A method and system for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology

Abstract

This invention discloses a method and system for detecting the safety status of hazardous chemical transport tank trucks 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 data acquisition module collects data from various aspects of the tank truck transportation process. The risk assessment module incorporates an intelligent assessment algorithm that can diagnose risks based on four aspects: people, vehicle, cargo, and environment. The digital twin module integrates digital models and dynamic data to achieve visualized management of the tank truck structure, risk evolution process, and coupling relationships between sub-models. The decision support module provides decision support to operators by combining current conditions with historical data. The data-model-knowledge-driven multi-domain performance evaluation solution provided by this invention can effectively improve the safety and reliability of the transportation process.

Description

Technical Field

[0001] This invention belongs to the field of hazardous chemical transportation monitoring, specifically relating to a method and system for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology. Background Technology

[0002] With the rapid development of my country's industrial economy, the demand for hazardous chemicals is increasing, and the transportation of hazardous chemicals is gradually playing an important role in modern industrial and economic activities. However, due to the inherent dangers of hazardous chemicals, accidents frequently occur during their transportation. Each hazardous chemical transportation accident can lead to casualties, property damage, and environmental pollution, thereby affecting social stability and sustainable development. Therefore, improving the safety of hazardous chemical transportation has become a common concern for the industry and society.

[0003] With the increase in transportation volume and the significant expansion of road transport mileage, the transportation situation is becoming increasingly complex, and the number of traffic accidents involving hazardous chemicals is gradually increasing. However, the uneven professional competence of practitioners greatly increases the probability of accidents. Therefore, in order to analyze the internal and external influencing factors of accidents and take targeted measures, it is particularly important to establish a suitable safety status assessment method and monitoring system for hazardous chemical tanker trucks. However, most current technologies focus on a single link or use related means to achieve full-process data monitoring of hazardous chemical transportation, but lack precise status perception of hazardous chemical tanker trucks during transportation and real-time risk evolution early warning. In addition, existing technologies still face limitations in practical applications, such as data accuracy, real-time performance, and system stability.

[0004] Therefore, this patent proposes a digital twin system for detecting the safety status of hazardous chemical transport tank trucks. It aims to establish a multi-layered structure tree that can realistically depict the operation of tank trucks by adding spatial relationships, constraints, and other relationships to parts and components. This structure is then assembled and integrated into a digital twin model of complex equipment. Based on intelligent early warning algorithms, the system performs risk assessment and visualization of the operating status of hazardous chemical transport tank trucks, 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 this invention is to provide a method and system for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology, so as to overcome the shortcomings of the prior art.

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

[0007] Step 1: Collect multi-element perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemical tank trucks through the data acquisition module. The data includes: vehicle speed, acceleration, tilt angle, tank temperature, tank pressure, tank liquid level, driver behavior, relative speed and distance between vehicles in front and behind, weather conditions, and road area.

[0008] Step 2: The collected data is preprocessed by the data preprocessing module. The preprocessing includes cleaning, missing value imputation, outlier handling, and classification. The processed data is then transmitted to the risk assessment module.

[0009] Step 3: Construct a risk assessment and early warning model through an intelligent assessment algorithm. Input the preprocessed data into 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.

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

[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 the sub-models of the digital twin tanker truck model in a three-dimensional interactive manner. Provide early warning of the safety risks of the operating status of the hazardous chemical transport tanker truck to achieve intelligent early warning driven by data, model, and knowledge.

[0012] Step 6: Combining the current situation with historical data, and 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 for operators, and ensure the safety and reliability of the transportation process.

[0013] Furthermore, the data acquisition module collects multi-element perception data of "people-vehicle-goods-environment" during the transportation of hazardous chemical tank trucks, including:

[0014] The multi-element perception data of "people-vehicle-goods-environment" during the transportation of hazardous chemical tank trucks comes from the vehicle monitoring data and hazardous chemical monitoring data of the hazardous chemical tank trucks.

[0015] Data is collected on various unsafe conditions of hazardous chemical transport tank trucks during operation;

[0016] Among these, the various unsafe conditions include: abnormalities of the hazardous chemical transport tanker truck, abnormalities in the condition of the hazardous chemicals, abnormalities in the condition of the hazardous chemical transport tanker truck driver, and interference from the surrounding environment;

[0017] The abnormalities of the hazardous chemical transport tanker trucks include: fatigue failure of key components of the tanker trucks, side tilting of the tanker trucks, and collision threats to the tanker trucks;

[0018] The abnormal status of the hazardous chemicals includes abnormalities in four aspects: liquid level inside the tank, pressure inside the tank, temperature inside the tank, and gas concentration.

[0019] The abnormal state of the drivers of the hazardous chemical transport tanker trucks includes monitoring dangerous driving behaviors of the drivers, including monitoring the drivers' driving behavior, the number of blinks and yawns;

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

[0021] Furthermore, step 4 involves assessing the safety status of hazardous chemical transport tankers across four dimensions: people, vehicle, cargo, and environment, including:

[0022] First, the primary risk assessment module is used to conduct a first-level risk status assessment of the four dimensions of people, vehicles, goods, and environment. Then, the overall risk assessment module is used to integrate people, vehicles, goods, and environment together through 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 four dimensions: people, vehicles, goods, and environment. This includes: for the safety status of people, using visual detection algorithms to judge the behavior of drivers, dangerous behaviors include: making phone calls, yawning, drinking water, playing on mobile phones, and nodding while dozing off, and outputting the first-level risk status assessment factors related to "people".

[0024] To assess the safety status of tank trucks, firstly, tiered thresholds are set for tank truck speed, acceleration, and tank tilt angle in different scenarios and locations to conduct a preliminary evaluation of the tank truck's condition. Then, a secondary evaluation is performed using data collected on the relative speed and distance between the tank truck and the preceding and following vehicles to determine the tank truck's current status. Simultaneously, based on the relationship between mileage and stress cycle count, and by combining the fatigue strength index and fatigue strength coefficient in the SN curve with the cumulative damage concept in Miner's theory, an early warning model for component fatigue life estimated by mileage is constructed. Finally, the above algorithms are combined to output a primary risk status assessment factor for the "vehicle."

[0025] The safety status of hazardous chemicals transport tankers can be derived from the temperature, pressure, and liquid level of the hazardous chemicals. By using an LSTM neural network to predict the temperature and pressure, and using a threshold method based on the predicted data to assess the status of the hazardous chemicals, the system outputs a primary risk status assessment factor for the cargo.

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

[0027] A two-layer LSTM neural network is constructed. The input layer consists of time vectors of feature parameters such as temperature, pressure, vehicle speed, liquid level, and tank tilt angle. The first layer is an LSTM layer with multiple memory units, some of which are used to process the input data and others to retrieve the memory from the previous layer. The second layer is a dropout layer, which randomly discards the output of the previous layer to reduce the risk of overfitting. The third layer is a second LSTM layer, which continues to process the output of the previous layer, further extracting features and generating new outputs. The fourth layer is a second dropout layer, which again randomly discards the output to ensure the network's generalization ability. The last layer is a fully connected layer, which calculates the output of the previous layer through a linear transformation, ultimately generating a multi-class prediction result vector.

[0028] In the training process of the primary risk assessment module, mean squared error (MSE) is selected as the loss function, and in order to prevent the model from overfitting and improve the stability of training, the Adam optimizer is used for optimization.

[0029] Based on the predicted data, a threshold method is used for graded evaluation. When the predicted value reaches the first-level warning threshold, the current status is output. If it reaches the second-level warning threshold, a second evaluation is conducted using the same type of temperature difference comparison method, temperature change rate, and temperature deviation.

[0030] Furthermore, the overall risk assessment module integrates people, vehicles, goods, and the environment through fuzzy comprehensive evaluation to conduct a secondary assessment, including:

[0031] A two-layer fuzzy evaluation model is constructed, and the various characteristic data of the hazardous chemical transport tanker are used for research. An index evaluation system is established, and its factor set can be expressed as:

[0032] U = {u1, u2, u3, ..., u} n}, where u1, u2, u3, ... u n Indicate the evaluation factors;

[0033] The degree of influence of each factor on the safety status of the tanker truck can be divided into 5 levels: poor, slightly poor, moderate, slightly good, and good; the level set of any one factor can be represented 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 assigned to each factor, expressed as follows:

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

[0037] and Where a1, a2, a3..., a n This indicates the weight for each factor.

[0038] The fuzzy evaluation level obtained through 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 for each factor.

[0040] By analyzing a certain factor u in the factor set U. i An evaluation is conducted to obtain the V score for each evaluation level. j 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] Given the factor weight set A and the comprehensive evaluation matrix R, and using the generalized fuzzy synthesis operator*, we obtain the fuzzy comprehensive evaluation set B: B = A*R = (b1, b2, b3, ..., b n )

[0044] A multi-level evaluation method is used for comprehensive evaluation. If its subset can be divided into m factors, then its 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 This indicates the weight for each factor.

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

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

[0050] By taking the comprehensive evaluation result of the first level as input and performing fuzzy synthesis operation again, the final comprehensive evaluation result can be obtained.

[0051] Once the fuzzy evaluation model is established, the risk assessment level of the hazardous chemical transport tanker is output in the form of a membership function. The degree of influence of each factor on the safety status of the tanker can be divided into 5 levels: poor, slightly poor, medium, slightly good, and good.

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

[0053] The system is constructed sequentially, consisting of a 3D display module, a data transmission module, a model calibration module, and an early warning module.

[0054] The three-dimensional display module is used to display the digital model of the hazardous chemical transport tanker truck. By considering the behavioral coupling relationship between various components, a response model describing the behavioral characteristics of the tanker truck is constructed.

[0055] 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 calibration module.

[0056] The model correction module corrects the model displayed by the 3D display module using the received data, and constructs the model output as close as possible to the physical result based on the parameters and objective function. Its goal is to ensure the accuracy of the model and make it better adaptable to different application needs and conditions. The early warning module, based on preset safety thresholds and logical rules, immediately triggers the corresponding alarm mechanism when it detects changes in indicators that exceed the normal range, so as to provide warnings for the various states of the hazardous chemical transport tanker truck and remind the driver and the back-end supervisor.

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

[0058] Optionally, the present invention also provides a safety status detection system for hazardous chemical transport tank trucks 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] The data acquisition module is used to collect multi-element perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemical tank trucks. The data includes: vehicle speed, acceleration, tilt angle, tank temperature, tank pressure, tank liquid level, driver behavior, relative speed and distance between vehicles in front and behind, weather conditions, and road area.

[0060] The data processing module is used to preprocess the collected data through the data preprocessing module. The preprocessing includes cleaning, missing value imputation, outlier handling, and classification operations, and the processed data is transmitted to the risk assessment module.

[0061] The risk model construction module is used to construct a risk assessment and early warning model through an intelligent assessment algorithm. It uses preprocessed data to input the initial risk assessment and early warning model and trains 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.

[0062] The risk assessment module is used to acquire real-time multi-element perception data of "people-vehicle-cargo-environment" of hazardous chemical transport tankers. Through the risk assessment and early warning model, it identifies and warns of various unsafe conditions in the operation of hazardous chemical transport tankers, so as to realize the assessment of the safety status of hazardous chemical transport tankers in four dimensions: people, vehicle, cargo, and environment.

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

[0064] The decision support module combines current conditions with historical data, and based on the model output and intelligent state representation of the digital twin module, it predicts possible failures or dangerous events in advance, providing decision support for operators and ensuring the safety and reliability of the transportation process.

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

[0066] Optionally, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the method for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology.

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

[0068] Optionally, the present invention also provides a computer storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the steps of the method for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology. Attached Figure Description

[0069] Figure 1 A schematic flowchart of a state detection method provided in an embodiment of the present invention.

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

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

[0072] Figure 4 A structural diagram of a fuzzy evaluation model provided in an embodiment of the present invention.

[0073] Figure 5 Membership function graph provided in an embodiment of the present invention

[0074] Figure 6 A schematic diagram of a digital twin module structure provided in an embodiment of the present invention.

[0075] Figure 7 A schematic diagram of a safety status detection system module provided in an embodiment of the present invention.

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

[0077] In the diagram: 1. Electronic device, 10. Processor, 11. Memory, 12. Program, 13. Communication interface.

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

[0079] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0080] This application provides a method for detecting the safety status of hazardous chemical transport tankers based on digital twin technology. The execution subject of the method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. 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] Example 1:

[0082] A method for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology, such as Figure 1 As shown, it includes the following steps:

[0083] S1: The data acquisition module collects multi-element perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemical tank trucks. The data includes: vehicle speed, acceleration, tilt angle, tank temperature, tank pressure, tank liquid level, driver behavior, relative speed and distance between vehicles in front and behind, weather conditions, and road area.

[0084] Specifically, the data acquisition module is used to collect various data during the transportation of hazardous chemical tank trucks, and the data collected by the data acquisition module will be transmitted to the data processing module for various preprocessing operations.

[0085] S2: The collected data is preprocessed by the data preprocessing module. The preprocessing includes cleaning, missing value imputation, outlier handling, and classification. The processed data is then transmitted to the risk assessment module.

[0086] Specifically, the data processing module is used to clean, fill in missing values, handle 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, input the preprocessed data into 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.

[0088] S4: Acquire real-time multi-element perception data of "people-vehicle-cargo-environment" of hazardous chemical transport tankers, and identify and warn of various unsafe conditions in the operation of hazardous chemical transport tankers through a risk assessment and early warning model, so as to realize the safety status assessment of hazardous chemical transport tankers in four dimensions: people-vehicle-cargo-environment.

[0089] S5: 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 the digital twin tanker truck model in a three-dimensional interactive manner. Provide early warning of safety risks in the operation status of hazardous chemical tanker trucks to achieve intelligent early warning driven by data, model, and knowledge.

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

[0091] like Figure 2 The diagram shows the structure of an intelligent early warning algorithm for tanker truck safety status. The intelligent early warning algorithm model includes: a sequence input layer, a neural network layer, and a regression output layer. The feature vector input sequence layer obtains a time-series feature input vector, which is then transmitted to the neural network layer. The neural network layer comprises multiple LSTM neural network structures, which undergo multi-dimensional time-series processing to obtain a pre-result input vector.

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

[0093] Specifically, regarding a person's safety status, visual detection algorithms can be used to assess the driver's behavior. Dangerous behaviors include: making phone calls, yawning, drinking water, playing on a mobile phone, and nodding off while drowsy. The algorithm then outputs a primary risk assessment factor for the "person".

[0094] To assess the safety status of tank trucks, firstly, tiered thresholds are set for tank truck speed, acceleration, and tank tilt angle in different scenarios and locations to conduct a preliminary evaluation of the tank truck's condition. Then, a secondary evaluation is performed using data collected on the relative speed and distance between the tank truck and the preceding and following vehicles to determine the tank truck's current status. Simultaneously, based on the relationship between mileage and stress cycle count, and by combining the fatigue strength index and fatigue strength coefficient in the SN curve with the cumulative damage concept from Miner's theory, an early warning model for component fatigue life estimated by mileage is constructed. Finally, the above algorithms are combined to output a primary risk status assessment factor for the "vehicle".

[0095] The safety status of hazardous chemicals transport tankers can be derived from the temperature, pressure, and liquid level of the hazardous chemicals. By using an LSTM neural network to predict the temperature and pressure, and using a threshold method based on the predicted data to assess the status of the hazardous chemicals, the system outputs a primary risk status assessment factor for the cargo.

[0096] The preprocessed data on the hazardous chemical storage environment and the data on the hazardous chemicals themselves are input into the LSTM model for training to obtain the training results. Error back-analysis is performed on the training results, and the training parameters of the LSTM prediction model are adjusted based on the back-analysis to obtain the trained LSTM prediction model.

[0097] Construct a two-layer LSTM neural network; its structure is as follows: Figure 3 As shown, the input layer consists of time vectors of feature parameters such as temperature, pressure, vehicle speed, liquid level, and tank tilt angle. The first layer is an LSTM layer with multiple memory units, some of which are used to process the input data and others to retrieve the memory from the previous layer. The second layer is a dropout layer, which randomly discards the output of the previous layer to reduce the risk of overfitting. The third layer is a second LSTM layer, which continues to process the output of the previous layer, further extracting features and generating new outputs. The fourth layer is a second dropout layer, which again randomly discards the output to ensure the network's generalization ability. The last layer is a fully connected layer, which calculates the output of the previous layer through a linear transformation, ultimately generating a multi-class prediction result vector.

[0098] In the training process of the primary risk assessment module, mean squared error (MSE) is selected as the loss function, and the Adam optimizer is used to optimize the model in order to prevent overfitting and improve the stability of training.

[0099] Based on the predicted data, a threshold method is used for graded evaluation. When the predicted value reaches the first-level warning threshold, the current status is output. If it reaches the second-level warning threshold, a second evaluation is conducted using the same type of temperature difference comparison method, temperature change rate, and temperature deviation.

[0100] The overall risk assessment module utilizes fuzzy comprehensive evaluation to integrate people, vehicles, goods, and the environment for secondary evaluation, including:

[0101] Place Figure 4 The diagram shows the structure of the fuzzy evaluation model. A two-layer fuzzy evaluation model is constructed, and the various characteristic data of the hazardous chemical transport tanker are used for research to establish an index evaluation system. The factor set can then be represented as:

[0102] U = {u1, u2, u3, ..., u} n}, where u1, u2, u3, ... u n Indicate the evaluation factors;

[0103] The degree of influence of each factor on the safety status of the tanker truck can be divided into 5 levels: poor, slightly poor, moderate, slightly good, and good; the level set of any one factor can be represented 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 assigned to each factor, expressed as follows:

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

[0107] and Where a1, a2, a3..., a n This indicates the weight for each factor.

[0108] The fuzzy evaluation level obtained through 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 for each factor.

[0110] like Figure 5 The membership function graph is shown below. This is achieved by considering a specific factor u in the factor set U. i An evaluation is conducted to obtain the V score for each evaluation level. j 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] Given the factor weight set A and the comprehensive evaluation matrix R, and using the generalized fuzzy synthesis operator "*", we obtain the fuzzy comprehensive evaluation set B: B = A * R = (b1, b2, b3, ..., b n )

[0114] A multi-level evaluation method is used for comprehensive evaluation. If its subset can be divided into m factors, then its 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, its 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 This indicates the weight for each factor.

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

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

[0120] By taking the comprehensive evaluation result of the first level as input and performing fuzzy synthesis operation again, the final comprehensive evaluation result can be obtained.

[0121] Once the fuzzy evaluation model is established, the risk assessment level of the hazardous chemical transport tanker is output in the form of a membership function. The degree of influence of each factor on the safety status of the tanker can be divided into 5 levels: poor, slightly poor, medium, slightly good, and good.

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

[0123] First, multi-source heterogeneous data from hazardous chemical transport tankers is collected and integrated using data acquisition devices to create comprehensive operational status information for these tankers. Key features are then extracted from the raw data, including vehicle status, driver behavior, hazardous chemical status, and environmental factors. These features will then be used as input vectors for intelligent algorithms.

[0124] Furthermore, a digital model of the hazardous chemical transport tanker truck is constructed, including information such as the truck's geometry, structure, performance, and behavior. It can also receive data from the physical tanker truck in real time to maintain dynamic consistency between the virtual and physical objects.

[0125] Furthermore, based on deep learning technology, an intelligent early warning algorithm model was designed to assess the risk level of hazardous chemical transport tank trucks.

[0126] The intelligent early warning algorithm model described above can conduct risk assessments in four aspects: people, vehicles, goods, and environment.

[0127] The risk assessment of people is achieved through visual recognition algorithms, which can learn from driver hazard datasets to assess the risk of dangerous driving by drivers.

[0128] To assess the safety status of tank trucks, firstly, graded thresholds are set for tank truck speed, acceleration, and tank tilt angle in different scenarios and locations to make a preliminary judgment on the vehicle status of the tank truck itself; then, a secondary judgment is made by collecting data on the relative speed and relative distance between the front and rear vehicles 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 cumulative damage concept in Miner's theory, an early warning model for component fatigue life estimated by mileage is constructed.

[0129] The safety status of hazardous chemicals transported by tank trucks can be determined from their temperature, pressure, and liquid level. Specifically, an LSTM neural network is used to predict temperature and pressure, and a threshold method is applied based on the predicted data to assess the status of the hazardous chemicals.

[0130] Furthermore, regarding road disturbances, status assessments are conducted by acquiring data and accident information released by the National Meteorological Information Center and the Transportation Bureau. Specific road disturbances can be categorized into various adverse weather conditions, such as rain, snow, fog, and sandstorms, as well as congested roads, construction areas, and accident zones. A risk probability is assigned to each disturbance by combining big data analysis technology and fuzzy comprehensive evaluation methods.

[0131] Furthermore, the status of hazardous chemical transport tank trucks is assessed by combining four aspects: people, vehicles, goods, and environment, and risk assessment is conducted using fuzzy comprehensive evaluation method.

[0132] Once the fuzzy evaluation model is established, the risk assessment level of the hazardous chemical transport tanker is output in the form of a membership function. The degree of influence of each factor on the safety status of the tanker can be divided into 5 levels: poor, slightly poor, medium, slightly good, and good.

[0133] Furthermore, the system monitors the status of hazardous chemical tanker trucks in real time, including personnel behavior, vehicle status, cargo condition, and the surrounding environment. Based on the output of intelligent algorithms, these statuses are intelligently represented to visualize intelligent risk warnings. Simultaneously, the digital model is calibrated to ensure that the model output closely approximates the physical results.

[0134] First, the physical model of the tanker truck is acquired by collecting data from the equipment or directly reading it to obtain the target model data. Based on geometric feature parameters and physical properties, a geometric model and a physical model are constructed. Given the complexity and data scale of the tanker truck model, lightweight data processing is required, converting the OBJ format model to GLTF format to improve efficient model browsing and interaction, thereby better adapting to the limitations of computer equipment resource performance.

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

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

[0137] Furthermore, based on deep learning technology, an intelligent early warning algorithm model was designed to assess the risk level of hazardous chemical transport tank trucks.

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

[0139] Regarding the safety status of "people", visual detection algorithms are used to evaluate the driver's behavior. Dangerous behaviors include: making phone calls, yawning, drinking water, playing on mobile phones, and nodding while dozing off. The algorithm also outputs a first-level risk status assessment factor for "people".

[0140] Regarding the safety status of tank trucks, firstly, graded thresholds are set for the speed, acceleration, and tank tilt angle of tank trucks in different scenarios and locations to make a preliminary assessment of the vehicle's condition. Then, a secondary assessment is made by collecting data on the relative speed and relative distance between the tank truck and the vehicle in front and behind to determine the current state of the tank truck. At the same time, based on the relationship between mileage and stress cycle count, and by combining the fatigue strength index and fatigue strength coefficient in the SN curve and the concept of cumulative damage in Miner's theory, an early warning model for component fatigue life estimated by mileage is constructed. Finally, the above algorithms are combined to output a first-level risk status assessment factor for the "vehicle".

[0141] The safety status of hazardous chemicals transported by tank trucks can be derived from their temperature, pressure, and liquid level. Specifically, an LSTM neural network is used to predict temperature and pressure, and a threshold method is applied based on the predicted data to assess the status of the hazardous chemicals, outputting a primary risk status assessment factor for the "cargo." The specific steps are as follows:

[0142] To achieve accurate predictions from the LSTM neural network, a two-layer neural network was constructed, and its overall network structure is as follows: Figure 2 , 3 As shown:

[0143] The input layer consists of time vectors of feature parameters such as temperature, pressure, vehicle speed, liquid level, and tank tilt angle. The first layer is an LSTM layer with multiple memory units, some of which process the input data and others retrieve information from the previous layer. The second layer is a dropout layer, designed to randomly discard the output of the previous layer to reduce the risk of overfitting. The third layer is a second LSTM layer, which further processes the output of the previous layer, extracts more features, and generates new outputs. The fourth layer is a second dropout layer, which again randomly discards the output to ensure the network's generalization ability. The final layer is a fully connected layer, which calculates a multi-class prediction vector by linearly transforming the output of the previous layer. During training, mean squared error (MSE) is used as the loss function, and the Adam optimizer is employed to prevent overfitting and improve training stability.

[0144] Furthermore, based on the predicted data, a threshold method is used for graded evaluation. When the predicted value reaches the first-level warning threshold, the current status is output. If it reaches the second-level warning threshold (the first-level warning value is greater than the second-level warning value), a second judgment is made using the same type of temperature difference comparison method, temperature change rate, and temperature deviation.

[0145] Regarding environmental factors, status assessment is conducted by acquiring data and accident information released by the National Meteorological Information Center and the Transportation Bureau. Specific road disturbances can be categorized into various adverse weather conditions, such as rain, snow, fog, and sandstorms, as well as congested roads, construction areas, and accident areas. The primary risk status assessment factors for the relevant "rings" are output by combining big data analysis technology and fuzzy comprehensive evaluation methods.

[0146] Then, combining an expert knowledge base, a risk assessment of the status of hazardous chemical transport tank trucks is conducted from four aspects: people, vehicles, goods, and environment. The assessment is performed using the fuzzy comprehensive evaluation method, and the following structure is constructed: Figure 4 The specific steps of the two-layer fuzzy evaluation structure shown are as follows:

[0147] Based on the characteristic data of the aforementioned hazardous chemical transport tanker trucks, an index evaluation system is established, with evaluation factors denoted as u1, u2, u3, ... u n Then its factor set can be represented as:

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

[0149] The impact of each factor on the safety status of the tanker truck can be categorized into five levels: poor, slightly poor, moderate, slightly good, and good. The level set for any single factor can be represented as:

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

[0151] In addition, we need to assign weights to each factor, which can be expressed by the following formula:

[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-order fuzzy comprehensive evaluation method. By evaluating a factor ui in the factor set U, the evaluation level V is obtained. j 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] This allows us to establish a comprehensive evaluation matrix:

[0159]

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

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

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

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

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

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

[0166] This allows us to establish a second-level comprehensive evaluation matrix, from which we can derive the second-level comprehensive evaluation set:

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

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

[0169] Once the fuzzy evaluation model is established, the risk assessment level of the hazardous chemical transport tanker is output in the form of a membership function. The degree of influence of each factor on the safety status of the tanker can be divided into 5 levels: poor, slightly poor, medium, slightly good, and good.

[0170] Furthermore, after conducting a condition assessment of hazardous chemical transport tankers, a digital twin technology and system for tankers driven by a numerical model is built using WebGL technology and a microservice architecture, establishing a digital twin-driven platform for hazardous chemical transport tankers. Numerous existing digital models of roads and oil and gas station buildings are integrated into the digital twin system as the basic framework. Details of different types of stations and characteristics of roads of different grades are incorporated through various methods to characterize the system outline. Regarding system dynamics, high-speed communication technology is used, with dynamic GIS data as the base map, and dynamic data collected by existing sensors are integrated at key locations to construct a dynamic information layer for vehicles and personnel. The specific steps are as follows:

[0171] First, import the models of each component of the hazardous chemical transport tanker into the web-based system.

[0172] Secondly, the numerous components of hazardous chemical transport tank trucks and various influencing factors are spatially correlated. Through multi-scale twin models, the relationships at multiple scales, from the part level to the component level and then to the complex equipment level, can be described. The vertical, parallel and tangential spatial relationships between component models are analyzed, and a multi-layer structure tree is established to effectively describe the relationships between each scale.

[0173] Next, the consistency between the digital twin model and the actual tanker model is verified. Data connections are used to make the model output as close to the physical results as possible. Then, based on the aforementioned early warning algorithm model, the risk status of the hazardous chemical transport tanker is output, and based on the corresponding risk status, different states are displayed on the digital twin model of the hazardous chemical transport tanker.

[0174] Finally, the system presents the status of the hazardous chemical tanker truck, including personnel behavior, vehicle status, cargo condition, and surrounding environment. Based on the output of the intelligent algorithm, these statuses are intelligently represented to assess risk factors. Based on the model output and the intelligent status representation, the system will execute intelligent early warning actions.

[0175] The digital twin module is divided into a 3D display module, a data transmission module, a model correction module, and an early warning module, as follows: Figure 6 As shown.

[0176] The 3D display module showcases the digital model of the hazardous materials transport tanker truck, constructing a response model describing its behavioral characteristics by considering the behavioral coupling relationships between various components. The data transmission module inputs data collected by the data acquisition module and the results of the risk assessment module's evaluations of various aspects into the model calibration module. The model calibration module corrects the model displayed in the 3D display module using the received data, constructing parameters and objective functions to ensure the model's output closely approximates the physical results. Its goal is to guarantee the model's accuracy and better adapt it to different application needs and conditions. Finally, the early warning module, based on preset safety thresholds and logical rules, immediately triggers the corresponding alarm mechanism upon detecting changes in indicators exceeding normal ranges. This provides alerts for various states of the hazardous materials transport tanker truck, reminding the driver and back-end monitoring personnel.

[0177] Example 2:

[0178] like Figure 7 As shown in the example, this document provides a safety status monitoring system for hazardous chemical transport tank trucks 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. Its purpose is to improve the safety factor during the transportation of hazardous chemicals, as detailed below:

[0179] The data acquisition module is used to collect multi-element perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemical tank trucks. The data includes: vehicle speed, acceleration, tilt angle, tank temperature, tank pressure, tank liquid level, driver behavior, relative speed and distance between vehicles in front and behind, weather conditions, and road area.

[0180] The data processing module is used to preprocess the collected data through the data preprocessing module. The preprocessing includes cleaning, missing value imputation, outlier handling, and classification operations, and the processed data is transmitted 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. It uses preprocessed data to input the initial risk assessment and early warning model and trains 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 acquire real-time multi-element perception data of "people-vehicle-cargo-environment" of hazardous chemical transport tankers. Through the risk assessment and early warning model, it identifies and warns of various unsafe conditions in the operation of hazardous chemical transport tankers, so as to realize the safety status assessment of hazardous chemical transport tankers in four dimensions: people, vehicle, cargo, and environment.

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

[0184] The decision support module combines current conditions with historical data, and based on the model output and intelligent state representation of the digital twin module, it predicts possible failures or dangerous events in advance, providing decision support for operators and ensuring the safety and reliability of the transportation process.

[0185] The risk assessment module is divided into a primary risk assessment module and a comprehensive risk assessment module. The risk assessment module is used to evaluate various conditions of hazardous chemical transport tank trucks. It incorporates an intelligent assessment algorithm capable of risk diagnosis based on four aspects: people, vehicle, cargo, and environment. The primary risk assessment module assesses the risks of each of these four aspects separately, while the comprehensive risk assessment module combines all four aspects for an overall assessment.

[0186] Example 3:

[0187] like Figure 8 The diagram shown is a schematic representation of the structure of an electronic device using a method provided in 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, such as program 12, stored in the memory 11 and executable on the processor 10.

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

[0190] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (such as program 12 for adaptive database detection data link construction) and calls data stored in the memory 11 to perform 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 typically used to establish communication connections between the electronic device 1 and other electronic devices, and to enable communication between internal components of the electronic device.

[0192] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0193] Figure 8 Only electronic devices with components are shown; it will be understood by those skilled in the art 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, or combine certain components, or have different component arrangements.

[0194] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail 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 or wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0196] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

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

[0198] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 7 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0199] It should be noted that the sequence numbers of the above embodiments of the present invention are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

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

[0201] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology, characterized in that, include: Step 1: Collect multi-element perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemical tank trucks through the data acquisition module. The data includes: vehicle speed, acceleration, tilt angle, tank temperature, tank pressure, tank liquid level, driver behavior, relative speed and distance between vehicles in front and behind, weather conditions, and road area. Step 2: The collected data is preprocessed by the data preprocessing module. The preprocessing includes cleaning, missing value imputation, outlier handling, and classification. The processed data is then transmitted to the risk assessment module. Step 3: Construct a risk assessment and early warning model through an intelligent assessment algorithm. Input the preprocessed data into 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. Step 4: Obtain real-time multi-element perception data of "people-vehicle-cargo-environment" of hazardous chemical transport tankers, and identify and warn of various unsafe conditions in the operation of hazardous chemical transport tankers through a risk assessment and early warning model, so as to realize the safety status assessment of hazardous chemical transport tankers in four dimensions: people-vehicle-cargo-environment. 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 the sub-models of the digital twin tanker truck model in a three-dimensional interactive manner. Provide early warning of the safety risks of the operating status of the hazardous chemical transport tanker truck to achieve intelligent early warning driven by data, model, and knowledge. 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 for operators, and ensure the safety and reliability of the transportation process. Step 4 involves assessing the safety status of hazardous chemical transport tankers across four dimensions: people, vehicle, cargo, and environment. First, the primary risk assessment module is used to conduct a first-level risk status assessment of the four dimensions of people, vehicles, goods, and environment. Then, the overall risk assessment module is used to integrate people, vehicles, goods, and environment together through fuzzy comprehensive evaluation method for a second-level assessment. The method of using the primary risk assessment module to conduct a first-level risk status assessment across four dimensions—people, vehicles, goods, and environment—includes: To assess a person's safety status, a visual detection algorithm is used to evaluate the driver's behavior. Dangerous behaviors include: making a phone call, yawning, drinking water, playing on a mobile phone, and nodding while drowsy. The algorithm also outputs a first-level risk status assessment factor for the "person". To assess the safety status of tank trucks, firstly, tiered thresholds are set for tank truck speed, acceleration, and tank tilt angle in different scenarios and locations to conduct a preliminary assessment of the tank truck's condition. Then, a secondary assessment is performed using data collected on the relative speed and distance between the tank truck and the preceding and following vehicles to determine the tank truck's current status. Simultaneously, based on the relationship between mileage and stress cycle count, and by combining the fatigue strength index and fatigue strength coefficient in the SN curve with the cumulative damage concept in Miner's theory, an early warning model for component fatigue life estimated by mileage is constructed. Finally, the above algorithms are combined to output a primary risk status assessment factor for the "vehicle." The safety status of hazardous chemicals transport tankers can be derived from the temperature, pressure, and liquid level of the hazardous chemicals. By using an LSTM neural network to predict the temperature and pressure, and using a threshold method based on the predicted data to assess the status of the hazardous chemicals, the system outputs a primary risk status assessment factor for the cargo.

2. The method for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology according to claim 1, characterized in that, The data acquisition module collects multi-element perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemical tank trucks, including: The multi-element perception data of "people-vehicle-goods-environment" during the transportation of hazardous chemical tank trucks comes from the vehicle monitoring data and hazardous chemical monitoring data of the hazardous chemical tank trucks. Data is collected on various unsafe conditions of hazardous chemical transport tank trucks during operation; Among these, the various unsafe conditions include: abnormalities of the hazardous chemical transport tanker truck, abnormalities in the condition of the hazardous chemicals, abnormalities in the condition of the hazardous chemical transport tanker truck driver, and interference from the surrounding environment; The abnormalities of the hazardous chemical transport tanker trucks include: fatigue failure of key components of the tanker trucks, side tilting of the tanker trucks, and collision threats to the tanker trucks; The abnormal status of the hazardous chemicals includes abnormalities in four aspects: liquid level inside the tank, pressure inside the tank, temperature inside the tank, and gas concentration. The abnormal state of the drivers of the hazardous chemical transport tanker trucks includes monitoring dangerous driving behaviors of the drivers, including monitoring the drivers' driving behavior, the number of blinks and yawns; The surrounding environmental 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 hazardous chemical transport tank trucks based on digital twin technology according to claim 2, characterized in that: The method of using an LSTM neural network to predict temperature and pressure includes: A two-layer LSTM neural network is constructed. The input layer consists of time vectors of feature parameters such as temperature, pressure, vehicle speed, liquid level, and tank tilt angle. The first layer is an LSTM layer with multiple memory units, some of which are used to process the input data and others to retrieve the memory from the previous layer. The second layer is a dropout layer, which randomly discards the output of the previous layer to reduce the risk of overfitting. The third layer is a second LSTM layer, which continues to process the output of the previous layer, further extracting features and generating new outputs. The fourth layer is a second dropout layer, which again randomly discards the output to ensure the network's generalization ability. The last layer is a fully connected layer, which calculates the output of the previous layer through a linear transformation, ultimately generating a multi-class prediction result vector. In the training process of the primary risk assessment module, mean squared error (MSE) is selected as the loss function, and in order to prevent the model from overfitting and improve the stability of training, the Adam optimizer is used for optimization. Based on the predicted data, a threshold method is used for graded evaluation. When the predicted value reaches the first-level warning threshold, the current status is output. If it reaches the second-level warning threshold, a second evaluation is conducted using the same type of temperature difference comparison method, temperature change rate, and temperature deviation.

4. The method for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology according to claim 3, characterized in that: The overall risk assessment module utilizes fuzzy comprehensive evaluation to integrate people, vehicles, goods, and the environment for secondary evaluation, including: A two-layer fuzzy evaluation model is constructed, and the various characteristic data of the hazardous chemical transport tanker are used for research. An index evaluation system is established, and its factor set can be expressed as: ,in, , , ... Indicate the evaluation factors; The degree of influence of each factor on the safety status of the tanker truck can be divided into 5 levels: poor, slightly poor, moderate, slightly good, and good; the level set of any one factor can be represented as: ,in, , , , , Indicates the evaluation level under the corresponding evaluation factor; A weight is assigned to each factor, expressed as follows: ； and ,in, This indicates the weight for each factor. The fuzzy evaluation level obtained through the first-level fuzzy comprehensive evaluation method is: ,in, This represents the fuzzy evaluation level for each factor. By analyzing a factor of U in the factor set An evaluation is conducted to obtain the evaluation levels. membership degree ,Right now: ； Establish a comprehensive evaluation matrix: ; After obtaining the factor weight set A and the comprehensive evaluation matrix R, the fuzzy comprehensive evaluation set B is obtained through the generalized fuzzy synthesis operator*. ; A multi-level evaluation method is used for comprehensive evaluation. If its subset can be divided into m factors, then its corresponding factor set is: ,in, Indicates the evaluation level under the corresponding evaluation factor; Its factor weight set is: ,in, This indicates the weight for each factor. By establishing the second-level comprehensive evaluation matrix, the second-level comprehensive evaluation set can be obtained: ,in ; By taking the comprehensive evaluation result of the first level as input and performing fuzzy synthesis operation again, the final comprehensive evaluation result can be obtained. Once the fuzzy evaluation model is established, the risk assessment level of the hazardous chemical transport tanker is output in the form of a membership function. The degree of influence of each factor on the safety status of the tanker can be divided into 5 levels: poor, slightly poor, medium, slightly good, and good.

5. The method for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology according to claim 4, characterized in that: The construction of the digital twin module in step 5 includes: The system is constructed sequentially, consisting of a 3D display module, a data transmission module, a model calibration module, and an early warning module. The three-dimensional display module is used to display the digital model of the hazardous chemical transport tanker truck. By considering the behavioral coupling relationship between various components, a response model describing the behavioral characteristics of the tanker truck 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 calibration module. The model correction module corrects the model displayed by the 3D display module using the received data, and constructs the model output results as close as possible to the physical results based on the parameters and objective function. Its goal is to ensure the accuracy of the model and make it better adaptable to different application needs 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 alert the driver and back-end supervisors to various states of the hazardous chemical transport tanker.

6. A safety status detection system for hazardous chemical transport tank trucks based on digital twin technology, characterized in that: The system is implemented based on the method of claim 5, and 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 data acquisition module is used to collect multi-element perception data of "people-vehicle-cargo-environment" during the transportation of hazardous chemical tank trucks. The data includes: vehicle speed, acceleration, tilt angle, tank temperature, tank pressure, tank liquid level, driver behavior, relative speed and distance between vehicles in front and behind, weather conditions, and road area. The data processing module is used to preprocess the collected data through the data preprocessing module. The preprocessing includes cleaning, missing value imputation, outlier handling, and classification operations, and the processed data is transmitted to the risk assessment module. The risk model construction module is used to construct a risk assessment and early warning model through an intelligent assessment algorithm. It uses preprocessed data to input the initial risk assessment and early warning model and trains 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. The risk assessment module is used to acquire real-time multi-element perception data of "people-vehicle-cargo-environment" of hazardous chemical transport tankers. Through the risk assessment and early warning model, it identifies and warns of various unsafe conditions in the operation of hazardous chemical transport tankers, so as to realize the assessment of the safety status of hazardous chemical transport tankers in four dimensions: people, vehicle, cargo, and environment. The digital twin module is used to display the structure, risk evolution process, parameter details and coupling relationship between its sub-models of the digital twin tanker truck model in a three-dimensional interactive manner based on the data output of the risk assessment and early warning model, and to provide early warning of the safety risks of the operating status of the hazardous chemical transport tanker truck, so as to realize intelligent early warning driven by data-model-knowledge. The decision support module combines current conditions with historical data, and based on the model output and intelligent state representation of the digital twin module, it predicts possible failures or dangerous events in advance, providing decision support for operators and ensuring the safety and reliability of the transportation process.

7. 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, it implements the steps of the method for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology as described in any one of claims 1 to 5.

8. A computer storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for detecting the safety status of hazardous chemical transport tank trucks based on digital twin technology as described in any one of claims 1 to 5.

Images