmission module, a model correction module, and an early warning module. Figure 6 shown.

[0176] The three-dimensional display module is used to display the digital model of the hazardous chemicals transport tanker. By considering the behavioral coupling relationship between each component, a response model describing the tanker's behavioral characteristics is constructed. The data transmission module is used to input the data collected by the data acquisition module and the results of the risk assessment module's evaluation of various aspects into the model correction module. The model correction module corrects the model displayed by the three-dimensional display module through the received data, and constructs the model output results as close as possible to the physical results according to the parameters and objective functions. The goal is to ensure the accuracy of the model so that it can better adapt to different application requirements and conditions. Finally, the early warning module is based on the preset safety thresholds and logical rules. Once the indicator changes beyond the normal range are detected, the corresponding alarm mechanism is immediately triggered to realize the alarm of each state of the hazardous chemicals transport tanker to remind the driver and the background supervisor.

[0177] Embodiment 2:

[0178] like Figure 7 As shown, this example provides a safety status detection system for hazardous chemicals transport tankers based on digital twin technology. The system includes a data acquisition module, a data processing module, a risk assessment module, a digital twin module and a decision support module. The purpose is to improve the safety factor in the process of hazardous chemicals transportation. The details are as follows:

[0179] The data acquisition module is used to collect the "people-vehicle-cargo-environment" multi-factor perception data during the transportation of hazardous chemicals tank trucks through the data acquisition module. The data includes: vehicle speed, acceleration, roll angle, tank temperature, tank pressure, tank liquid level, driver's driving behavior, relative speed of front and rear vehicles, relative distance, weather conditions, and road area.

[0180] The data processing module is used to pre-process the collected data through the data pre-processing module, and the pre-processing includes: cleaning, missing value filling, outlier processing, classification operations, and transmitting the processed data to the risk assessment module.

[0181] The risk model construction module is used to construct a risk assessment and early warning model through an intelligent assessment algorithm, use the preprocessed data to input the initial risk assessment and early warning model and train it to obtain a trained risk assessment and early warning model. The risk assessment and early warning model includes a primary risk assessment module and an overall risk assessment module.

[0182] The risk assessment module is used to obtain real-time multi-factor perception data of "people-vehicle-cargo-environment" of hazardous chemicals transport tank trucks, and identify and warn of various unsafe conditions in the operation of hazardous chemicals transport tank trucks through the risk assessment and early warning model, so as to realize the evaluation of the safety status of the four dimensions of people-vehicle-cargo-environment of hazardous chemicals transport tank trucks.

[0183] The digital twin module is used to display the structure, risk evolution process, parameter details and coupling relationship between sub-models of the digital twin tank truck model in a three-dimensional interactive manner based on the data output of the risk assessment and early warning model, and to issue early warnings for the safety risks of the operating status of hazardous chemicals tank trucks, so as to realize data-model-knowledge driven intelligent early warning.

[0184] The decision support module is used to combine the current situation with historical data, based on the model output and intelligent state representation of the digital twin module, to predict possible failures or dangerous events in advance, provide decision support operations for operators, and ensure the safety and reliability of the transportation process.

[0185] The risk assessment module is divided into a primary risk assessment module and an overall risk assessment module. The risk assessment module is used to judge the various states of hazardous chemicals transport tankers. The risk assessment module has a built-in intelligent assessment algorithm, which can perform risk diagnosis based on the four aspects of people-vehicle-cargo-environment. The primary risk assessment module is used to perform risk assessment on the four aspects of people-vehicle-cargo-environment respectively, and the overall risk assessment module is used to make an overall judgment based on the four aspects.

[0186] Embodiment 3:

[0187] like Figure 8 FIG. 1 is a schematic diagram of the structure of an electronic device of a method provided by an embodiment of the present invention.

[0188] The electronic device 1 may include a processor 10 , a memory 11 , a communication interface 13 and a bus, and may also include a computer program stored in the memory 11 and executable on the processor 10 , such as a program 12 .

[0189] The memory 11 includes at least one type of readable storage medium, and the readable storage medium includes a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as a mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 may be used not only to store application software and various types of data installed in the electronic device 1, such as the code of the program 12, etc., but also to temporarily store data that has been output or is to be output.

[0190] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as the program 12 for implementing the construction of the adaptive database detection data link), and calls the data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0191] The communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices, and to achieve connection and communication between internal components of the electronic device.

[0192] The bus may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0193] Figure 8 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 8 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0194] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, etc. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0195] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0196] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0197] The program 12 stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, and when running in the processor 10, the transmission chain vibration monitoring and diagnosis method can be implemented.

[0198] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 7 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0199] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variants thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "including a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0200] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0201] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for detecting the safety status of a hazardous chemicals transport tanker based on digital twin technology, characterized in that: include: Step 1: The data acquisition module is used to collect the multi-factor perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemicals tank trucks. The data includes: vehicle speed, acceleration, roll angle, tank temperature, tank pressure, tank liquid level, driver's driving behavior, relative speed of front and rear vehicles, relative distance, weather conditions, and road area; Step 2: Preprocess the collected data through the data preprocessing module, the preprocessing includes: cleaning, missing value filling, outlier processing, classification operations, and transmit the processed data to the risk assessment module; Step 3: construct a risk assessment and early warning model through an intelligent assessment algorithm, use the preprocessed data to input the initial risk assessment and early warning model and train it to obtain a trained risk assessment and early warning model, wherein the risk assessment and early warning model includes a primary risk assessment module and an overall risk assessment module; Step 4: Obtain real-time multi-factor perception data of "people-vehicle-cargo-environment" of hazardous chemicals transport tankers, and identify and warn of various unsafe conditions in the operation of hazardous chemicals transport tankers through risk assessment and early warning models, so as to evaluate the safety status of the four dimensions of people-vehicle-cargo-environment of hazardous chemicals transport tankers; Step 5: Construct a digital twin module, based on the data output of the risk assessment and early warning model, display the structure, risk evolution process, parameter details and coupling relationship between sub-models of the digital twin tank truck model in a three-dimensional interactive manner, and issue early warnings for safety risks in the operation status of hazardous chemicals tank trucks, so as to realize data-model-knowledge driven intelligent early warning; Step 6: Combining the current situation with historical data, based on the model output and intelligent state representation of the digital twin module, predict possible failures or dangerous events in advance, provide decision support operations for operators, and ensure the safety and reliability of the transportation process.

2. According to claim 1, the method for detecting the safety status of a hazardous chemicals transport tanker based on digital twin technology is characterized in that: The data acquisition module is used to collect the multi-factor perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemicals tank trucks, including: The "people-vehicle-cargo-environment" multi-factor perception data in the transportation process of the hazardous chemicals transport tanker is derived from the vehicle monitoring data of the hazardous chemicals transport tanker and the hazardous chemicals monitoring data; Collect various unsafe conditions of hazardous chemicals tank trucks in operation; Among them, the various unsafe conditions include abnormalities of the hazardous chemicals transport tanker, abnormal status of hazardous chemicals, abnormal status of the driver of the hazardous chemicals transport tanker, and interference from the surrounding environment; The abnormalities of the hazardous chemicals transport tanker vehicles include: fatigue failure of key parts of the tanker vehicles, tanker vehicle rollover, and tanker vehicle collision threats; The abnormal state of hazardous chemicals includes abnormal reactions in four aspects: liquid level in the tank, pressure in the tank, temperature in the tank, and gas concentration; The abnormal state of the driver of the hazardous chemicals transport tanker includes monitoring the driver's dangerous driving behavior, including monitoring the driver's driving behavior, the number of times the driver blinks and yawns; The surrounding environment interference is obtained by monitoring weather conditions in different scenarios, including road accidents in fog, rain, snow, temperature, and wind speed scenarios.

3. The method for detecting the safety status of a hazardous chemicals transport tanker based on digital twin technology according to claim 2 is characterized in that: In step 4, the safety status of the hazardous chemicals transport tanker in four dimensions of personnel, vehicle, cargo and environment is evaluated, including: First, use the primary risk assessment module to conduct a first-level risk status assessment on the four dimensions of people, vehicles, cargo and environment. Then use the overall risk assessment module to integrate people, vehicles, cargo and environment together through the fuzzy comprehensive evaluation method for a second-level assessment.

4. The method for detecting the safety status of a hazardous chemicals transport tanker based on digital twin technology according to claim 3 is characterized in that: The primary risk assessment module is used to conduct a primary risk status assessment on the four dimensions of people, vehicles, cargo and environment, including: In terms of the safety status of people, the visual detection algorithm is used to judge the driver's behavior. Dangerous behaviors include: making phone calls, yawning, drinking water, playing with mobile phones, and nodding sleepily. The first-level risk status assessment factor of the "person" is output; In view of the safety status of the tank truck, firstly, the classification thresholds are set for the speed, acceleration and tank inclination of the tank truck in different scenes and locations to make a preliminary assessment of the vehicle status of the tank truck itself; then, a secondary assessment is made through the relative speed and relative distance of the front and rear vehicles collected by data to obtain the current status of the tank truck; at the same time, based on the relationship between mileage and stress cycle number, by combining the fatigue strength index and fatigue strength coefficient in the SN curve and the concept of cumulative damage in Miner theory, an early warning model for the fatigue life of components estimated by mileage is constructed; combined with the above algorithm, the first-level risk status assessment factor of the "vehicle" is output; The safety status of hazardous chemicals in hazardous chemicals transport tankers can be derived from their temperature, pressure, and liquid level. The temperature and pressure are predicted by using the LSTM neural network, and the status of hazardous chemicals is evaluated based on the predicted data using the threshold method. At the same time, the first-level risk status assessment factor of the relevant goods is output.

5. The method for detecting the safety status of a hazardous chemicals transport tanker based on digital twin technology according to claim 4 is characterized in that: The method of using the LSTM neural network to predict temperature and pressure includes: Construct a two-layer LSTM neural network; the input layer is composed of time vectors of characteristic parameters such as temperature, pressure, vehicle speed, liquid level, tank inclination, etc.; the first layer is the LSTM layer, in which multiple memory units are set, and one part is used to process input data, and the other part is used to obtain the memory layer from the previous layer; the second layer is the dropout layer, which is used to randomly discard the output of the previous layer to reduce the risk of overfitting; the third layer is the second LSTM layer, which is used to continue processing the output of the previous layer, further extract features and generate new outputs; the fourth layer is the second dropout layer, which will randomly discard the output again to ensure the generalization ability of the network; the last layer is the fully connected layer, which calculates the output of the previous layer through linear transformation and finally generates a prediction result vector of multiple categories; Among them, the mean square error (MSE) is selected as the loss function during the training of the primary risk assessment module, and the Adam optimizer is used for optimization to prevent overfitting of the model and improve the stability of training; The threshold method is used to perform graded judgment based on the predicted data. When the predicted value reaches the first-level warning threshold, the current state is output. If it reaches the second-level warning threshold, it is judged again through the same temperature difference comparison method, temperature change rate and temperature deviation.

6. The method for detecting the safety status of a hazardous chemicals transport tanker based on digital twin technology according to claim 4 is characterized in that: The overall risk assessment module uses a fuzzy comprehensive evaluation method to integrate people, vehicles, cargo and environment for secondary evaluation, including: A double-layer fuzzy evaluation model is constructed, and the characteristic data of the hazardous chemicals transport tank truck are studied to establish an index evaluation system. The factor set can be expressed as: U={u1,u2,u3...,u n }, where u1, u2, u3, … u n Indicates the evaluation factor; The influence of each factor in the factor set on the safety status of the tank truck can be divided into five levels: poor, slightly poor, medium, slightly better, and good; the level set of any factor can be expressed as: u i = {u i1 ,u i2 ,u i3 ,u i4 ,u i5 },(i=1,2,3...,n), where u i1 、u i2 、u i3 、u i4 、u i5 Indicates the evaluation level under the corresponding evaluation factor; A weight is set for each factor, expressed as: <h2 style=";text-align:left;direction:ltr">A = {a1,a2,a3...,a<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr">} and Among them, a1, a2, a3..., a n Indicates the weight corresponding to each factor; The fuzzy evaluation level obtained by the first-level fuzzy comprehensive evaluation method is: V = {v1, v2, v3, v4, v5}, where v1, v2, v3, v4, v5 represent the fuzzy evaluation levels of each factor; By calculating a factor u of the factor set U i Evaluate and obtain V for each evaluation level j The membership degree r ij ,Right now: r ij ={r i1 ,r i2 ,r i3 ,r i4 ,r i5 },(i=1,2,3...,n) Establish a comprehensive evaluation matrix: The factor weight set A and the comprehensive evaluation matrix R are obtained, and the fuzzy comprehensive evaluation set B is obtained through the generalized fuzzy synthesis operator*: B=A*R=(b1,b2,b3,...,b n ); A multi-level evaluation method is used for comprehensive evaluation. Assuming that the subset can be divided into m factors, the corresponding factor set is: U2={u i1 ,u i2 ,u i3 ...,u im },(i=1,2,3...,n), where u i1 ,u i2 ,u i3 ...,u im Indicates the evaluation level under the corresponding evaluation factor; Its factor weight set is: A2={a i1 ,a i2 ,a i3 ...,a im },(i=1,2,3,...,n), where, a i1 ,a i2 ,a i3 ...,a in Indicates the weight corresponding to each factor; By establishing the second-level comprehensive evaluation matrix, we can obtain the second-level comprehensive evaluation set: B i = A i *R i = (b i1 ,b i2 ,b i3 ,...,b in ), where i=1, 2, 3, 4...,n; The first-level comprehensive evaluation result is used as input, and the fuzzy synthesis operation is performed again to obtain the final comprehensive evaluation result; Once the fuzzy evaluation model is established, the risk evaluation level of hazardous chemicals transport tank trucks is output in the form of a membership function, where the degree of influence of each factor on the safety status of the tank truck can be divided into five levels, namely: poor, slightly poor, medium, slightly better, and good.

7. The method for detecting the safety status of a hazardous chemicals transport tanker based on digital twin technology according to claim 5 is characterized in that: The digital twin module construction in step 5 includes: Construct the three-dimensional display module, data transmission module, model correction module, and early warning module in sequence; The three-dimensional display module is used to display the digital model of the hazardous chemicals transport tanker, and to construct a response model describing the behavior characteristics of the tanker by considering the behavioral coupling relationship between various components; The data transmission module is used to input the data collected by the data collection module and the results of the risk assessment module on various aspects into the model correction module; The model correction module corrects the model displayed by the three-dimensional display module through the received data, and constructs the model output results as close as possible to the physical results according to the parameters and the objective function, with the goal of ensuring the accuracy of the model so that it can better adapt to different application requirements and conditions; The early warning module is based on preset safety thresholds and logical rules. When it detects changes in indicators that exceed the normal range, it immediately triggers the corresponding alarm mechanism to warn of various states of the hazardous chemicals transport tanker to remind the driver and back-end supervisory personnel.

8. A safety status detection system for hazardous chemicals transport tankers based on digital twin technology, characterized by: The system includes a data acquisition module, a data processing module, a risk assessment module, a digital twin module and a decision support module; A data acquisition module is used to collect multi-factor perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemicals tank trucks. The data includes: vehicle speed, acceleration, roll angle, tank temperature, tank pressure, tank liquid level, driver's driving behavior, relative speed of front and rear vehicles, relative distance, weather conditions, and road area; The data processing module is used to pre-process the collected data through the data pre-processing module, wherein the pre-processing includes: cleaning, missing value filling, outlier processing, classification operations, and transmitting the processed data to the risk assessment module; A risk model building module is used to build a risk assessment and early warning model through an intelligent assessment algorithm, use the preprocessed data to input the initial risk assessment and early warning model and perform training to obtain a trained risk assessment and early warning model, wherein the risk assessment and early warning model includes a primary risk assessment module and an overall risk assessment module; The risk assessment module is used to obtain real-time multi-factor perception data of "people-vehicle-cargo-environment" of hazardous chemicals transport tankers, and identify and warn of various unsafe conditions in the operation of hazardous chemicals transport tankers through risk assessment and early warning models, so as to evaluate the safety status of hazardous chemicals transport tankers in four dimensions: people-vehicle-cargo-environment; The digital twin module is used to display the structure, risk evolution process, parameter details and coupling relationship between sub-models of the digital twin tank truck model in a three-dimensional interactive manner based on the data output of the risk assessment and early warning model, and to warn of the safety risks of the operation status of the hazardous chemicals tank truck, so as to realize data-model-knowledge driven intelligent early warning; The decision support module is used to combine the current situation with historical data, based on the model output and intelligent state representation of the digital twin module, to predict possible failures or dangerous events in advance, provide decision support operations for operators, and ensure the safety and reliability of the transportation process.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for detecting the safety status of a hazardous chemical transport tanker based on digital twin technology as described in any one of claims 1 to 7 are implemented.

10. A computer storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the method for detecting the safety status of a hazardous chemical transport tanker based on digital twin technology as described in any one of claims 1 to 7 are implemented.

Images