Methods, devices, and media for safe operation control of fuel cell systems considering concurrent failures

Abstract

This application discloses a method, apparatus, and medium for safe operation control of a fuel cell system considering concurrent faults, relating to the field of battery safety technology. The method includes: obtaining the probability of each accessory failing based on an accessory fault probability model, thereby determining the concurrent probability of different types of battery faults; determining the occasional probability of different types of battery faults and battery-free faults based on fuel cell fault information and a fuel cell occasional fault diagnosis model; determining the combined probability of different types of battery faults and battery-free faults based on the concurrent and occasional probabilities of different types of battery faults and the occasional probability of battery-free faults; determining the safety dispersion of the fuel cell system based on the combined probability of different types of battery faults and battery-free faults; and controlling the operation of the fuel cell system using the safety dispersion of the fuel cell system. This ensures the safe operation of the fuel cell system.

Description

Technical Field

[0001] This application relates to the field of battery safety technology, and in particular to a method, apparatus and medium for safe operation control of a fuel cell system considering concurrent faults. Background Technology

[0002] A fuel cell system comprises an air supply subsystem, a hydrogen supply subsystem, and a cooling subsystem, among others, and its operation requires the coordinated operation of multiple accessories. A failure in any accessory directly impacts the fuel cell's operating conditions, easily leading to concurrent failures. Currently, modeling concurrent failures in fuel cells typically utilizes methods such as fault trees and Petri nets, which can only achieve qualitative analysis of concurrent failures.

[0003] In a fuel cell system safety domain modeling method, multiple types of fault constraints of the fuel cell system are comprehensively considered to construct its safe operation boundary, and then a three-dimensional safety domain model of the fuel cell system is established, realizing a quantitative assessment of the safety of the fuel cell operating state. However, it is difficult to analyze the correlation characteristics between accessory faults and fuel cell body faults.

[0004] The fault tree theory was used to qualitatively analyze the faults of each subsystem of the fuel cell, and the correlation between subsystem faults and stack faults was analyzed. A neural network was used to realize the fault diagnosis of the fuel cell. However, it only considered concurrent faults. Even when the accessories are normal, the fuel cell may still fail.

[0005] All of the above methods fail to guarantee the operational safety of the fuel cell system. Summary of the Invention

[0006] The purpose of this application is to provide a method, device, and medium for safe operation control of a fuel cell system that takes into account concurrent faults, so as to solve the problem of the one-sided fault analysis of fuel cell systems.

[0007] To achieve the above objectives, this application provides the following solution.

[0008] In a first aspect, this application provides a method for safe operation control of a fuel cell system considering concurrent faults, including:

[0009] Determine any point in the operation of the fuel cell system to be controlled as the current point in time;

[0010] The current time is input into the accessory failure probability model of each accessory in the fuel cell system to be controlled, so as to obtain the probability of each accessory failing at the current time; the accessory failure probability model is a bathtub curve, where the horizontal axis of the bathtub curve is the time and the vertical axis is the probability of accessory failure.

[0011] Based on the probability of each accessory failing at the current moment, determine the concurrent probability of different types of battery failures occurring in the fuel cell system under control at the current moment;

[0012] Obtain the current fuel cell fault information of the fuel cell system to be controlled; the fuel cell fault information includes: stack current, voltage, temperature, cathode inlet pressure, anode inlet pressure, cathode exhaust pressure, anode exhaust pressure, coolant inlet temperature and coolant outlet temperature;

[0013] Based on the fuel cell fault information of the fuel cell system under control at the current moment and the fuel cell sporadic fault diagnosis model, the sporadic probability of different types of battery faults and the sporadic probability of no battery faults occurring in the fuel cell system under control at the current moment are determined; the fuel cell sporadic fault diagnosis model is obtained by training a backpropagation neural network.

[0014] Based on the concurrent and occasional probabilities of different types of battery failures occurring in the fuel cell system under control at the current moment, as well as the occasional probability of no battery failure, the combined probability of different types of battery failures occurring in the fuel cell system under control at the current moment and the combined probability of no battery failure are determined.

[0015] Based on the combined probability of different types of battery failures and the combined probability of no battery failure in the fuel cell system under control at the current moment, the safety dispersion of the fuel cell system under control at the current moment is determined.

[0016] The operation of the fuel cell system under control is controlled by utilizing the safety dispersion of the fuel cell system under control at the current moment.

[0017] Optionally, the attachment failure probability model for any attachment includes:

[0018] ;

[0019] ;

[0020] ;

[0021] ;

[0022] in, Let be the probability that an attachment failure occurs at time t. Let be the early failure probability of the attachment at time t; Let be the probability of the attachment failing due to wear at time t; Let be the probability of accidental failure of the attachment at time t; For shape parameters; Dimensions of the accessories; It is a long short-term memory network; Let be the probability that an attachment failure occurs at time tn. Let be the probability that an attachment failure occurs at time tn-1; Let be the probability that an attachment failure occurs at time t-1.

[0023] Optionally, based on the fuel cell fault information of the fuel cell system under control at the current moment and the fuel cell sporadic fault diagnosis model, the sporadic probability of different types of battery faults and the sporadic probability of no battery fault occurring in the fuel cell system under control at the current moment are determined, including:

[0024] Gaussian filtering is applied to the current fuel cell fault information of the fuel cell system to be controlled to obtain the Gaussian-filtered fuel cell fault information of the current fuel cell system to be controlled.

[0025] The Gaussian-filtered fuel cell fault information of the fuel cell system to be controlled at the current moment is input into the fuel cell occasional fault diagnosis model to obtain the occasional probability of different types of battery faults and the occasional probability of no battery fault in the fuel cell system to be controlled at the current moment.

[0026] Optionally, the process of determining the intermittent fault diagnosis model for the fuel cell includes:

[0027] Obtain fuel cell fault information for multiple sample fuel cell systems at various times, as well as the probability of occurrence of different types of battery faults and the probability of no battery fault at the corresponding times.

[0028] Gaussian filtering is applied to the fuel cell fault information of each sample fuel cell system at each time step to obtain the Gaussian-filtered fuel cell fault information of each sample fuel cell system at each time step.

[0029] Initialize the backpropagation neural network;

[0030] Using the Gaussian-filtered fuel cell fault information of each sample fuel cell system at each time point as input, and the occasional probability of different types of battery faults and the occasional probability of no battery fault occurring at the corresponding time point of the sample fuel cell system as output, the backpropagation neural network is trained to obtain the fuel cell occasional fault diagnosis model.

[0031] Optionally, based on the concurrent and random probabilities of different types of battery failures occurring in the fuel cell system under control at the current moment, and the random probability of no battery failure, the comprehensive probability of different types of battery failures occurring in the fuel cell system under control at the current moment and the comprehensive probability of no battery failure are determined, including:

[0032] Using the first comprehensive fault calculation formula, the comprehensive probability of the fuel cell system under control experiencing different types of battery faults at the current moment is calculated based on the concurrent and occasional probabilities of different types of battery faults occurring in the current moment, as well as the occasional probability of no battery fault.

[0033] Using the second comprehensive fault calculation formula, the comprehensive probability of the fuel cell system under control having no battery fault at the current moment is calculated based on the concurrent and occasional probabilities of different types of battery faults occurring in the current moment, as well as the occasional probability of no battery fault.

[0034] Optionally, the first comprehensive fault calculation formula includes:

[0035] ;

[0036] in, Let be the combined probability of the j-th type of battery failure occurring in the fuel cell system at time t; The number of accessories in the fuel cell system; Let be the concurrent probability of the battery failure caused by the i-th accessory at time t; Let be the probability that a fault in the i-th accessory causes a fault in the j-th type of battery. Let be the random probability of a type j battery failure occurring in the fuel cell system at time t; Number of battery fault types; Let be the probability that the fuel cell system will not experience a battery failure at time t.

[0037] Optionally, the second comprehensive fault calculation formula includes:

[0038] ;

[0039] in, Let be the combined probability that the fuel cell system has no battery failure at time t.

[0040] Optionally, based on the combined probability of different types of battery failures and the combined probability of no battery failure occurring in the fuel cell system under control at the current moment, the safety dispersion of the fuel cell system under control at the current moment is determined, including:

[0041] Using the safety dispersion calculation formula, the safety dispersion of the fuel cell system under control at the current moment is calculated based on the combined probability of different types of battery failures and the combined probability of no battery failure at the current moment; the safety dispersion calculation formula includes:

[0042] ;

[0043] ;

[0044] ;

[0045] in, Let be the safety dispersion of the fuel cell system at time t; It is a natural constant; Let be the first-level safety evaluation value of the fuel cell system at time t; Let be the second-level safety evaluation value of the fuel cell system at time t.

[0046] In a second aspect, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the fuel cell system safe operation control method considering concurrent faults as described in any of the preceding claims.

[0047] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the fuel cell system safe operation control method considering concurrent faults as described in any of the above claims.

[0048] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0049] This application discloses a method, apparatus, and medium for safe operation control of a fuel cell system considering concurrent faults. First, any moment during the operation of the fuel cell system to be controlled is defined as the current moment. Second, the current moment is input into the accessory fault probability model of each accessory in the fuel cell system to be controlled, obtaining the probability of accessory faults occurring at the current moment. Based on the probability of accessory faults occurring at the current moment, the concurrent probability of different types of fuel cell faults occurring in the fuel cell system to be controlled at the current moment is determined. Then, fuel cell fault information of the fuel cell system to be controlled at the current moment is obtained. Based on the fuel cell fault information of the fuel cell system to be controlled at the current moment and the fuel cell intermittent fault diagnosis model, the concurrent probability of different types of fuel cell faults occurring in the fuel cell system to be controlled is determined. This paper proposes a safety dispersion assessment method for the fuel cell system. This method considers both concurrent and random failures caused by faults in the appendix and its own random failures, analyzes the correlation between fuel cell system faults, and proposes a safety dispersion assessment method that, compared to fault tree and safety domain models, considers the impact of fault uncertainty on safety, achieves real-time safety assessment of the fuel cell system, and ensures the safe operation of the fuel cell system. The method then calculates the combined probability of different types of battery failures and the combined probability of no battery failure based on these probabilities. Next, based on these probabilities, the combined probability of different types of battery failures and the combined probability of no battery failure are used to determine the safety dispersion of the fuel cell system at the current moment. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a schematic flowchart of a fuel cell system safe operation control method considering concurrent faults, provided as an embodiment of this application.

[0052] Figure 2 A schematic diagram of a control architecture for the safe operation of a fuel cell system considering concurrent failures.

[0053] Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0054] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0055] The purpose of this application is to provide a method, device, and medium for safe operation control of a fuel cell system that considers concurrent faults, aiming to comprehensively consider concurrent faults caused by accessory faults and occasional faults of the system itself, and to analyze the correlation between faults in the fuel cell system.

[0056] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0057] In one exemplary embodiment, such as Figure 1 and Figure 2 As shown, the fuel cell system safe operation control method considering concurrent faults in this embodiment includes steps 1-8.

[0058] Step 1: Determine any moment in the operation of the fuel cell system to be controlled as the current moment.

[0059] Step 2: Input the current time into the accessory failure probability model of each accessory in the fuel cell system to be controlled, and obtain the probability of each accessory failing at the current time.

[0060] Among them, the accessory failure probability model is a bathtub curve, where the horizontal axis of the bathtub curve represents time and the vertical axis represents the probability of accessory failure.

[0061] Specifically, the failure probability function of each battery accessory is a function of time, and the accessory failure probability model is a bathtub curve. Based on the characteristics of the bathtub curve, it can be divided into early failure period, random failure period, and wear-out failure period. Therefore, the accessory failure probability model can be decomposed into a superposition of models for these three periods. Early failure and wear-out failure follow a certain pattern, and their probabilities can be characterized using a two-parameter Weibull distribution. A particle swarm optimization algorithm is then used to fit the fuel cell accessory bathtub curve.

[0062] Random failures can be considered as random faults, and their distribution is the original data minus the probability of early failure and the probability of loss failure. The probability of random failures can be predicted using Long Short-Term Memory (LSTM) networks.

[0063] As an optional implementation, the accessory failure probability model of any accessory includes:

[0064] .

[0065] .

[0066] .

[0067] .

[0068] in, Let be the probability that an attachment failure occurs at time t. Let be the early failure probability of the attachment at time t; Let be the probability of the attachment failing due to wear at time t; Let be the probability of accidental failure of the attachment at time t; For shape parameters; Dimensions of the accessories; It is a long short-term memory network; Let be the probability that an attachment failure occurs at time tn. Let be the probability that an attachment failure occurs at time tn-1; Let be the probability that an attachment failure occurs at time t-1.

[0069] Step 3: Based on the probability of each accessory failing at the current moment, determine the concurrent probability of different types of battery failures occurring in the fuel cell system to be controlled at the current moment.

[0070] Specifically, if accessories malfunction, such as the hydrogen ejector, air compressor, or water pump, the cathode inlet pressure, anode inlet pressure, and coolant inlet temperature of the fuel cell system will inevitably become abnormal. Therefore, fuel cell malfunctions can be divided into two types: concurrent malfunctions caused by accessories in the fuel cell system and occasional malfunctions of the fuel cell itself.

[0071] Accessory failures have a significant impact on the operating conditions of fuel cells. It can be assumed that accessory failures will inevitably lead to battery failures. In this case, the probability of concurrent failures can be considered to be the same as the probability of accessory failures.

[0072] .

[0073] in, Let be the concurrent probability of the battery failure caused by the i-th accessory at time t; Let be the probability that the i-th attachment fails at time t.

[0074] The types of fuel cell faults caused by different accessory failures were statistically analyzed using Markov chains, resulting in Table 1.

[0075] .

[0076] in, Let be the probability that a battery of type j is caused by a fault in the i-th accessory. , , The number of accessories in a fuel cell system. This represents the number of types of battery malfunctions.

[0077] Step 4: Obtain the current fuel cell fault information of the fuel cell system to be controlled.

[0078] The fuel cell fault information includes: stack current. ,Voltage ,temperature Cathode inlet pressure Anode inlet pressure Cathode exhaust pressure Anode exhaust pressure Coolant inlet temperature and coolant outlet temperature .

[0079] Step 5: Based on the fuel cell fault information of the fuel cell system under control at the current moment and the fuel cell intermittent fault diagnosis model, determine the intermittent probability of different types of battery faults and the intermittent probability of no battery fault occurring in the fuel cell system under control at the current moment.

[0080] Among them, the fuel cell intermittent fault diagnosis model is obtained by training a backpropagation neural network.

[0081] As an optional implementation, step 5 includes steps 501-502.

[0082] Step 501: Perform Gaussian filtering on the current fuel cell fault information of the fuel cell system to be controlled to obtain the Gaussian-filtered fuel cell fault information of the current fuel cell system to be controlled.

[0083] Specifically, the expression for Gaussian filtering is:

[0084] .

[0085] in, The Gaussian kernel function; For data location, if the data window is 3, Possible values ​​are (-1, 0, 1); These are adjustable parameters.

[0086] Step 502: Input the Gaussian-filtered fuel cell fault information of the fuel cell system to be controlled at the current moment into the fuel cell random fault diagnosis model to obtain the random probability of different types of battery faults and the random probability of no battery fault in the fuel cell system to be controlled at the current moment.

[0087] Specifically, the expression for the fuel cell intermittent fault diagnosis model is as follows:

[0088] .

[0089] in, Let be the probability that the fuel cell system will not experience a battery failure at time t. Let be the random probability of a Type 1 battery failure occurring in the fuel cell system at time t; Let be the random probability of a type 2 battery failure occurring in the fuel cell system at time t; Let be the random probability of the Nth type of battery failure occurring in the fuel cell system at time t; This is a backpropagation (BP) neural network.

[0090] As an optional implementation, the process of determining the intermittent fault diagnosis model for fuel cells includes steps 511-514.

[0091] Step 511: Obtain fuel cell fault information for multiple sample fuel cell systems at each time point, as well as the probability of occurrence of different types of battery faults and the probability of no battery fault at the corresponding time point.

[0092] Step 512: Perform Gaussian filtering on the fuel cell fault information of each sample fuel cell system at each time step to obtain the Gaussian-filtered fuel cell fault information of each sample fuel cell system at each time step.

[0093] Step 513: Initialize the backpropagation neural network.

[0094] Step 514: Using the Gaussian-filtered fuel cell fault information of each sample fuel cell system at each time as input, and the occasional probability of different types of battery faults and the occasional probability of no battery fault occurring at the corresponding time of the sample fuel cell system as output, train the backpropagation neural network to obtain the fuel cell occasional fault diagnosis model.

[0095] Step 6: Based on the concurrent and occasional probabilities of different types of battery failures occurring in the fuel cell system to be controlled at the current moment, as well as the occasional probability of no battery failure, determine the comprehensive probability of different types of battery failures occurring in the fuel cell system to be controlled at the current moment and the comprehensive probability of no battery failure.

[0096] As an optional implementation, step 6 includes steps 61-62.

[0097] Step 61: Using the first comprehensive fault calculation formula, calculate the comprehensive probability of different types of battery faults occurring in the fuel cell system under control at the current moment, based on the concurrent and occasional probabilities of different types of battery faults occurring in the current moment, as well as the occasional probability of no battery fault.

[0098] As an optional implementation method, the first comprehensive fault calculation formula includes:

[0099] .

[0100] in, Let be the combined probability of the j-th type of battery failure occurring in the fuel cell system at time t; The number of accessories in the fuel cell system; Let be the concurrent probability of the battery failure caused by the i-th accessory at time t; Let be the probability that a fault in the i-th accessory causes a fault in the j-th type of battery. Let be the random probability of a type j battery failure occurring in the fuel cell system at time t; Number of battery fault types; Let be the probability that the fuel cell system will not experience a battery failure at time t.

[0101] Step 62: Using the second comprehensive fault calculation formula, calculate the comprehensive probability of the fuel cell system under control having no battery fault at the current moment, based on the concurrent and occasional probabilities of different types of battery faults occurring in the current moment, as well as the occasional probability of no battery fault.

[0102] As an optional implementation, the second comprehensive fault calculation formula includes:

[0103] .

[0104] in, Let be the combined probability that the fuel cell system has no battery failure at time t.

[0105] Step 7: Based on the combined probability of different types of battery failures and the combined probability of no battery failure occurring in the fuel cell system to be controlled at the current moment, determine the safety dispersion of the fuel cell system to be controlled at the current moment.

[0106] As an optional implementation, step 7 includes:

[0107] Using the safety dispersion calculation formula, the safety dispersion of the fuel cell system under control at the current moment is calculated based on the combined probability of different types of battery failures and the combined probability of no battery failure. The safety dispersion calculation formula includes:

[0108] .

[0109] .

[0110] .

[0111] in, Let be the safety dispersion of the fuel cell system at time t; It is a natural constant; Let be the first-level safety evaluation value of the fuel cell system at time t; Let be the second-level safety evaluation value of the fuel cell system at time t.

[0112] Specifically, the safety evaluation is divided into two levels: the first level safety evaluation value is used to evaluate the safety and probability of failure of fuel cells, and the comprehensive probability of no battery failure can be directly used as the evaluation index; the second level safety evaluation value depends on the comprehensive probability of various types of battery failures. If the comprehensive probability of multiple battery failures is more average, it means that each type of battery failure needs to be prevented and controlled. If the comprehensive probability of battery failure is concentrated on a certain type of battery failure, it means that only the prevention and control of this type of battery failure needs to be done.

[0113] Step 8: Use the safety dispersion of the fuel cell system to be controlled at the current moment to control the operation of the fuel cell system to be controlled.

[0114] Specifically, if the safety dispersion of the fuel cell system to be controlled at the current moment exceeds the preset safety entropy range, the operation of the fuel cell system to be controlled will be stopped; if the safety dispersion of the fuel cell system to be controlled at the current moment is within the preset safety entropy range, the safety dispersion of the next moment will be calculated, and control will be achieved at the next moment.

[0115] In one exemplary embodiment, a computer device is provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a fuel cell system safe operation control method that takes into account concurrent faults.

[0116] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements a method for safe operation control of a fuel cell system taking into account concurrent faults.

[0117] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements a method for safe operation control of a fuel cell system taking into account concurrent faults.

[0118] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 3 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a safe operation control method for a fuel cell system considering concurrent faults.

[0119] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0120] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0121] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0122] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0123] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0124] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for safe operation control of a fuel cell system considering concurrent faults, characterized in that, The method for safe operation control of fuel cell systems that considers concurrent faults includes: Determine any point in the operation of the fuel cell system to be controlled as the current point in time; The current time is input into the accessory failure probability model of each accessory in the fuel cell system to be controlled, so as to obtain the probability of each accessory failing at the current time; the accessory failure probability model is a bathtub curve, where the horizontal axis of the bathtub curve is the time and the vertical axis is the probability of accessory failure. Based on the probability of each accessory failing at the current moment, determine the concurrent probability of different types of battery failures occurring in the fuel cell system under control at the current moment; Obtain the current fuel cell fault information of the fuel cell system to be controlled; the fuel cell fault information includes: stack current, voltage, temperature, cathode inlet pressure, anode inlet pressure, cathode exhaust pressure, anode exhaust pressure, coolant inlet temperature and coolant outlet temperature; Based on the fuel cell fault information of the fuel cell system under control at the current moment and the fuel cell sporadic fault diagnosis model, the sporadic probability of different types of battery faults and the sporadic probability of no battery faults occurring in the fuel cell system under control at the current moment are determined; the fuel cell sporadic fault diagnosis model is obtained by training a backpropagation neural network. Based on the concurrent and occasional probabilities of different types of battery failures occurring in the fuel cell system under control at the current moment, as well as the occasional probability of no battery failure, the combined probability of different types of battery failures occurring in the fuel cell system under control at the current moment and the combined probability of no battery failure are determined. Based on the combined probability of different types of battery failures and the combined probability of no battery failure in the fuel cell system under control at the current moment, the safety dispersion of the fuel cell system under control at the current moment is determined. The operation of the fuel cell system to be controlled is controlled by utilizing the safety dispersion of the fuel cell system at the current moment. The attachment failure probability model for any attachment includes: ； ； ； ； in, Let be the probability that an attachment failure occurs at time t. Let be the early failure probability of the attachment at time t; Let be the probability of the attachment failing due to wear at time t; Let be the probability of accidental failure of the attachment at time t; and All are shape parameters; For the dimensions of the accessories; It is a long short-term memory network; Let be the probability that an attachment failure occurs at time tn. Let be the probability that an attachment failure occurs at time tn-1; Let be the probability that an attachment failure occurs at time t-1. Based on the combined probability of different types of battery failures and the combined probability of no battery failure in the fuel cell system under control at the current moment, the safety dispersion of the fuel cell system under control at the current moment is determined, including: Using the safety dispersion calculation formula, the safety dispersion of the fuel cell system under control at the current moment is calculated based on the combined probability of different types of battery failures and the combined probability of no battery failure. The safety dispersion calculation formula includes: ； ； ； in, Let be the safety dispersion of the fuel cell system at time t; It is a natural constant; Let be the first-level safety evaluation value of the fuel cell system at time t; Let be the second-level safety evaluation value of the fuel cell system at time t.

2. The fuel cell system safe operation control method considering concurrent faults according to claim 1, characterized in that, Based on the current-moment fuel cell fault information and the fuel cell sporadic fault diagnosis model of the fuel cell system under control, the sporadic probability of different types of battery faults and the sporadic probability of no battery fault occurring in the fuel cell system under control at the current moment are determined, including: Gaussian filtering is applied to the current fuel cell fault information of the fuel cell system to be controlled to obtain the Gaussian-filtered fuel cell fault information of the current fuel cell system to be controlled. The Gaussian-filtered fuel cell fault information of the fuel cell system to be controlled at the current moment is input into the fuel cell occasional fault diagnosis model to obtain the occasional probability of different types of battery faults and the occasional probability of no battery fault in the fuel cell system to be controlled at the current moment.

3. The fuel cell system safe operation control method considering concurrent faults according to claim 2, characterized in that, The process of determining the intermittent fault diagnosis model for the fuel cell includes: Obtain fuel cell fault information for multiple sample fuel cell systems at various times, as well as the probability of occurrence of different types of battery faults and the probability of no battery fault at the corresponding times. Gaussian filtering is applied to the fuel cell fault information of each sample fuel cell system at each time step to obtain the Gaussian-filtered fuel cell fault information of each sample fuel cell system at each time step. Initialize the backpropagation neural network; Using the Gaussian-filtered fuel cell fault information of each sample fuel cell system at each time point as input, and the occasional probability of different types of battery faults and the occasional probability of no battery fault occurring at the corresponding time point of the sample fuel cell system as output, the backpropagation neural network is trained to obtain the fuel cell occasional fault diagnosis model.

4. The fuel cell system safe operation control method considering concurrent faults according to claim 1, characterized in that, Based on the concurrent and random probabilities of different types of battery failures occurring in the fuel cell system under control at the current moment, as well as the random probability of no battery failure, the comprehensive probability of different types of battery failures occurring in the fuel cell system under control at the current moment and the comprehensive probability of no battery failure are determined, including: Using the first comprehensive fault calculation formula, the comprehensive probability of the fuel cell system under control experiencing different types of battery faults at the current moment is calculated based on the concurrent and occasional probabilities of different types of battery faults occurring in the current moment, as well as the occasional probability of no battery fault. Using the second comprehensive fault calculation formula, the comprehensive probability of the fuel cell system under control having no battery fault at the current moment is calculated based on the concurrent and occasional probabilities of different types of battery faults occurring in the current moment, as well as the occasional probability of no battery fault.

5. The fuel cell system safe operation control method considering concurrent faults according to claim 4, characterized in that, The first comprehensive fault calculation formula includes: ； in, Let be the combined probability of the j-th type of battery failure occurring in the fuel cell system at time t; The number of accessories in the fuel cell system; Let be the concurrent probability of the battery failure caused by the i-th accessory at time t; Let be the probability that a fault in the i-th accessory causes a fault in the j-th type of battery. Let be the random probability of a type j battery failure occurring in the fuel cell system at time t; Number of battery fault types; Let be the probability that the fuel cell system will not experience a battery failure at time t.

6. The fuel cell system safe operation control method considering concurrent faults according to claim 5, characterized in that, The second comprehensive fault calculation formula includes: ； in, Let be the combined probability that the fuel cell system has no battery failure at time t.

7. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the fuel cell system safe operation control method considering concurrent faults as described in any one of claims 1-6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the safe operation control method for a fuel cell system considering concurrent faults as described in any one of claims 1-6.

Images