Hybrid power system energy management method based on proton exchange membrane fuel cell

Abstract

The invention provides a hybrid power system energy management method based on a proton exchange membrane fuel cell, and relates to the technical field of energy management, and the method specifically comprises the steps: obtaining key parameters during the operation of a fuel cell, and calculating an environment influence index, an electric energy evaluation index and a power response index based on the key parameters; constructing a comprehensive evaluation model according to the environmental influence index, the electric energy evaluation index and the power response index, and generating a comprehensive energy management index; and comparing the comprehensive energy management index with a preset threshold value, formulating a real-time energy distribution strategy according to a comparison result, and further optimizing the energy distribution strategy by applying a genetic algorithm. According to the method, multi-dimensional analysis and evaluation of the system performance are realized, the constructed comprehensive evaluation model enables an energy management strategy to comprehensively consider environmental factors and energy use efficiency, and the optimal performance of the system under different loads is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of energy management, and in particular to an energy management method for a hybrid power system based on a proton exchange membrane fuel cell. Background Art

[0002] Proton exchange membrane fuel cell (PEMFC) is an efficient and clean energy conversion device widely used in transportation, fixed power supply and portable devices. Its core advantage is that it can use hydrogen as fuel to directly generate electricity through electrochemical reactions, and the only emission of this reaction is water. However, in practical applications, PEMFC still faces many technical challenges, especially in energy management and system response performance. Under dynamic load conditions, the output power of the fuel cell needs to be adjusted quickly to meet the changes in demand to ensure the performance and stability of the system. However, traditional energy management strategies often lack real-time and flexibility, and cannot effectively cope with the system instability caused by load fluctuations, resulting in reduced battery efficiency and possible energy waste.

[0003] In addition, most of the current energy management methods are based on static models and fail to effectively consider the impact of environmental factors and various operating conditions on system performance. For example, environmental variables such as temperature, humidity and gas flow have a significant impact on the working efficiency of fuel cells, but the existing technology generally lacks real-time monitoring and comprehensive analysis of these parameters. Therefore, in practical applications, the system cannot achieve a rapid response to environmental changes, resulting in reduced efficiency of power use and increased environmental impact. At the same time, the existing methods are also insufficient in terms of power responsiveness, especially when faced with instantaneous load changes, the system cannot adjust power distribution in time. These deficiencies not only affect the overall performance and service life of fuel cells, but also restrict their promotion and application in a wider range of application fields. Therefore, it is urgent to develop new energy management methods to achieve efficient coordination and optimization of fuel cells and other energy storage devices, thereby improving the overall performance of the system.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The object of the present invention is to provide an energy management method for a hybrid power system based on a proton exchange membrane fuel cell to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: A hybrid power system energy management method based on a proton exchange membrane fuel cell, the specific steps comprising: Step 1: Monitor and analyze the operating status of the fuel cell to obtain key parameters, including temperature, humidity, current, voltage, gas flow rate and actual response time of the system, and calculate the load power through current and voltage data; Step 2: Calculate the environmental impact index based on the dimensionless processed temperature, humidity and gas flow data; calculate the electric energy evaluation index based on the dimensionless processed load power data; and calculate the power response index based on the dimensionless processed load power and actual response time; Step 3: Construct a comprehensive evaluation model based on the environmental impact index, electric energy evaluation index and power response index of the battery to be evaluated, generate the weights in the comprehensive evaluation model through the hierarchical analysis method, and use the comprehensive evaluation model to generate a comprehensive energy management index; Step 4: Compare the comprehensive energy management index with the preset threshold, and formulate a real-time energy allocation strategy based on the comparison results, and apply the genetic algorithm to further optimize the energy allocation strategy.

[0007] Furthermore, a time synchronization mechanism is implemented to ensure that the data of all the following sensors are collected at the same timestamp: The PEMFC operating temperature is obtained using an NTC thermistor, denoted as ; Use the humidity sensor to obtain the humidity of the PEMFC working environment, denoted as ; Use a current sensor to monitor the current flowing through the fuel cell and the load, recorded as ; Use a voltage sensor to monitor the voltage of the fuel cell and the load, denoted as ; The flow meter is installed between the gas source and the fuel cell stack to collect gas flow data, which is recorded as ; The actual response time of the system is the time delay required for the system to adjust its state after receiving a new load change signal. The specific logic for obtaining the actual response time is: When the system receives a new load change signal, record the time , after the system responds, monitor the time it takes for the current and voltage data to reach a stable state : ;in, is the actual response time; Use the following formula to calculate the load power: in, is the load power at the current moment, is the voltage value at the current moment, is the current value at the current moment, is the power factor at the current moment, is the total harmonic distortion; The acquisition method is as follows: use a digital instrument to sample the voltage signal, the sampling frequency is 10 times the highest frequency of the signal, and satisfies the Nyquist sampling theorem. For the collected time domain signal, use fast Fourier transform to convert it into a frequency domain signal to obtain the amplitude of each harmonic component. For each harmonic, calculate its effective value according to the following formula: ;in, is the effective value of the harmonic, The time required for the signal to complete a complete waveform. The time for a complete waveform The signal value at time is the time variable within a complete waveform time; Use the above harmonic effective value calculation formula to calculate the effective value of the fundamental wave and the effective value of the ath harmonic, where a represents the index of the harmonic, where , represents the total number of fundamental waves and harmonics, and substitute the calculated results into the following Calculation formula: ;in, is the total harmonic distortion, is the effective value of the fundamental wave, that is, the effective value of the first harmonic, is the effective value of the ath harmonic, .

[0008] Furthermore, the environmental impact index is calculated according to the following formula: ;in, is the environmental impact index, is the current temperature, is the temperature threshold, is the current humidity, is the humidity threshold, is the current gas flow data, is the gas flow threshold, is the denominator adjustment constant, when or or When it is zero, the corresponding denominator adjustment constant is 1. or or When it is not zero, the corresponding denominator adjustment constant is 0. is the preset proportional coefficient; The electric energy evaluation index is calculated according to the following formula: ;in, is the electric energy assessment index, is the load power, is the efficiency factor, is the input power, i.e. the total input power of the fuel cell; The calculation formula is: ;in, It indicates the highest efficiency that the system can achieve under ideal conditions. is the current gas flow data, Indicates the gas flow data under ideal conditions; The power response index is calculated according to the following formula: ;in, is the power response index, is the load power, is the expected power, is the maximum output power, is the actual response time, The maximum response time designed for the system, is the scaling factor used to adjust the effect of the power difference on the power response index, It is an adjustment factor used to balance the impact of response time on the power response index.

[0009] Furthermore, a comprehensive evaluation model is constructed based on the environmental impact index, electric energy evaluation index and power response index of the system to be evaluated. The model expression is as follows: ;in, is the comprehensive energy management index, is the environmental impact index, is the electric energy assessment index, is the power response index, is the proportionality coefficient.

[0010] Furthermore, the specific logic of generating the weights in the comprehensive evaluation model through the hierarchical analysis method is as follows: The three indicators of environmental impact index, electric energy evaluation index and power response index are marked, and the relative importance values ​​between them are determined by the nine-scale method to construct a judgment matrix, in which the index of the environmental impact index is marked as 1, the index of the electric energy evaluation index is marked as 2, and the index of the power response index is marked as 3. The constructed judgment matrix is: ;in, denotes the index of the index, and , Indicates that the index is The index relative to the index is The index importance of ; Each element value in the judgment matrix is ​​divided by the sum of its columns to obtain a normalized normalized judgment matrix. The mean of the element values ​​in each row of the normalized judgment matrix is ​​calculated, and the mean of the element values ​​in the first row is used as the weight of the environmental impact index, the mean of the element values ​​in the second row is used as the weight of the electric energy evaluation index, and the mean of the element values ​​in the third row is used as the weight of the power response index. With the constraint that the sum of the scaled values ​​is equal to 1, the three weights are scaled in equal proportions, and the scaled weights are used as the proportional coefficients of the corresponding indexes.

[0011] Furthermore, the comprehensive energy management index is compared with a preset threshold: like , continue to use the current energy allocation strategy, set the main energy source in the system to fuel cells, and give priority to the use of fuel cells; like , using supercapacitors to quickly respond to load changes; in, is the comprehensive energy management index, Evaluation thresholds for preset indices; Genetic algorithm is used to further optimize the energy allocation strategy, based on the following specific logic: A sample set containing n individuals is set, each individual represents an energy allocation strategy, indicating the power allocation ratio of fuel cells and supercapacitors under different load conditions. For each individual, its corresponding environmental impact index, electric energy evaluation index and power response index are calculated, and the maximum and minimum values ​​of the environmental impact index, electric energy evaluation index and power response index in the sample set are used as constraints. The initial population is randomly generated, and the individuals are input into the comprehensive evaluation model to obtain the corresponding comprehensive energy management index. The individuals are sorted from large to small according to the comprehensive energy management index, and the individuals at the front of the sorting are selected as the parent generation and crossover and mutation operations are performed to obtain new individuals. After the newly generated individuals and the individuals as the parent generation are integrated as a new population, the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached, and the individual with the largest comprehensive energy management index is selected as the optimal parameter combination. The current energy allocation strategy is adjusted according to the power allocation ratio in the optimal parameter combination.

[0012] Compared with the prior art, the present invention has the following beneficial effects: The present invention obtains the operating status of the system by real-time monitoring of key parameters such as temperature, humidity, current and voltage, and calculates the environmental impact index, electric energy evaluation index and power response index based on dimensionless processing, thereby realizing multi-dimensional analysis and evaluation of system performance. The constructed comprehensive evaluation model enables the energy management strategy to comprehensively consider environmental factors and energy utilization efficiency, ensuring the optimal performance of the system under different loads. At the same time, the genetic algorithm is applied to optimize the energy allocation strategy, so that the system can flexibly adapt to instantaneous load changes and improve response speed and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a schematic diagram of the overall method flow of the present invention; Figure 2 Schematic diagram of the genetic algorithm of the present invention. DETAILED DESCRIPTION

[0014] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0015] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0016] Example

[0017] See also Figure 1 , the present invention provides a technical solution: A hybrid power system energy management method based on a proton exchange membrane fuel cell, the specific steps comprising: Step 1: Monitor and analyze the operating status of the fuel cell to obtain key parameters, including temperature, humidity, current, voltage, gas flow rate and actual response time of the system, and calculate the load power through current and voltage data; In this embodiment, a time synchronization mechanism is implemented to ensure that the data of all the following sensors are collected at the same timestamp: The PEMFC operating temperature is obtained using an NTC thermistor, denoted as ; Use the humidity sensor to obtain the humidity of the PEMFC working environment, denoted as ; Use a current sensor to monitor the current flowing through the fuel cell and the load, recorded as ; Use a voltage sensor to monitor the voltage of the fuel cell and the load, denoted as ; The flow meter is installed between the gas source and the fuel cell stack to collect gas flow data, which is recorded as ; The actual response time of the system is the time delay required for the system to adjust its state after receiving a new load change signal. The specific logic for obtaining the actual response time is: When the system receives a new load change signal, record the time , after the system responds, monitor the time it takes for the current and voltage data to reach a stable state : in, is the actual response time; Use the following formula to calculate the load power: in, is the load power at the current moment, is the voltage value at the current moment, is the current value at the current moment, is the power factor at the current moment, is the total harmonic distortion; The acquisition method is as follows: use a digital instrument to sample the voltage signal, the sampling frequency is 10 times the highest frequency of the signal, and satisfies the Nyquist sampling theorem. For the collected time domain signal, use fast Fourier transform to convert it into a frequency domain signal to obtain the amplitude of each harmonic component. For each harmonic, calculate its effective value according to the following formula: ;in, is the effective value of the harmonic, The time required for the signal to complete a complete waveform. The time for a complete waveform The signal value at time is the time variable within a complete waveform time; Use the above harmonic effective value calculation formula to calculate the effective value of the fundamental wave and the effective value of the ath harmonic, where a represents the index of the harmonic, where , represents the total number of fundamental waves and harmonics, and substitute the calculated results into the following Calculation formula: ;in, is the total harmonic distortion, is the effective value of the fundamental wave, that is, the effective value of the first harmonic, is the effective value of the ath harmonic, .

[0018] Step 1 comprehensively monitors and analyzes the operating status of the fuel cell, obtains key parameters, and uses these data to calculate the load power. This real-time monitoring mechanism can ensure the accuracy and timeliness of data, providing a solid foundation for subsequent energy management decisions. Compared with the existing technology, this method not only improves the comprehensiveness and accuracy of data collection, but also can respond quickly under complex dynamic load conditions, avoiding the system instability and energy waste caused by data lag in traditional methods.

[0019] In this patent solution, implementing step 1 can significantly improve the effectiveness of the overall solution, and ensure the optimal performance and energy efficiency of the system under different operating conditions through real-time monitoring and data analysis. This provides reliable data support for the comprehensive evaluation model, making the subsequent energy allocation strategy and optimization adjustment more scientific and reasonable, thereby promoting the flexibility and efficiency of fuel cells and their hybrid power systems in practical applications. Such improvements not only improve the economy of the system, but also lay the foundation for the promotion and application of renewable energy technologies.

[0020] Step 2: Calculate the environmental impact index based on the dimensionless processed temperature, humidity and gas flow data; calculate the electric energy evaluation index based on the dimensionless processed load power data; and calculate the power response index based on the dimensionless processed load power and actual response time; In this embodiment, the environmental impact index is calculated according to the following formula: ;in, is the environmental impact index, is the current temperature, is the temperature threshold, is the current humidity, is the humidity threshold, is the current gas flow data, is the gas flow threshold, is the denominator adjustment constant, when or or When it is zero, the corresponding denominator adjustment constant is 1. or or When it is not zero, the corresponding denominator adjustment constant is 0. It is a preset proportional coefficient used for environmental impact index Adjust the scale and sensitivity. . The specific value is based on industry standards, historical data and laboratory testing.

[0021] when When it increases, it means that the current temperature deviation increases and the stability of the environment decreases. decrease; when When it increases, it means that the current humidity is getting worse and the stability of the environment is decreasing. decrease; when When it increases, it means that the current gas flow data deviates further from the threshold, so correspondingly decreases; that is, , , Environmental Impact Index There is a negative correlation. The calculation is designed to assess the suitability of a fuel cell system under specific environmental conditions by taking into account the difference between the current temperature, humidity and gas flow rate and preset thresholds. It can reflect the impact of the environment on the performance of the fuel cell. When the value increases, it means that the current environmental conditions are more suitable for the fuel cell, which may mean that the system can operate efficiently under this condition; When the value decreases, it means that the environmental conditions are less adaptable to the fuel cell, which may affect the efficiency and stability of the system.

[0022] The electric energy evaluation index is calculated according to the following formula: ;in, is the electric energy assessment index, is the load power, is the efficiency factor, is the input power, i.e. the total input power of the fuel cell; Efficiency Factor The calculation formula is: ;in, It indicates the highest efficiency that the system can achieve under ideal conditions. is the current gas flow data, Indicates the gas flow data under ideal conditions; and The specific value of can be obtained from the technical manual.

[0023] When the load power When it increases, it means that more input power is converted into load power. At this time, the power utilization efficiency increases and the power evaluation index decreases. When it decreases, it means that the input power cannot be effectively converted into load power, resulting in a decrease in the efficiency of power use. The value increases; the power evaluation index It is used to quantify the energy efficiency of the fuel cell system. By comparing the load power with the input power, it can intuitively reflect the energy utilization of the system in actual operation. When the value decreases, it means that the system's power efficiency is improving, which may mean that the fuel cell performs better under the current environmental conditions and reduces energy loss. This is a positive sign that the system is running more efficiently. When the value increases, it means that the system's power efficiency decreases.

[0024] The power response index is calculated according to the following formula: ;in, is the power response index, is the load power, is the expected power, is the maximum output power, is the actual response time, The maximum response time designed for the system, is the scaling factor used to adjust the effect of the power difference on the power response index, is the adjustment factor used to balance the effect of response time on the power response index, and ,This is because the impact of the power difference on the power response is greater than the response time. In many systems, especially in power and energy management, the impact of load changes on system performance is often more ,direct and important.

[0025] when When increasing, Increase means that the system can handle greater power requirements. Increase; when the actual response time When it decreases, it means that the system responds faster to load changes. The value increases; that is, and There is a positive correlation, and Calculate the power response index Can help evaluate and optimize the power system's ability to respond to load changes. When the value increases, it means that the system responds faster when the load changes and can better meet the actual power demand; when When the value decreases, it means that the system is not responsive enough and cannot adapt to load changes quickly.

[0026] Step 2 generates the environmental impact index, electric energy evaluation index and power response index by calculating the dimensionless temperature, humidity, gas flow and load power data. The key advantage of this process is that it can convert performance indicators of different dimensions into dimensionless values, which is convenient for comparison and comprehensive evaluation. This method effectively reduces the evaluation deviation caused by different data magnitudes and improves the accuracy and reliability of the overall evaluation. Compared with the existing technology, step 2 not only simplifies the complex parameter calculation process, but also better reflects the performance changes of the fuel cell system under dynamic load conditions, ensuring the scientific nature of the energy management strategy.

[0027] In this patent solution, the use of step 2 can significantly enhance the evaluation capability of the overall solution and provide basic data for the comprehensive evaluation model. The implementation of this process promotes the effectiveness of subsequent steps, enabling energy management strategies to more accurately reflect actual operating conditions, thereby optimizing energy distribution and improving system operating efficiency. Through real-time environmental impact and energy efficiency evaluation, this step provides forward-looking support for system decision-making, enabling the hybrid system to achieve optimal performance and resource utilization in a complex working environment.

[0028] Step 3: Construct a comprehensive evaluation model based on the environmental impact index, electric energy evaluation index and power response index of the battery to be evaluated, generate the weights in the comprehensive evaluation model through the hierarchical analysis method, and use the comprehensive evaluation model to generate a comprehensive energy management index; In this embodiment, a comprehensive evaluation model is constructed according to the environmental impact index, electric energy evaluation index and power response index of the system to be evaluated. The model expression is as follows: ;in, is the comprehensive energy management index, is the environmental impact index, is the electric energy assessment index, is the power response index, is the proportionality coefficient.

[0029] When the environmental impact index When it increases, it means that the current environmental conditions are more suitable, and the comprehensive energy management index Increase; when the power evaluation index When it increases, it means that the input power cannot be effectively converted into load power, resulting in a decrease in the efficiency of power use. Therefore, the comprehensive energy management index Decrease; when the power response index When it increases, it means that the system responds faster when the load changes and can better meet the actual power demand. The comprehensive energy management index Increase, that is, , and There is a positive correlation, and There is a negative correlation.

[0030] The specific logic of generating weights in the comprehensive evaluation model through the hierarchical analysis method is: The three indicators of environmental impact index, electric energy evaluation index and power response index are marked, and the relative importance values ​​between them are determined by the nine-scale method to construct a judgment matrix, in which the index of the environmental impact index is marked as 1, the index of the electric energy evaluation index is marked as 2, and the index of the power response index is marked as 3. The constructed judgment matrix is: ;in, denotes the index of the index, and , Indicates that the index is The index relative to the index is The index importance of ; Each element value in the judgment matrix is ​​divided by the sum of its columns to obtain a normalized normalized judgment matrix. The mean of the element values ​​in each row of the normalized judgment matrix is ​​calculated, and the mean of the element values ​​in the first row is used as the weight of the environmental impact index, the mean of the element values ​​in the second row is used as the weight of the electric energy evaluation index, and the mean of the element values ​​in the third row is used as the weight of the power response index. With the constraint that the sum of the scaled values ​​is equal to 1, the three weights are scaled in equal proportions, and the scaled weights are used as the proportional coefficients of the corresponding indexes.

[0031] Step 3: By building a comprehensive evaluation model, the environmental impact index, power evaluation index and power response index are integrated to generate a comprehensive energy management index. The key advantage of this process is that it provides a systematic approach to comprehensively evaluate the overall performance of the fuel cell system, thereby making more scientific and reasonable energy management decisions under complex operating conditions. Compared with existing technologies, this step not only improves the comprehensiveness and accuracy of the evaluation, but also clarifies the weight relationship of each indicator through the hierarchical analysis method, making the decision-making process more transparent and logical.

[0032] In this patent solution, the adoption of step 3 can effectively improve the decision-making ability and flexibility of the overall solution. By establishing a comprehensive evaluation model, the system can evaluate and adjust the energy management strategy in real time when facing different operating conditions and environmental influences. This dynamic adjustment capability ensures the efficient operation of the system, greatly reduces energy waste, and improves overall energy utilization. Ultimately, the implementation of this step promotes the optimization of the hybrid system, enabling it to achieve higher economy and environmental friendliness in practical applications, while also providing strong support for future technological development.

[0033] Step 4: Compare the comprehensive energy management index with the preset threshold, and formulate a real-time energy allocation strategy based on the comparison result, and apply the genetic algorithm to further optimize the energy allocation strategy; In this embodiment, the comprehensive energy management index is compared with a preset threshold: like , continue to use the current energy allocation strategy, set the main energy source in the system to fuel cells, and give priority to the use of fuel cells; like , using supercapacitors to quickly respond to load changes; in, is the comprehensive energy management index, Evaluation thresholds for preset indices; Genetic algorithm is used to further optimize the energy allocation strategy, based on the following specific logic: A sample set containing n individuals is set, each individual represents an energy allocation strategy, indicating the power allocation ratio of fuel cells and supercapacitors under different load conditions. For each individual, its corresponding environmental impact index, electric energy evaluation index and power response index are calculated, and the maximum and minimum values ​​of the environmental impact index, electric energy evaluation index and power response index in the sample set are used as constraints. The initial population is randomly generated, and the individuals are input into the comprehensive evaluation model to obtain the corresponding comprehensive energy management index. The individuals are sorted from large to small according to the comprehensive energy management index, and the individuals at the top of the sorting are selected as the parent generation and crossover and mutation operations are performed to obtain new individuals. After the newly generated individuals and the individuals as the parent generation are integrated as a new population, the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached. The preset number of iterations in this scheme is 200 times. This number of iterations can ensure that the algorithm has enough opportunities to find the best solution and avoid the waste of computing resources caused by excessive iterations. The individual with the largest comprehensive energy management index is selected as the optimal parameter combination, and the current energy allocation strategy is adjusted according to the power allocation ratio in the optimal parameter combination.

[0034] The core benefit of step 4 is to integrate the comprehensive energy management index With preset threshold Compare and formulate real-time energy allocation strategy. This method can respond to the operating status of the system in a timely manner and ensure the flexibility and efficiency of the system under different load change conditions. Compared with the existing technology, this step can achieve more intelligent energy management, avoid the problem of unreasonable energy allocation caused by data delay or inaccurate prediction in traditional methods, and thus improve the overall reliability and response speed of the system.

[0035] In the present patent scheme, the adoption of step 4 can significantly enhance the dynamic adjustment capability of the overall scheme. By real-time monitoring and adjusting the energy allocation strategy, the system can quickly switch the main energy source according to the actual operating conditions, thereby maintaining the stability and efficiency of the system when the load changes. This flexibility not only optimizes energy utilization, but also reduces operating costs, provides a more competitive solution for the hybrid power system of proton exchange membrane fuel cells, and promotes the promotion and development of renewable energy technology in practical applications. The genetic algorithm used in step 4 is an optimization algorithm based on natural selection and genetic mechanisms, which can effectively find near-optimal solutions in complex search spaces. In the energy allocation strategy, the genetic algorithm helps the system quickly find the optimal power allocation ratio by simulating the evolutionary process, thereby improving the efficiency and effectiveness of energy management.

[0036] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0037] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0038] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0039] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A hybrid power system energy management method based on proton exchange membrane fuel cells, characterized in that: The specific steps include: Step 1: Monitor and analyze the operating status of the fuel cell to obtain key parameters, including temperature, humidity, current, voltage, gas flow rate and actual response time of the system, and calculate the load power through current and voltage data; Step 2: Calculate the environmental impact index based on the dimensionless processed temperature, humidity and gas flow data, calculate the electric energy evaluation index based on the dimensionless processed load power data, and calculate the power response index based on the dimensionless processed load power and actual response time; Step 3: Construct a comprehensive evaluation model based on the environmental impact index, electric energy evaluation index and power response index of the battery to be evaluated, generate the weights in the comprehensive evaluation model through the hierarchical analysis method, and use the comprehensive evaluation model to generate a comprehensive energy management index; Step 4: Compare the comprehensive energy management index with the preset threshold, and formulate a real-time energy allocation strategy based on the comparison results, and apply the genetic algorithm to further optimize the energy allocation strategy.

2. The energy management method of a hybrid power system based on a proton exchange membrane fuel cell according to claim 1, characterized in that: Implement a time synchronization mechanism to ensure that data from all the following sensors are collected at the same timestamp: The PEMFC operating temperature is obtained using an NTC thermistor, denoted as ; Use the humidity sensor to obtain the humidity of the PEMFC working environment, denoted as ; Use a current sensor to monitor the current flowing through the fuel cell and the load, recorded as ; Use a voltage sensor to monitor the voltage of the fuel cell and the load, denoted as ; The flow meter is installed between the gas source and the fuel cell stack to collect gas flow data, which is recorded as ; The actual response time of the system is the time delay required for the system to adjust its state after receiving a new load change signal. The specific logic for obtaining the actual response time is: When the system receives a new load change signal, record the time , after the system responds, monitor the time it takes for the current and voltage data to reach a stable state : ;in, is the actual response time; Use the following formula to calculate the load power: ;in, is the load power at the current moment, is the voltage value at the current moment, is the current value at the current moment, is the power factor at the current moment, is the total harmonic distortion; The acquisition method is as follows: use a digital instrument to sample the voltage signal, the sampling frequency is 10 times the highest frequency of the signal, and satisfies the Nyquist sampling theorem. For the collected time domain signal, use fast Fourier transform to convert it into a frequency domain signal to obtain the amplitude of each harmonic component. For each harmonic, calculate its effective value according to the following formula: ;in, is the effective value of the harmonic, The time required for the signal to complete a complete waveform. The time for a complete waveform The signal value at time is the time variable within a complete waveform time; Use the above harmonic effective value calculation formula to calculate the effective value of the fundamental wave and the effective value of the ath harmonic, where a represents the index of the harmonic, where , represents the total number of fundamental waves and harmonics, and substitute the calculated results into the following Calculation formula: ;in, is the total harmonic distortion, is the effective value of the fundamental wave, that is, the effective value of the first harmonic, is the effective value of the ath harmonic, .

3. The energy management method of a hybrid power system based on a proton exchange membrane fuel cell according to claim 1, characterized in that: The environmental impact index is calculated according to the following formula: ； in, is the environmental impact index, is the current temperature, is the temperature threshold, is the current humidity, is the humidity threshold, is the current gas flow data, is the gas flow threshold, is the denominator adjustment constant, when or or When it is zero, the corresponding denominator adjustment constant is 1. or or When it is not zero, the corresponding denominator adjustment constant is 0. is the preset proportional coefficient; The electric energy evaluation index is calculated according to the following formula: ;in, is the electric energy assessment index, is the load power, is the efficiency factor, is the input power, i.e. the total input power of the fuel cell; The calculation formula is: ;in, It indicates the highest efficiency that the system can achieve under ideal conditions. is the current gas flow data, Indicates the gas flow data under ideal conditions; The power response index is calculated according to the following formula: ;in, is the power response index, is the load power, is the expected power, is the maximum output power, is the actual response time, The maximum response time designed for the system, is the scaling factor used to adjust the effect of the power difference on the power response index, It is an adjustment factor used to balance the impact of response time on the power response index.

4. The energy management method of a hybrid power system based on a proton exchange membrane fuel cell according to claim 1, characterized in that: A comprehensive evaluation model is constructed based on the environmental impact index, electric energy evaluation index and power response index of the system to be evaluated. The model expression is as follows: ;in, is the comprehensive energy management index, is the environmental impact index, is the electric energy assessment index, is the power response index, is the proportionality coefficient.

5. The energy management method of a hybrid power system based on a proton exchange membrane fuel cell according to claim 4, characterized in that: The specific logic of generating weights in the comprehensive evaluation model through the hierarchical analysis method is: The three indicators of environmental impact index, electric energy evaluation index and power response index are marked, and the relative importance values ​​between them are determined by the nine-scale method to construct a judgment matrix, in which the index of the environmental impact index is marked as 1, the index of the electric energy evaluation index is marked as 2, and the index of the power response index is marked as 3. The constructed judgment matrix is: ;in, denotes the index of the index, and , Indicates that the index is The index relative to the index is The index importance of ; Each element value in the judgment matrix is ​​divided by the sum of its columns to obtain a normalized normalized judgment matrix. The mean of the element values ​​in each row of the normalized judgment matrix is ​​calculated, and the mean of the element values ​​in the first row is used as the weight of the environmental impact index, the mean of the element values ​​in the second row is used as the weight of the electric energy evaluation index, and the mean of the element values ​​in the third row is used as the weight of the power response index. With the constraint that the sum of the scaled values ​​is equal to 1, the three weights are scaled in equal proportions, and the scaled weights are used as the proportional coefficients of the corresponding indexes.

6. The energy management method of a hybrid power system based on a proton exchange membrane fuel cell according to claim 1, characterized in that: Compare the overall energy management index with the preset threshold: like , continue to use the current energy allocation strategy, set the main energy source in the system to fuel cells, and give priority to the use of fuel cells; like , using supercapacitors to quickly respond to load changes; in, is the comprehensive energy management index, Evaluation thresholds for preset indices; Genetic algorithm is used to further optimize the energy allocation strategy. The specific logic is as follows: A sample set containing n individuals is set, each individual represents an energy allocation strategy, indicating the power allocation ratio of fuel cells and supercapacitors under different load conditions. For each individual, its corresponding environmental impact index, electric energy evaluation index and power response index are calculated, and the maximum and minimum values ​​of the environmental impact index, electric energy evaluation index and power response index in the sample set are used as constraints. The initial population is randomly generated, and the individuals are input into the comprehensive evaluation model to obtain the corresponding comprehensive energy management index. The individuals are sorted from large to small according to the comprehensive energy management index, and the individuals at the front of the sorting are selected as the parent generation and crossover and mutation operations are performed to obtain new individuals. After the newly generated individuals and the individuals as the parent generation are integrated as a new population, the selection, crossover and mutation operations are repeated until the predetermined number of iterations is reached, and the individual with the largest comprehensive energy management index is selected as the optimal parameter combination. The current energy allocation strategy is adjusted according to the power allocation ratio in the optimal parameter combination.

Images