Drainage control method and system of fuel cell system and fuel cell vehicle

Abstract

The invention relates to the technical field of new energy power generation vehicles, in particular to a drainage control method and system of a fuel cell system and a fuel cell vehicle. The method comprises the following steps: firstly, performing feature extraction on initial drainage water quality data of a fuel cell system to obtain initial water quality feature data of the fuel cell system, and searching in a primary processing strategy knowledge base based on the initial water quality feature data to obtain a primary processing strategy; and secondly, monitoring the water quality treated by the primary treatment strategy to obtain intermediate water quality characteristic data of the treated drainage, and searching in an emergency treatment strategy knowledge base based on the intermediate water quality characteristic data to obtain an emergency treatment strategy. And finally, performing water quality correction on the treated drainage based on an emergency treatment strategy, and performing deep purification on the corrected drainage. Through a self-adaptive drainage treatment strategy, the drainage quality of the fuel cell system reaches the recycling standard.

Description

Technical Field

[0001] The present application relates to the technical field of new energy power generation vehicles, and in particular to a drainage control method and system for a fuel cell system and a fuel cell vehicle. Background Art

[0002] Hydrogen energy storage emergency power supply vehicle uses hydrogen fuel cells to replace traditional diesel generators or lithium battery packs as the main emergency power supply, and has broad development prospects. The fuel cell system will generate a large amount of drainage during operation. If these drainages are directly discharged, it will cause waste of water resources and environmental pollution. In order to achieve the reuse of drainage, it is necessary to treat the drainage and control the water quality.

[0003] The water quality of the fuel cell system drainage is complex and changeable, containing various impurities such as metal ions, organic matter and microorganisms, and the drainage volume and water quality change dynamically with the working conditions of the fuel cell. However, the adaptive adjustment degree of the drainage control method in the related art needs to be improved so that the complex and changeable drainage water quality can meet the recycling standard. Summary of the invention

[0004] The present application provides a drainage control method, system and fuel cell vehicle of a fuel cell system, which solves the technical problem that the adaptive adjustment degree of the drainage control method in the related art needs to be improved, and achieves the technical effect of making drainage with complex and changeable water quality recyclable after treatment.

[0005] In order to achieve the above objectives, the main technical solutions adopted in this application include: In a first aspect, an embodiment of the present application provides a drainage control method for a fuel cell system, which is applied to a fuel cell vehicle; the method comprises: Extracting features of initial drainage water quality data of the fuel cell system to obtain initial water quality feature data of the fuel cell system; Searching in a preliminary treatment strategy knowledge base according to the initial water quality characteristic data to obtain a preliminary treatment strategy; wherein the preliminary treatment strategy knowledge base stores the corresponding relationship between water quality characteristics and drainage treatment strategies; After the wastewater of the fuel cell system is processed by the preliminary processing strategy, determining intermediate water quality characteristic data of the processed wastewater; Searching in an emergency treatment strategy knowledge base according to the intermediate water quality characteristic data to obtain an emergency treatment strategy; wherein the emergency treatment strategy knowledge base stores a correspondence between water quality characteristics and emergency treatment strategies; The emergency treatment strategy is used to correct the water quality of the treated wastewater, and the corrected wastewater is deeply purified to achieve wastewater recycling of the fuel cell system.

[0006] Optionally, the preliminary processing strategy knowledge base is constructed by the following method: Performing a first water quality monitoring on historical drainage of the fuel cell system to obtain historical drainage water quality data of the fuel cell system; Classify and judge the historical drainage status of the fuel cell system according to the historical drainage water quality data to obtain a historical drainage processing strategy for the fuel cell system; Processing the drainage of the fuel cell system by the historical drainage processing strategy, and performing a second water quality test on the historically processed drainage to obtain historical intermediate drainage water quality data; If the historical intermediate drainage water quality data does not exceed the preset water quality index range, the preliminary treatment strategy knowledge base is constructed based on the historical drainage water quality data and the historical drainage treatment strategy.

[0007] Optionally, the constructing of the preliminary treatment strategy knowledge base based on the historical drainage water quality data and the historical drainage treatment strategy includes: Extracting features from the historical drainage water quality data to obtain historical water quality feature data; A corresponding relationship between the historical water quality characteristic data and the historical drainage treatment strategy is constructed and stored in the preliminary treatment strategy knowledge base.

[0008] Optionally, the method further comprises: If the historical intermediate drainage water quality data exceeds the preset water quality index range, the historical emergency treatment strategy is initiated; Performing water quality correction on the historical treated drainage using the historical emergency treatment strategy, and performing water quality testing on the historical corrected drainage to obtain historical corrected water quality data; If the historical corrected water quality data does not exceed the preset water quality index range, the emergency treatment strategy knowledge base is constructed based on the historical intermediate drainage water quality data and the historical emergency treatment strategy.

[0009] Optionally, the constructing of the emergency treatment strategy knowledge base based on the historical intermediate drainage water quality data and the historical emergency treatment strategies includes: Extracting features from the historical intermediate drainage water quality data to obtain historical intermediate water quality feature data; A corresponding relationship between the historical intermediate water quality characteristic data and the historical emergency treatment strategy is constructed and stored in the emergency treatment strategy knowledge base.

[0010] Optionally, searching in a preliminary treatment strategy knowledge base according to the initial water quality characteristic data to obtain a preliminary treatment strategy includes: Calculate the similarity between the initial water quality characteristic data and the water quality characteristics in the preliminary treatment strategy knowledge base to obtain K historical drainage treatment strategies that meet a preset similarity threshold; Determining an initial treatment strategy with the best historical treatment evaluation result among the K historical drainage treatment strategies; The initial processing strategy is dynamically optimized through a DQN reinforcement learning algorithm to determine the preliminary processing strategy that minimizes energy consumption costs.

[0011] Optionally, searching in an emergency treatment strategy knowledge base according to the intermediate water quality characteristic data to obtain an emergency treatment strategy includes: Calculate the similarity between the intermediate water quality characteristic data and the water quality characteristics in the emergency treatment strategy knowledge base to obtain a historical emergency treatment strategy; The process parameters of the historical emergency treatment strategy are used as initial parameters, and the process parameters of the historical emergency treatment strategy are dynamically adjusted through a PID control algorithm to obtain adjusted parameters of the emergency treatment strategy.

[0012] Optionally, the initial drainage water quality data includes drainage pH value and drainage conductivity; the method further includes: Determine the pressure change data before and after drainage; The drainage time of the fuel cell system is set according to the pressure change data, the drainage pH value and the drainage conductivity.

[0013] Optionally, setting the drainage time of the fuel cell system according to the pressure change data, the drainage pH value and the drainage conductivity includes: Determining the working state of the anode of the fuel cell system according to the pressure change data, the drainage pH value and the drainage conductivity; If the working state is that the anode is in a liquid water agglomeration fault state, the drainage time is extended.

[0014] Optionally, the deep purification of the corrected drainage includes: Determining a target nanofiltration membrane separation component according to the water quality test result of the corrected drainage; The corrected wastewater is deeply purified by the target nanofiltration membrane separation component to remove residual trace pollutants and microorganisms.

[0015] In a second aspect, the embodiment of the present application further provides a drainage control system of a fuel cell system, which is applied to a fuel cell vehicle; the system comprises: An initial feature extraction module, used to extract features from initial drainage water quality data of the fuel cell system to obtain initial water quality feature data of the fuel cell system; A preliminary strategy search module, used to search in a preliminary treatment strategy knowledge base according to the initial water quality characteristic data to obtain a preliminary treatment strategy; wherein the preliminary treatment strategy knowledge base stores the correspondence between water quality characteristics and drainage treatment strategies; an intermediate characteristic determination module, for determining intermediate water quality characteristic data of the treated drainage after the drainage of the fuel cell system is processed by the preliminary processing strategy; An emergency strategy search module, used to search in an emergency treatment strategy knowledge base according to the intermediate water quality characteristic data to obtain an emergency treatment strategy; wherein the emergency treatment strategy knowledge base stores the corresponding relationship between water quality characteristics and emergency treatment strategies; The water quality correction and purification module is used to correct the water quality of the treated wastewater through the emergency treatment strategy and deeply purify the corrected wastewater to achieve wastewater recycling of the fuel cell system.

[0016] In a third aspect, an embodiment of the present application further provides a fuel cell vehicle, which includes an electric vehicle chassis and a container, wherein the container includes a hydrogen fuel cell system, a hydrogen storage system, a buffered lithium battery system, a power inverter system, an air conditioning system, and an air intake and exhaust system, wherein the control device of the hydrogen fuel cell system executes the method described in any of the above embodiments.

[0017] In an embodiment of the present application, a preliminary treatment strategy is obtained by searching in a preliminary treatment strategy knowledge base based on the initial drainage water quality data characteristics of the fuel cell system. Furthermore, the intermediate water quality processed by the preliminary treatment strategy is monitored. If the intermediate water quality data exceeds the standard, the emergency treatment strategy is searched in the emergency treatment strategy knowledge base based on the intermediate water quality characteristic data. Then, the water quality of the treated drainage is corrected based on the emergency treatment strategy, and the corrected drainage is deeply purified. Through preliminary treatment, emergency treatment and deep purification, layered treatment can be implemented for different water quality conditions, which improves the adaptability of the drainage treatment strategy of the fuel cell system, and finally makes the drainage water quality of the fuel cell system reach the standard that can be recycled. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1A flow chart of a fuel cell system drainage control method provided in an embodiment of this specification; Figure 2 A flow chart of a fuel cell system drainage control method provided in an embodiment of this specification; Figure 3 A flow chart of a fuel cell system drainage control method provided in an embodiment of this specification; Figure 4 A flow chart of a fuel cell system drainage control method provided in an embodiment of this specification; Figure 5 A flow chart of a fuel cell system drainage control method provided in an embodiment of this specification; Figure 6 A flow chart of a fuel cell system drainage control method provided in an embodiment of this specification; Figure 7 A flow chart of a fuel cell system drainage control method provided in an embodiment of this specification; Figure 8 A flow chart of a fuel cell system drainage control method provided in an embodiment of this specification; Fig. 9 A flow chart of a fuel cell system drainage control method provided in an embodiment of this specification; Fig.10 A flow chart of a fuel cell system drainage control method provided in an embodiment of this specification; Fig.11 A schematic diagram of a fuel cell system drainage control system provided in an embodiment of this specification; Fig.12 A schematic diagram of a fuel cell vehicle provided in an embodiment of this specification. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0021] Hydrogen energy is environmentally friendly and highly efficient. With the advancement of technology, the potential of hydrogen energy is being continuously explored, and it has broad development prospects in the future. Hydrogen fuel cell systems that use hydrogen as energy are highly efficient and can efficiently convert the chemical energy of hydrogen into electrical energy. They are widely used in transportation, power generation and other industrial fields.

[0022] A large amount of drainage is generated during the operation of the hydrogen fuel cell system. If the drainage is discharged directly, it will not only waste water resources, but also pollute the environment if it is not treated. In order to recycle the drainage, it is necessary to effectively treat the drainage. However, the water quality of the drainage from the fuel cell system is complex and changeable, containing impurities such as various metal ions, organic matter and microorganisms. The drainage volume and water quality change dynamically with the operating conditions of the fuel cell, which requires the drainage treatment strategy to be adaptive.

[0023] Therefore, the present application proposes a drainage control method applicable to a fuel cell system, which can be applied in a fuel cell system, and a preliminary treatment strategy knowledge base and an emergency treatment strategy knowledge base are prepared in advance. The strategies in the preliminary treatment strategy knowledge base are applicable to untreated drainage discharged from the fuel cell, and the strategies in the emergency treatment strategy knowledge base are applicable to drainage that has been treated by the preliminary treatment strategy but whose water quality does not meet the standard after treatment. The drainage of the fuel cell is detected by a multi-parameter water quality sensor array. First, the preliminary treatment strategy is found in the preliminary treatment strategy knowledge base according to the initial water quality characteristic data. After the fuel cell drainage is treated using the preliminary treatment strategy, the intermediate water quality is monitored in real time. If the intermediate water quality fails to meet the standard, it is necessary to find the emergency treatment strategy in the emergency treatment strategy knowledge base according to the intermediate water quality characteristic data. After the intermediate drainage is treated using the emergency treatment strategy, the corrected water quality is monitored in real time. If the corrected water quality meets the standard, the target nanofiltration membrane separation component is further determined according to the corrected water quality data, and the corrected drainage is deeply purified. The purified water that meets the standard can be recycled.

[0024] In the above scenario example, the use of a multi-parameter water quality sensor array to detect the drainage water quality of the fuel cell system can make a more accurate judgment on the water quality and provide more accurate water quality data for determining the drainage treatment strategy. Through the preliminary treatment strategy knowledge base, emergency treatment strategy knowledge base and nanofiltration membrane separation component technology, the system can implement layered treatment for different water quality conditions, improving the adaptability of the fuel cell system drainage treatment strategy.

[0025] According to an embodiment of the present application, an embodiment of a drainage control method for a fuel cell system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] See also Figure 1 The embodiment of the present application provides a drainage control method for a fuel cell system of a fuel cell vehicle, and the specific steps include: S110 , extracting features from initial drainage water quality data of the fuel cell system to obtain initial water quality feature data of the fuel cell system.

[0027] Among them, the initial drainage water quality data can be the water quality data of the water discharged from the fuel cell system before it is treated, which is obtained by real-time monitoring of the drainage through a multi-parameter water quality sensor array, including pH value and conductivity data. Specifically, the monitoring system also needs to clean and pre-process the received initial drainage water quality data, remove abnormal values, and then store the data in a time series database. By extracting features from the initial drainage water quality data in the time series database, the initial water quality characteristic data of the fuel cell system can be obtained.

[0028] S120. Search in a preliminary treatment strategy knowledge base according to the initial water quality characteristic data to obtain a preliminary treatment strategy.

[0029] Among them, the correspondence between water quality characteristics and drainage treatment strategies is stored in the preliminary treatment strategy knowledge base. The drainage treatment strategy can be a series of processes and technologies formulated to effectively treat the untreated drainage generated by the fuel cell, such as chemical treatment first, followed by precipitation, filtration, etc. Its goal can include reducing conductivity, neutralizing pH, etc., to ensure that the treated drainage meets the relevant standards. Exemplarily, based on the initial water quality characteristic data and combined with the preset water quality standard threshold, a fuzzy control algorithm can be used to comprehensively evaluate and classify the water quality status to obtain the water quality category corresponding to the current water quality characteristic data. Further, according to the water quality category, a search is performed in the preliminary treatment strategy knowledge base to obtain the corresponding preliminary treatment strategy.

[0030] S130, after the drainage of the fuel cell system is processed by the preliminary processing strategy, intermediate water quality characteristic data of the processed drainage is determined.

[0031] Among them, the intermediate water quality can be the water quality after being treated by the preliminary treatment strategy. Specifically, after the drainage of the fuel cell system is treated by the preliminary treatment strategy, the effect of the treatment needs to be monitored. For example, a multi-point water quality detection device can be set at the key link of the treatment process to collect the data required to evaluate the intermediate water quality. The collected intermediate water quality data is cleaned and pre-processed, and after the outliers are removed, the data is stored in the time series database. By extracting features from the intermediate water quality data in the time series database, the intermediate water quality characteristic data of the treated drainage can be obtained.

[0032] S140. Search in an emergency treatment strategy knowledge base according to the intermediate water quality characteristic data to obtain an emergency treatment strategy.

[0033] Among them, the correspondence between water quality characteristics and emergency treatment strategies is stored in the emergency treatment strategy knowledge base. Emergency treatment strategies can be processes and technologies formulated to effectively deal with drainage that has undergone preliminary treatment but still does not meet water quality standards. This strategy generally processes one or several water quality indicators that do not meet standards after preliminary treatment to ensure that the treated drainage meets relevant standards. Specifically, if the intermediate water quality characteristic data of the treated drainage meets the expected standards, then no emergency treatment is required. If the expected standards are not met, it is necessary to search for emergency treatment strategies in the emergency treatment strategy knowledge base based on the intermediate water quality characteristic data. Exemplarily, if the drainage is treated with a preliminary treatment strategy, and it is judged from the intermediate water quality characteristic data that the concentration of a certain metal ion exceeds the standard, then it is necessary to search for the corresponding emergency treatment strategy in the emergency treatment strategy knowledge base for the metal ion and the degree of exceeding the standard.

[0034] S150. Correct the water quality of the treated wastewater through an emergency treatment strategy, and deeply purify the corrected wastewater to achieve wastewater recycling in the fuel cell system.

[0035] Among them, deep purification can be used to remove residual trace pollutants and microorganisms to improve the safety of water quality. Specifically, through the emergency treatment strategy for the treated drainage, it is monitored that the metal ions and pH value in the water have reached the standard, but there may still be trace pollutants or microorganisms in the water. These residual substances still need to be deeply purified. For example, these residual substances can be filtered using nanofiltration membrane separation component technology to make the drainage water quality of the fuel cell system reach the preset standard for recycling.

[0036] In the above embodiment, based on feature extraction of the initial drainage water quality data of the fuel cell system, the initial water quality characteristic data of the fuel cell system is obtained, and based on the initial water quality characteristic data, a search is performed in the preliminary processing strategy knowledge base to obtain a preliminary processing strategy. Furthermore, based on monitoring the water quality after treatment by the preliminary processing strategy, intermediate water quality characteristic data of the treated drainage is obtained, and based on the intermediate water quality characteristic data, a search is performed in the emergency processing strategy knowledge base to obtain an emergency processing strategy. Finally, the water quality of the treated drainage is corrected based on the emergency processing strategy, and the corrected drainage is deeply purified. Through the adaptive drainage processing strategy, the drainage water quality of the fuel cell system reaches the standard that can be recycled.

[0037] In some embodiments, see Figure 2 , a preliminary processing strategy knowledge base can be constructed by the following methods: S210 , performing a first water quality monitoring on historical drainage of the fuel cell system to obtain historical drainage water quality data of the fuel cell system.

[0038] The historical drainage is the untreated drainage that has been discharged from the fuel cell system in the historical data. Specifically, the historical drainage of the fuel cell system can be the first water quality monitoring using a multi-parameter water quality sensor array to collect the data required for evaluating the water quality, such as key water quality index parameters such as pH value and conductivity. The data can be saved in a database to obtain the historical drainage water quality data of the fuel cell system.

[0039] S220 , classify and judge the historical drainage status of the fuel cell system according to the historical drainage water quality data, and obtain the historical drainage processing strategy of the fuel cell system.

[0040] Among them, the historical drainage treatment strategy can be a strategy for the initial treatment of historical drainage, which is a series of processes and technologies developed to effectively treat the untreated historical drainage generated by fuel cells, such as chemical treatment first, followed by precipitation, filtration, etc. Its goal can include reducing conductivity, neutralizing pH, etc., to ensure that the treated drainage meets relevant standards. Specifically, it can be based on the historical drainage water quality data and combined with the preset water quality standard threshold, to classify and judge the historical drainage status and determine the historical drainage treatment strategy. Exemplarily, it can be a fuzzy reasoning method, based on the historical drainage water quality data and fuzzy rules, to calculate the membership of the historical water quality status, and obtain the water quality status evaluation result, wherein the category with the largest membership is the current comprehensive water quality evaluation result, and the corresponding historical drainage treatment strategy is determined according to the evaluation result.

[0041] S230, processing the drainage of the fuel cell system through the historical drainage processing strategy, and performing a second water quality test on the historically processed drainage to obtain historical intermediate drainage water quality data.

[0042] The historical intermediate drainage water quality data may be drainage water quality data processed by the historical drainage processing strategy. Specifically, after the historical drainage processing strategy is implemented on the drainage of the fuel cell system, the treated drainage may be subjected to a second water quality monitoring, for example, water quality data may be collected every 10 seconds after 1 minute of the start of the processing, and the data may be saved in a time series database. If the water quality data collected for 10 consecutive times tends to be stable, it may be used as the historical intermediate drainage water quality data of the fuel cell system.

[0043] S240: If the historical intermediate drainage water quality data does not exceed the preset water quality index range, a preliminary treatment strategy knowledge base is constructed based on the historical drainage water quality data and the historical drainage treatment strategy.

[0044] Specifically, after the implementation of the historical drainage treatment strategy, after a certain period of time, the collected historical intermediate drainage water quality index data do not exceed the preset water quality index range of the corresponding time period, proving that the historical drainage treatment strategy is an effective strategy. The historical drainage water quality data and the historical drainage treatment strategy can be added to the preliminary treatment strategy knowledge base.

[0045] In the above embodiment, the historical drainage water quality data of the fuel cell system is obtained based on the first water quality monitoring of the historical drainage of the fuel cell system, and the historical drainage water quality state of the fuel cell system is classified and judged based on the historical drainage water quality data to obtain the corresponding historical drainage processing strategy. Then, the historical intermediate drainage water quality data is obtained based on the drainage processed by the historical drainage processing strategy. The effectiveness of the historical drainage processing strategy is judged based on the historical intermediate drainage water quality data. Finally, based on the effective historical drainage processing strategy and the corresponding historical drainage water quality data, a preliminary processing strategy knowledge base is constructed for reference or use in the subsequent processing of fuel cell system drainage.

[0046] In some embodiments, see Figure 3 , based on historical drainage water quality data and historical drainage treatment strategies, a preliminary treatment strategy knowledge base is constructed, including: S310: Extract features from historical drainage water quality data to obtain historical water quality feature data.

[0047] Specifically, the sensor technology can be used to monitor the water quality of the historical drainage of the fuel cell system, and the data required for evaluating the water quality can be collected, such as key water quality index parameters such as pH value and conductivity. The data can be saved in the database, thereby obtaining the historical drainage water quality data of the fuel cell system. The historical water quality feature data can be obtained by extracting the features of the historical drainage water quality data in the database.

[0048] S320: construct a correspondence between historical water quality characteristic data and historical drainage treatment strategies, and store the correspondence in a preliminary treatment strategy knowledge base.

[0049] Specifically, any historical drainage can be classified and judged according to the historical water quality characteristic data to obtain the treatment process and treatment time of the drainage, so as to determine the historical drainage treatment strategy for the fuel cell system. After the historical drainage treatment strategy is implemented, the drainage water quality is monitored several times again. After the monitored water quality meets the standard, the effectiveness of the historical drainage treatment strategy is proved, and the corresponding relationship between the historical water quality characteristic data and the historical drainage treatment strategy is constructed and stored in the preliminary treatment strategy knowledge base.

[0050] In the above embodiment, based on feature extraction of historical drainage water quality data, historical water quality feature data is obtained. Based on the correspondence between historical water quality feature data and effective historical drainage treatment strategies, a preliminary treatment strategy knowledge base is constructed, which can be used as a reference or used in subsequent treatment of fuel cell system drainage.

[0051] In some embodiments, see Figure 4 , the drainage control method of the fuel cell system further includes: S410: If the historical intermediate drainage water quality data exceeds the preset water quality index range, the historical emergency treatment strategy is initiated.

[0052] Among them, the historical emergency treatment strategy can be a process and technology developed to effectively deal with historical intermediate drainage that has undergone historical drainage treatment but still does not meet the water quality standards. This strategy generally targets one or several water quality indicators that do not meet the standards after preliminary treatment to ensure that the treated drainage meets the relevant standards. Specifically, it can be detected that the water quality data of the historical intermediate drainage exceeds the preset water quality indicator range, and the historical intermediate drainage status is classified and judged to obtain which water quality indicators exceed the standard and the degree of exceeding the standard, and analyze the treatment process that needs to be taken, such as which agent needs to be added and how long the treatment is required, so as to determine the historical emergency treatment strategy.

[0053] S420. Correct the water quality of the historically treated drainage using a historical emergency treatment strategy, and test the water quality of the historically corrected drainage to obtain historically corrected water quality data.

[0054] The historical corrected water quality data may be the water quality data monitored after the historical emergency treatment strategy is activated when any historical intermediate drainage water quality data exceeds the preset water quality index range.

[0055] Specifically, after implementing the historical emergency treatment strategy for the historical treated drainage, the water quality of the historical corrected drainage can be tested through a multi-parameter water quality sensor array. For example, water quality data can be collected every 5 seconds after 30 seconds of treatment. The data can be saved in a database. If the water quality data collected for 10 consecutive times tends to be stable, it can be used as the historical corrected water quality data.

[0056] S430: If the historical corrected water quality data does not exceed the preset water quality index range, an emergency treatment strategy knowledge base is constructed based on the historical intermediate drainage water quality data and historical emergency treatment strategies.

[0057] Specifically, after the implementation of the historical emergency treatment strategy, the historical corrected drainage water quality index data collected continuously for multiple times did not exceed the preset water quality index range, proving that the historical emergency treatment strategy was an effective strategy. A corresponding relationship between the historical intermediate drainage water quality data and the historical emergency treatment strategy can be established and added to the emergency treatment strategy knowledge base.

[0058] In the above embodiment, the historical emergency treatment strategy is initiated based on the excessive condition of the historical intermediate drainage water quality data, and the effectiveness of the historical emergency treatment strategy is judged based on the water quality data processed by the historical emergency treatment strategy. Finally, based on the effective historical emergency treatment strategy and the historical intermediate drainage water quality data, an emergency treatment strategy knowledge base is constructed, which can be used as a reference or used when the intermediate drainage water quality exceeds the standard and emergency treatment is required.

[0059] In some embodiments, see Figure 5 , based on historical intermediate drainage water quality data and historical emergency treatment strategies, build an emergency treatment strategy knowledge base, including: S510, extracting features from historical intermediate drainage water quality data to obtain historical intermediate water quality feature data.

[0060] Specifically, the sensor technology can be used to monitor the water quality of the historical intermediate drainage of the fuel cell system, and the data required for evaluating the water quality can be collected, such as key water quality index parameters such as pH value and conductivity. The data can be saved in a database, thereby obtaining the historical intermediate drainage water quality data of the fuel cell system. The historical intermediate water quality feature data can be obtained by extracting features from the historical intermediate drainage water quality data in the database.

[0061] S520: Construct a correspondence between historical intermediate water quality characteristic data and historical emergency treatment strategies, and store the correspondence in an emergency treatment strategy knowledge base.

[0062] Specifically, any historical intermediate drainage can be classified and judged according to the historical intermediate water quality characteristic data to obtain the treatment process and treatment time of the historical intermediate drainage, thereby determining the historical emergency treatment strategy for the fuel cell system. If the historical emergency treatment strategy is implemented, the drainage water quality is monitored several times again, and the monitored water quality meets the standard, proving that the historical emergency treatment strategy is effective, then the corresponding relationship between the historical intermediate water quality characteristic data and the historical emergency treatment strategy can be constructed and stored in the emergency treatment strategy knowledge base.

[0063] In the above embodiment, based on feature extraction of historical intermediate drainage water quality data, historical intermediate water quality feature data is obtained. A correspondence between the historical intermediate water quality feature data and effective historical emergency treatment strategies is constructed and stored in the emergency treatment strategy knowledge base, which can be used as a reference or used when the intermediate drainage water quality exceeds the standard and emergency treatment is required.

[0064] In some embodiments, see Figure 6 , search in the preliminary treatment strategy knowledge base according to the initial water quality characteristic data to obtain the preliminary treatment strategy, including: S610: Calculate the similarity between the initial water quality characteristic data and the water quality characteristics in the preliminary treatment strategy knowledge base to obtain K historical drainage treatment strategies that meet a preset similarity threshold.

[0065] Specifically, the Euclidean distance or cosine similarity between the initial water quality characteristic data and the water quality characteristics in the preliminary treatment strategy knowledge base can be calculated to obtain K water quality characteristics with a similarity higher than a preset similarity threshold, and K historical drainage treatment strategies can be obtained based on the correspondence between the water quality characteristics and the preliminary treatment strategies.

[0066] S620: Determine an initial treatment strategy with the best historical treatment evaluation result among K historical drainage treatment strategies.

[0067] Specifically, first, set the evaluation indicators of historical treatment effects, such as the treatment water quality compliance rate, system energy consumption, and operating costs. Secondly, assign weights to each evaluation indicator, such as a combination of subjective and objective weights, or other weight assignment methods, to determine the weight corresponding to each evaluation indicator. Finally, for the K selected historical drainage treatment strategies, evaluate their comprehensive treatment effects on the initial water quality characteristic data. The evaluation formula can be: w1, w2, w3…are the weights corresponding to each evaluation index, and the historical drainage treatment strategy with the highest comprehensive evaluation is determined as the optimal initial treatment strategy.

[0068] S630, dynamically optimizing the initial processing strategy through the DQN reinforcement learning algorithm to determine a preliminary processing strategy that minimizes energy consumption costs.

[0069] Exemplarily, the initial treatment strategy is dynamically optimized by the DQN reinforcement learning algorithm. First, the state space (such as water quality parameters) and action space (such as adjusting the type of reagent, dosage, treatment time, etc.) are defined, and a reward function is designed to measure the reduction of energy consumption and cost. Secondly, data collection can be to collect real-time data of the current water treatment system, including water quality indicators, energy consumption, operating costs, etc., as training data and evaluation data. Then, a deep neural network is constructed to approximate the Q-value function to input the current state and output the expected return value of each possible action. Then, the experience replay mechanism is used to store tuples of state, action, reward and next state, and random sampling is performed for training. Finally, the trained DQN model is used to make decisions, and the initial treatment strategy with the best input historical processing evaluation result is dynamically optimized to obtain a preliminary treatment strategy with minimized energy consumption cost.

[0070] In the above embodiment, based on the similarity between the initial water quality characteristic data and the water quality characteristics in the preliminary treatment strategy knowledge base, K historical drainage treatment strategies are obtained, and the treatment effect of the initial drainage is evaluated based on the K historical drainage treatment strategies to obtain the initial treatment strategy with the best historical treatment evaluation result. Based on the DQN reinforcement learning algorithm, the initial treatment strategy with the best historical treatment evaluation result is dynamically optimized to obtain the preliminary treatment strategy with the minimum energy consumption cost. This embodiment not only meets the water quality standards of drainage treatment, but also takes into account the minimization of system energy consumption and operating costs, and realizes the optimal control of multi-objective balance.

[0071] In some embodiments, see Figure 7 , search in the emergency treatment strategy knowledge base according to the intermediate water quality characteristic data to obtain the emergency treatment strategy, including: S710, calculating the similarity between the intermediate water quality characteristic data and the water quality characteristics in the emergency treatment strategy knowledge base to obtain the historical emergency treatment strategy.

[0072] Specifically, the Euclidean distance or cosine similarity between the intermediate water quality characteristic data and the intermediate water quality characteristic data in the emergency treatment strategy knowledge base can be calculated, and the intermediate water quality characteristic data that is most similar to the intermediate water quality characteristic data can be selected from the emergency treatment strategy knowledge base. According to the correspondence between the intermediate water quality characteristic data and the historical emergency treatment strategy, the corresponding historical emergency treatment strategy can be obtained.

[0073] S720: Using the process parameters of the historical emergency treatment strategy as initial parameters, dynamically adjusting the process parameters of the historical emergency treatment strategy through a PID control algorithm to obtain adjusted parameters of the emergency treatment strategy.

[0074] Among them, the process parameters can be the type, dosage, reaction time, etc. of the reagents that need to be added during wastewater treatment.

[0075] Specifically, first, the initial parameters such as the type of reagent to be added and the initial dosage can be determined based on historical emergency treatment strategies. Then, through precision metering instruments, such as metering pumps, the reagents are accurately added to the water body to carry out emergency treatment of the water quality. After treatment, the water quality is monitored in real time through a multi-parameter water quality sensor array, and the sampled data is stored in a time series database. It can be based on the monitored water quality exceeding the standard and the effect of reagent addition, through the PID control algorithm to dynamically adjust the process parameters such as the dosage of the reagent, flocculation time and sedimentation time. When the water quality indicators monitored for multiple consecutive sampling cycles are stable within the preset threshold range, it is judged that the water quality has returned to normal, then the emergency treatment measures are stopped and the normal water treatment process operation is restored.

[0076] Specifically, data such as the start and end time of the emergency treatment process, the amount of reagent added, and the process parameter adjustment can be recorded, and the recorded data can be analyzed through a data mining algorithm to obtain the adjusted parameters of the emergency treatment strategy.

[0077] In the above embodiment, the historical emergency treatment strategy is obtained by calculating the similarity between the intermediate water quality characteristic data and the water quality characteristics in the emergency treatment strategy knowledge base. The process parameters of the historical emergency treatment strategy are used as initial parameters, and the process parameters of the historical emergency treatment strategy are dynamically adjusted based on the PID control algorithm to obtain the adjusted parameters of the emergency treatment strategy, thereby optimizing the historical emergency treatment strategy.

[0078] In hydrogen fuel cells, too much water will reduce the performance and efficiency of the battery, so it needs to be discharged in time. In some embodiments, refer to Figure 8 The initial drainage water quality data includes drainage pH value and drainage conductivity; the drainage control method of the fuel cell system also includes: S810, determining pressure change data before and after drainage.

[0079] Specifically, pressure sensors may be used to monitor pressure data at the outlets of the anode and cathode of the fuel cell, and pressure change data before and after the drainage may be determined by acquiring pressure data before and after the drainage.

[0080] S820: Set the drainage time of the fuel cell system according to the pressure change data, the drainage pH value and the drainage conductivity.

[0081] Specifically, the above pressure data is jointly generated by water and gas in the battery, where the gas includes a large amount of water vapor generated by the chemical reaction of the battery, so it is impossible to judge whether there is too much water only by the pressure change data. Furthermore, the pH value affects the aggregation and dispersion behavior of liquid water. When the pH value is close to neutral, it is conducive to the agglomeration of water, while too high or too low is not conducive to the agglomeration of water, so it is possible to judge whether liquid water agglomeration occurs based on the pH value. When the amount of water increases, the conductivity of the drainage will also increase significantly. Therefore, it is possible to combine the pressure change data, drainage pH value and drainage conductivity to judge whether there is too much water in the battery.

[0082] Specifically, the water in the fuel cell can be discharged at regular intervals. The initial drainage time is set to the drainage time when the fuel cell is in normal working condition. When the pressure change data exceeds the threshold, and the pH value is acidic or alkaline, and the drainage conductivity does not exceed the threshold, the judgment result is that the fuel cell is in normal working condition, and the set initial drainage time can be used for drainage; when the pressure change data exceeds the threshold, and the pH value approaches 7, and the drainage conductivity exceeds the threshold, the judgment result is that the fuel cell produces too much water, and the drainage time needs to be extended based on the set initial drainage time.

[0083] In the above embodiment, based on the combination of the pressure change before and after the fuel cell is drained, the pH value of the drained water and the conductivity of the drained water, it is judged whether the amount of water is too much, and a reasonable draining time is further set. When there is too much water in the battery, the excess water in the battery can be drained in time by extending the draining time, thereby stabilizing the performance of the battery.

[0084] The anode of a hydrogen fuel cell is the end where the hydrogen oxidation reaction occurs. Excessive water may inhibit the supply of hydrogen, causing the hydrogen oxidation reaction to slow down, or even form bubbles, increase internal resistance, and affect current output. Therefore, when there is too much water in the anode, it is necessary to extend the drainage time to drain the excess water in time. In some embodiments, please refer to Fig. 9 , set the drainage time of the fuel cell system according to the pressure change data, drainage pH value and drainage conductivity, including: S910, determining the working state of the anode of the fuel cell system according to the pressure change data, the pH value of the drainage water and the drainage conductivity.

[0085] S920: If the working status is that the anode is in a liquid water agglomeration fault state, extend the drainage time.

[0086] Specifically, a pressure sensor may be used to monitor pressure data at the outlet of the anode of the fuel cell. By acquiring the pressure data before and after drainage, the pressure change data before and after drainage is determined. When the pressure change data does not exceed the threshold, the judgment result is that too much water is not produced, and the working state of the anode is judged to be normal; when the pressure change data exceeds the threshold, and the pH value is acidic or alkaline, and the drainage conductivity does not exceed the threshold, the judgment result is that too much water is not produced, and the working state of the anode is judged to be normal; when the pressure change data exceeds the threshold, and the pH value approaches 7, and the drainage conductivity exceeds the threshold, it is judged that the anode is in a liquid water agglomeration fault state, and the drainage time needs to be extended based on the set drainage time.

[0087] In the above embodiment, the working state of the anode is comprehensively judged based on the combination of three data, namely, the pressure change before and after the fuel cell is drained, the pH value of the drainage, and the drainage conductivity. When a liquid water agglomeration failure occurs at the anode, the failure can be eliminated in a timely manner by extending the drainage time, thereby stabilizing the performance of the battery.

[0088] In some embodiments, see Fig.10 , deep purification of the corrected drainage, including: S1010. Determine the target nanofiltration membrane separation component based on the water quality test results of the corrected drainage.

[0089] Among them, the corrected drainage can be the initial drainage of the fuel cell system, which has been processed by the preliminary treatment strategy, and the water quality is monitored to be substandard, and then the water quality meets the standard after being processed by the emergency treatment strategy.

[0090] Specifically, although the water quality of the corrected drainage has reached a certain quality standard, there may still be trace amounts of harmful substances remaining in it. Therefore, further testing of the water quality is required, which can be to detect the types and concentrations of trace pollutants and microorganisms remaining in the water, and determine the target nanofiltration membrane separation component based on the test results, including determining the appropriate nanofiltration membrane material and pore size.

[0091] S1020, deeply purify the corrected wastewater through a targeted nanofiltration membrane separation component to remove residual trace pollutants and microorganisms.

[0092] Specifically, it is necessary to ensure that the connection between the target nanofiltration membrane separation component and the inlet and outlet water pipes is normal and leak-free, and by adjusting the inlet pressure and flow rate and controlling the molecular weight cutoff, efficient removal of trace pollutants and microorganisms in the water can be achieved. The water quality index of the effluent of the target nanofiltration membrane separation component can be tested by a conductivity meter and a turbidity meter to ensure that the effluent water quality is stable and meets the standard, and to achieve deep purification of the corrected drainage.

[0093] In the above embodiment, the target nanofiltration membrane separation component is determined based on the water quality test result of the corrected drainage. Further, the residual trace pollutants and microorganisms are removed by the target nanofiltration membrane separation component, thereby achieving deep purification of the corrected drainage.

[0094] In some embodiments, see Fig.11 , a drainage control system 1100 of a fuel cell system, applied to a fuel cell vehicle; the system comprises: The initial feature extraction module 1110 is used to extract features from the initial drainage water quality data of the fuel cell system to obtain the initial water quality feature data of the fuel cell system.

[0095] The preliminary strategy search module 1120 is used to search in the preliminary treatment strategy knowledge base according to the initial water quality characteristic data to obtain a preliminary treatment strategy; wherein the preliminary treatment strategy knowledge base stores the correspondence between water quality characteristics and drainage treatment strategies.

[0096] The intermediate characteristic determination module 1130 is used to determine the intermediate water quality characteristic data of the treated drainage after the drainage of the fuel cell system is processed by the preliminary processing strategy.

[0097] The emergency strategy search module 1140 is used to search in the emergency treatment strategy knowledge base according to the intermediate water quality characteristic data to obtain the emergency treatment strategy; wherein the emergency treatment strategy knowledge base stores the correspondence between water quality characteristics and emergency treatment strategies.

[0098] The water quality correction and purification module 1150 is used to correct the water quality of the treated wastewater through an emergency treatment strategy, and deeply purify the corrected wastewater to achieve wastewater recycling in the fuel cell system.

[0099] In some embodiments, the drainage control system 1100 of the fuel cell system further includes a water quality monitoring module, a drainage state classification judgment module, a drainage processing module, and a preliminary processing strategy knowledge base construction module.

[0100] The water quality monitoring module is used to perform the first water quality monitoring on the historical drainage of the fuel cell system to obtain the historical drainage water quality data of the fuel cell system. It is also used to perform the second water quality testing on the historical treated drainage to obtain the historical intermediate drainage water quality data.

[0101] The drainage status classification and judgment module is used to classify and judge the historical drainage status of the fuel cell system according to the historical drainage water quality data, and obtain the historical drainage processing strategy of the fuel cell system.

[0102] The drainage processing module is used to process the drainage of the fuel cell system through a historical drainage processing strategy.

[0103] The preliminary treatment strategy knowledge base construction module is used to construct a preliminary treatment strategy knowledge base based on historical drainage water quality data and historical drainage treatment strategies if the historical intermediate drainage water quality data does not exceed the preset water quality index range.

[0104] In some embodiments, the preliminary treatment strategy knowledge base construction module also includes a historical water quality characteristic data extraction module and a corresponding relationship construction module.

[0105] The historical water quality characteristic data extraction module is used to extract the characteristics of historical drainage water quality data to obtain historical water quality characteristic data.

[0106] The corresponding relationship building module is used to build the corresponding relationship between the historical water quality characteristic data and the historical drainage treatment strategy, and store it in the preliminary treatment strategy knowledge base.

[0107] In some embodiments, the drainage control system 1100 of the fuel cell system further includes a historical emergency treatment strategy startup module, a water quality monitoring module, and an emergency treatment strategy knowledge base construction module.

[0108] The historical emergency treatment strategy startup module is used to start the historical emergency treatment strategy if the historical intermediate drainage water quality data exceeds the preset water quality index range.

[0109] The water quality monitoring module is used to test the water quality of the historically treated drainage after the water quality is corrected through the historical emergency treatment strategy to obtain the historically corrected water quality data.

[0110] The emergency treatment strategy knowledge base construction module builds an emergency treatment strategy knowledge base based on the historical intermediate drainage water quality data and historical emergency treatment strategies if the historical corrected water quality data does not exceed the preset water quality index range.

[0111] In some embodiments, the emergency treatment strategy knowledge base construction module also includes a historical intermediate drainage water quality data extraction module and a corresponding relationship construction module.

[0112] The historical intermediate drainage water quality data extraction module is used to extract features from the historical intermediate drainage water quality data to obtain historical intermediate water quality feature data.

[0113] The corresponding relationship building module is used to build the corresponding relationship between the historical intermediate water quality characteristic data and the historical emergency treatment strategy, and store it in the emergency treatment strategy knowledge base.

[0114] In some embodiments, the preliminary strategy search module 1120 is also used to calculate the similarity between the initial water quality characteristic data and the water quality characteristics in the preliminary treatment strategy knowledge base to obtain K historical drainage treatment strategies that meet the preset similarity threshold; determine the initial treatment strategy with the best historical treatment evaluation result among the K historical drainage treatment strategies; and dynamically optimize the initial treatment strategy through the DQN reinforcement learning algorithm to determine the preliminary treatment strategy that minimizes energy consumption costs.

[0115] In some embodiments, the emergency strategy search module 1140 is also used to calculate the similarity between the intermediate water quality characteristic data and the water quality characteristics in the emergency treatment strategy knowledge base to obtain the historical emergency treatment strategy; use the process parameters of the historical emergency treatment strategy as the initial parameters, and dynamically adjust the process parameters of the historical emergency treatment strategy through the PID control algorithm to obtain the adjusted parameters of the emergency treatment strategy.

[0116] In some embodiments, the drainage control system 1100 of the fuel cell system further includes a pressure determination module and a drainage time setting module.

[0117] The pressure determination module is used to determine the pressure change data before and after drainage.

[0118] The drainage time setting module is used to set the drainage time of the fuel cell system according to the pressure change data and the drainage pH value.

[0119] In some embodiments, the drainage control system 1100 of the fuel cell system further includes a working state determination module and a drainage time setting module.

[0120] The working state determination module is used to determine the working state of the anode of the fuel cell system according to the pressure change data and the pH value of the drainage water.

[0121] The drainage time setting module is used to extend the drainage time if the working state is that the anode is in a liquid water agglomeration fault state.

[0122] In some embodiments, the drainage control system 1100 of the fuel cell system further includes a target nanofiltration membrane separation component determination module.

[0123] The target nanofiltration membrane separation component determination module is used to determine the target nanofiltration membrane separation component according to the water quality detection result of the corrected drainage.

[0124] The water quality correction and purification module 1150 deeply purifies the corrected wastewater through a targeted nanofiltration membrane separation component to remove residual trace pollutants and microorganisms.

[0125] In some embodiments, see Fig.12Based on the application of hydrogen fuel cells, the present application provides a fuel cell vehicle, including an electric vehicle chassis and a container, wherein the container includes a hydrogen fuel cell system 101, a hydrogen storage system 102, a buffer lithium battery system 103, a power inverter system 104, an air conditioning system 105 and an air intake and exhaust system 106, wherein the control device of the hydrogen fuel cell system executes any one of the methods in the above embodiments.

[0126] Specifically, the hydrogen fuel cell system 101 is used to output electrical energy to the outside for emergency power supply operations. For example, the hydrogen fuel cell group is composed of two hydrogen fuel cell reactors with an output power of 130kW in parallel, with a power density of 700W / kg and a service life of up to 30,000h. In the parallel output mode, the two hydrogen fuel cell reactors are required to operate at the same operating voltage and ensure current balance to ensure that the two reactors share the load evenly. In addition, the hydrogen fuel cell group also integrates a monitoring system to detect the working status of the fuel cell in real time, and complete the safety isolation between the two reactors when necessary to ensure the stability of the system operation.

[0127] Furthermore, the hydrogen carrying system 102 is used to store hydrogen energy, including a hydrogen filling system, a hydrogen storage system and a hydrogen supply system. Exemplarily, the hydrogen storage system consists of 16 210L aluminum alloy liner carbon fiber wrapped Class III composite hydrogen cylinders, each of which is equipped with a bottle tail combination valve and a bottle mouth combination valve. The bottle tail combination valve is equipped with a PRD device, which can release hydrogen at a set pressure threshold (35MPa) to achieve over-temperature and over-pressure protection.

[0128] Furthermore, the buffer lithium battery system 103 is used to assist the hydrogen fuel cell system 101 in outputting electrical energy to solve the problem of long startup time of the hydrogen fuel cell system 101. The buffer lithium battery system 103 includes a lithium battery pack, and the lithium battery pack and the hydrogen fuel cell are controlled by an energy management system. The fuel cell vehicle has two working conditions: off-grid power supply and grid-connected power supply. Under the off-grid power supply condition, the fuel cell vehicle outputs AC400V power to the external load, and its power comes from the fuel cell and the lithium battery; when the grid is connected to the power supply, if the mains power is normal, the power output to the external load comes from the power grid, and the inverter power supply PCS is in a backup state. If the mains power fails, the inverter power supply PCS switches from grid-connected to off-grid, and the power output to the external load comes from the fuel cell and the lithium battery.

[0129] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application.

[0130] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

[0131] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0132] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0133] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0134] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0135] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0136] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0137] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

[0138] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A drainage control method for a fuel cell system, characterized in that: Applied to fuel cell vehicles; The method comprises: Extracting features of initial drainage water quality data of the fuel cell system to obtain initial water quality feature data of the fuel cell system; Searching in a preliminary treatment strategy knowledge base according to the initial water quality characteristic data to obtain a preliminary treatment strategy; wherein the preliminary treatment strategy knowledge base stores the corresponding relationship between water quality characteristics and drainage treatment strategies; After the wastewater of the fuel cell system is processed by the preliminary processing strategy, determining intermediate water quality characteristic data of the processed wastewater; Searching in an emergency treatment strategy knowledge base according to the intermediate water quality characteristic data to obtain an emergency treatment strategy; wherein the emergency treatment strategy knowledge base stores a correspondence between water quality characteristics and emergency treatment strategies; The emergency treatment strategy is used to correct the water quality of the treated wastewater, and the corrected wastewater is deeply purified to achieve wastewater recycling of the fuel cell system.

2. The method according to claim 1, characterized in that The preliminary processing strategy knowledge base is constructed by the following method: Performing a first water quality monitoring on historical drainage of the fuel cell system to obtain historical drainage water quality data of the fuel cell system; Classify and judge the historical drainage status of the fuel cell system according to the historical drainage water quality data to obtain a historical drainage processing strategy for the fuel cell system; Processing the drainage of the fuel cell system by the historical drainage processing strategy, and performing a second water quality test on the historically processed drainage to obtain historical intermediate drainage water quality data; If the historical intermediate drainage water quality data does not exceed the preset water quality index range, the preliminary treatment strategy knowledge base is constructed based on the historical drainage water quality data and the historical drainage treatment strategy.

3. The method according to claim 2, characterized in that The constructing of the preliminary treatment strategy knowledge base based on the historical drainage water quality data and the historical drainage treatment strategy includes: Extracting features from the historical drainage water quality data to obtain historical water quality feature data; A corresponding relationship between the historical water quality characteristic data and the historical drainage treatment strategy is constructed and stored in the preliminary treatment strategy knowledge base.

4. The method according to claim 2, characterized in that: The method further comprises: If the historical intermediate drainage water quality data exceeds the preset water quality index range, the historical emergency treatment strategy is initiated; Performing water quality correction on the historical treated drainage using the historical emergency treatment strategy, and performing water quality testing on the historical corrected drainage to obtain historical corrected water quality data; If the historical corrected water quality data does not exceed the preset water quality index range, the emergency treatment strategy knowledge base is constructed based on the historical intermediate drainage water quality data and the historical emergency treatment strategy.

5. The method according to claim 4, characterized in that The emergency treatment strategy knowledge base is constructed based on the historical intermediate drainage water quality data and the historical emergency treatment strategy, including: Extracting features from the historical intermediate drainage water quality data to obtain historical intermediate water quality feature data; A corresponding relationship between the historical intermediate water quality characteristic data and the historical emergency treatment strategy is constructed and stored in the emergency treatment strategy knowledge base.

6. The method according to claim 1, characterized in that The searching in the preliminary treatment strategy knowledge base according to the initial water quality characteristic data to obtain the preliminary treatment strategy includes: Calculate the similarity between the initial water quality characteristic data and the water quality characteristics in the preliminary treatment strategy knowledge base to obtain K historical drainage treatment strategies that meet a preset similarity threshold; Determining an initial treatment strategy with the best historical treatment evaluation result among the K historical drainage treatment strategies; The initial processing strategy is dynamically optimized through a DQN reinforcement learning algorithm to determine the preliminary processing strategy that minimizes energy consumption costs.

7. The method according to claim 1, characterized in that The step of searching in an emergency treatment strategy knowledge base according to the intermediate water quality characteristic data to obtain an emergency treatment strategy includes: Calculate the similarity between the intermediate water quality characteristic data and the water quality characteristics in the emergency treatment strategy knowledge base to obtain a historical emergency treatment strategy; The process parameters of the historical emergency treatment strategy are used as initial parameters, and the process parameters of the historical emergency treatment strategy are dynamically adjusted through a PID control algorithm to obtain adjusted parameters of the emergency treatment strategy.

8. The method according to any one of claims 1 to 7, characterized in that: The initial drainage water quality data includes the drainage pH value; the method further includes: Determine the pressure change data before and after drainage; The drainage time of the fuel cell system is set according to the pressure change data and the drainage pH value.

9. The method according to claim 8, characterized in that The step of setting the drainage time of the fuel cell system according to the pressure change data and the drainage pH value includes: Determining the working state of the anode of the fuel cell system according to the pressure change data and the drainage pH value; If the working state is that the anode is in a liquid water agglomeration fault state, the drainage time is extended.

10. The method according to claim 1, characterized in that The deep purification of the corrected drainage includes: Determining a target nanofiltration membrane separation component according to the water quality test result of the corrected drainage; The corrected wastewater is deeply purified by the target nanofiltration membrane separation component to remove residual trace pollutants and microorganisms.

11. A drainage control system for a fuel cell system, characterized in that: Applied to fuel cell vehicles; The system comprises: An initial feature extraction module, used to extract features from initial drainage water quality data of the fuel cell system to obtain initial water quality feature data of the fuel cell system; A preliminary strategy search module, used to search in a preliminary treatment strategy knowledge base according to the initial water quality characteristic data to obtain a preliminary treatment strategy; wherein the preliminary treatment strategy knowledge base stores the correspondence between water quality characteristics and drainage treatment strategies; an intermediate characteristic determination module, for determining intermediate water quality characteristic data of the treated drainage after the drainage of the fuel cell system is processed by the preliminary processing strategy; An emergency strategy search module, used to search in an emergency treatment strategy knowledge base according to the intermediate water quality characteristic data to obtain an emergency treatment strategy; wherein the emergency treatment strategy knowledge base stores the corresponding relationship between water quality characteristics and emergency treatment strategies; The water quality correction and purification module is used to correct the water quality of the treated wastewater through the emergency treatment strategy and deeply purify the corrected wastewater to achieve wastewater recycling of the fuel cell system.

12. A fuel cell vehicle, characterized in that: The fuel cell vehicle includes an electric vehicle chassis and a container, wherein the container includes a hydrogen fuel cell system, a hydrogen storage system, a buffer lithium battery system, a power inverter system, an air conditioning system and an air intake and exhaust system, wherein the control device of the hydrogen fuel cell system executes the method as described in any one of claims 1 to 10.

Images