Distributed control system and method for liquid hydrogen refueling station

Abstract

The invention provides a distributed control system and method for a liquid hydrogen refueling station, and relates to the technical field of intelligent control, and the system comprises a fault diagnosis and early warning module which is used for monitoring the operation state and technological parameters of all equipment of the liquid hydrogen refueling station in real time, and when abnormal conditions or potential risks are detected, the abnormal conditions or potential risks comprise equipment faults and technological parameter overrun, and the fault diagnosis and early warning module is used for monitoring the operation state and technological parameters of all equipment of the liquid hydrogen refueling station; an early warning signal is sent out, and corresponding processing measure suggestions are generated; and the distributed control node module is used for controlling specific equipment or areas in the liquid hydrogen refueling station and comprises liquid hydrogen storage equipment, hydrogen compression equipment, a hydrogen refueling machine and safety monitoring equipment. According to the invention, through integration of monitoring, diagnosis, control, analysis and self-adaption functions, the operation efficiency, safety and intelligent management capability of the liquid hydrogen refueling station are improved, and automatic generation of fault early warning and optimization suggestions and automatic adjustment of a control scheme are realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a distributed control system and method for a liquid hydrogen refueling station. Background Art

[0002] Although the traditional centralized control system can achieve unified management and control of the entire liquid hydrogen refueling station to a certain extent, it also has some defects that cannot be ignored.

[0003] First, the centralized control system is highly dependent on the central controller. This dependence may increase the vulnerability of the system. Once the central controller fails or is disturbed, the control system of the entire liquid hydrogen refueling station may be affected or even paralyzed, which will seriously affect the normal operation of the liquid hydrogen refueling station. For example, in an actual operation, the central controller was damaged by lightning, causing the entire liquid hydrogen refueling station to fail to work normally, causing considerable losses to the operation.

[0004] Secondly, as the scale of liquid hydrogen refueling stations expands, the complexity and maintenance costs of centralized control systems will continue to increase. This increase is not only reflected in the increase in hardware equipment and the complexity of wiring, but also in the upgrade and maintenance of software systems. For example, when a liquid hydrogen refueling station needs to add new equipment or functions, it may be necessary to make large-scale modifications and debugging of the entire control system, which not only increases the difficulty of the work, but may also introduce new risk points. Summary of the invention

[0005] The technical problem to be solved by the present invention is to provide a distributed control system and method for a liquid hydrogen refueling station, which improves the reliability and flexibility of the system.

[0006] In order to solve the above technical problems, the technical solution of the present invention is as follows: In a first aspect, a distributed control system for a liquid hydrogen refueling station includes: The central control unit module is used to pre-process and extract features of control instructions, and then classify them through the trained classification model to obtain classification results; determine the execution plan and issue instructions based on the classification results, and collect the operating data of the liquid hydrogen refueling station in real time through control nodes and sensors; Fault diagnosis and early warning module, used to monitor the operating status and process parameters of each equipment in the liquid hydrogen refueling station in real time. When abnormal conditions or potential risks are detected, including equipment failure and process parameter exceeding the limit, early warning signals are issued and corresponding treatment measures are recommended; Distributed control node modules are used to control specific equipment or areas within a liquid hydrogen refueling station, including liquid hydrogen storage equipment, hydrogen compression equipment, hydrogen refueling machines, and safety monitoring equipment; The analysis module is used to analyze the real-time sensor data, equipment operation status data, process parameter data, historical fault record data and environmental monitoring data collected during the operation of the liquid hydrogen refueling station, and generate operation efficiency reports, fault predictions and optimization suggestions based on the data analysis results; The adaptive control function module is used to automatically adjust the control scheme according to the actual operation of the liquid hydrogen refueling station and changes in the external environment, including temperature, humidity and equipment aging.

[0007] Furthermore, after preprocessing and feature extraction of the control instructions, the control instructions are classified by the trained classification model to obtain classification results; the execution plan is determined and instructions are issued according to the classification results, and the operation data of the liquid hydrogen refueling station is collected in real time through the control nodes and sensors, including: Preprocess the control instructions and extract instruction features, including instruction length, keyword frequency and instruction structure; Using the historical control instruction data set to train the preset classification model to obtain a trained classification model; The extracted instruction features are input into the trained classification model, and the types of instructions are classified according to the input feature vector, including equipment control instructions, process control instructions or safety monitoring instructions, to obtain a classified instruction set; Formulate instruction execution plans based on the priority, equipment load, process progress and safety status of the instructions in the classified instruction set; According to the instruction execution plan, the control instructions are sent to the corresponding distributed control nodes, and the operating status data of the liquid hydrogen refueling station is collected in real time through the distributed control nodes and sensors, including the current operating status of the equipment, real-time parameters of the process flow and relevant data of environmental monitoring.

[0008] Furthermore, the preset classification model is trained using the historical control instruction data set to obtain a trained classification model, including: Acquire a historical control instruction data set, wherein the instruction data set includes equipment control instructions, process flow control instructions, and safety monitoring instructions; Use the neural network as the preset classification model and initialize the parameters of the classification model, including setting the initial learning rate and number of iterations; During the classification model training process, the scope of parameter updates is limited by the trust region method; Determine the initial size of the trust region, and calculate the direction and size of the parameter update based on the parameters of the current classification model and the size of the trust region; Use the historical control instruction dataset to train the classification model and calculate the value of the objective function; Adjust and update the parameters of the classification model according to the value of the objective function and the limits of the trust region; After a preset number of iterative training, a trained classification model is obtained.

[0009] Furthermore, the calculation formula of the objective function value is: ; in, represents the loss function; represents the total number of samples; Indicates the sample index; Indicates the total number of categories; , Represents the category index; Indicates category frequency; Representation sample For categories The weight coefficient of Representation sample Belongs to category The true label of Represents the classification model for samples Belongs to category The original output of Representation sample For categories Bias adjustment term; Represents the classification model for samples Belongs to category The original output of Representation sample For categories Bias adjustment term; represents the regularization coefficient; represents the square of the classification model parameter; Represents the base of natural logarithms.

[0010] Furthermore, the operating status and process parameters of each device in the liquid hydrogen refueling station are monitored in real time. When abnormal conditions or potential risks are detected, including equipment failure and process parameter exceeding the limit, an early warning signal is issued and corresponding treatment measures are generated, including: Continuously analyze real-time monitoring equipment and process parameters to detect the real-time status of equipment and process parameters by comparing current data with the preset normal operating range or mode; Set a threshold range for each process parameter. When a process parameter exceeds the threshold range, it is considered abnormal and triggers the early warning mechanism to generate an early warning signal. The early warning signal includes the abnormal type, occurrence time, and related equipment or parameter information. According to the abnormal type in the early warning signal, the corresponding treatment measures are determined from the emergency treatment plan library, and treatment measure suggestions are generated, including operation steps, a list of required tools or equipment, and safety precautions information.

[0011] Furthermore, the real-time sensor data, equipment operation status data, process parameter data, historical fault record data and environmental monitoring data collected during the operation of the liquid hydrogen refueling station are analyzed, and based on the data analysis results, operation efficiency reports, fault predictions and optimization suggestions are generated, including: Continuously collect real-time sensor data during the operation of the liquid hydrogen refueling station, including key parameters such as temperature, pressure, flow, and liquid level, and record the operating status of the equipment, including startup, shutdown, fault status changes, operating hours, and maintenance records; Extract features that affect operating efficiency, fault prediction, and optimization suggestion generation from real-time sensor data and equipment operating status data, including average equipment operating time, fault frequency, and energy consumption level; Based on the extracted features, the operating efficiency indicators of the liquid hydrogen refueling station are calculated, including equipment utilization, energy efficiency and process stability, and an operating efficiency report is generated, including the calculation results of efficiency indicators, trend analysis, and problem point identification content; Build a fault prediction model based on operating efficiency indicators, historical fault record data, and real-time monitoring data to predict the type and probability of future faults; Improving the operating efficiency of liquid hydrogen refueling stations and reducing the failure rate are taken as optimization goals, and the optimization problem is defined. The solution space of the optimization problem is mapped to the search space of the whale group, and each individual whale represents a solution. By simulating the foraging behavior of whales, including surrounding prey, bubbling net attack and searching for prey, the position of individual whales is continuously updated, and the quality of individual whales is evaluated through fitness functions. Repeat the process of simulating the whale's foraging behavior and updating the individual whale's position until the preset number of iterations is reached and the final solution is determined; Based on the final solution, optimization suggestions are generated, including suggestions on equipment adjustment, process improvement and maintenance plan optimization.

[0012] Furthermore, the calculation formula of the fitness function is: ; in, Indicates that the device is in period Comprehensive performance; , , , represents the weight coefficient; Indicates that during the period The actual operating time of the equipment within; Indicates that during the period The planned operating time of the equipment within; Indicates unplanned downtime; Indicates the planned running time; Indicates the period Theoretical output of internal equipment; represents the theoretical output; Indicates the actual output; Indicates that during the period Theoretical energy consumption of internal equipment; represents input energy; Indicates output energy; Indicates that during the period Quality factor of internal equipment; Indicates the number of defective products; Indicates the total product quantity; Indicates the period Failure rate of internal equipment; A coefficient indicating the severity of the consequences of a failure.

[0013] Furthermore, according to the actual operation of the liquid hydrogen refueling station and changes in the external environment, including temperature, humidity and equipment aging, the control scheme is automatically adjusted, including: Define fuzzy sets for air temperature, humidity, equipment status, and control parameter adjustments; Determine the membership function for each fuzzy set and formulate fuzzy rules; Infer the fuzzy values ​​of output variables based on fuzzy sets, membership functions and fuzzy rules; The real-time monitored temperature, humidity and equipment status data are converted into fuzzy values ​​through membership functions, and fuzzy rules are used for reasoning to obtain the fuzzy values ​​of the control parameter adjustment amounts; The fuzzy value of the control parameter adjustment amount is converted into a specific numerical value through the defuzzification method. When changes in temperature, humidity or equipment status are detected, the control plan is automatically adjusted.

[0014] Furthermore, the calculation formula of the membership function is: ; in, Representation variables Belongs to fuzzy sets the extent of; Represents a variable; Indicates the base value of the left endpoint; Indicates the offset of the left endpoint; represents the index of the left half; represents a vertex; Indicates the base value of the right endpoint; Indicates the offset of the right endpoint; Indicates the scaling factor of the left half; Indicates the scaling factor of the right half; Indicates the exponent of the right half.

[0015] In a second aspect, a distributed control method for a liquid hydrogen refueling station includes: After preprocessing and feature extraction of control instructions, they are classified through the trained classification model to obtain classification results; the execution plan is determined and instructions are issued based on the classification results, and the operation data of the liquid hydrogen refueling station is collected in real time through control nodes and sensors; Real-time monitoring of the operating status and process parameters of each equipment in the liquid hydrogen refueling station. When abnormal conditions or potential risks are detected, including equipment failure and process parameter exceeding the limit, early warning signals are issued and corresponding treatment measures are recommended; Control specific equipment or areas within a liquid hydrogen refueling station, including liquid hydrogen storage equipment, hydrogen compression equipment, hydrogen refueling machines, and safety monitoring equipment; Analyze the real-time sensor data, equipment operation status data, process parameter data, historical fault record data and environmental monitoring data collected during the operation of the liquid hydrogen refueling station, and generate operation efficiency reports, fault predictions and optimization suggestions based on the data analysis results; The control scheme is automatically adjusted according to the actual operation of the liquid hydrogen refueling station and changes in the external environment, including temperature, humidity and equipment aging.

[0016] The above solution of the present invention includes at least the following beneficial effects: The central control unit module can pre-process and extract features of control instructions, and then classify them through the trained classification model to obtain classification results; determine the execution plan and issue instructions based on the classification results, and collect the operating data of the liquid hydrogen refueling station in real time through control nodes and sensors to ensure that all equipment works together, thereby improving the overall operating efficiency. The analysis module can generate an operating efficiency report by analyzing real-time sensor data, equipment operating status data, etc., to provide data support for optimizing the operation of liquid hydrogen refueling stations. The fault diagnosis and early warning module can monitor the operating status and process parameters of each device in the liquid hydrogen refueling station in real time, detect abnormal conditions or potential risks in a timely manner, and issue early warning signals to help prevent the occurrence of safety accidents.

[0017] The distributed control node module can control specific equipment or areas within the liquid hydrogen refueling station, including safety monitoring equipment, to ensure rapid response and measures in emergency situations. Through the real-time monitoring and early warning functions of the fault diagnosis and early warning module, preventive measures can be taken before equipment failure occurs to reduce the failure rate.

[0018] The analysis module can analyze historical fault record data to help identify fault modes and provide support for fault prediction and preventive maintenance. The analysis module can analyze equipment operating status data and process parameter data to help formulate a more reasonable maintenance plan and reduce unnecessary maintenance costs. Through the fault prediction function, maintenance work can be arranged in advance to avoid liquid hydrogen refueling station shutdowns due to equipment failures.

[0019] The adaptive control function module can automatically adjust the control scheme according to the actual operating conditions of the liquid hydrogen refueling station and external environmental changes (such as temperature, humidity and equipment aging), ensuring that the liquid hydrogen refueling station can maintain stable operation in different environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a schematic diagram of a distributed control system of a liquid hydrogen refueling station provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0022] like Figure 1 As shown, an embodiment of the present invention provides a distributed control system for a liquid hydrogen refueling station, comprising: The central control unit module 11 is used to pre-process and extract features of the control instructions, and then classify them through the trained classification model to obtain classification results; determine the execution plan and issue instructions based on the classification results, and collect the operation data of the liquid hydrogen refueling station in real time through the control nodes and sensors; The fault diagnosis and early warning module 12 is used to monitor the operating status and process parameters of each device in the liquid hydrogen refueling station in real time. When abnormal conditions or potential risks are detected, including equipment failure and process parameter exceeding the limit, an early warning signal is issued and corresponding treatment measures are generated; Distributed control node module 13, used to control specific equipment or areas in the liquid hydrogen refueling station, including liquid hydrogen storage equipment, hydrogen compression equipment, hydrogen refueling machine and safety monitoring equipment; The analysis module 14 is used to analyze the real-time sensor data, equipment operation status data, process parameter data, historical fault record data and environmental monitoring data collected during the operation of the liquid hydrogen refueling station, and generate an operation efficiency report, fault prediction and optimization suggestions based on the data analysis results; The adaptive control function module 15 is used to automatically adjust the control scheme according to the actual operation of the liquid hydrogen refueling station and changes in the external environment, including temperature, humidity and equipment aging.

[0023] In an embodiment of the present invention, unified management and scheduling of liquid hydrogen refueling stations are achieved by centrally receiving, processing and sending control instructions. The operating status of the liquid hydrogen refueling station is continuously monitored to ensure the normal operation of each device, and abnormal situations are discovered and handled in a timely manner. The central control unit can respond quickly to control instructions and improve the overall operating efficiency of the liquid hydrogen refueling station. Real-time monitoring of equipment operating status and process parameters, timely detection of abnormal situations or potential risks, and issuance of early warning signals. Through early warning and treatment measures, losses caused by equipment failure or process parameter out-of-limit can be reduced. Effectively prevent the occurrence of safety accidents and ensure the safe operation of liquid hydrogen refueling stations.

[0024] Precisely control specific equipment or areas within the liquid hydrogen refueling station to improve control accuracy and efficiency. Distributed control nodes can be flexibly configured according to actual needs to meet the needs of different liquid hydrogen refueling stations. Through distributed control, the impact of a single node failure on the entire system is reduced, and the reliability of the system is improved. Through the analysis of a large amount of data, data support is provided for the operation and management of the liquid hydrogen refueling station to achieve data-driven decision-making. Based on the data analysis results, an operation efficiency report is generated to help optimize the operation efficiency of the liquid hydrogen refueling station. Through the analysis of historical fault record data, fault prediction and preventive maintenance are achieved to reduce the occurrence of faults.

[0025] The control scheme is automatically adjusted according to the actual operation of the liquid hydrogen refueling station and changes in the external environment to ensure the stable operation of the liquid hydrogen refueling station. By optimizing the control scheme, the goal of energy saving and emission reduction can be achieved and the environmental protection performance of the liquid hydrogen refueling station can be improved.

[0026] In a preferred embodiment of the present invention, after preprocessing and feature extraction of the control instructions, the control instructions are classified by a trained classification model to obtain a classification result; an execution plan is determined and instructions are issued according to the classification result, and the operation data of the liquid hydrogen refueling station is collected in real time through the control node and the sensor, which may include: Preprocess the control instructions and extract instruction features, including instruction length, keyword frequency and instruction structure; Using the historical control instruction data set to train the preset classification model to obtain a trained classification model; The extracted instruction features are input into the trained classification model, and the types of instructions are classified according to the input feature vector, including equipment control instructions, process control instructions or safety monitoring instructions, to obtain a classified instruction set; Formulate instruction execution plans based on the priority, equipment load, process progress and safety status of the instructions in the classified instruction set; According to the instruction execution plan, the control instructions are sent to the corresponding distributed control nodes, and the operating status data of the liquid hydrogen refueling station is collected in real time through the distributed control nodes and sensors, including the current operating status of the equipment, real-time parameters of the process flow and relevant data of environmental monitoring.

[0027] In an embodiment of the present invention, an original control instruction text is received. The instruction is cleaned using text processing techniques (such as word segmentation, stop word removal, etc.). The length of the instruction, i.e., the number of characters or words, is calculated. The frequency of occurrence of keywords in the instruction is counted, and the keywords may be preset words related to equipment control, process flow, or safety monitoring. The structure of the instruction is analyzed, such as the beginning, body, and end of the instruction, and the logical relationship between them.

[0028] Collect and organize historical control instruction datasets, including instruction samples with labeled types. Select an appropriate classification algorithm (such as a decision tree) as the preset model. Use the historical dataset to train the preset model and adjust the model parameters to optimize the classification performance. Evaluate the performance of the trained model on the validation set to ensure that the model has sufficient accuracy and generalization ability.

[0029] Convert the preprocessed instruction features into feature vectors. Input the feature vectors into the trained classification model. The model performs inference based on the input feature vectors and outputs the type label of the instruction. Collect all classified instructions to form a classified instruction set.

[0030] Analyze the classified instruction set and determine the priority of each instruction. Monitor the equipment load in real time and evaluate the equipment's ability to execute instructions. Track the progress of the process to ensure the coordination of instructions and process. Consider the safety status and avoid executing instructions that may cause safety risks. Based on the above factors, formulate a reasonable instruction execution plan.

[0031] According to the instruction execution plan, the control instructions are sent to the corresponding distributed control nodes. The distributed control nodes receive the instructions and execute them to control the corresponding equipment or process flow. The operating status data of the liquid hydrogen refueling station is collected in real time through sensors, including equipment status, process parameters and environmental data. The collected data is sent to the central control unit for further processing and analysis.

[0032] Suppose a control instruction is received: "Start the hydrogen compression equipment, adjust the pressure to 10MPa, and monitor the equipment temperature." Clean the instruction text and remove irrelevant words. Calculate the instruction length: a number of characters. Count the frequency of keywords: "Start" 1 time, "Hydrogen compression equipment" 1 time, "Pressure" 1 time, "10MPa" 1 time, "Monitor" 1 time, "Equipment temperature" 1 time. The instruction consists of a beginning (start the equipment), a body (adjust the pressure, monitor the temperature), and an end (no specific end). Extract the feature vector and input it into the trained classification model. The model outputs the instruction type as "Equipment control instruction". Determine the instruction priority as high.

[0033] Check the load of the hydrogen compression equipment and confirm that the equipment is available. Confirm that the process progress allows the execution of the instruction. Evaluate the safety of executing the instruction and there is no safety risk. Start the equipment immediately, adjust the pressure to 10MPa, and continuously monitor the equipment temperature. Send the instruction to the distributed control node that controls the hydrogen compression equipment. The control node executes the instruction, starts the equipment and adjusts the pressure. The sensor collects equipment status, pressure value and temperature data in real time.

[0034] Through preprocessing and classification, the instruction type can be quickly identified to reduce the instruction processing time. A reasonable execution plan can be formulated to ensure that the instructions are executed in order according to the priority and actual situation. It can handle various types of control instructions to meet the needs of different equipment and process flows. Through real-time data collection and analysis, the instruction execution plan can be adjusted in time to improve the adaptability of the system. Before executing instructions, a safety assessment can be conducted to avoid executing instructions that may cause safety risks. Real-time monitoring of equipment status and process parameters can be carried out to promptly detect and handle abnormal situations to ensure the safe operation of the liquid hydrogen refueling station. Develop an execution plan based on equipment load and process progress to make rational use of resources and avoid resource waste. Through data analysis, equipment operating parameters and process flows can be optimized to improve resource utilization efficiency.

[0035] In another preferred embodiment of the present invention, using the historical control instruction data set to train a preset classification model to obtain a trained classification model may include: Acquire a historical control instruction data set, wherein the instruction data set includes equipment control instructions, process flow control instructions, and safety monitoring instructions; Use the neural network as the preset classification model and initialize the parameters of the classification model, including setting the initial learning rate and number of iterations; During the classification model training process, the scope of parameter updates is limited by the trust region method; Determine the initial size of the trust region, and calculate the direction and size of the parameter update based on the parameters of the current classification model and the size of the trust region; Use the historical control instruction dataset to train the classification model and calculate the value of the objective function; Adjust and update the parameters of the classification model according to the value of the objective function and the limits of the trust region; After a preset number of iterative training, a trained classification model is obtained.

[0036] In an embodiment of the present invention, a historical control instruction data set is loaded from a database or a file system. The data set should contain multiple types of instructions, such as equipment control instructions, process control instructions, and safety monitoring instructions. A neural network is selected as a classification model, and its structure (such as the number of layers, the number of neurons in each layer, etc.) is determined. The parameters of the neural network, such as weights and biases, are initialized, usually using random initialization or pre-trained model initialization. The learning rate is set, which is a hyperparameter that controls the speed of parameter updates. The number of iterations, that is, the number of times the model is updated during training, is determined. Through the trust region method, which is an optimization algorithm used to limit the range of parameter updates to prevent the model from deviating excessively during training. Define the size of the trust region, that is, the maximum range of variation allowed when the parameters are updated.

[0037] Set the initial size of the trust region. At each iteration, the direction and size of the parameter update are calculated based on the parameters of the current model and the size of the trust region. This involves calculating the gradient to determine the direction of the parameter update.

[0038] Input the historical control instruction data set into the classification model for training. In each iteration, calculate the value of the objective function. Determine whether the parameter update is valid based on the value of the objective function and the limits of the trust region. If the update is valid, adjust the parameters of the model based on the calculated update direction and size. If the update is invalid or exceeds the trust region range, adjust the size of the trust region or reject the update. Train according to the set number of iterations until the preset number of iterations is reached. Save the trained classification model for subsequent use.

[0039] Suppose there is a historical data set containing equipment control instructions, process control instructions, and safety monitoring instructions, and you want to train a neural network classification model to identify these instructions.

[0040] Load the historical control instruction data set from the database, which contains 1000 instructions, including 300 equipment control instructions, 400 process control instructions, and 300 safety monitoring instructions. Select a neural network with two hidden layers as the classification model. Initialize the weights and biases of the neural network to random values.

[0041] Set the learning rate to 0.01 and the number of iterations to 1000. Set the initial size of the trust region to 0.1. In each iteration, calculate the direction and size of the parameter update to ensure that the update is within the trust region. Input the dataset into the neural network for training. In each iteration, calculate the value of the loss function and adjust the parameters of the model according to the limits of the trust region. After 1000 iterations of training, the trained neural network classification model is obtained. The accuracy of the model on the validation set reaches 95%, which can be used for actual instruction classification tasks.

[0042] By training the neural network classification model, equipment control instructions, process control instructions and safety monitoring instructions can be more accurately identified. The introduction of the trust region method limits the scope of parameter updates and prevents overfitting and instability of the model during training. Through training with historical data sets, the model can learn the characteristics and rules of instructions and has a certain classification ability for unseen instructions. The trust region method helps the model maintain stability during training and improves the generalization ability of the model. The neural network model can improve training efficiency through parallel computing and GPU acceleration. The trust region method reduces invalid updates and waste of computing resources by limiting the scope of parameter updates. The neural network model has good scalability and maintainability, and the model structure and parameters can be adjusted according to actual needs. The trust region method in the training process can provide certain guidance for model updates, making model updates more stable and reliable.

[0043] In a preferred embodiment of the present invention, the calculation formula of the value of the objective function is: ; in, represents the loss function; represents the total number of samples; Indicates the sample index; Indicates the total number of categories; , Represents the category index; Indicates category frequency; Representation sample For categories The weight coefficient of Representation sample Belongs to category The true label of Represents the classification model for samples Belongs to category The original output of Representation sample For categories Bias adjustment term; Represents the classification model for samples Belongs to category The original output of Representation sample For categories Bias adjustment term; represents the regularization coefficient; represents the square of the classification model parameter; Represents the base of natural logarithms.

[0044] In the embodiment of the present invention, the total number of samples is set , total number of categories . Initialize sample index , category index , . Prepare all the required array storage , , , Equal values. Traverse all samples and count each category Count the number of occurrences. Calculate the frequency of each category , i.e. category The number of samples divided by the total number of samples According to the pre-set rules, for each sample and categories Assign weight coefficient . Read each sample from the dataset The true category label is converted into one-hot encoding form, that is, if the sample Belongs to category ,but ,otherwise . Input the classification model and get the model for the sample Belongs to each category The original output of . Calculate the bias adjustment term based on the model design .

[0045] Initialize the first part of the loss function to 0. Traverse all samples and categories , calculate each sample For categories The loss item . The above results are compared with , and Multiply to get the current sample For categories The loss term. and categories The loss terms of are added and multiplied by , and get the first part of the loss function.

[0046] Initialize the regularization term value to 0. Traverse all parameters of the classification model , calculate the sum of their squares. Multiply the sum of squares by and the regularization coefficient , get the regularization term value. Add the first part of the loss function value and the regularization term value to get the total loss function value .

[0047] By considering the weight coefficient of the sample for the category and category frequency , the loss function can more accurately reflect the impact of different samples and categories on model training. Bias adjustment term The model's output for samples can be further adjusted to improve classification accuracy. It can prevent the model from overfitting and enhance the generalization ability of the model. By limiting the sum of squares of model parameters, the regularization term can prompt the model to choose a simpler solution, thereby improving the generalization performance of the model. The loss function is designed to be flexible and the weight coefficient can be adjusted according to actual needs. , Deviation Adjustment and the regularization coefficient This flexibility allows the loss function to be adapted to different classification tasks and datasets. When calculating the logarithmic function, term to prevent numerical instability when the input of the logarithmic function is 0 or close to 0. This numerical stability treatment can ensure that the calculation process of the loss function is more reliable and robust.

[0048] In a preferred embodiment of the present invention, the operating status and process parameters of each device in the liquid hydrogen refueling station are monitored in real time. When abnormal conditions or potential risks are detected, including equipment failure and process parameter exceeding the limit, an early warning signal is issued and corresponding treatment measures are generated, which may include: Continuously analyze real-time monitoring equipment and process parameters to detect the real-time status of equipment and process parameters by comparing current data with the preset normal operating range or mode; Set a threshold range for each process parameter. When a process parameter exceeds the threshold range, it is considered abnormal and triggers the early warning mechanism to generate an early warning signal. The early warning signal includes the abnormal type, occurrence time, and related equipment or parameter information. According to the abnormal type in the early warning signal, the corresponding treatment measures are determined from the emergency treatment plan library, and treatment measure suggestions are generated, including operation steps, a list of required tools or equipment, and safety precautions information.

[0049] In an embodiment of the present invention, the operating status and process parameter data of each device of the liquid hydrogen refueling station are obtained in real time through sensors and data acquisition systems. The raw data is cleaned, denoised, calibrated, etc. to ensure the accuracy and reliability of the data. The pre-processed data is analyzed in real time using a data analysis algorithm, and the current data is compared with the preset normal operating range or mode. Set the normal operating range or mode: Based on historical data and expert experience, a normal operating range or mode is set for each device and process parameter. Compare the current data with the preset normal operating range or mode to determine whether the real-time status of the equipment and process parameters is normal. According to process requirements and safety standards, a reasonable threshold range is set for each process parameter. Monitor the changes in process parameters in real time. When the parameter value exceeds the set threshold range, it is judged to be abnormal. Once an abnormality is detected, the early warning mechanism is immediately triggered to prepare to generate an early warning signal. According to the results of the abnormality detection, the specific type of abnormality (such as equipment failure, process parameter overrun, etc.) is determined. The exact time when the abnormality occurs is recorded. Determine the equipment or parameters related to the abnormality and extract relevant information. Combine the abnormality type, occurrence time, and related equipment or parameter information into an early warning signal, which is ready to be sent to relevant personnel or systems.

[0050] Establish an emergency response solution library: Prepare and store emergency response solutions for various types of anomalies in advance. Search for matching solutions in the emergency response solution library based on the anomaly type in the early warning signal. Extract matching solutions from the emergency response solution library. Generate specific treatment measures based on the solution, including operation steps, a list of required tools or equipment, and safety precautions. Send the treatment measures to relevant personnel or systems so that timely measures can be taken to handle the anomaly.

[0051] Assume that a liquid hydrogen refueling station has a temperature sensor for real-time monitoring of the reactor temperature. The normal operating range is set to 20°C to 80°C. The sensor collects temperature data once a second, and the data acquisition system transmits this data to the monitoring system in real time. The monitoring system preprocesses the received data, such as denoising and calibration, and then performs comparative analysis. A threshold range is set for the temperature parameter: a lower limit of 20°C and an upper limit of 80°C. The monitoring system monitors the temperature data in real time, and when the temperature exceeds 80°C, it is judged as abnormal.

[0052] The monitoring system generates an early warning signal, including the type of abnormality (temperature exceeding the limit), the time of occurrence (such as 12:05:30 on April 1, 2023), and related equipment (reactor temperature sensor). The emergency treatment solution library contains treatment solutions for temperature exceeding the limit, such as immediately shutting down the heating system, turning on the cooling system, etc. The monitoring system searches and extracts matching treatment solutions from the emergency treatment solution library based on the type of abnormality in the early warning signal. Generate treatment measure suggestions, including operating steps (such as pressing the emergency stop button to shut down the heating system, opening the cooling water valve, etc.), a list of required tools or equipment (such as wrenches, cooling water valve keys, etc.), and safety precautions information (such as wearing protective gloves, avoiding electric shock, etc.). The monitoring system sends the treatment measure suggestions to the operator or control system of the liquid hydrogen refueling station so that timely measures can be taken to deal with the abnormality.

[0053] Through the real-time monitoring and early warning mechanism, abnormalities in equipment and process parameters can be discovered in time, measures can be taken to prevent accidents, and the safety of liquid hydrogen refueling stations can be improved. Early detection and handling of abnormalities can avoid losses such as equipment damage and production interruptions, and reduce the operating costs of liquid hydrogen refueling stations. The automated monitoring and early warning system can respond to abnormalities quickly, reduce delays in manual monitoring and processing, and improve the operating efficiency of liquid hydrogen refueling stations. The generated treatment measures provide operators with clear operating procedures and safety precautions, enhancing the scientificity and accuracy of decision-making. The combination of real-time monitoring and early warning systems and emergency response solution libraries provides strong support for the intelligent management of liquid hydrogen refueling stations and promotes the digital transformation and upgrading of liquid hydrogen refueling stations.

[0054] In a preferred embodiment of the present invention, controlling specific equipment or areas in a liquid hydrogen refueling station, including liquid hydrogen storage equipment, hydrogen compression equipment, hydrogen refueling machines and safety monitoring equipment, may include: In an embodiment of the present invention, according to the layout and equipment distribution of the liquid hydrogen refueling station, the control system architecture is designed, including a central control room, a field equipment layer, a communication network layer, etc. Select a suitable industrial control system (such as SCADA, PLC, etc.) as the control platform to ensure the stability and reliability of the system. Cooperate with suppliers of liquid hydrogen storage equipment, hydrogen compression equipment, hydrogenation machines and safety monitoring equipment to obtain equipment interface protocols and achieve seamless integration of equipment and control systems. Install sensors (such as temperature sensors, pressure sensors, flow sensors, etc.) and actuators (such as valves, switches, etc.) on key equipment to collect equipment status parameters and control equipment operation in real time. Set up a data acquisition system to collect sensor data in real time to ensure the accuracy and timeliness of the data. Establish a data monitoring interface in the central control room to display the real-time status, operating parameters and alarm information of the equipment, so that operators can understand the equipment status at any time. According to the functions and operating procedures of the equipment, analyze the control requirements of the equipment, such as temperature control of liquid hydrogen storage equipment, pressure regulation of hydrogen compression equipment, and hydrogenation amount control of hydrogenation machines. Based on the control requirements, design automated control logic, including conditional judgment, logical operations, control algorithms, etc., to achieve automated control of the equipment. Program the control logic into the control system, conduct simulation tests and on-site debugging to ensure the correctness and effectiveness of the control logic.

[0055] Safety monitoring equipment, such as hydrogen leak detectors, fire alarms, and video surveillance cameras, are installed in liquid hydrogen refueling stations to monitor safety hazards in real time. According to safety standards and equipment characteristics, thresholds for safety monitoring parameters are set, such as upper limits for hydrogen concentration and temperature. When safety monitoring parameters exceed the set thresholds, the early warning mechanism is triggered to remind operators to handle them in a timely manner through sound and light alarms, SMS notifications, and other means.

[0056] Through the communication network layer, the central control room can remotely control the field equipment, such as remotely switching equipment on and off, adjusting equipment parameters, etc. An intuitive and easy-to-use operation interface is designed, providing equipment control buttons, parameter setting input boxes, etc., to facilitate remote operation by operators. Different levels of operation permissions are set to ensure that only authorized personnel can perform remote control and operation, thereby ensuring the security of the system.

[0057] Regularly maintain the control system, including software upgrades, hardware inspections, data backups, etc., to ensure stable operation of the system. Optimize and adjust the control logic, operation interface, etc. based on system operation status and feedback to improve system performance and user experience.

[0058] In a preferred embodiment of the present invention, real-time sensor data, equipment operation status data, process parameter data, historical fault record data and environmental monitoring data collected during the operation of the liquid hydrogen refueling station are analyzed, and an operation efficiency report, fault prediction and optimization suggestions are generated based on the data analysis results, which may include: Continuously collect real-time sensor data during the operation of the liquid hydrogen refueling station, including key parameters such as temperature, pressure, flow, and liquid level, and record the operating status of the equipment, including startup, shutdown, fault status changes, operating hours, and maintenance records; Extract features that affect operating efficiency, fault prediction, and optimization suggestion generation from real-time sensor data and equipment operating status data, including average equipment operating time, fault frequency, and energy consumption level; Based on the extracted features, the operating efficiency indicators of the liquid hydrogen refueling station are calculated, including equipment utilization, energy efficiency and process stability, and an operating efficiency report is generated, including the calculation results of efficiency indicators, trend analysis, and problem point identification content; Build a fault prediction model based on operating efficiency indicators, historical fault record data, and real-time monitoring data to predict the type and probability of future faults; Improving the operating efficiency of liquid hydrogen refueling stations and reducing the failure rate are taken as optimization goals, and the optimization problem is defined. The solution space of the optimization problem is mapped to the search space of the whale group, and each individual whale represents a solution. By simulating the foraging behavior of whales, including surrounding prey, bubbling net attack and searching for prey, the position of individual whales is continuously updated, and the quality of individual whales is evaluated through fitness functions. Repeat the process of simulating the whale's foraging behavior and updating the individual whale's position until the preset number of iterations is reached and the final solution is determined; Based on the final solution, optimization suggestions are generated, including suggestions on equipment adjustment, process improvement and maintenance plan optimization.

[0059] In an embodiment of the present invention, temperature, pressure, flow, liquid level and other sensors are deployed at key locations of the liquid hydrogen refueling station to ensure accurate collection of real-time data. A data acquisition system is established to obtain data from sensors regularly or in real time and store it in a database. Through the integrated equipment control system, information such as the equipment's startup, shutdown, fault status changes, operating time and maintenance records are recorded in real time. The collected data is cleaned, denoised, calibrated and other processes are performed to ensure the accuracy and reliability of the data. Real-time sensor data and equipment operating status data are analyzed to identify features that affect operating efficiency, fault prediction and optimization recommendations. Based on the identified features, key indicators such as the average operating time, fault frequency and energy consumption level of the equipment are calculated.

[0060] Using the extracted eigenvalues, calculate the operating efficiency indicators such as equipment utilization, energy efficiency and process stability. Integrate the calculated efficiency indicators, trend analysis (such as time series analysis, trend charts, etc.) and problem point identification (such as anomaly detection, bottleneck analysis, etc.) into an operating efficiency report. Intuitively display the contents of the operating efficiency report in the form of charts, tables, etc., which is easy for decision makers and operators to understand.

[0061] Integrate operating efficiency indicators, historical fault record data, and real-time monitoring data into a data set for the fault prediction model. Select a suitable machine learning algorithm (such as random forest) to build a fault prediction model based on data characteristics and prediction requirements. Use the integrated data set to train the selected machine learning algorithm to obtain a fault prediction model. Verify the performance of the fault prediction model through methods such as cross-validation and accuracy evaluation.

[0062] Clearly improve the operating efficiency of liquid hydrogen refueling stations and reduce the failure rate as the optimization goals. According to the optimization goals, define specific optimization problems, such as minimizing energy consumption, maximizing equipment utilization, minimizing failure rate, etc. Map the solution space of the optimization problem to the search space of the whale group optimization algorithm (such as the whale optimization algorithm), and each whale individual represents a solution. Implement foraging behaviors such as surrounding prey, bubbling net attack, and searching for prey in the whale optimization algorithm. According to the foraging behavior of the whale, the position of the individual whale is continuously updated, that is, new solutions are continuously searched. Define a fitness function to evaluate the quality of the individual whale, that is, the quality of the solution. Repeat the process of simulating the foraging behavior of the whale and updating the position of the individual whale until the preset number of iterations is reached. According to the evaluation results of the fitness function, determine the final individual whale as the final solution. Based on the final solution, generate specific optimization suggestions, such as equipment adjustment plans, process improvement measures, and maintenance plan optimization plans. Present the optimization suggestions in the form of reports or plans to facilitate implementation by decision makers and operators.

[0063] Suppose a liquid hydrogen refueling station has a hydrogen compression device, and data analysis is needed to optimize its operating efficiency and predict failures.

[0064] Collect sensor data such as temperature, pressure, flow rate, and operating status data of compression equipment in real time. Extract characteristics such as average operating time, failure frequency, and energy consumption level of equipment. Calculate operating efficiency indicators such as equipment utilization, energy efficiency, and process stability. Generate an operating efficiency report to display the calculation results, trend analysis, and problem point identification content of the indicators. Build a fault prediction model using operating efficiency indicators, historical fault record data, and real-time monitoring data. Train the model and verify its performance to ensure that it can accurately predict the type and probability of future faults. Improve the operating efficiency of compression equipment and reduce the failure rate as the optimization goal. Define the optimization problem and map the solution space to the search space of the whale group. Simulate the foraging behavior of whales, continuously update the position of individual whales, and evaluate their pros and cons through fitness functions.

[0065] The optimal whale individual is determined as the final solution through an iterative process. Based on the final solution, optimization suggestions are generated, such as adjusting the operating parameters of the compression equipment, improving the process flow, and optimizing the maintenance plan.

[0066] Through real-time data analysis and operation efficiency index calculation, the operation efficiency of the liquid hydrogen refueling station can be accurately evaluated, and efficiency bottlenecks can be discovered and resolved in a timely manner. The implementation of optimization suggestions can further improve the utilization rate and energy efficiency of equipment and reduce operating costs. The construction of a fault prediction model can accurately predict the type and probability of future faults, providing strong support for fault prevention. By taking maintenance measures or adjusting operating parameters in advance, faults can be effectively avoided, reducing downtime and maintenance costs. Operation efficiency reports and optimization suggestions provide decision makers with scientific data support and decision-making basis, which helps to make more reasonable decisions. Through the optimization process driven by data analysis, the scientificity and accuracy of decisions can be ensured, and the overall operation level of liquid hydrogen refueling stations can be improved.

[0067] In a preferred embodiment of the present invention, the calculation formula of the fitness function is: ; in, Indicates that the device is in period Comprehensive performance; , , , represents the weight coefficient; Indicates that during the period The actual operating time of the equipment within; Indicates that during the period The planned operating time of the equipment within; Indicates unplanned downtime; Indicates the planned running time; Indicates the period Theoretical output of internal equipment; represents the theoretical output; Indicates the actual output; Indicates that during the period Theoretical energy consumption of internal equipment; represents input energy; Indicates output energy; Indicates that during the period Quality factor of internal equipment; Indicates the number of defective products; Indicates the total product quantity; Indicates the period Failure rate of internal equipment; A coefficient indicating the severity of the consequences of a failure.

[0068] In the embodiment of the present invention, the equipment operation data of the liquid hydrogen refueling station at different periods (such as daily, weekly, and monthly) are collected, including the actual operation time ( )、Planned running time( ), unplanned downtime ( )、Theoretical output( ), actual output ( )、Theoretical energy consumption( ), input energy ( )、Output Energy( )、Quality coefficient( )、Number of defective products( )、Total Product Quantity( )、Failure rate( ) and the severity factor of the failure consequences ( ). Ensure the accuracy and completeness of the data and handle missing or abnormal data appropriately. Determine the weight coefficient according to the specific operation objectives and priorities of the liquid hydrogen refueling station. , , , .

[0069] Using the collected data and the determined weight coefficients, the calculations are performed according to the fitness function formula. The ratio of actual operating time to planned operating time is calculated, and the impact of unplanned downtime is considered. The difference between theoretical output and actual output is calculated, and the impact of energy efficiency is considered. The quality coefficient is calculated, and the impact of the number of defective products is considered. The failure rate is calculated, and the impact of the severity coefficient of the consequences of the failure is considered. The results of the above parts are weighted and summed according to the weight coefficient to obtain the equipment in the period. Comprehensive performance . Analyze the calculated fitness function values ​​and compare the changes in comprehensive performance in different periods. Identify the key factors affecting comprehensive performance, such as operating time, output, energy consumption, quality and failure rate. According to the analysis results, formulate optimization measures, such as adjusting the operation plan, improving the process flow, and strengthening equipment maintenance.

[0070] The fitness function comprehensively considers the equipment's operating time, output, energy consumption, quality, and failure rate, and can comprehensively evaluate the equipment's overall performance. By regularly calculating the fitness function value, the changing trend of equipment performance can be discovered in a timely manner, providing a basis for decision-making. By analyzing the operating time ratio part of the fitness function, the operating efficiency of the equipment can be evaluated, providing a basis for optimizing the equipment operation plan.

[0071] According to the difference between the actual running time and the planned running time, the equipment operation plan can be adjusted to improve the equipment utilization rate. The output part of the fitness function takes into account the difference between the theoretical output and the actual output, as well as the impact of energy efficiency. By analyzing this part of the data, the output bottleneck and energy waste problems can be identified, and corresponding measures can be taken to improve the output and energy efficiency. The quality coefficient part of the fitness function takes into account the impact of the number of defective products. By analyzing this part of the data, the source of quality problems can be identified and corresponding measures can be taken to improve product quality. The failure rate part of the fitness function takes into account the impact of the severity coefficient of the consequences of the failure. By analyzing this part of the data, the areas where failures occur frequently and the types of failures with serious consequences can be identified, and corresponding measures can be taken to reduce the failure rate and the consequences of failures.

[0072] In a preferred embodiment of the present invention, according to the actual operation of the liquid hydrogen refueling station and external environmental changes, including temperature, humidity and equipment aging, the automatic adjustment control scheme may include: Define fuzzy sets for air temperature, humidity, equipment status, and control parameter adjustments; Determine the membership function for each fuzzy set and formulate fuzzy rules; Infer the fuzzy values ​​of output variables based on fuzzy sets, membership functions and fuzzy rules; The real-time monitored temperature, humidity and equipment status data are converted into fuzzy values ​​through membership functions, and fuzzy rules are used for reasoning to obtain the fuzzy values ​​of the control parameter adjustment amounts; The fuzzy value of the control parameter adjustment amount is converted into a specific numerical value through the defuzzification method. When changes in temperature, humidity or equipment status are detected, the control plan is automatically adjusted.

[0073] In the embodiment of the present invention, fuzzy sets such as low temperature, medium temperature, and high temperature are defined to represent different ranges of temperature. For example, low temperature means that the temperature is below 0°C, medium temperature means between 0°C and 30°C, and high temperature means above 30°C. Fuzzy sets such as low humidity, medium humidity, and high humidity are defined to represent different levels of humidity. For example, low humidity may mean that the humidity is below 30%, medium humidity means between 30% and 70%, and high humidity means above 70%. Fuzzy sets such as good, general, and poor are defined to represent the operating status of the equipment. Good means that the equipment has no faults and excellent performance, general means that the equipment has slight wear or slightly reduced performance, and poor means that the equipment has obvious faults or serious performance reduction. Fuzzy sets such as small adjustment, medium adjustment, and large adjustment are defined to represent the adjustment range of the control parameters. Small adjustment means that the adjustment amount is within 5%, medium adjustment means that the adjustment amount is between 5% and 20%, and large adjustment means that the adjustment amount is above 20%. Select a suitable membership function for each fuzzy set, such as a triangular, trapezoidal, or Gaussian function. For example, for the low temperature set of air temperature, a triangular membership function with a left endpoint of 0°C and a right endpoint of 10°C (or lower) can be selected, indicating that the lower the temperature, the higher the membership of the low temperature set. Fuzzy rules are formulated based on the actual operating experience and expert knowledge of liquid hydrogen refueling stations. For example, if the temperature is high and the equipment status is poor, the control parameters need to be adjusted significantly; if the temperature is medium and the equipment status is good, the control parameters only need to be adjusted slightly.

[0074] Input the real-time monitored temperature, humidity, and equipment status data into the fuzzy system. Through the membership function, these data are converted into fuzzy values. According to the fuzzy rules, fuzzy reasoning is performed to obtain the fuzzy value of the control parameter adjustment amount. Real-time monitoring of temperature, humidity, and equipment status, such as temperature is 25°C, humidity is 60%, and equipment status is general. Through the membership function, these data are converted into fuzzy values, such as temperature belongs to the medium temperature set, humidity belongs to the medium humidity set, and equipment status belongs to the general set. Use fuzzy rules for reasoning to obtain the fuzzy value of the control parameter adjustment amount, such as medium adjustment.

[0075] Select an appropriate defuzzification method, such as the centroid method. Convert the fuzzy value of the control parameter adjustment amount into a specific value, such as a medium adjustment may correspond to a 10% adjustment amount. When changes in temperature, humidity or equipment status are detected, the control scheme is automatically adjusted according to the converted specific values.

[0076] Assume that the current temperature of the liquid hydrogen refueling station is 28°C, the humidity is 55%, and the equipment status is general. The temperature of 28°C belongs to the medium temperature set, and the membership is 0.8 (assuming that the membership function of the medium temperature set changes linearly between 25°C and 30°C, and the membership is 0.8 at 28°C). The humidity of 55% belongs to the medium humidity set, and the membership is 0.6 (assuming that the membership function of the medium humidity set changes linearly between 40% and 70%, and the membership is 0.6 at 55%). The equipment status generally belongs to the general set, and the membership is 0.9 (assuming that the membership function of the general set changes linearly between 0.7 and 1.0, and the membership is 0.9 in the general state).

[0077] If the air temperature is medium and the equipment status is normal, the control parameters need to be adjusted. Since humidity has little effect on the adjustment (or is not explicitly mentioned in the rules), the air temperature and equipment status are mainly considered.

[0078] The fuzzy value of the control parameter adjustment is inferred as the middle adjustment. The weighted average method is used for defuzzification, and the specific value corresponding to the middle adjustment is 12% (assuming that the range of the middle adjustment is 5% to 20%, and the membership changes linearly within this range, the center point of the middle adjustment is 12.5%, but considering the influence of the membership, the final value is 12%). According to the specific value of 12% corresponding to the middle adjustment, the control parameters of the liquid hydrogen refueling station are automatically adjusted, such as adjusting the operating frequency of the compressor, the flow rate of the cooling system, etc.

[0079] Through fuzzy control, control parameters can be adjusted more accurately according to changes in temperature, humidity and equipment status, improving the operating efficiency and stability of liquid hydrogen refueling stations. Fuzzy control can handle uncertainty and ambiguity, and adapt to factors such as changes in the external environment and equipment aging. Fuzzy control has low dependence on models and does not require precise mathematical models, so it can enhance the robustness of the system and resist external interference and internal changes.

[0080] Through fuzzy rules and membership functions, complex control logic can be simplified, making the control process more intuitive and easy to understand. Fuzzy control can automatically adjust control parameters according to real-time monitoring data, reduce manual intervention, and improve the automation level of liquid hydrogen refueling stations. Through precise control of parameters, the utilization of energy and raw materials can be optimized, operating costs can be reduced, and economic benefits can be improved.

[0081] In a preferred embodiment of the present invention, the calculation formula of the membership function is: ; in, Representation variables Belongs to fuzzy sets the extent of; Represents a variable; Indicates the base value of the left endpoint; Indicates the offset of the left endpoint; represents the index of the left half; represents a vertex; Indicates the base value of the right endpoint; Indicates the offset of the right endpoint; Indicates the scaling factor of the left half; Indicates the scaling factor of the right half; Indicates the exponent of the right half.

[0082] In the embodiment of the present invention, various parameters are determined: is the base value of the left endpoint, indicating the point where the fuzzy set begins to work. It is the offset of the left endpoint, which is used to adjust the position of the left endpoint to make the membership function more flexible. It is the exponent of the left half, which affects the shape of the curve in the left half and determines the speed at which the membership increases or decreases. is a vertex, indicating the point where the degree of membership reaches its maximum value. is the base value of the right endpoint, indicating the point where the fuzzy set stops working. It is the offset of the right endpoint, used to adjust the position of the right endpoint. It is the scaling factor of the left part, which is used to adjust the size of the membership of the left part. is the scaling factor of the right half, which is used to adjust the size of the membership of the right half. These parameters need to be determined according to the specific fuzzy set and actual application scenario.

[0083] For a given variable , according to the membership function formula, it belongs to the fuzzy set The extent .when hour, = 0, indicating Not a fuzzy set at all .when When , the membership degree is calculated using the formula in the left half, that is, = This formula means that as from Increase to , the membership degree gradually increases, and the speed of increase is exponential Control, the final membership is Point reached (Assumption It reaches the maximum value when it is 1, otherwise it is scaled proportionally). When , the right half of the formula is used to calculate the membership degree, that is, This formula means that as from Increase to , the membership degree gradually decreases, and the speed of decrease is exponential Control, the final membership is point becomes 0 (or close to 0, depending on ). hour, = 0, indicating Not a fuzzy set at all After the membership is calculated, it can be used in the fuzzy reasoning process. For example, in the control system of a liquid hydrogen refueling station, the real-time monitored temperature, humidity or equipment status data can be converted into fuzzy values ​​through the membership function, and then these fuzzy values ​​can be used for fuzzy reasoning to obtain the fuzzy values ​​of the control parameter adjustment amount.

[0084] By using a detailed membership function formula, the degree to which a variable belongs to a fuzzy set can be described more accurately. This helps to improve the accuracy of fuzzy control and enables the control system to respond more accurately to changes in the external environment. , , , , 、m、 , , ) provides great flexibility and can be adjusted according to specific application scenarios and needs. This allows the membership function to adapt to different control requirements and system characteristics. The membership function can handle uncertainty and fuzziness. Even if the system parameters or environmental conditions change, the membership function can still provide reasonable control output. The membership function is an important part of fuzzy control, and its application has promoted the development of intelligent control.

[0085] An embodiment of the present invention further provides a distributed control method for a liquid hydrogen refueling station, comprising: After preprocessing and feature extraction of control instructions, they are classified through the trained classification model to obtain classification results; the execution plan is determined and instructions are issued based on the classification results, and the operation data of the liquid hydrogen refueling station is collected in real time through control nodes and sensors; Real-time monitoring of the operating status and process parameters of each equipment in the liquid hydrogen refueling station. When abnormal conditions or potential risks are detected, including equipment failure and process parameter exceeding the limit, early warning signals are issued and corresponding treatment measures are recommended; Control specific equipment or areas within a liquid hydrogen refueling station, including liquid hydrogen storage equipment, hydrogen compression equipment, hydrogen refueling machines, and safety monitoring equipment; Analyze the real-time sensor data, equipment operation status data, process parameter data, historical fault record data and environmental monitoring data collected during the operation of the liquid hydrogen refueling station, and generate operation efficiency reports, fault predictions and optimization suggestions based on the data analysis results; The control scheme is automatically adjusted according to the actual operation of the liquid hydrogen refueling station and changes in the external environment, including temperature, humidity and equipment aging.

[0086] It should be noted that this method is a method corresponding to the above-mentioned system, and all implementation methods in the above-mentioned method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0087] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A distributed control system for a liquid hydrogen refueling station, characterized in that: include: The central control unit module is used to pre-process and extract features of the control instructions, and then classify them through the trained classification model to obtain classification results; Determine the execution plan and issue instructions based on the classification results, and collect the operating data of the liquid hydrogen refueling station in real time through control nodes and sensors; Fault diagnosis and early warning module, used to monitor the operating status and process parameters of each equipment in the liquid hydrogen refueling station in real time. When abnormal conditions or potential risks are detected, including equipment failure and process parameter exceeding the limit, early warning signals are issued and corresponding treatment measures are recommended; Distributed control node modules are used to control specific equipment or areas within a liquid hydrogen refueling station, including liquid hydrogen storage equipment, hydrogen compression equipment, hydrogen refueling machines, and safety monitoring equipment; The analysis module is used to analyze the real-time sensor data, equipment operation status data, process parameter data, historical fault record data and environmental monitoring data collected during the operation of the liquid hydrogen refueling station, and generate operation efficiency reports, fault predictions and optimization suggestions based on the data analysis results; The adaptive control function module is used to automatically adjust the control scheme according to the actual operation of the liquid hydrogen refueling station and changes in the external environment, including temperature, humidity and equipment aging.

2. The distributed control system of the liquid hydrogen refueling station according to claim 1, characterized in that: After preprocessing and feature extraction of the control instructions, they are classified by the trained classification model to obtain classification results; Determine the execution plan and issue instructions based on the classification results, and collect the operating data of the liquid hydrogen refueling station in real time through control nodes and sensors, including: Preprocess the control instructions and extract instruction features, including instruction length, keyword frequency and instruction structure; Using the historical control instruction data set to train the preset classification model to obtain a trained classification model; The extracted instruction features are input into the trained classification model, and the types of instructions are classified according to the input feature vector, including equipment control instructions, process control instructions or safety monitoring instructions, to obtain a classified instruction set; Formulate instruction execution plans based on the priority, equipment load, process progress and safety status of the instructions in the classified instruction set; According to the instruction execution plan, the control instructions are sent to the corresponding distributed control nodes, and the operating status data of the liquid hydrogen refueling station is collected in real time through the distributed control nodes and sensors, including the current operating status of the equipment, real-time parameters of the process flow and relevant data of environmental monitoring.

3. The distributed control system of the liquid hydrogen refueling station according to claim 2 is characterized in that: The preset classification model is trained using the historical control instruction data set to obtain a trained classification model, including: Acquire a historical control instruction data set, wherein the instruction data set includes equipment control instructions, process flow control instructions, and safety monitoring instructions; Use the neural network as the preset classification model and initialize the parameters of the classification model, including setting the initial learning rate and number of iterations; During the classification model training process, the scope of parameter updates is limited by the trust region method; Determine the initial size of the trust region, and calculate the direction and size of the parameter update based on the parameters of the current classification model and the size of the trust region; Use the historical control instruction dataset to train the classification model and calculate the value of the objective function; Adjust and update the parameters of the classification model according to the value of the objective function and the limits of the trust region; After a preset number of iterative training, a trained classification model is obtained.

4. The distributed control system of the liquid hydrogen refueling station according to claim 3 is characterized in that: The objective function value is calculated as: ； in, represents the loss function; represents the total number of samples; Indicates the sample index; Indicates the total number of categories; , Represents the category index; Indicates category frequency; Representation sample For categories The weight coefficient of Representation sample Belongs to category The true label of Represents the classification model for samples Belongs to category The original output of Representation sample For categories Bias adjustment term; Represents the classification model for samples Belongs to category The original output of Representation sample For categories Bias adjustment term; represents the regularization coefficient; represents the square of the classification model parameter; Represents the base of natural logarithms.

5. The distributed control system of the liquid hydrogen refueling station according to claim 4, characterized in that: Real-time monitoring of the operating status and process parameters of each device in the liquid hydrogen refueling station. When abnormal conditions or potential risks are detected, including equipment failure and process parameter exceeding the limit, an early warning signal is issued and corresponding treatment measures are generated, including: Continuously analyze real-time monitoring equipment and process parameters to detect the real-time status of equipment and process parameters by comparing current data with the preset normal operating range or mode; Set a threshold range for each process parameter. When a process parameter exceeds the threshold range, it is considered abnormal and triggers the early warning mechanism to generate an early warning signal. The early warning signal includes the abnormal type, occurrence time, and related equipment or parameter information. According to the abnormal type in the early warning signal, the corresponding treatment measures are determined from the emergency treatment plan library, and treatment measure suggestions are generated, including operation steps, a list of required tools or equipment, and safety precautions information.

6. The distributed control system of the liquid hydrogen refueling station according to claim 5, characterized in that: Analyze the real-time sensor data, equipment operation status data, process parameter data, historical fault record data and environmental monitoring data collected during the operation of the liquid hydrogen refueling station, and generate operation efficiency reports, fault predictions and optimization suggestions based on the data analysis results, including: Continuously collect real-time sensor data during the operation of the liquid hydrogen refueling station, including key parameters such as temperature, pressure, flow, and liquid level, and record the operating status of the equipment, including startup, shutdown, fault status changes, operating hours, and maintenance records; Extract features that affect operating efficiency, fault prediction, and optimization suggestion generation from real-time sensor data and equipment operating status data, including average equipment operating time, fault frequency, and energy consumption level; Based on the extracted features, the operating efficiency indicators of the liquid hydrogen refueling station are calculated, including equipment utilization, energy efficiency and process stability, and an operating efficiency report is generated, including the calculation results of efficiency indicators, trend analysis, and problem point identification content; Build a fault prediction model based on operating efficiency indicators, historical fault record data, and real-time monitoring data to predict the type and probability of future faults; Improving the operating efficiency of liquid hydrogen refueling stations and reducing the failure rate are taken as optimization goals, and the optimization problem is defined. The solution space of the optimization problem is mapped to the search space of the whale group, and each individual whale represents a solution. By simulating the foraging behavior of whales, including surrounding prey, bubbling net attack and searching for prey, the position of individual whales is continuously updated, and the quality of individual whales is evaluated through fitness functions. Repeat the process of simulating the whale's foraging behavior and updating the individual whale's position until the preset number of iterations is reached and the final solution is determined; Based on the final solution, optimization suggestions are generated, including suggestions on equipment adjustment, process improvement and maintenance plan optimization.

7. The distributed control system of the liquid hydrogen refueling station according to claim 6, characterized in that: The calculation formula of the fitness function is: ； in, Indicates that the device is in period Comprehensive performance; , , , represents the weight coefficient; Indicates that during the period The actual operating time of the equipment within; Indicates that during the period The planned operating time of the equipment within; Indicates unplanned downtime; Indicates the planned running time; Indicates the period Theoretical output of internal equipment; represents the theoretical output; Indicates the actual output; Indicates that during the period Theoretical energy consumption of internal equipment; represents the input energy; Indicates output energy; Indicates that during the period Quality factor of internal equipment; Indicates the number of defective products; Indicates the total product quantity; Indicates the period Failure rate of internal equipment; A coefficient indicating the severity of the consequences of a failure.

8. The distributed control system of liquid hydrogen refueling station according to claim 7, characterized in that: According to the actual operation of the liquid hydrogen refueling station and changes in the external environment, including temperature, humidity and equipment aging, the control scheme is automatically adjusted, including: Define fuzzy sets for air temperature, humidity, equipment status, and control parameter adjustments; Determine the membership function for each fuzzy set and formulate fuzzy rules; Infer the fuzzy values ​​of output variables based on fuzzy sets, membership functions and fuzzy rules; The real-time monitored temperature, humidity and equipment status data are converted into fuzzy values ​​through membership functions, and fuzzy rules are used for reasoning to obtain the fuzzy values ​​of the control parameter adjustment quantities; The fuzzy value of the control parameter adjustment amount is converted into a specific numerical value through the defuzzification method. When changes in temperature, humidity or equipment status are detected, the control plan is automatically adjusted.

9. The distributed control system of liquid hydrogen refueling station according to claim 8, characterized in that: The calculation formula of membership function is: ； in, Representation variables Belongs to fuzzy sets the extent of; Represents a variable; Indicates the base value of the left endpoint; Indicates the offset of the left endpoint; represents the index of the left half; represents a vertex; Indicates the base value of the right endpoint; Indicates the offset of the right endpoint; Indicates the scaling factor of the left half; Indicates the scaling factor of the right half; Indicates the exponent of the right half.

10. A distributed control method for a liquid hydrogen refueling station, the method realizing the system as claimed in any one of claims 1 to 9, characterized in that: include: After preprocessing and feature extraction of the control instructions, they are classified by the trained classification model to obtain classification results; Determine the execution plan and issue instructions based on the classification results, and collect the operating data of the liquid hydrogen refueling station in real time through control nodes and sensors; Real-time monitoring of the operating status and process parameters of each equipment in the liquid hydrogen refueling station. When abnormal conditions or potential risks are detected, including equipment failure and process parameter exceeding the limit, early warning signals are issued and corresponding treatment measures are recommended; Control specific equipment or areas within a liquid hydrogen refueling station, including liquid hydrogen storage equipment, hydrogen compression equipment, hydrogen refueling machines, and safety monitoring equipment; Analyze the real-time sensor data, equipment operation status data, process parameter data, historical fault record data and environmental monitoring data collected during the operation of the liquid hydrogen refueling station, and generate operation efficiency reports, fault predictions and optimization suggestions based on the data analysis results; The control scheme is automatically adjusted according to the actual operation of the liquid hydrogen refueling station and changes in the external environment, including temperature, humidity and equipment aging.

Images