A fuel cell engine control method and system

Abstract

The application relates to the technical field of control systems and discloses a fuel cell engine control method and system, which comprises the following steps: performing noise cleaning on a real-time parameter sequence of a fuel cell engine to obtain a standard parameter sequence of the fuel cell engine; performing situation simulation on the running state of the fuel cell engine based on the standard parameter sequence to obtain a change trend of the fuel cell engine; performing dynamic trend coupling calibration on the standard parameter sequence based on the change trend to obtain an efficiency evaluation value of the fuel cell engine; performing traceability decision mapping on the efficiency evaluation value based on historical running mode data of the fuel cell engine to obtain a control decision scheme of the fuel cell engine; and performing encoding mapping on the control decision scheme to obtain a control decision instruction of the fuel cell engine. The application can improve the control efficiency of the fuel cell engine.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of control systems, in particular to a fuel cell engine control method and system. BACKGROUND

[0002] As the core power device in the field of new energy, the running stability and control precision of the fuel cell engine directly affect the efficiency output of the overall system. However, the existing fuel cell engine control technology has obvious defects in the real-time parameter processing link, which makes it difficult to effectively eliminate the parameter noise caused by various interference factors in the running process, so that the accuracy of the obtained real-time parameter sequence is insufficient, and reliable data support cannot be provided for subsequent running state analysis. This problem directly leads to deviation in the judgment of the engine running state, making it difficult to accurately capture its dynamic change characteristics, thereby affecting the timeliness and adaptability of the control strategy, and restricting the improvement of the overall control efficiency.

[0003] At the same time, the existing technology lacks systematic design in the efficiency evaluation and decision generation link. When evaluating the efficiency of the engine, the change trend of the running state is not fully combined for dynamic calibration, resulting in deviation between the efficiency evaluation value and the actual running condition; when formulating the control decision scheme, the reference value of the historical running mode data is often ignored, and the accurate mapping relationship between the efficiency evaluation and the control strategy cannot be established through trace analysis, so that the generated control decision scheme lacks pertinence. In addition, part of the control technology lacks strict logical integrity verification in the instruction generation stage, which may lead to execution vulnerabilities in the control instruction, further reducing the control effect, and cannot meet the actual needs of efficient and stable running of the fuel cell engine. Therefore, how to improve the control efficiency of the fuel cell engine has become a problem to be solved. SUMMARY

[0004] The present application provides a fuel cell engine control method and system to solve the problems raised in the background art.

[0005] To achieve the above-mentioned purpose, the present application provides a fuel cell engine control method, comprising:

[0006] S1, performing noise cleaning on the real-time parameter sequence of the fuel cell engine to obtain a standard parameter sequence of the fuel cell engine;

[0007] S2, based on the standard parameter sequence, simulating the situation of the running state of the fuel cell engine to obtain the change trend of the fuel cell engine;

[0008] S3, based on the change trend, performing dynamic trend coupling calibration on the standard parameter sequence to obtain the efficiency evaluation value of the fuel cell engine;

[0009] S4, mapping the efficiency evaluation value to a traceability decision based on historical operation mode data of the fuel cell engine to obtain a control decision scheme of the fuel cell engine;

[0010] S5, encoding mapping the control decision scheme to obtain a control decision instruction of the fuel cell engine.

[0011] In a preferred embodiment, the noise cleaning of the real-time parameter sequence of the fuel cell engine to obtain the standard parameter sequence of the fuel cell engine comprises:

[0012] Obtaining a real-time parameter sequence of a fuel cell engine;

[0013] Detecting abnormal points of the real-time parameter sequence to obtain a noise point identification sequence of the fuel cell engine;

[0014] Based on the noise point identification sequence, data repair is performed on the real-time parameter sequence to obtain a repaired parameter sequence of the fuel cell engine;

[0015] Eliminating high-frequency fluctuation parameters of the repaired parameter sequence to obtain a standard parameter sequence of the fuel cell engine.

[0016] In a preferred embodiment, the state simulation of the operating state of the fuel cell engine based on the standard parameter sequence to obtain the change trend of the fuel cell engine comprises:

[0017] Extracting key parameters in the standard parameter sequence representing the operating state of the fuel cell engine to obtain an operating state parameter of the fuel cell engine;

[0018] Quantifying the state index of the operating state parameter to obtain a real-time state vector of the operating state parameter;

[0019] Based on a preset dynamic evolution strategy, forward simulation is performed on the real-time state vector to obtain a predicted state of the fuel cell engine;

[0020] Trend fitting is performed on the predicted state to obtain a change trend of the fuel cell engine.

[0021] In a preferred embodiment, the trend fitting of the predicted state to obtain the change trend of the fuel cell engine comprises:

[0022] Analyzing the predicted state to generate prediction information of the predicted state;

[0023] Dimension reconstruction is performed on the prediction information to obtain a predicted state vector of the predicted state;

[0024] trend-quantizing the predicted state vector to obtain a comprehensive trend intensity value of the fuel cell engine, wherein a calculation formula of the comprehensive trend intensity value is as follows:

[0025] ;

[0026] wherein, denotes the comprehensive trend intensity value, denotes a quantity of the predicted state vector, denotes an i-th predicted state vector of the fuel cell engine, denotes a preset reference state vector, denotes a weight factor of the i-th predicted state vector of the fuel cell engine, denotes a norm of a difference between two vectors;

[0027] According to a positive or negative and a size of the comprehensive trend intensity value, an evolution direction and a severity of the performance of the fuel cell engine are determined, and a change trend of the fuel cell engine is generated.

[0028] In a preferred embodiment, the dynamic trend coupling calibration of the standard parameter sequence based on the change trend to obtain the efficiency evaluation value of the fuel cell engine comprises:

[0029] degree discrimination of a key parameter of the standard parameter sequence based on the change trend to obtain a calibration strategy of the key parameter;

[0030] calculating a dynamic calibration weight of the key parameter according to the calibration strategy, wherein a calculation formula of the dynamic calibration weight is as follows:

[0031] ;

[0032] wherein, denotes a dynamic calibration weight of an i-th key parameter in the standard parameter sequence, denotes a total number of key parameters in the standard parameter sequence, denotes a trend intensity value corresponding to the i-th key parameter in the standard parameter sequence, denotes a trend intensity value corresponding to the i-th key parameter in the standard parameter sequence, denotes a preset trend sensitivity coefficient, denotes an exponential function;

[0033] ​​​​​Based on the dynamic calibration weights, the parameters of the standard parameter sequence are weighted and fused to obtain the calibration parameters of the fuel cell engine;

[0034] The calibration parameters are normalized to obtain the efficiency evaluation value of the fuel cell engine.

[0035] In a preferred embodiment, the calibration parameter is calculated using the following formula:

[0036] ;

[0037] In the formula, This indicates the calibration parameters of the fuel cell engine. This represents the total number of key parameters in the standard parameter sequence. Indicates the first in the standard parameter sequence Dynamic calibration weights for each parameter, Indicates the first in the standard parameter sequence The values ​​of the parameters, This represents the weighted average of the parameters in the standard parameter sequence. This indicates the preset fusion adjustment coefficient.

[0038] In a preferred embodiment, the step of performing abductive decision mapping on the efficiency evaluation value based on the historical operating mode data of the fuel cell engine to obtain the control decision scheme of the fuel cell engine includes:

[0039] Modal classification is performed on the historical operating mode data to obtain the historical operating modes of the fuel cell engine;

[0040] By matching the efficiency evaluation value with the historical operating mode, the historical cases of the fuel cell engine are obtained;

[0041] Based on the historical control strategies in the historical cases, the efficiency evaluation value is represented in a coordinated manner to obtain the preliminary control decision of the fuel cell engine;

[0042] Based on the current constraints of the fuel cell engine, the preliminary control decision is modified to obtain a control decision scheme for the fuel cell engine.

[0043] In a preferred embodiment, the step of matching the efficiency assessment value with the historical operating modes to obtain historical cases of the fuel cell engine includes:

[0044] Based on the efficiency evaluation value, obtain the real-time operating parameter vector of the fuel cell engine and the historical parameter vector of the historical operating mode;

[0045] Calculate the similarity between the real-time running parameter vector and the historical parameter vector, wherein the formula for calculating the similarity is as follows:

[0046] ;

[0047] In the formula, This indicates that the real-time running parameter vector is related to the first... The similarity of historical operating patterns This represents the dimension of the parameter vector. The first element of the real-time running parameter vector represents the... One portion, Indicating the first in the historical operation mode The th historical parameter vector of the th One component;

[0048] Historical cases with similarity higher than a preset matching threshold are used as historical cases of the fuel cell engine.

[0049] In a preferred embodiment, encoding and mapping the control decision scheme to obtain the control decision command for the fuel cell engine includes:

[0050] The control decision scheme is analyzed in a structured manner to obtain the decision elements of the fuel cell engine;

[0051] Based on the aforementioned decision elements, the control decision scheme is matched and mapped with the controller of the fuel cell engine to obtain the control logic unit of the fuel cell engine.

[0052] According to the preset communication protocol, the control logic units are organized and packaged in sequence to generate the original control commands for the fuel cell engine;

[0053] The original control commands are logically verified to obtain the control decision commands for the fuel cell engine.

[0054] To address the above problems, the present invention also provides a fuel cell engine control system, the system comprising:

[0055] The data preprocessing module is used to clean the noise from the real-time parameter sequence of the fuel cell engine to obtain the standard parameter sequence of the fuel cell engine.

[0056] The situation prediction module is used to simulate the operating state of the fuel cell engine based on the standard parameter sequence, and obtain the changing trend of the fuel cell engine.

[0057] A performance evaluation and calibration module is configured to perform dynamic trend coupling calibration on the standard parameter sequence based on the change trend, so as to obtain an efficiency evaluation value of the fuel cell engine;

[0058] An intelligent decision-making module is configured to perform traceable decision mapping on the efficiency evaluation value based on historical operation mode data of the fuel cell engine, so as to obtain a control decision scheme of the fuel cell engine;

[0059] An instruction generation module is configured to perform encoding mapping on the control decision scheme, so as to obtain a control decision instruction of the fuel cell engine.

[0060] Compared with the prior art, the present application has the following beneficial effects:

[0061] 1. The present application performs noise cleaning on the real-time parameter sequence of the fuel cell engine, detects abnormal points, repairs data and eliminates high-frequency fluctuations to obtain a standard parameter sequence, and then performs dynamic trend coupling calibration in combination with the change trend of the operation state, weights and fuses the key parameters according to the dynamic calibration weight, and normalizes the efficiency evaluation value, so as to avoid parameter noise interference and static evaluation deviation, ensure that the efficiency evaluation is in line with the actual operation, and provide high-quality data support for subsequent control decision-making.

[0062] 2. The present application performs traceable decision mapping on the efficiency evaluation value based on historical operation mode data, matches similar historical cases, corrects the preliminary decision in combination with the current constraint, generates a targeted control scheme, analyzes the control decision scheme, matches the controller and checks the logical integrity, generates a reliable control instruction, reduces decision deviation and instruction execution vulnerabilities, makes the control decision more adaptive to the actual demand of the engine, and effectively improves the control efficiency and operation stability of the fuel cell engine. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 A flowchart of a fuel cell engine control method provided by an embodiment of the present application is shown in the figure;

[0064] Figure 2 A functional module diagram of a fuel cell engine control system provided by an embodiment of the present application is shown in the figure;

[0065] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0066] It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0067] The embodiment of the present application provides a fuel cell engine control method. The execution subject of the fuel cell engine control method includes but is not limited to at least one of electronic devices such as a server and a terminal which can be configured to execute the method provided by the embodiment of the present application. In other words, the fuel cell engine control method can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be a stand-alone server, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks (CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0068] Referring to Figure 1 Fig. 1 is a flowchart of a fuel cell engine control method provided by an embodiment of the present application. In the embodiment, the fuel cell engine control method includes the following steps.

[0069] S1, performing noise cleaning on a real-time parameter sequence of a fuel cell engine to obtain a standard parameter sequence of the fuel cell engine;

[0070] In the embodiment of the present application, the noise cleaning on the real-time parameter sequence of the fuel cell engine to obtain the standard parameter sequence of the fuel cell engine includes the following steps.

[0071] Obtaining a real-time parameter sequence of a fuel cell engine;

[0072] Detecting an abnormal point in the real-time parameter sequence to obtain a noise point identification sequence of the fuel cell engine;

[0073] Based on the noise point identification sequence, performing data repair on the real-time parameter sequence to obtain a repaired parameter sequence of the fuel cell engine;

[0074] Eliminating high-frequency fluctuation parameters in the repaired parameter sequence to obtain a standard parameter sequence of the fuel cell engine.

[0075] Specifically, the whole process is carried out around the parameter processing of the fuel cell engine, and first, the real-time parameter sequence of the fuel cell engine is obtained, and then the abnormal points in the sequence are detected to obtain a noise point identification sequence.

[0076] Specifically, the real-time parameter sequence is repaired according to the noise point identification sequence to obtain a repaired parameter sequence, and finally, the high-frequency fluctuation parameters in the repaired parameter sequence are eliminated to obtain a standard parameter sequence.

[0077] Further, when acquiring the real-time parameter sequence, temperature sensors, pressure sensors, current sensors and voltage sensors are installed at key operating positions of the fuel cell engine, and all sensors continuously collect real-time values of corresponding parameters at fixed time intervals.

[0078] Further, during the collection process, the parameter values recorded at each time point are ensured to fully correspond to the actual operating state of the engine, and then all collected parameter values are arranged in chronological order to form the real-time parameter sequence.

[0079] Further, when detecting abnormal points in the real-time parameter sequence, the reasonable value range of each parameter is determined based on the design operating standard of the fuel cell engine and the parameter data accumulated during normal operating state in the past period of time.

[0080] Further, each parameter value in the real-time parameter sequence is checked one by one, and if a parameter value exceeds the corresponding reasonable range, the position of the value in the sequence is marked as "abnormal", and if it is within the reasonable range, it is marked as "normal".

[0081] Further, all the marks are arranged in chronological order of the real-time parameter sequence to obtain a noise point identification sequence.

[0082] Further, when repairing data based on the noise point identification sequence, the positions marked as "abnormal" and their corresponding abnormal values in the real-time parameter sequence are found by comparing the noise point identification sequence, and for each abnormal value, the normal value corresponding to the position before it marked as "normal" and the normal value corresponding to the position after it marked as "normal" are found.

[0083] Further, the average value obtained by adding the two normal values and dividing by 2 is used to replace the corresponding abnormal value in the real-time parameter sequence, and after all positions marked as "abnormal" are replaced, a repaired parameter sequence is obtained.

[0084] Further, when eliminating high-frequency fluctuation parameters in the repaired parameter sequence, the size of the sliding window is determined, which should contain a plurality of consecutive parameter values. Starting from the first parameter value in the repaired parameter sequence, the average value of the parameter values covered by the sliding window is calculated, and this average value is used as the value at the corresponding position in the new sequence.

[0085] Further, the sliding window is moved one position forward to cover the next consecutive parameter values in the repaired parameter sequence, and the operation of calculating the average value is repeated until the sliding window moves to the last parameter value in the repaired parameter sequence. All calculated average values are arranged in chronological order to obtain a standard parameter sequence.

[0086] In general, by installing multiple sensors at key operating positions of the fuel cell engine, collecting parameter values at fixed time intervals, and sorting them by time, a real-time parameter sequence of the engine can be obtained.

[0087] In general, by determining the reasonable range of each parameter based on the design operating standards and historical normal operating parameters of the fuel cell engine, checking the values of the real-time parameter sequence one by one, and marking the state, a noise point identification sequence of the engine can be obtained.

[0088] In general, by comparing the noise point identification sequence to find abnormal values in the real-time parameter sequence, and replacing them with the average of the normal values before and after them, a repaired parameter sequence of the engine can be obtained.

[0089] In general, by setting a sliding window and sequentially calculating the average of the repaired parameter sequence values within the window, a standard parameter sequence of the engine can be obtained.

[0090] S2, based on the standard parameter sequence, simulating the state of the fuel cell engine, obtaining the change trend of the fuel cell engine;

[0091] In the embodiment of the present application, based on the standard parameter sequence, the state of the fuel cell engine is simulated, and the change trend of the fuel cell engine is obtained, which includes:

[0092] Extracting the key parameters in the standard parameter sequence that represent the operating state of the fuel cell engine, obtaining the operating state parameters of the fuel cell engine;

[0093] Quantifying the state index of the operating state parameters, obtaining the real-time state vector of the operating state parameters;

[0094] Based on the preset dynamic evolution strategy, the real-time state vector is simulated forwardly, and the predicted state of the fuel cell engine is obtained;

[0095] Trend fitting is performed on the predicted state to obtain the change trend of the fuel cell engine.

[0096] The trend fitting of the predicted state to obtain the change trend of the fuel cell engine includes:

[0097] Analyzing the predicted state to generate prediction information of the predicted state;

[0098] The prediction information is dimensionally reconstructed to obtain the prediction state vector of the predicted state;

[0099] The predicted state vector is trend-quantized to obtain the comprehensive trend intensity value of the fuel cell engine, wherein the comprehensive trend intensity value is calculated using the following formula:

[0100] ;

[0101] In the formula, This represents the overall trend strength value. This indicates the number of predicted state vectors. Indicates the fuel cell engine's first A predicted state vector, This represents the preset reference state vector. Indicates the fuel cell engine's first Weight factors for each predicted state vector, The norm representing the difference between two vectors;

[0102] Based on the sign and magnitude of the comprehensive trend strength value, the evolution direction and severity of the fuel cell engine performance are determined, and the change trend of the fuel cell engine is generated.

[0103] Specifically, the entire process revolves around the state analysis of the fuel cell engine. First, key parameters characterizing its operating state are extracted from the standard parameter sequence to obtain operating state parameters. Then, the operating state parameters are quantified by state indices to obtain the real-time state vector.

[0104] Specifically, the real-time state vector is forward-simulated based on a preset dynamic evolution strategy to obtain the predicted state, and finally the predicted state is trend-fitted to obtain the change trend.

[0105] Furthermore, when extracting key parameters, the four types of parameters that directly reflect the engine's chemical reaction efficiency, gas supply stability, energy output capability, and membrane module working status are first identified as key parameter types: reaction temperature, hydrogen intake pressure, output current, and electrolyte membrane humidity.

[0106] Furthermore, all values ​​corresponding to these four parameter types are identified one by one from the standard parameter sequence. According to the classification method of reaction temperature value group, hydrogen inlet pressure value group, output current value group, and electrolyte membrane humidity value group, the identified values ​​are assigned to the corresponding groups. After all the corresponding values ​​have been assigned, the set containing these four value groups is the operating status parameter of the fuel cell engine.

[0107] Further, when quantifying the state indicators, first, a specific quantification rule is formulated for each value group in the operating state parameters, such as different temperatures corresponding to different quantification values in the reaction temperature value group, different pressures corresponding to different quantification values in the hydrogen inlet pressure value group, different currents corresponding to different quantification values in the output current value group, and different humidities corresponding to different quantification values in the electrolyte membrane humidity value group.

[0108] Further, according to these rules, the values in each value group are converted into corresponding quantification values one by one, and then all the converted quantification values are arranged in a fixed order of reaction temperature quantification value, hydrogen inlet pressure quantification value, output current quantification value, and electrolyte membrane humidity quantification value to form an ordered quantification value combination, which is the real-time state vector of the operating state parameters.

[0109] Further, when implementing the forward simulation, the preset dynamic evolution strategy includes time interval setting of evolution step and parameter variation rule, the time interval setting is that each hour is taken as an evolution step, and the parameter variation rule stipulates that the variation amplitude of each parameter quantification value in each evolution step does not exceed one unit, and the variation direction is determined according to the variation trend of the parameters in the previous three hours corresponding to the real-time state vector.

[0110] Further, if the quantification value of a certain parameter continues to rise in the previous three hours, the quantification value of the parameter continues to rise in this evolution step, if it continues to fall, it continues to fall, and if there is no obvious trend, it remains unchanged.

[0111] Further, taking the real-time state vector as the initial data, the parameter quantification values after the first evolution step are calculated according to the set evolution step and variation rule to form the simulation vector at the first time, and then the simulation vector at the second time is calculated repeatedly based on the simulation vector at the first time, and so on, to continuously calculate the simulation vectors corresponding to the next six evolution steps, which together constitute the predicted state of the fuel cell engine.

[0112] Further, when developing the trend fitting, the evolution step time corresponding to each simulation vector in the predicted state is taken as the horizontal axis coordinate, and the horizontal axis coordinates are sequentially marked as one hour later, two hours later, three hours later, four hours later, five hours later, and six hours later.

[0113] Further, the quantification values of each parameter in each simulation vector are taken as the vertical axis coordinates, for the reaction temperature parameter, each horizontal axis coordinate and the corresponding reaction temperature quantification value form a coordinate point, and after sequentially marking these coordinate points on the plane and connecting adjacent coordinate points with a straight line to form a broken line, the overall trend of the broken line is observed to determine the variation trend of the reaction temperature parameter.

[0114] Further, if the broken line continues to go up, it is an upward trend, if it continues to go down, it is a downward trend, and if there is no obvious rise and fall, it is a stable trend. In the same way, the hydrogen inlet pressure, output current, and electrolyte membrane humidity parameters are marked with coordinate points, drawn with broken lines, and determined in terms of trend. Finally, the trend determination results of the four types of parameters are summarized to obtain the change trend of the fuel cell engine.

[0115] Specifically, the entire process revolves around the determination of the comprehensive trend and change trend of the fuel cell engine. First, prediction information is generated from the prediction state, and then a prediction state vector is constructed.

[0116] Specifically, the comprehensive trend intensity value is calculated, and its source, significance, and trend are explained in combination with the formula. Finally, the performance evolution direction and severity are determined based on the comprehensive trend intensity value to obtain the change trend.

[0117] Further, when generating the prediction information, first extract the time markers corresponding to each simulation vector in the prediction state. The time markers are one hour later, two hours later, three hours later, four hours later, five hours later, and six hours later, respectively. Then, for each simulation vector corresponding to each time marker, extract the reaction temperature quantitative value, hydrogen inlet pressure quantitative value, output current quantitative value, and electrolyte membrane humidity quantitative value.

[0118] Further, each time marker and the corresponding four types of parameter quantitative values are described in words, such as "one hour later, the reaction temperature quantitative value is a certain value, the hydrogen inlet pressure quantitative value is a certain value, the output current quantitative value is a certain value, and the electrolyte membrane humidity quantitative value is a certain value". All such word descriptions corresponding to the time markers are sequentially organized and summarized to form a complete set of words, which is the prediction information of the prediction state.

[0119] Further, when constructing the prediction state vector, first extract the reaction temperature quantitative value, hydrogen inlet pressure quantitative value, output current quantitative value, and electrolyte membrane humidity quantitative value corresponding to each time marker from the word description of the prediction information. Combine the four types of quantitative values corresponding to each time marker in the order of "reaction temperature quantitative value, hydrogen inlet pressure quantitative value, output current quantitative value, and electrolyte membrane humidity quantitative value" to form a sub-vector.

[0120] Further, arrange the sub-vectors corresponding to all time markers in the order of time markers to form an ordered vector structure containing six sub-vectors, which is the prediction state vector of the prediction state.

[0121] Further, when calculating the comprehensive trend intensity value, first extract the first sub-vector and the last sub-vector from the prediction state vector. The first sub-vector corresponds to one hour later, and the last sub-vector corresponds to six hours later.

[0122] Further, the difference of the quantized values of the same parameter in the two types of sub-vectors is calculated, i.e. the difference of the quantized values of the reaction temperature is the quantized value of the reaction temperature of the last sub-vector minus the quantized value of the reaction temperature of the first sub-vector, the difference of the quantized values of the hydrogen inlet pressure is the quantized value of the hydrogen inlet pressure of the last sub-vector minus the quantized value of the hydrogen inlet pressure of the first sub-vector, the difference of the quantized values of the output current is the quantized value of the output current of the last sub-vector minus the quantized value of the output current of the first sub-vector, and the difference of the quantized values of the electrolyte membrane humidity is the quantized value of the electrolyte membrane humidity of the last sub-vector minus the quantized value of the electrolyte membrane humidity of the first sub-vector.

[0123] Further, the difference of the quantized values of the four parameters is added to obtain a difference sum, and the difference sum is divided by four to obtain the comprehensive trend intensity value of the fuel cell engine.

[0124] Further, regarding the formula of the comprehensive trend intensity value, the comprehensive trend intensity value is the final calculation result; the number of prediction state vectors is determined by the number of actually generated prediction state vectors; the th prediction state vector is obtained by sequentially extracting each vector from the prediction state vectors; the preset reference state vector is a vector set in advance according to the ideal or standard operating state of the fuel cell engine; the weight factor of the th prediction state vector is assigned according to the time or importance degree corresponding to each prediction state vector, for example, the weight is larger when the time is closer; and the norm of the difference between the two vectors is obtained by calculating the difference between the values of the corresponding positions of the two vectors, and then performing Euclidean norm operation on the differences, that is, the square root of the sum of the squares of the differences.

[0125] Further, the formula obtains the comprehensive trend intensity value by multiplying the norm of the difference between each prediction state vector and the reference state vector by the corresponding weight factor, summing them up, and then dividing by the number of prediction state vectors , which comprehensively measures the overall deviation degree of all prediction state vectors relative to the reference state vector, so as to obtain the comprehensive trend intensity value reflecting the comprehensive trend intensity of the fuel cell engine.

[0126] Further, when the prediction state vectors as a whole are close to the reference state vector, the overall deviation is small, the value obtained by dividing the sum by is smaller, indicating that the comprehensive trend intensity is weak, and the engine state is closer to the reference state.

[0127] Further, when the prediction state vectors as a whole are far away from the reference state vector, ​The whole is too large, sum after dividing The value is greater, the comprehensive trend intensity is strong, and the engine state deviates from the reference state farther, that is The greater the value, the more significant the deviation trend of the fuel cell engine state relative to the reference state, The smaller the value, the less significant the deviation trend.

[0128] Further, when determining the change trend of the fuel cell engine, first judge the positive and negative of the comprehensive trend intensity value. If the comprehensive trend intensity value is greater than zero, the evolution direction of the performance of the fuel cell engine is performance improvement.

[0129] Further, if the comprehensive trend intensity value is less than zero, the evolution direction is performance decline; if the comprehensive trend intensity value is equal to zero, the evolution direction is performance stability.

[0130] Further, further judge the absolute value of the comprehensive trend intensity value. If the absolute value is less than or equal to 1, the degree of performance evolution is slight change; if the absolute value is greater than 1 and less than or equal to 2, the degree of performance evolution is moderate change; if the absolute value is greater than 2, the degree of performance evolution is significant change. Finally, the determined evolution direction and degree of change are combined to form a complete conclusion in words to obtain the change trend of the fuel cell engine.

[0131] In summary, by determining the reaction temperature, hydrogen inlet pressure, output current, and electrolyte membrane humidity as key parameter types, selecting corresponding values from the standard parameter sequence and classifying them into corresponding groups, the running state parameters of the fuel cell engine can be obtained.

[0132] In summary, by formulating exclusive quantification rules for each value group, converting each value in the running state parameters into a quantification value and arranging them in a fixed order, the real-time state vector of the running state parameters can be obtained.

[0133] In summary, by calculating the simulation vectors of multiple evolution steps in the future based on the preset dynamic evolution strategy containing evolution step and parameter change rule, and taking the real-time state vector as the initial data, the predicted state of the fuel cell engine can be obtained.

[0134] In summary, by setting the x-axis and y-axis coordinates, marking the coordinate points of each parameter in the predicted state, drawing the broken line and judging the trend, and summarizing the results, the change trend of the fuel cell engine can be obtained.

[0135] In summary, by extracting the time markers of each simulation vector in the predicted state, and combining the four types of parameter quantification values of the corresponding simulation vector to describe in words and summarize, the prediction information of the predicted state can be generated.

[0136] ​In summary, by extracting the quantized values ​​of the four types of parameters corresponding to each time marker from the prediction information and combining them into sub-vectors in a fixed order, and then arranging the sub-vectors in chronological order, the prediction state vector of the prediction state can be obtained.

[0137] In summary, by extracting the first and last sub-vectors from the predicted state vector, calculating the difference in quantized values ​​of the same parameters, summing them, and then averaging them, the comprehensive trend strength value of the fuel cell engine can be obtained.

[0138] In summary, by clarifying the sources of each parameter in the comprehensive trend strength value formula, explaining the significance of the formula in measuring the overall deviation of the predicted state vector from the reference state vector, and illustrating... The relationship between the value and the degree of deviation of the engine state clearly demonstrates the effect of the formula.

[0139] In summary, by determining the direction of performance evolution by judging the sign of the comprehensive trend strength value, determining the degree of evolution by judging its absolute value, and combining the two to form a textual conclusion, the changing trend of fuel cell engines can be obtained.

[0140] S3. Based on the changing trend, perform dynamic trend coupling calibration on the standard parameter sequence to obtain the efficiency evaluation value of the fuel cell engine;

[0141] In this embodiment of the invention, the step of performing dynamic trend coupling calibration on the standard parameter sequence based on the changing trend to obtain the efficiency evaluation value of the fuel cell engine includes:

[0142] Based on the aforementioned trend, the degree of influence of key parameters in the standard parameter sequence is determined, and a calibration strategy for the key parameters is obtained.

[0143] Based on the calibration strategy, the dynamic calibration weights of the key parameters are calculated, wherein the calculation formula for the dynamic calibration weights is as follows:

[0144] ;

[0145] In the formula, Indicates the first in the standard parameter sequence Dynamic calibration weights for key parameters, This represents the total number of key parameters in the standard parameter sequence. Indicates the first in the standard parameter sequence The trend strength values ​​corresponding to the key parameters Indicates the first in the standard parameter sequence The trend strength values ​​corresponding to the key parameters This represents the preset trend sensitivity coefficient. Represents an exponential function;

[0146] Based on the dynamic calibration weights, the parameters of the standard parameter sequence are weighted and fused to obtain the calibration parameters of the fuel cell engine;

[0147] The calibration parameters are normalized to obtain the efficiency evaluation value of the fuel cell engine.

[0148] The formula for calculating the calibration parameters is as follows:

[0149] ;

[0150] In the formula, This indicates the calibration parameters of the fuel cell engine. This represents the total number of key parameters in the standard parameter sequence. Indicates the first in the standard parameter sequence Dynamic calibration weights for each parameter, Indicates the first in the standard parameter sequence The values ​​of the parameters, This represents the weighted average of the parameters in the standard parameter sequence. This indicates the preset fusion adjustment coefficient.

[0151] Specifically, the entire process revolves around the parameter calibration and efficiency evaluation of fuel cell engines, always taking the changing trend as the core basis, and successively advancing the determination of key parameter calibration strategies, the accurate calculation of dynamic calibration weights, and the scientific acquisition of calibration parameters, ultimately generating a quantifiable evaluation value of engine efficiency. Each step is deeply integrated with the analysis of changing trends and is gradually implemented through clear and explicit calculation logic or operating rules.

[0152] Specifically, based on the changing trends of fuel cell engines, a detailed analysis was conducted on several key parameters in the standard parameter sequence, including reaction temperature, hydrogen inlet pressure, output current, and electrolyte membrane humidity. This analysis explored the close correlation between these parameters and the changing trends, determining how fluctuations in each key parameter would affect the trends. If a fluctuation in a certain key parameter caused a significant change in the changing trend, that key parameter was identified as requiring focused calibration.

[0153] Specifically, based on the degree of influence of each key parameter on the trend of change, specific calibration directions and adjustment range requirements are formulated for different key parameters. The calibration directions and adjustment range requirements corresponding to all key parameters are systematically organized and summarized to form a complete set of rules, which is the calibration strategy for key parameters.

[0154] Further, when calculating the dynamic calibration weight of the key parameter, on the one hand, the initial weight of each key parameter is assigned by strictly checking the calibration direction and adjustment amplitude requirement of each key parameter in the calibration strategy. The more urgent the calibration requirement is, the higher the initial weight is set.

[0155] Further, the initial weight is dynamically adjusted in combination with the proximity of the current value of the key parameter in the standard parameter sequence to the calibration target value. If the current value is close to the calibration target value, it indicates that the current state of the parameter is good, and the weight is appropriately reduced. If the current value is far from the calibration target value, it indicates that the current state of the parameter deviates greatly, and the weight is appropriately increased.

[0156] Further, the dynamic calibration weight is calculated by formula: first, the index of the trend intensity value corresponding to each key parameter is calculated. These trend intensity values are obtained from the change trend analysis process, and the preset trend sensitivity coefficient is set according to the inherent characteristics of the fuel cell engine or long-term operation experience. The exponential function is calculated according to the exponential operation rule with natural constant as the base.

[0157] Further, the index of the trend intensity value corresponding to each key parameter is divided by the sum of the indexes of the trend intensity values of all key parameters, so as to reasonably allocate the weight of subsequent calibration according to the trend intensity of the key parameter.

[0158] Further, the more significant the trend intensity of the key parameter is to the change trend, the greater the dynamic calibration weight is. When the trend intensity value of the key parameter is greater, the index result calculated is also greater, and the dynamic calibration weight will also increase accordingly, and the importance of subsequent calibration of the parameter will also be correspondingly improved. After a series of operations such as initial allocation, dynamic adjustment and formula calculation, the final dynamic calibration weight of each key parameter is obtained.

[0159] Further, when calculating the calibration parameter of the fuel cell engine, on the one hand, the value of each key parameter in the standard parameter sequence is accurately obtained, and the dynamic calibration weight corresponding to each key parameter is also obtained. The value of each key parameter is multiplied by the dynamic calibration weight corresponding thereto, and then the weighted values of all key parameters are summed.

[0160] Further, the calibration parameter is calculated by formula, which is divided into two parts: the first part is the sum of the product of each parameter value and its dynamic calibration weight, wherein the parameter value is directly extracted from the standard parameter sequence, and the dynamic calibration weight comes from the calculation result of the previous dynamic calibration weight. The second part is the square root of the weighted sum of the weighted square sum of the deviation of each parameter value from the weighted average value multiplied by the fusion adjustment coefficient, which is set in advance according to actual needs or industry experience; the weighted average value is calculated by multiplying the value of each parameter by its dynamic calibration weight and then summing; the square root operation is the square root operation of the internal square sum according to the operation rule of the square root in mathematics.

[0161] Further, such a calculation method comprehensively considers the influence of the weighted fusion effect and the dispersion degree of the parameter on the calibration. The greater the dispersion degree of the parameter, the greater the value of the second part, and the greater the final calibration parameter. The greater the dynamic calibration weight or parameter value of a certain parameter, the greater the contribution of the first part to the parameter, and the calibration parameter will tilt towards the influence direction of the parameter. The whole will adjust with the change of the dynamic calibration weight, parameter value and dispersion degree of the parameter, so as to reflect more accurate calibration requirements. Through the calculation of the two methods, the calibration parameter of the fuel cell engine is finally obtained.

[0162] Further, when obtaining the efficiency evaluation value of the fuel cell engine, it is first determined that the numerical range of the efficiency evaluation of the fuel cell engine is 0 to 100, which represents the interval from the lowest level to the highest level of efficiency.

[0163] Further, through analysis or theoretical derivation of a large amount of historical data, the maximum and minimum values of the calibration parameter are found.

[0164] Further, the current value of the calibration parameter is subtracted from the minimum value, and the result is divided by the difference between the maximum value and the minimum value. Finally, the calculation result is multiplied by 100, so as to map the calibration parameter to the range of 0 to 100, and the obtained value is the evaluation value that can quantify the efficiency of the fuel cell engine.

[0165] In summary, by comprehensively analyzing the close degree of the correlation between the key parameters and the change trend, and formulating specific calibration direction and adjustment amplitude requirement for each key parameter, the calibration strategy of the key parameter can be formed.

[0166] In summary, by combining the calibration strategy to reasonably allocate and dynamically adjust the initial weight, and according to the trend intensity value and other factors to calculate the formula, the dynamic calibration weight of the key parameter can be obtained.

[0167] In summary, the calibration parameters for fuel cell engines can be obtained by weighted summation of key parameter values ​​and dynamic calibration weights, as well as by formula calculations that take into account factors such as parameter dispersion.

[0168] In summary, by determining the numerical range of efficiency assessment and performing scientific mapping calculations on the calibration parameters, the efficiency assessment value of the fuel cell engine can be obtained.

[0169] S4. Based on the historical operating mode data of the fuel cell engine, perform a retrospective decision mapping on the efficiency evaluation value to obtain the control decision scheme of the fuel cell engine;

[0170] In this embodiment of the invention, the step of performing abductive decision mapping on the efficiency evaluation value based on the historical operating mode data of the fuel cell engine to obtain the control decision scheme of the fuel cell engine includes:

[0171] Modal classification is performed on the historical operating mode data to obtain the historical operating modes of the fuel cell engine;

[0172] By matching the efficiency evaluation value with the historical operating mode, the historical cases of the fuel cell engine are obtained;

[0173] Based on the historical control strategies in the historical cases, the efficiency evaluation value is represented in a coordinated manner to obtain the preliminary control decision of the fuel cell engine;

[0174] Based on the current constraints of the fuel cell engine, the preliminary control decision is modified to obtain a control decision scheme for the fuel cell engine.

[0175] The step of matching the efficiency evaluation value with the historical operating modes to obtain historical cases of the fuel cell engine includes:

[0176] Based on the efficiency evaluation value, obtain the real-time operating parameter vector of the fuel cell engine and the historical parameter vector of the historical operating mode;

[0177] Calculate the similarity between the real-time running parameter vector and the historical parameter vector, wherein the formula for calculating the similarity is as follows:

[0178] ;

[0179] In the formula, This indicates that the real-time running parameter vector is related to the first... The similarity of historical operating patterns This represents the dimension of the parameter vector. a first component of the real-time operation parameter vector, a first component of the real-time operation parameter vector, a first component of the real-time operation parameter vector, a first component of the real-time operation parameter vector, a first component of the real-time operation parameter vector,

[0180] The historical case with the similarity higher than the preset matching threshold is taken as the historical case of the fuel cell engine.

[0181] Specifically, the whole process is carried out around the control decision scheme generation of the fuel cell engine, the historical operation mode is obtained by mode classification on the historical operation mode data, and the historical case is obtained by similarity matching of the efficiency evaluation value and the historical operation mode.

[0182] Specifically, the preliminary control decision is obtained by coordinating the efficiency evaluation value based on the historical control strategy in the historical case, and the control decision scheme is obtained by feasibility correction on the preliminary control decision combined with the current constraint condition.

[0183] Further, when the mode classification is carried out, the historical operation mode data of the fuel cell engine is first sorted out, which contains the reaction temperature, hydrogen inlet pressure, output current, electrolyte membrane humidity and corresponding efficiency data in different operation periods in the past, and then two core dimensions of mode classification are determined, i.e. power output level divided according to output current corresponding power interval, and chemical reaction stability divided according to reaction temperature fluctuation amplitude.

[0184] Further, each group of data in the historical operation mode data is viewed one by one, the corresponding power is calculated according to the output current and is attributed to the corresponding power interval, and all data under the same power interval and stability level are classified into a class according to the reaction temperature fluctuation amplitude, each class corresponds to an operation characteristic, and the set with clear operation characteristics formed after all classes are sorted is the historical operation mode of the fuel cell engine.

[0185] Further, when the similarity matching is carried out, the average efficiency evaluation value corresponding to each historical operation mode is first extracted, which is calculated by averaging the efficiency values of all historical data in the mode, and then the current efficiency evaluation value of the fuel cell engine is compared with the average efficiency evaluation values of all historical operation modes, the difference between the current efficiency evaluation value and each average efficiency evaluation value is calculated, and the historical operation mode with the smallest difference is found out.

[0186] Further, check whether the historical fluctuation range of the key parameters such as reaction temperature, hydrogen inlet pressure, output current, and electrolyte membrane humidity in the historical operation mode is consistent with the fluctuation range of the key parameters in the current standard parameter sequence. If consistent, all historical operation records and supporting control measures in the historical operation mode are taken as reference cases, and the reference cases are historical cases of the fuel cell engine.

[0187] Further, when the coordination representation is implemented, the historical control strategy is extracted from the historical cases, which includes the adjustment threshold of the reaction temperature, the control range of the hydrogen inlet pressure, the adjustment step of the output current, and the maintenance method of the electrolyte membrane humidity.

[0188] Further, the current efficiency evaluation value is compared with the control strategy triggering condition corresponding to the efficiency level in the historical cases. If the current efficiency evaluation value is lower than the average efficiency in the historical cases under the same mode, the adjustment method for improving the efficiency in the historical control strategy is referred to, and the parameters to be adjusted, the adjustment direction, and the target range after adjustment are determined. These adjustment contents are arranged in the form of clear operation instructions to form an operation instruction set, which is the preliminary control decision of the fuel cell engine.

[0189] Further, when the feasibility is corrected, the current constraint conditions of the fuel cell engine are first determined, including the maximum supply amount of the hydrogen supply system, the maximum heat dissipation capacity of the cooling system, the maximum bearing current of the output load, and the maximum humidification amount of the humidification device.

[0190] Further, each operation instruction in the preliminary control decision is checked one by one to determine whether the parameter adjustment corresponding to the instruction is within the range allowed by the current constraint condition. If the parameter value required by a certain instruction exceeds the upper limit of the constraint or is lower than the lower limit of the constraint, the parameter adjustment target value is corrected to the limit value allowed by the constraint condition. After all operation instructions are corrected, a complete operation instruction set that meets the current constraint condition is formed, which is the control decision scheme of the fuel cell engine.

[0191] Specifically, the whole process is carried out around the matching of the historical cases of the fuel cell engine. The real-time operation parameter vector and the historical parameter vector are first determined, then the similarity between the two is calculated through two ways, and finally the historical cases are screened out in combination with the preset matching threshold.

[0192] Further, when the parameter vector is determined, the real-time operation time corresponding to the efficiency evaluation value is determined, the values of the four key parameters such as reaction temperature, hydrogen inlet pressure, output current, and electrolyte membrane humidity are extracted from the standard parameter sequence at the time, and arranged in the fixed order of “reaction temperature value, hydrogen inlet pressure value, output current value, and electrolyte membrane humidity value” to form the real-time operation parameter vector of the fuel cell engine.

[0193] Further, in the historical operation mode, find the historical operation mode closest to the average efficiency evaluation value and the current efficiency evaluation value, extract the reaction temperature, hydrogen inlet pressure, output current, and electrolyte membrane humidity value of each group of data from all historical data in the historical operation mode, calculate the average value of each group of data corresponding parameters, and arrange these average values in the same order as the real-time operation parameter vector to form a historical parameter vector of the historical operation mode.

[0194] Further, when calculating the similarity, on the one hand, the parameter values at corresponding positions of the real-time operation parameter vector and the historical parameter vector are compared one by one, the difference value of each pair of corresponding parameter values is calculated, such as the reaction temperature difference, the hydrogen inlet pressure difference, the output current difference, and the electrolyte membrane humidity difference, the absolute values of the four parameter differences are added to obtain the absolute value sum of the difference, and then the absolute value sum of the difference is divided by the number of parameters to obtain the average difference. The smaller the average difference is, the higher the similarity between the real-time operation parameter vector and the historical parameter vector is. The size of the average difference quantifies the similarity between the two.

[0195] Further, on the other hand, the similarity is calculated by formula: the value at the th position in the real-time operation parameter vector, which is extracted from the standard parameter sequence of the fuel cell engine at the corresponding time, is multiplied by the value at the th position in the real-time operation parameter vector arranged in a fixed order.

[0196] Further, the value at the th position in the th historical parameter vector in the historical operation mode is obtained by extracting the reaction temperature, hydrogen inlet pressure, output current, and electrolyte membrane humidity value of each group of data from the historical data in the historical operation mode, calculating the average value of each corresponding parameter, and arranging the historical parameter vector in the same order, and then taking the value at the th position in the th historical parameter vector.

[0197] Further, the dimension of the parameter vector is determined by the number of key parameters contained in the real-time operation parameter vector and the historical parameter vector. If four key parameters are contained, the dimension is four.

[0198] Further, when calculating, first multiply each component of the real-time operation parameter vector with the corresponding component of the historical parameter vector, add all the products to obtain the numerator; then calculate the square sum of each component of the real-time operation parameter vector and take the square root to obtain its module length, calculate the square sum of each component of the historical parameter vector and take the square root to obtain its module length, and multiply the two module lengths to obtain the denominator.

[0199] Furthermore, dividing the numerator by the denominator yields a ratio that reflects the angle between the two vectors. The closer the ratio is to 1, the more aligned the directions of the two vectors are. The real-time running parameter vector and the... The higher the similarity between two historical operating patterns, the better.

[0200] Furthermore, when the real-time running parameter vector is compared with the first... When the corresponding component values ​​of two historical parameter vectors are closer and their trends are more consistent, the product of each component is larger, the sum of the numerators is also larger, and the product of the magnitudes of the two vectors is closer to the size of the numerator, the ratio is closer to 1, and the similarity is higher. Conversely, when the corresponding component values ​​are different and their trends are inconsistent, the sum of the numerators is smaller, the product of the magnitudes of the two vectors is larger than the numerator, the ratio is closer to 0, and the similarity is lower.

[0201] Furthermore, when determining the preset matching threshold, the average difference between the real-time running parameter vector and the historical parameter vector in multiple successful matching cases in history is analyzed, and the maximum value of the average difference in these successful cases is selected as the preset matching threshold.

[0202] Furthermore, the average difference between the currently calculated real-time running parameter vector and the historical parameter vector is compared with a preset matching threshold.

[0203] Furthermore, if the average difference is less than or equal to the preset matching threshold, it means that the similarity between the two is higher than the preset matching threshold. At this time, all historical operation records, corresponding control measures and operation effect data corresponding to the historical operation mode to which the historical parameter vector belongs are compiled into reference cases. If the average difference is greater than the preset matching threshold, the historical operation mode to which the historical parameter vector belongs is excluded, and the historical parameter vectors of other historical operation modes are compared until a historical operation mode with a similarity higher than the preset matching threshold is found. The reference cases finally compiled are the historical cases of fuel cell engines.

[0204] In summary, by analyzing historical operating modal data, determining classification dimensions, and categorizing the data, we can obtain the historical operating modes of fuel cell engines.

[0205] In summary, by extracting the average efficiency assessment value of historical operating modes, comparing the difference between the current efficiency and the average efficiency, and checking the range of parameter fluctuations, historical cases of fuel cell engines can be obtained.

[0206] In summary, by extracting historical control strategies, comparing current efficiency with historical triggering conditions, and organizing adjustment instructions, preliminary control decisions for fuel cell engines can be obtained.

[0207] In summary, by determining the current constraints, checking and correcting the operation instructions in the preliminary control decision, the control decision scheme of the fuel cell engine can be obtained.

[0208] In summary, by determining the real-time operation moment and extracting the key parameter values in a fixed order, and extracting the average values of the parameters from the historical operation mode and arranging them in the same order, the real-time operation parameter vector and the historical parameter vector can be obtained.

[0209] In summary, by means of difference average calculation and vector formula calculation, the similarity between the real-time operation parameter vector and the historical parameter vector can be measured.

[0210] In summary, by analyzing the historical successful cases to determine the preset matching threshold, and comparing the current average difference with the threshold and screening and sorting, the historical cases of the fuel cell engine can be obtained.

[0211] S5, encoding and mapping the control decision scheme to obtain the control decision instruction of the fuel cell engine.

[0212] The encoding and mapping of the control decision scheme to obtain the control decision instruction of the fuel cell engine comprises:

[0213] Structurally analyzing the control decision scheme to obtain the decision elements of the fuel cell engine;

[0214] Based on the decision elements, the control decision scheme and the controller of the fuel cell engine are matched and mapped to obtain the control logic unit of the fuel cell engine;

[0215] According to a preset communication protocol, the control logic unit is organized and packaged in sequence to generate the original control instruction of the fuel cell engine;

[0216] The original control instruction is subjected to logical integrity check to obtain the control decision instruction of the fuel cell engine.

[0217] Specifically, the whole process is carried out around the generation of the fuel cell engine control decision instruction, and the control decision scheme is first structurally analyzed to obtain the decision elements.

[0218] Specifically, based on the decision elements, the control decision scheme and the controller are matched and mapped to obtain the control logic unit.

[0219] Specifically, the control logic unit is organized and packaged according to the preset communication protocol to generate the original control instruction, and finally the original control instruction is subjected to logical integrity check to obtain the control decision instruction.

[0220] Further, when performing structured analysis, first, the content of the control decision scheme is combed, covering the adjustment target values of several key parameters such as reaction temperature, hydrogen inlet pressure, output current, and electrolyte membrane humidity, the execution sequence of each parameter adjustment, the components responsible for performing the adjustment operation, and the operation mode of each component.

[0221] Further, these contents are classified and disassembled according to the "parameter adjustment target class, execution sequence class, execution component class, and operation mode class", and specific information items are sorted under each class. The set of all classes and corresponding information items constitutes the decision elements of the fuel cell engine.

[0222] Further, when performing matching mapping, first, the functional module division of the fuel cell engine controller is clarified, including the temperature control module responsible for processing reaction temperature adjustment instructions, the pressure control module responsible for processing hydrogen inlet pressure adjustment instructions, the current control module responsible for processing output current adjustment instructions, and the humidity control module responsible for processing electrolyte membrane humidity adjustment instructions, and the input interface requirements of each module are clarified.

[0223] Further, the "parameter adjustment target class" information in the decision elements is mapped to the input target parameters of each control module, the "execution sequence class" information is mapped to the startup sequence of each module, the "execution component class" information is mapped to the hardware execution unit associated with each module, and the "operation mode class" information is mapped to the specific control parameters of each module. These corresponding relationships are integrated into a logical combination that can be recognized by the controller, forming the control logic unit of the fuel cell engine.

[0224] Further, when performing organization packaging, first, the preset communication protocol requirements are determined, including the structure of the instruction, the length of each segment, and the encoding format of the data.

[0225] Further, each part of the control logic unit is filled into the corresponding field according to the structure of the communication protocol: the instruction identification segment is filled with the protocol-specific identification, the module address segment is filled with the address code of each control module, the control logic segment is filled with the specific control parameters of each module, the timing segment is filled with the execution sequence of each module, and the verification segment generates verification information according to the protocol-specified calculation method. All fields are concatenated in the order specified by the protocol to form a complete instruction, which is the original control instruction of the fuel cell engine.

[0226] Further, when performing logical integrity verification, first, the logical integrity verification standard is formulated, including the verification content: checking whether the original control instruction contains the address code of all control modules, whether the control parameters of each module are complete, whether there is a conflict in the execution sequence, and whether the verification segment data matches the previous segment data.

[0227] Furthermore, the original control instructions are checked segment by segment according to the standard: first, the module address segment is checked to confirm that the address codes of all control modules are included and there are no duplicates; then the control logic segment is checked to confirm that the control parameters of each module are not missing; then the timing segment is checked to confirm that there are no conflicts in the execution order.

[0228] Furthermore, the verification segment is verified by recalculating the verification values ​​of the previous data segments and comparing them with the verification segment data in the instruction to confirm that the two are consistent. If all check items meet the standards and no logical omissions or conflicts are found, the original control instruction is the control decision instruction of the fuel cell engine that has passed the verification.

[0229] In summary, by sorting out the content of the control decision-making scheme and breaking down and organizing the information items by category, the decision-making elements of the fuel cell engine can be obtained.

[0230] In summary, by clearly defining the functional modules and input requirements of the controller, and integrating the decision elements and modules into a logical combination, the control logic unit of the fuel cell engine can be obtained.

[0231] In summary, by filling in and concatenating fields according to the structure and requirements of a preset communication protocol, the raw control commands for a fuel cell engine can be generated.

[0232] In summary, by establishing verification standards and checking the original control commands segment by segment, the control decision commands for the fuel cell engine can be obtained.

[0233] like Figure 2 The diagram shown is a functional block diagram of a fuel cell engine control system provided in an embodiment of the present invention.

[0234] The fuel cell engine control system 100 described in this invention can be installed in an electronic device. Depending on the functions implemented, the fuel cell engine control system 100 may include a data preprocessing module 101, a situation prediction module 102, a performance evaluation and calibration module 103, an intelligent decision-making module 104, and an instruction generation module 105. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0235] In this embodiment, the functions of each module / unit are as follows:

[0236] The data preprocessing module 101 is used to perform noise cleaning on the real-time parameter sequence of the fuel cell engine to obtain the standard parameter sequence of the fuel cell engine.

[0237] The trend prediction module 102 is configured to perform trend simulation on the operation state of the fuel cell engine based on the standard parameter sequence, and obtain a change trend of the fuel cell engine.

[0238] The performance evaluation and calibration module 103 is configured to perform dynamic trend coupling calibration on the standard parameter sequence based on the change trend, and obtain an efficiency evaluation value of the fuel cell engine.

[0239] The intelligent decision module 104 is configured to perform traceability decision mapping on the efficiency evaluation value based on historical operation mode data of the fuel cell engine, and obtain a control decision scheme of the fuel cell engine.

[0240] The instruction generation module 105 is configured to perform encoding mapping on the control decision scheme, and obtain a control decision instruction of the fuel cell engine.

[0241] In several embodiments provided in the present application, it should be understood that the disclosed method and system can be implemented in other manners. For example, the above-described system embodiments are merely illustrative, and the division of the modules is merely a logical function division, and there can be another division manner in actual implementation.

[0242] The modules illustrated as separate components may or may not be physically separate, and the components illustrated as modules may or may not be physical units, that is, they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments.

[0243] In addition, each functional module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or in the form of hardware plus software function modules.

[0244] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0245] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive environment, acquire knowledge and use knowledge to obtain the best results.

[0246] Finally, it should be noted that the above examples are merely intended to illustrate the technical solutions of the present application and not to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the present application.

Claims

1. A fuel cell engine control method characterized by, The method comprises: S1, noise cleaning is carried out on the real-time parameter sequence of the fuel cell engine, and a standard parameter sequence of the fuel cell engine is obtained; S2, based on the standard parameter sequence, the running state of the fuel cell engine is simulated, and the change trend of the fuel cell engine is obtained, comprising: extracting the key parameters in the standard parameter sequence that represent the running state of the fuel cell engine to obtain the running state parameters of the fuel cell engine; quantifying the state index of the running state parameters to obtain the real-time state vector of the running state parameters; based on the preset dynamic evolution strategy, the real-time state vector is forward simulated to obtain the predicted state of the fuel cell engine; trend fitting is performed on the predicted state to obtain the change trend of the fuel cell engine, comprising: analyzing the predicted state to generate prediction information of the predicted state; dimension reconstruction is performed on the prediction information to obtain a prediction state vector of the predicted state; trend quantization is performed on the prediction state vector to obtain a comprehensive trend intensity value of the fuel cell engine, wherein the calculation formula of the comprehensive trend intensity value is as follows: ； wherein denotes the overall trend strength value, denotes the number of predicted state vectors, denotes the fuel cell engine first predicted state vector, denotes a preset reference state vector, denotes the weight factor of the fuel cell engine first predicted state vector, denotes a norm of the difference between two vectors; According to the positive and negative and size of the comprehensive trend intensity value, the evolution direction and intensity of the performance of the fuel cell engine are determined, and the change trend of the fuel cell engine is generated; S3, based on the change trend, the standard parameter sequence is dynamically coupled and calibrated to obtain the efficiency evaluation value of the fuel cell engine, comprising: based on the change trend, the influence degree of the key parameters of the standard parameter sequence is determined to obtain the calibration strategy of the key parameters; According to the calibration strategy, the dynamic calibration weight of the key parameters is calculated, wherein the calculation formula of the dynamic calibration weight is as follows: ； In the formula, denotes a dynamic calibration weight of a key parameter in the standard parameter sequence, denotes a total number of key parameters in the standard parameter sequence, denotes a trend intensity value corresponding to a key parameter in the standard parameter sequence, denotes a trend intensity value corresponding to a key parameter in the standard parameter sequence, denotes a preset trend sensitivity coefficient, denotes an exponential function.​​​ based on the dynamic calibration weight, the parameters of the standard parameter sequence are weighted and fused to obtain the calibration parameters of the fuel cell engine; the calibration parameters are normalized to obtain the efficiency evaluation value of the fuel cell engine; S4, based on the historical running mode data of the fuel cell engine, the efficiency evaluation value is traced and decision mapped to obtain the control decision scheme of the fuel cell engine, comprising: modal classification is performed on the historical running mode data to obtain the historical running mode of the fuel cell engine; the efficiency evaluation value is matched with the historical running mode to obtain the historical case of the fuel cell engine, comprising: based on the efficiency evaluation value, the real-time running parameter vector of the fuel cell engine and the historical parameter vector of the historical running mode are obtained; the similarity between the real-time running parameter vector and the historical parameter vector is calculated, wherein the calculation formula of the similarity is as follows: ； wherein represents the similarity of the real-time operating parameter vector to the i-th historical operating pattern, represents the similarity of the real-time operating parameter vector to the i-th historical operating pattern, represents the dimension of the parameter vector, represents the i-th component of the real-time operating parameter vector, represents the i-th component of the real-time operating parameter vector, represents the i-th component of the i-th historical parameter vector in the historical operating pattern; and represents the i-th component of the i-th historical parameter vector in the historical operating pattern; and represents the i-th component of the i-th historical parameter vector in the historical operating pattern. the historical case with a similarity higher than a preset matching threshold is taken as the historical case of the fuel cell engine; based on the historical control strategy in the historical case, the efficiency evaluation value is represented coordinately to obtain the preliminary control decision of the fuel cell engine; Based on the current constraint condition of the fuel cell engine, the preliminary control decision is modified for feasibility to obtain a control decision scheme of the fuel cell engine; S5, encoding mapping is performed on the control decision scheme to obtain a control decision instruction of the fuel cell engine.

2. A fuel cell engine control method according to claim 1, characterized by, The noise cleaning on the real-time parameter sequence of the fuel cell engine obtains a standard parameter sequence of the fuel cell engine, including: Obtaining a real-time parameter sequence of a fuel cell engine; Detecting an abnormal point of the real-time parameter sequence to obtain a noise point identification sequence of the fuel cell engine; Based on the noise point identification sequence, data repair is performed on the real-time parameter sequence to obtain a repaired parameter sequence of the fuel cell engine; Eliminating high-frequency fluctuation parameters of the repaired parameter sequence to obtain a standard parameter sequence of the fuel cell engine.

3. A fuel cell engine control method according to claim 1, characterized by, The calculation formula of the calibration parameter is as follows: ； wherein represents a calibration parameter of the fuel cell engine, represents a total number of key parameters in the standard parameter sequence, represents a dynamic calibration weight of the parameter in the standard parameter sequence, represents a value of the parameter in the standard parameter sequence, represents a weighted average value of the parameters in the standard parameter sequence, represents a preset fusion adjustment coefficient.

4. A fuel cell engine control method according to claim 1, characterized by, The encoding mapping on the control decision scheme obtains a control decision instruction of the fuel cell engine, including: Structural analysis is performed on the control decision scheme to obtain a decision element of the fuel cell engine; Based on the decision element, matching mapping is performed on the control decision scheme and a controller of the fuel cell engine to obtain a control logic unit of the fuel cell engine; According to a preset communication protocol, the control logic unit is sequentially organized and packaged to generate an original control instruction of the fuel cell engine; Logical integrity check is performed on the original control instruction to obtain a control decision instruction of the fuel cell engine.

5. A fuel cell engine control system for implementing the fuel cell engine control method of claim 1, the system comprising: a data preprocessing module for noise cleaning on a real-time parameter sequence of a fuel cell engine to obtain a standard parameter sequence of the fuel cell engine; a situation prediction module for simulating a situation of the fuel cell engine based on the standard parameter sequence to obtain a change trend of the fuel cell engine, including: extracting a key parameter in the standard parameter sequence representing a running state of the fuel cell engine to obtain a running state parameter of the fuel cell engine; quantifying a state index of the running state parameter to obtain a real-time state vector of the running state parameter; based on a preset dynamic evolution strategy, forward simulating the real-time state vector to obtain a predicted state of the fuel cell engine; trend fitting is performed on the predicted state to obtain a change trend of the fuel cell engine, including: analyzing the predicted state to generate prediction information of the predicted state; dimension reconstruction is performed on the prediction information to obtain a predicted state vector of the predicted state; trend quantization is performed on the predicted state vector to obtain a comprehensive trend intensity value of the fuel cell engine, wherein the calculation formula of the comprehensive trend intensity value is as follows: ； wherein denotes the overall trend strength value, denotes the number of predicted state vectors, denotes the fuel cell engine first predicted state vector, denotes a preset reference state vector, denotes the fuel cell engine first predicted state vector, denotes a norm of the difference between two vectors; According to the positive and negative and size of the comprehensive trend intensity value, the evolution direction and intensity of the fuel cell engine performance are determined, and the change trend of the fuel cell engine is generated; The performance evaluation and calibration module is configured to perform dynamic trend coupling calibration on the standard parameter sequence based on the change trend, to obtain the efficiency evaluation value of the fuel cell engine, including: Performing influence degree discrimination on key parameters of the standard parameter sequence based on the change trend, to obtain a calibration strategy of the key parameters; According to the calibration strategy, a dynamic calibration weight of the key parameters is calculated, and a calculation formula of the dynamic calibration weight is as follows: ； In the formula, Indicates the first in the standard parameter sequence Dynamic calibration weights for key parameters, This represents the total number of key parameters in the standard parameter sequence. Indicates the first in the standard parameter sequence The trend strength values ​​corresponding to the key parameters Indicates the first in the standard parameter sequence The trend strength values ​​corresponding to the key parameters This represents the preset trend sensitivity coefficient. Represents an exponential function; Based on the dynamic calibration weight, parameters of the standard parameter sequence are weighted and fused to obtain a calibration parameter of the fuel cell engine; The calibration parameter is normalized to obtain the efficiency evaluation value of the fuel cell engine; The intelligent decision module is configured to perform traceable decision mapping on the efficiency evaluation value based on historical running mode data of the fuel cell engine, to obtain a control decision scheme of the fuel cell engine, including: Performing mode classification on the historical running mode data to obtain a historical running mode of the fuel cell engine; The efficiency evaluation value is matched with the historical running mode in similarity to obtain a historical case of the fuel cell engine, including: Based on the efficiency evaluation value, a real-time running parameter vector of the fuel cell engine and a historical parameter vector of the historical running mode are obtained; The similarity between the real-time running parameter vector and the historical parameter vector is calculated, and a calculation formula of the similarity is as follows: ； wherein represents the similarity of the real-time operating parameter vector to the i-th historical operating pattern, represents the dimension of the parameter vector, represents the i-th component of the real-time operating parameter vector, represents the i-th component of the i-th historical parameter vector in the historical operating pattern, represents the i-th component of the i-th historical parameter vector in the historical operating pattern, represents the i-th component of the i-th historical parameter vector in the historical operating pattern, represents the i-th component of the i-th historical parameter vector in the historical operating pattern. The historical case with a similarity higher than a preset matching threshold is taken as the historical case of the fuel cell engine; Based on a historical control strategy in the historical case, the efficiency evaluation value is represented in coordination to obtain a preliminary control decision of the fuel cell engine; Based on a current constraint condition of the fuel cell engine, the preliminary control decision is modified in feasibility to obtain the control decision scheme of the fuel cell engine; The instruction generation module is configured to encode and map the control decision scheme to obtain a control decision instruction of the fuel cell engine.

Images