A method, system and device for dispatching output power of fuel cell on emergency power supply vehicle

Abstract

The present application relates to the technical field of emergency resource scheduling, and discloses a method, system and device for scheduling the output power of a fuel cell on an emergency power supply vehicle, wherein the method comprises: extracting historical demand data, preprocessing the historical demand data, and obtaining a standardized data set; setting fuzzy control rules between the standardized data set and the output power of the fuel cell, and establishing a fuzzy rule base; constructing an energy scheduling model based on the fuzzy rule base; predicting future electricity demand based on historical demand data, and obtaining a prediction result; using the prediction result as the input of the energy scheduling model, and obtaining an energy scheduling plan; judging whether the deviation value between the real-time demand data and the corresponding prediction result is greater than a set threshold value, and if so, regenerating the energy scheduling plan according to the deviation value, thereby solving the technical problem of optimal scheduling of the output power of the fuel cell and achieving the technical effect of balancing the vehicle driving performance and the power supply quality of the external device.

Description

Technical Field

[0001] The present application relates to the technical field of emergency resource scheduling, and in particular to a method, system and device for scheduling output power of a fuel cell on an emergency power supply vehicle. Background Art

[0002] Emergency power supply vehicles face complex and changeable working conditions and external equipment load requirements during driving, which brings challenges to fuel cell power scheduling. There is a mutual influence and constraint relationship between vehicle driving conditions and external equipment load requirements. For example, when going uphill, the vehicle requires greater power, which may affect the stability of external equipment power supply; and when high-power equipment is started, it may cause insufficient vehicle power. In addition, the load demand of external equipment is random and volatile, and it is difficult to predict accurately. This requires the fuel cell power scheduling strategy to respond quickly to changes in working conditions and balance the vehicle's driving performance and the quality of power supply to external equipment. However, frequent adjustments to the output power of the fuel cell may reduce its service life and efficiency. How to achieve the optimal scheduling of the fuel cell output power while ensuring the vehicle's driving performance and the quality of power supply to external equipment has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The present application provides a method, system and device for scheduling the output power of a fuel cell on an emergency power supply vehicle, which solves the technical problem of optimal scheduling of the output power of the fuel cell on the emergency power supply vehicle and achieves the technical effect of balancing the vehicle's driving performance and the power supply quality of external devices.

[0004] In order to achieve the above objectives, the main technical solutions adopted in this application include:

[0005] In a first aspect, an embodiment of the present application provides a method for scheduling the output power of a fuel cell on an emergency power supply vehicle, the method comprising: extracting historical demand data, including driving condition data of the emergency power supply vehicle and load demand data of an external device, preprocessing the historical demand data to obtain a standardized data set; setting fuzzy control rules between the standardized data set and the output power of the fuel cell, and establishing a fuzzy rule base; based on the fuzzy rule base, constructing an energy scheduling model with the goal of minimizing energy consumption and maximizing power supply stability; based on the historical demand data, using a Kalman filter algorithm to predict future electricity demand and obtain a prediction result; using the prediction result as an input to the energy scheduling model to obtain an energy scheduling plan; obtaining real-time demand data, and determining whether the deviation value between the real-time demand data and the corresponding prediction result is greater than a set threshold, and if so, regenerating the energy scheduling plan based on the deviation value.

[0006] The embodiment of the present application proposes a method for scheduling the output power of a fuel cell on an emergency power supply vehicle. The method extracts historical demand data, including driving condition data of the emergency power supply vehicle and load demand data of external devices, pre-processes the historical demand data to obtain a standardized data set; sets fuzzy control rules between the standardized data set and the output power of the fuel cell to establish a fuzzy rule base; based on the fuzzy rule base, constructs an energy scheduling model with the goal of minimizing energy consumption and maximizing power supply stability; based on the historical demand data, uses a Kalman filter algorithm to predict future electricity demand to obtain a prediction result; uses the prediction result as an input to the energy scheduling model to obtain an energy scheduling plan; obtains real-time demand data, and determines whether the deviation value between the real-time demand data and the corresponding prediction result is greater than a set threshold. If so, regenerates the energy scheduling plan according to the deviation value, thereby solving the technical problem of optimal scheduling of the output power of the fuel cell on the emergency power supply vehicle and achieving the technical effect of balancing the vehicle's driving performance and the power supply quality of the external device.

[0007] Optionally, the historical demand data is extracted, including the driving condition data of the emergency power supply vehicle and the load demand data of the external device, and the historical demand data is preprocessed to obtain a standardized data set, specifically including: obtaining the driving condition data of the emergency power supply vehicle, including vehicle speed, acceleration and slope, through on-board sensors, and obtaining the load demand data of the external device, including current, voltage and power, through on-board power monitoring equipment; using a Kalman filter algorithm to denoise the historical demand data; using preset data cleaning rules to clean the denoised data; normalizing the cleaned data; integrating the normalized data, aligning the data according to timestamps, and generating a standardized data set.

[0008] Optionally, based on the historical demand data, the Kalman filter algorithm is used to predict the future electricity demand to obtain the prediction results, which specifically includes: constructing a prediction model based on the Kalman filter algorithm; obtaining the historical demand data of the past 24 hours, and inputting it into the prediction model after preprocessing to obtain the prediction results within the next 1 hour, including 12 prediction results, among which one prediction result is generated every 5 minutes.

[0009] Optionally, the real-time demand data is acquired, and it is determined whether the deviation value between the real-time demand data and the corresponding prediction result is greater than a set threshold value. If so, an energy scheduling plan is regenerated according to the deviation value. Specifically, the real-time demand data is collected every 5 minutes, and it is determined whether the deviation value between the real-time demand data and the corresponding prediction result exceeds a preset threshold value. If so, the parameters of the Kalman filter algorithm are updated to regenerate the energy scheduling plan.

[0010] Optionally, the set threshold is 5 times the root mean square error between the historical demand data and the corresponding prediction result.

[0011] Optionally, a particle swarm optimization algorithm is used to optimize the energy scheduling scheme, with the goals of minimizing energy consumption, maximizing power supply stability, minimizing system response time, and optimizing driving performance and load adaptability. The particle swarm optimization algorithm sets the number of particles to 50, the maximum number of iterations to 100, the inertia weight to 0.9, and the individual learning factor and the group learning factor to 2.

[0012] Optionally, based on the fuzzy rule base, an energy scheduling model is constructed with the goal of minimizing energy consumption and maximizing power supply stability, specifically including: constructing an energy scheduling model based on a long short-term memory network structure; based on the fuzzy rule base, using a standardized data set as the input of the energy scheduling model, using the fuel cell output power as the output of the energy scheduling model, training the energy scheduling model with the goal of minimizing energy consumption and maximizing power supply stability, and obtaining a trained energy scheduling model.

[0013] In the second aspect, an embodiment of the present application provides a fuel cell output power scheduling system on an emergency power supply vehicle, the system comprising: a data acquisition module, for collecting historical demand data, including driving condition data of the emergency power supply vehicle and load demand data of external equipment, and preprocessing the historical demand data to obtain a standardized data set; an energy scheduling module, for setting fuzzy control rules between the standardized data set and the fuel cell output power, and establishing a fuzzy rule base; for constructing an energy scheduling model based on the fuzzy rule base with the goal of minimizing energy consumption and maximizing power supply stability; for predicting future electricity demand based on historical demand data using a Kalman filter algorithm to obtain a prediction result; for using the prediction result as an input to an energy scheduling model to obtain an energy scheduling plan; an optimization module, for obtaining real-time demand data, and determining whether the deviation value between the real-time demand data and the corresponding prediction result is greater than a set threshold, and if so, regenerating an energy scheduling plan based on the deviation value.

[0014] Optionally, the data acquisition module includes: an acquisition unit, used to obtain the driving condition data of the emergency power supply vehicle, including vehicle speed, acceleration and slope, through on-board sensors; used to obtain the load demand data of external equipment, including current, voltage and power, through on-board power monitoring equipment; a preprocessing unit, used to denoise the historical demand data using a Kalman filter algorithm; used to clean the denoised data using preset data cleaning rules; used to normalize the cleaned data; used to integrate the normalized data, align the data according to timestamps, and generate a standardized data set.

[0015] In a third aspect, an embodiment of the present application provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the above method by executing the computer instructions.

[0016] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the above method.

[0017] In a fifth aspect, an embodiment of the present application provides a computer program product, including computer instructions, which are used to enable a computer to execute the above method. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0019] Figure 1 A flow chart of a method for scheduling output power of a fuel cell on an emergency power supply vehicle provided in an embodiment of the present application;

[0020] Figure 2 A diagram of a fuel cell output power dispatching system for an emergency power supply vehicle provided in an embodiment of the present application;

[0021] Figure 3 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0023] Emergency power supply vehicles face complex and changeable working conditions and external equipment load requirements during driving, which brings challenges to fuel cell power scheduling. There is a mutual influence and constraint relationship between the vehicle driving conditions (vehicle speed, acceleration, slope) and the external equipment load requirements (current, voltage, power). For example, when going uphill, the vehicle requires more power, which may affect the stability of the power supply of external equipment; and when high-power equipment is started, it may cause insufficient power for the vehicle. In addition, the load demand of external equipment is random and volatile, and it is difficult to predict accurately. This requires the fuel cell power scheduling strategy to respond quickly to changes in working conditions and balance the vehicle's driving performance and the quality of power supply to external equipment. However, frequent adjustments to the output power of the fuel cell may reduce its service life and efficiency. How to achieve the optimal scheduling of the output power of the fuel cell while ensuring the vehicle's driving performance and the quality of power supply to external equipment has become a technical problem that needs to be solved urgently.

[0024] According to an embodiment of the present application, an embodiment of a method for scheduling the output power of a fuel cell on an emergency power supply vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flow chart of a method for dispatching output power of a fuel cell on an emergency power supply vehicle provided in an embodiment of the present application, such as Figure 1 As shown, the process includes the following steps:

[0026] Step S1, extracting historical demand data, including the driving condition data of the emergency power supply vehicle and the load demand data of the external equipment, preprocessing the historical demand data to obtain a standardized data set, specifically including:

[0027] The driving condition data of the emergency power supply vehicle, including vehicle speed, acceleration and slope, is obtained through on-board sensors. The load demand data of external devices, including current, voltage and power, is obtained through on-board power monitoring equipment. The Kalman filter algorithm is used to denoise the historical demand data. The denoised data is cleaned using preset data cleaning rules. The cleaned data is normalized. The normalized data is integrated and aligned according to timestamps to generate a standardized data set.

[0028] For example, the real-time driving condition data of the emergency power supply vehicle is obtained through the on-board sensors, such as the speed sensor collects data every 1 second, the acceleration sensor sampling frequency is 100Hz, and the slope sensor accuracy reaches 1°. At the same time, the on-board power monitoring equipment obtains the load demand data such as current, voltage and power of the external device in a period of 10ms. The collected data is pre-processed, and the improved Kalman filter algorithm is used to dynamically estimate the system state by establishing the state equation and observation equation, and the noise covariance matrix is ​​adaptively adjusted to effectively remove Gaussian white noise and outliers, and the data quality is improved by more than 20%. According to the preset threshold range, data format and other cleaning rules, invalid data beyond the normal range is eliminated, such as the speed cannot exceed 120km / h, the voltage cannot be negative, etc., to ensure the rationality of the data. The minimum-maximum normalization method is used to map data of different dimensions such as speed, acceleration, slope, current, voltage, etc. to the [0,1] interval to achieve dimension unification. Through timestamp alignment, the normalized driving condition data and load demand data are integrated into a standardized data set at a frequency of one data point per second. Using the K-means clustering algorithm, by calculating the Euclidean distance between data points, the data set is divided into K clusters in an iterative optimization manner, such as dividing the driving condition into different categories such as low-speed stability (vehicle speed <30km / h, acceleration <1m / s^2), high-speed climbing (vehicle speed >60km / h, slope >5°), and rapid acceleration (acceleration >1m / s^2), to provide data support for the subsequent energy scheduling plan.

[0029] For example, obtain the historical demand data of the past 24 hours and preprocess the data. Use the 3σ criterion to remove outliers, that is, data points that exceed the mean ±3 times the standard deviation are considered outliers and are removed. Then use the minimum-maximum normalization method to map the data to the [0,1] interval. Based on the first-order autoregressive model, establish the state equation: x(k)=8x(k-1)+w(k), where x(k) represents the electricity demand state at time k, w(k) is the process noise, and obeys a Gaussian distribution with a mean of 0 and a variance of 01. The observation equation is: z(k)=x(k)+v(k), where z(k) is the actual observation value at time k, and v(k) is the observation noise, which obeys a Gaussian distribution with a mean of 0 and a variance of 02.

[0030] Step S3, setting fuzzy control rules between the standardized data set and the fuel cell output power, and establishing a fuzzy rule base.

[0031] In some embodiments, vehicle driving condition data, including vehicle speed, acceleration, slope, etc., are obtained and used as input variables of the fuzzy control algorithm. Fuzzification processing is performed through the membership function to obtain fuzzy input variables; external device load demand parameters are obtained, including load power, voltage stability requirements, power factor requirements, and harmonic distortion rate requirements, etc., and used as constraints and evaluation indicators of the fuzzy control algorithm. According to the fuel cell output characteristic model, the feasible range and optimal working range of the fuel cell output power are determined, and used as the output variable range of the fuzzy control algorithm. In the fuzzy rule base, fuzzy control rules between input variables such as vehicle speed, acceleration, slope, and load power and fuel cell output power are set to form a complete fuzzy rule base. According to the fuzzified input variables and the fuzzy rule base, a fuzzy inference algorithm is used to infer the fuzzy quantity of the fuel cell output power, and then through defuzzification processing, an accurate fuel cell output power value can be obtained.

[0032] When obtaining vehicle driving condition data, first collect data such as vehicle speed, acceleration and slope in real time through sensors. For example, the vehicle speed is 60 kilometers per hour, the acceleration is 2 meters per second squared, and the slope is 5 degrees. Input these data into the fuzzy control algorithm, perform fuzzification through the membership function, and obtain fuzzy input variables. Next, obtain the load demand parameters of the external device, including load power of 50 kilowatts, voltage stability requirement of ±5%, power factor requirement of 95, and harmonic distortion rate requirement of less than 3%. These parameters serve as constraints and evaluation indicators of the fuzzy control algorithm. Using historical data and real-time monitoring data, a time series prediction algorithm, such as the ARIMA model, is used to predict the trend of vehicle power demand in the next 30 minutes. The prediction results show that the future power demand will increase to 55 kilowatts. Use this prediction result as a reference input for the fuzzy control algorithm. According to the fuel cell output characteristic model, the feasible range of fuel cell output power is determined to be 40 to 70 kilowatts, and the optimal working range is 50 to 60 kilowatts. Use it as the output variable range of the fuzzy control algorithm. In the fuzzy rule base, the fuzzy control rules between the input variables such as vehicle speed, acceleration, slope and load power and the fuel cell output power are set. For example, when the vehicle speed is high and the load power is large, the fuel cell output power should increase. According to the fuzzified input variables and the fuzzy rule base, the fuzzy inference algorithm is used to infer the fuzzy value of the fuel cell output power to be 58 kilowatts. Then, through the defuzzification process, the accurate fuel cell output power value is 57 kilowatts.

[0033] Step S5, based on the fuzzy rule base, with the goal of minimizing energy consumption and maximizing power supply stability, construct an energy scheduling model, specifically including:

[0034] Construct an energy scheduling model based on a long short-term memory network structure; based on the fuzzy rule base, take the standardized data set as the input of the energy scheduling model, take the fuel cell output power as the output of the energy scheduling model, train the energy scheduling model with the goal of minimizing energy consumption and maximizing power supply stability, and obtain the trained energy scheduling model.

[0035] For example, an energy scheduling model with a long short-term memory network structure containing 3 hidden layers is constructed. Each hidden layer contains 128 neurons, the number of neurons in the input layer and the output layer are 10 and 2 respectively, the activation function of the hidden layer is the hyperbolic tangent function, the activation function of the output layer is the linear function, the learning rate is set to 001, and the batch size is set to 64. The preprocessed standardized data set is divided into a training set and a validation set with a ratio of 8:2, and input into the energy scheduling model for training. The Adam optimization algorithm and the mean square error loss function are used, and 1000 epochs are iterated to obtain the trained energy scheduling optimization model.

[0036] In some embodiments, a deep learning algorithm is introduced based on the fuzzy rule base to establish an energy scheduling optimization model. The model adopts a long short-term memory network structure to minimize energy consumption and maximize power supply stability as the optimization goal. The long short-term memory network processes time series data through input gates, forget gates, and output gates to capture the long-term dependency between vehicle driving performance and changes in external device load demand.

[0037] In some embodiments, an energy scheduling model based on a long short-term memory network structure is constructed, the number of neurons in the input layer, hidden layer, and output layer is set, the number of layers of the network and the activation function of each layer are determined, the model parameters are initialized, and the hyperparameters of the model, such as the learning rate and batch size, are determined. The preprocessed standardized data set is input into the energy scheduling model as training data, and the weights and biases of the network are continuously adjusted through the forward propagation and back propagation algorithms to minimize the loss function of energy consumption and maximize the power supply stability, and the trained energy scheduling optimization model is obtained. Through the input gate, forget gate, and output gate of the long short-term memory network, the long-term dependency between the vehicle driving performance and the load demand changes of the external device is captured, and the energy scheduling plan is dynamically generated. The generated energy scheduling plan is passed to the fuzzy control algorithm, and the energy scheduling plan is optimized and adjusted according to the fuzzy rule base and the membership function, and is finally used to control the working state of energy equipment such as fuel cells, battery packs, and supercapacitors to achieve the goal of minimizing energy consumption and maximizing power supply stability.

[0038] Step S7, based on the historical demand data, the Kalman filter algorithm is used to predict the future electricity demand, and the prediction result is used as the input of the energy scheduling model to obtain the energy scheduling plan, which specifically includes:

[0039] Construct a prediction model based on the Kalman filter algorithm; pre-process the historical demand data of the past 24 hours and input it into the prediction model to obtain the prediction results for the next hour, including 12 prediction results, among which one prediction result is generated every 5 minutes.

[0040] The Kalman filter algorithm establishes a mathematical model through state equations and observation equations, and uses historical demand data and current observations for recursive estimation to obtain prediction results. The prediction results provide a basis for fuel cell power scheduling and improve system response speed and stability.

[0041] In some embodiments, a state equation and an observation equation for electricity demand prediction are established based on historical demand data and current observation values. The state equation adopts a first-order autoregressive model, and the observation equation is a linear model. Based on these two equations, a mathematical model of the Kalman filter algorithm is constructed. The electricity demand data of the external device in the past 24 hours is obtained from the database, and the data is preprocessed, including removing outliers and normalizing. The processed data is used as the input of the Kalman filter algorithm, and the prediction result at the current moment is obtained by recursive estimation. The prediction result is used as the input of the energy scheduling model to obtain an energy scheduling plan. Among them, the time series analysis method is used to predict the electricity demand trend in the next 1 hour, and a prediction result is generated every 5 minutes, and a total of 12 prediction results are generated. The electricity demand trend is obtained based on the 12 prediction results, and the output power of the fuel cell is dynamically adjusted to meet the electricity demand.

[0042] Step S9, obtaining real-time demand data, determining whether the deviation between the real-time demand data and the corresponding prediction result is greater than a set threshold, and if so, regenerating an energy scheduling plan according to the deviation value, specifically including:

[0043] For example, it is determined whether the deviation between the real-time demand data and the corresponding forecast results exceeds a preset threshold. If so, the parameters of the Kalman filter algorithm are updated and the energy scheduling plan is regenerated. The threshold is set to 5 times the root mean square error between the historical demand data and the corresponding forecast results.

[0044] In some embodiments, if the deviation between the current observation value and the predicted result exceeds 5 times the historical root mean square error, it is determined that the electricity demand has fluctuated, and the diagonal elements of the process noise covariance matrix Q are increased by 10 times. After adjustment, the exponential smoothing method is used to predict the electricity demand for the next hour, the smoothing coefficient α is 6, and a prediction result is generated every 5 minutes. The prediction result is input into the energy scheduling model, with the prediction result as input and the fuel cell output power as output.

[0045] In some embodiments, the method further includes constructing an energy scheduling scheme simulation model for simulating and verifying the generated energy scheduling scheme. The simulation test environment includes a vehicle dynamics model, a fuel cell model, and an external load model.

[0046] For example, the vehicle driving condition data, external equipment load demand data and fault scenario data are obtained, and the data is preprocessed by using an anomaly detection algorithm based on cluster analysis to remove outliers and noise. The preprocessed data is analyzed to determine the key parameters and constraints of the vehicle dynamics model, fuel cell model and external load model. Based on the above-determined parameters and constraints, an energy scheduling scheme simulation model is constructed, fully considering the correlation between the vehicle driving condition and the change of external equipment load demand. The constructed simulation model is combined with the fuzzy PID control algorithm to dynamically adjust the energy scheduling scheme according to the changes in the vehicle driving condition and the external equipment load demand. A simulation test platform is built in the MATLAB / Simulink environment, and the simulation model, fuzzy PID control algorithm and long short-term memory network (LSTM) algorithm are integrated into the platform. According to different driving conditions, external equipment load demand and fault scenarios, multiple groups of simulation test cases are designed to comprehensively evaluate the feasibility of the energy scheduling scheme. During the simulation test process, the parameters of the vehicle dynamics model, fuel cell model and load model are dynamically adjusted to simulate the dynamic changes in actual applications, and the LSTM algorithm is used to analyze the simulation test results, extract key features, and optimize the energy scheduling scheme. Based on multiple groups of simulation test results, the weighted scoring method is used to evaluate the comprehensive performance of the energy scheduling scheme and obtain the simulation evaluation results.

[0047] In some embodiments, an abnormality detection algorithm based on cluster analysis is used to preprocess the data to remove outliers and noise. The K-means clustering algorithm is used to divide the data into two categories: normal and abnormal, and the abnormal data is eliminated to obtain high-quality data. Then, the key parameters and constraints of the vehicle dynamics model, fuel cell model and load model are determined by performing correlation analysis on the preprocessed data. For example, the analysis found that the correlation coefficient between vehicle speed and acceleration is 85, indicating that the two have a strong linear relationship, and they are used as key parameters in the dynamics model. After obtaining the vehicle driving condition data, external device load demand data and fault scenario data, the random forest algorithm is first used to preprocess the data. After preprocessing, the data is analyzed to determine the key parameters and constraints of the vehicle dynamics model, fuel cell model and load model. For example, the key parameters of the vehicle dynamics model may include vehicle mass, air resistance coefficient, etc., while the constraints of the fuel cell model may involve output power range and efficiency curve. Based on these parameters and constraints, an energy scheduling scheme simulation model is constructed, fully considering the correlation between vehicle driving conditions and load demand changes, so that the model is closer to the actual application scenario.

[0048] In some embodiments, the above method also includes using a particle swarm optimization algorithm to optimize the energy scheduling scheme, with the goals of minimizing energy consumption, maximizing power supply stability, minimizing system response time, and optimizing driving performance and load adaptability, wherein the particle swarm optimization algorithm sets the number of particles to 50, the maximum number of iterations to 100, the inertia weight to 0.9, and the individual learning factor and the group learning factor to 2.

[0049] For example, by analyzing the simulation data, it is found that when the vehicle is driving uphill, the fuel cell needs to provide a greater output power, while when it is driving downhill, the output power can be appropriately reduced. At the same time, the power demand of external devices also shows obvious fluctuation characteristics, with higher demand in certain time periods and lower demand in other time periods. Based on these data, the particle swarm optimization algorithm is used to build a multi-objective optimization model with energy utilization efficiency, power supply stability, system response time, vehicle driving performance and load adaptability as optimization goals. The parameters of the particle swarm optimization algorithm are set, including the number of particles as 50, the maximum number of iterations as 100, the inertia weight as 8, the individual learning factor as 5, and the group learning factor as 0. Through iterative optimization, the position and speed of the particles are continuously updated to search for the optimal solution of the energy scheduling scheme so that it can better adapt to the vehicle driving conditions and load demand changes. In the optimization process, an adaptive weight adjustment strategy is introduced to dynamically adjust the weight coefficient according to the importance of each optimization target to improve the optimization efficiency and accuracy. If the optimization result meets the convergence condition or reaches the maximum number of iterations, the optimized energy scheduling scheme is output; otherwise, iterative optimization continues. The optimized energy scheduling scheme is converted into specific execution instructions, including fuel cell power output setting value, load distribution strategy and energy management parameters. For example, when the vehicle is in the acceleration state, the fuel cell output power is set to 80% of the rated power, and the battery pack provides the remaining power; when the vehicle is in the cruising state, the fuel cell output power is set to 60% of the rated power, and the battery pack provides the remaining power and charges. Finally, the execution instructions are sent to the on-board controller to control the fuel cell system in real time to ensure that it operates according to the optimized scheduling scheme and improve the robustness and adaptability of the system.

[0050] The embodiment of the present application proposes a method for scheduling the output power of a fuel cell on an emergency power supply vehicle. The method extracts historical demand data, including the driving condition data of the emergency power supply vehicle and the load demand data of an external device, pre-processes the historical demand data, and obtains a standardized data set; sets fuzzy control rules between the standardized data set and the output power of the fuel cell, and establishes a fuzzy rule base; based on the fuzzy rule base, an energy scheduling model is constructed with the goal of minimizing energy consumption and maximizing power supply stability; based on the historical demand data, a Kalman filter algorithm is used to predict future electricity demand and obtain a prediction result; the prediction result is used as the input of the energy scheduling model to obtain an energy scheduling plan; real-time demand data is obtained to determine whether the deviation value between the real-time demand data and the corresponding prediction result is greater than a set threshold value, and if so, the energy scheduling plan is regenerated according to the deviation value, thereby solving the technical problem of optimal scheduling of the output power of the fuel cell and achieving the technical effect of balancing the driving performance of the vehicle and the power supply quality of the external device.

[0051] Please refer to Figure 2 , is a diagram of a fuel cell output power scheduling system on an emergency power supply vehicle provided in an embodiment of the present application, the system comprising: a data acquisition module, used to collect historical demand data, including driving condition data of the emergency power supply vehicle and load demand data of external equipment, preprocessing the historical demand data to obtain a standardized data set; an energy scheduling module, used to set fuzzy control rules between the standardized data set and the fuel cell output power, and establish a fuzzy rule base; used to construct an energy scheduling model based on the fuzzy rule base with the goal of minimizing energy consumption and maximizing power supply stability; used to predict future electricity demand based on historical demand data using a Kalman filter algorithm to obtain a prediction result; used to use the prediction result as an input to the energy scheduling model to obtain an energy scheduling plan; an optimization module, used to obtain real-time demand data, determine whether the deviation value between the real-time demand data and the corresponding prediction result is greater than a set threshold, and if so, regenerate the energy scheduling plan based on the deviation value.

[0052] In some embodiments, the data acquisition module includes: an acquisition unit, used to obtain the driving condition data of the emergency power supply vehicle through on-board sensors, including vehicle speed, acceleration and slope; used to obtain the load demand data of external devices through on-board power monitoring equipment, including current, voltage and power; a preprocessing unit, used to denoise the historical demand data using a Kalman filtering algorithm; used to clean the denoised data using preset data cleaning rules; used to normalize the cleaned data; used to integrate the normalized data, align the data according to timestamps, and generate a standardized data set.

[0053] The system in this embodiment is presented in the form of functional units, where the units refer to ASIC (Application Specific Integrated Circuit) circuits, processors and memories that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0054] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, such as Figure 3 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3 A processor 10 is taken as an example.

[0055] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0056] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0057] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0058] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0059] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0060] The embodiment of the present application also provides a computer-readable storage medium. The above method according to the embodiment of the present application can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0061] The embodiment of the present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method of any embodiment of the present application.

[0062] Although the embodiments of the present application are described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

[0063] The systems, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0064] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0065] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0066] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0067] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0068] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0069] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0070] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0071] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

[0072] Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for dispatching the output power of a fuel cell on an emergency power supply vehicle, characterized in that: The method comprises: Extracting historical demand data, including driving condition data of the emergency power supply vehicle and load demand data of external equipment, and preprocessing the historical demand data to obtain a standardized data set; A fuzzy control rule between the standardized data set and the fuel cell output power is set to establish a fuzzy rule base, wherein the vehicle driving condition data is used as a fuzzy input variable after being fuzzified by a membership function, and the vehicle driving condition data includes vehicle speed, acceleration and slope; and the external device load demand parameter is used as a constraint condition and evaluation index of the fuzzy control algorithm; Based on the fuzzy rule base, an energy scheduling model based on a long short-term memory network structure is constructed, wherein based on the fuzzy rule base, a standardized data set is used as an input of the energy scheduling model, and the output power of the fuel cell is used as an output of the energy scheduling model, and the energy scheduling model is trained to minimize energy consumption and maximize power supply stability, thereby obtaining a trained energy scheduling model; Based on the historical demand data, a Kalman filter algorithm is used to predict future electricity demand to obtain a prediction result, and the prediction result is used as an input of an energy scheduling model to obtain an energy scheduling plan; Acquire real-time demand data, and determine whether a deviation value between the real-time demand data and a corresponding prediction result is greater than a set threshold. If so, regenerate an energy scheduling plan based on the deviation value.

2. The method according to claim 1, characterized in that The historical demand data is extracted, including the driving condition data of the emergency power supply vehicle and the load demand data of the external device, and the historical demand data is preprocessed to obtain a standardized data set, specifically including: Obtain the driving condition data of the emergency power supply vehicle through the on-board sensors, including vehicle speed, acceleration and slope, and obtain the load demand data of the external equipment through the on-board power monitoring equipment, including current, voltage and power; The Kalman filter algorithm is used to denoise the historical demand data; Use the preset data cleaning rules to clean the denoised data; Normalize the cleaned data; The normalized data is integrated and aligned according to timestamps to generate a standardized data set.

3. The method according to claim 1, characterized in that Based on the historical demand data, the Kalman filter algorithm is used to predict the future electricity demand to obtain the prediction results, which specifically include: Construct a prediction model based on the Kalman filter algorithm; The historical demand data of the past 24 hours is preprocessed and input into the forecasting model to obtain the forecast results for the next hour, including 12 forecast results, among which one forecast result is generated every 5 minutes.

4. The method according to claim 3, characterized in that The acquiring of real-time demand data, determining whether a deviation between the real-time demand data and a corresponding prediction result is greater than a set threshold, and if so, regenerating an energy scheduling plan according to the deviation value, specifically includes: Real-time demand data is collected every 5 minutes to determine whether the deviation between the real-time demand data and the corresponding prediction result exceeds a preset threshold. If so, the parameters of the Kalman filter algorithm are updated and the energy scheduling plan is regenerated.

5. The method according to claim 4, characterized in that The set threshold is 5 times the root mean square error between the historical demand data and the corresponding prediction result.

6. The method according to claim 1, characterized in that The method also includes: optimizing the energy scheduling scheme using a particle swarm optimization algorithm to minimize energy consumption, maximize power supply stability, minimize system response time, and optimize driving performance and load adaptability performance, wherein in the particle swarm optimization algorithm, the number of particles is set to 50, the maximum number of iterations is 100, the inertia weight is 0.9, and the individual learning factor and the group learning factor are both 2.

7. A fuel cell output power dispatching system for an emergency power supply vehicle, characterized in that: The system comprises: A data acquisition module is used to collect historical demand data, including the driving condition data of the emergency power supply vehicle and the load demand data of the external equipment; and is used to pre-process the historical demand data to obtain a standardized data set; An energy scheduling module is used to set fuzzy control rules between the standardized data set and the fuel cell output power, and establish a fuzzy rule base, wherein the vehicle driving condition data is used as a fuzzy input variable after fuzzification through a membership function, and the vehicle driving condition data includes vehicle speed, acceleration and slope; the external device load demand parameter is used as a constraint condition and evaluation index of the fuzzy control algorithm; it is used to construct an energy scheduling model based on a long short-term memory network structure based on the fuzzy rule base, wherein based on the fuzzy rule base, the standardized data set is used as the input of the energy scheduling model, and the fuel cell output power is used as the output of the energy scheduling model, and the energy scheduling model is trained to minimize energy consumption and maximize power supply stability, and a trained energy scheduling model is obtained; it is used to predict future electricity demand based on historical demand data using a Kalman filter algorithm to obtain a prediction result; it is used to use the prediction result as the input of the energy scheduling model to obtain an energy scheduling plan; The optimization module is used to obtain real-time demand data, determine whether the deviation value between the real-time demand data and the corresponding prediction result is greater than a set threshold, and if so, regenerate an energy scheduling plan based on the deviation value.

8. The system according to claim 7, characterized in that The data acquisition module comprises: An acquisition unit is used to acquire the driving condition data of the emergency power supply vehicle through the vehicle-mounted sensor, including vehicle speed, acceleration and slope; and is used to acquire the load demand data of the external device through the vehicle-mounted power monitoring device, including current, voltage and power; The preprocessing unit is used to denoise the historical demand data using the Kalman filter algorithm; to clean the denoised data using preset data cleaning rules; to normalize the cleaned data; to integrate the normalized data, align the data according to timestamps, and generate a standardized data set.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 6 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

11. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method according to any one of claims 1 to 6.

Images