Method and device for monitoring and detecting voltage faults of fuel cell

By designing a monitoring and detection device for acquisition modules, sensor components and controller components in the fuel cell system, and using a collaborative diagnosis model to perform voltage health analysis, the dependence and speed problems of voltage fault diagnosis in the prior art are solved, and the System security and reliability.

CN118983473APending Publication Date: 2024-11-19SHUNDE INNOVATION SCHOOL UNIVERSITY OF SCIENCE & TECHNOLOGY BEIJING
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411071622.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-06
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

The prior art is difficult to quickly and independently diagnose voltage-type faults in fuel cell systems, resulting in insufficient system safety and reliability. Relying on cloud technology, it is difficult to achieve effective fault detection for voltage-type faults.

Method used

A monitoring and detection device including acquisition module, sensor component, generation module and controller component is designed. By acquiring multiple fault types, analyzing fault databases, real-time detection of battery status, using a collaborative diagnostic model to diagnose voltage health, and generating Safety control strategy to achieve rapid detection and repair of voltage-type faults.

Benefits of technology

It realizes independent fault diagnosis of fuel cell systems, improves the safety and reliability of the system, can quickly detect faulty batteries, and reduces dependence on cloud technology.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118983473A_ABST
    Figure CN118983473A_ABST
Patent Text Reader

Abstract

The invention discloses a monitoring and detecting method and device for voltage faults of a fuel cell, and the method comprises a first obtaining module which is used for obtaining a plurality of voltage fault types of the fuel cell, and building a fault feature library; the second acquisition module is used for analyzing multiple faults to obtain multiple fault diagnosis strategies and providing the multiple fault diagnosis strategies to the generation module; the sensor assembly is used for detecting the state of the fuel cell in real time and providing state data to the generation module; the generation module is used for diagnosing the voltage health degree of the fuel cell by using a multi-fault collaborative diagnosis model and generating a safety control strategy of the fuel cell system according to a diagnosis result; the controller assembly controls operation of the fuel cell system according to the safety control strategy. According to the method and the device for monitoring and detecting the voltage type faults of the fuel cell, the fault diagnosis of the voltage type faults of the fuel cell can be independently carried out, and the fault cell can be rapidly detected, so that the safety and the reliability of a fuel cell system are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cells, and in particular to a monitoring and detection method and device for fuel cell voltage faults. Background Art

[0002] Fuel cells are a new type of battery that uses hydrogen and other fuels to directly convert into electrical energy through electrochemical reactions. They have the advantages of high energy density, no pollution, and easy use, so they are widely used in automobiles, ships, mobile communication base stations, etc. However, the failure problem in the fuel cell system is also one of the difficulties that need to be solved in its development process.

[0003] In a fuel cell system, unstable or excessively fluctuating voltage may cause system failure or damage, so it is very important to monitor and detect the fuel cell voltage. Since a fuel cell stack contains a large number of single cells, problematic cells may be difficult to detect and repair quickly, so it is necessary to develop a method and device for monitoring and detecting fuel cell voltage failures to improve the safety and reliability of the fuel cell system. In the related art, when implementing fuel cell fault diagnosis, it is often not targeted, and the diagnostic method is highly dependent on cloud technology. It is difficult to perform independent fuel cell fault diagnosis for voltage failures. Summary of the invention

[0004] The purpose of the present invention is to provide a method and device for monitoring and detecting fuel cell voltage faults, which can independently diagnose fuel cell faults with voltage faults and quickly detect faulty batteries to improve the safety and reliability of the fuel cell system.

[0005] To achieve the above-mentioned object, the present invention provides a monitoring and detection device for fuel cell voltage faults, comprising a first acquisition module, the first acquisition module being used to acquire multiple fuel cell voltage fault types and establish a fuel cell fault feature library based on the multiple fault types;

[0006] A second acquisition module is used to analyze multiple faults in the fault database, obtain multiple fault diagnosis strategies, and provide the multiple fault diagnosis strategies to the generation module;

[0007] A sensor component, used to detect the state of the fuel cell in real time, mainly the voltage state, and provide the state data to the generation module;

[0008] A generation module is used to diagnose the health of the fuel cell voltage using a multi-fault collaborative diagnosis model, including detecting state parameters such as battery voltage, temperature, and depth of discharge, and generating a safety control strategy for the fuel cell system based on the diagnosis results;

[0009] A controller component controls the operation of the fuel cell system according to a safety control strategy.

[0010] Preferably, the first acquisition module acquires multiple power battery fault types, including but not limited to battery cell overvoltage, overtemperature, undervoltage, overcharge and other fault types.

[0011] Preferably, the second acquisition module analyzes various faults in the fault database based on algorithms such as machine learning and pattern recognition.

[0012] Preferably, the sensor assembly includes a variety of sensors for detecting various state parameters in real time.

[0013] A method for monitoring and detecting a fuel cell voltage fault comprises the following steps:

[0014] Step 1, detecting the voltage of each battery in the fuel cell group and recording it, and performing statistical analysis on the recorded battery voltage data, including calculating the standard deviation and entropy value;

[0015] Step 2: Compare the voltage value of each battery with a preset voltage range according to the statistical analysis results to determine whether there is inconsistency in the battery voltage and the degree of inconsistency;

[0016] Step 3: Compare the inconsistency level with a preset threshold value. If it is found that the voltage of a certain battery exceeds the preset range, an alarm is issued to indicate the location of the voltage inconsistency fault.

[0017] Step 4. Continue to detect and record the battery voltage and repair the battery or the entire fuel cell stack as needed.

[0018] Therefore, the present invention adopts the above-mentioned fuel cell voltage fault monitoring and detection method and device, which can independently diagnose fuel cell faults with voltage faults and quickly detect faulty batteries to improve the safety and reliability of the fuel cell system.

[0019] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of the use process of a monitoring and detection method and device embodiment of a fuel cell voltage fault of the present invention;

[0021] Figure 2 It is a flow chart of a monitoring and detection method and device embodiment of a fuel cell voltage fault of the present invention. DETAILED DESCRIPTION

[0022] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0023] Unless otherwise defined, technical or scientific terms used in the present invention shall have the common meanings understood by one having ordinary skills in the field to which the present invention belongs.

[0024] Embodiment 1

[0025] As shown in the figure, the present invention provides a monitoring and detection device for fuel cell voltage faults, including a first acquisition module, which is used to acquire multiple fuel cell voltage fault types, including but not limited to battery cell overvoltage, overtemperature, undervoltage, overcharge and other fault types, and establish a fuel cell fault feature library based on multiple fault types;

[0026] The second acquisition module is used to analyze various faults in the fault database through machine learning, pattern recognition and other algorithms to obtain various fault diagnosis strategies, and provide the various fault diagnosis strategies to the generation module;

[0027] A sensor component, including a variety of sensors, for detecting the state of the fuel cell in real time, mainly the voltage state, and providing the state data to the generation module;

[0028] A generation module is used to diagnose the health of the fuel cell voltage using a multi-fault collaborative diagnosis model, including detecting state parameters such as battery voltage, temperature, and depth of discharge, and generating a safety control strategy for the fuel cell system based on the diagnosis results;

[0029] A controller component controls the operation of the fuel cell system according to a safety control strategy.

[0030] When using the monitoring and detection device for fuel cell voltage faults provided by the present invention, a special sensor assembly is first installed on each battery in the fuel cell group to accurately monitor and record the real-time voltage value and voltage change trend of the battery. These sensors have high sensitivity and fast response capabilities to ensure accurate monitoring of battery voltage. The battery voltage data collected by the sensor assembly is then processed and analyzed by an advanced processor assembly, including data filtering, noise elimination, and data smoothing. At the same time, feature extraction and conversion are performed on the voltage data to convert it into a format that can be used for training machine learning models.

[0031] Then, using the trained machine learning model, the system analyzes the correlation between voltage performance and faults for different fault types, such as lack of gas, flooding, and membrane drying. By identifying the voltage drop amplitude, fluctuation state changes, and abnormal voltage jumps, the system can quickly and accurately diagnose and determine the possible fault types of the fuel cell. Based on the identified features and the results obtained by the machine learning model, the system will establish a maintenance fuel cell fault diagnosis library. The library stores the correlation information between different voltage performances and fault types for future fault diagnosis and classification.

[0032] Finally, the processor component monitors and analyzes the battery voltage data collected by the sensor component in real time. By comparing and matching with the fault diagnosis library, the system can detect in real time whether there are any abnormalities in the battery voltage, and classify and analyze them. Based on the results of real-time monitoring and analysis, the fuel cell fault diagnosis system will output the fault diagnosis results according to the preset rules and fault modes. The results are usually presented in a visual way and provided to the operator or relevant personnel for viewing and analysis. At the same time, the system can also promptly notify the user through alarms, notifications, etc., so that appropriate measures can be taken to repair the fault or maintain the fuel cell system.

[0033] A method for monitoring and detecting a fuel cell voltage fault comprises the following steps:

[0034] Step 1, detecting the voltage of each battery in the fuel cell group and recording it, and performing statistical analysis on the recorded battery voltage data, including calculating the standard deviation and entropy value;

[0035] Step 2: Compare the voltage value of each battery with a preset voltage range according to the statistical analysis results to determine whether there is inconsistency in the battery voltage and the degree of inconsistency;

[0036] Step 3: Compare the inconsistency level with a preset threshold value. If it is found that the voltage of a certain battery exceeds the preset range, an alarm is issued to indicate the location of the voltage inconsistency fault.

[0037] Step 4. Continue to detect and record the battery voltage and repair the battery or the entire fuel cell stack as needed.

[0038] Therefore, the present invention adopts the above-mentioned fuel cell voltage fault monitoring and detection method and device, which can independently diagnose fuel cell faults with voltage faults and quickly detect faulty batteries to improve the safety and reliability of the fuel cell system.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A monitoring and detection device for fuel cell voltage faults, characterized in that: It includes a first acquisition module, which is used to acquire multiple fuel cell voltage fault types and establish a fuel cell fault feature library based on the multiple fault types; A second acquisition module is used to analyze multiple faults in the fault database, obtain multiple fault diagnosis strategies, and provide the multiple fault diagnosis strategies to the generation module; A sensor component, used to detect the state of the fuel cell in real time, mainly the voltage state, and provide the state data to the generation module; A generation module is used to diagnose the health of the fuel cell voltage using a multi-fault collaborative diagnosis model, including detecting state parameters such as battery voltage, temperature, and depth of discharge, and generating a safety control strategy for the fuel cell system based on the diagnosis results; A controller component controls the operation of the fuel cell system according to a safety control strategy.

2. A fuel cell voltage fault monitoring and detection device according to claim 1, characterized in that: The first acquisition module acquires multiple power battery fault types, including but not limited to battery cell overvoltage, overtemperature, undervoltage, overcharge and other fault types.

3. A fuel cell voltage fault monitoring and detection device according to claim 1, characterized in that: The second acquisition module analyzes various faults in the fault database based on algorithms such as machine learning and pattern recognition.

4. A fuel cell voltage fault monitoring and detection device according to claim 1, characterized in that: The sensor assembly includes a variety of sensors for detecting various state parameters in real time.

5. A method for monitoring and detecting a fuel cell voltage fault as claimed in claims 1 to 4, comprising the following steps: Step 1, detecting the voltage of each battery in the fuel cell group and recording it, and performing statistical analysis on the recorded battery voltage data, including calculating the standard deviation and entropy value; Step 2: Compare the voltage value of each battery with a preset voltage range according to the statistical analysis results to determine whether there is inconsistency in the battery voltage and the degree of inconsistency; Step 3: Compare the inconsistency level with a preset threshold value. If it is found that the voltage of a certain battery exceeds the preset range, an alarm is issued to indicate the location of the voltage inconsistency fault. Step 4. Continue to detect and record the battery voltage and repair the battery or the entire fuel cell stack as needed.