CN113283005A - Optimized scheduling method of fuel cell engine test system - Google Patents

Abstract

The invention discloses an optimization scheduling method of a fuel cell engine test system. According to the operation requirements of the fuel cell engine, the operation conditions of the fuel cell engine test system are designed, and the feasible range of the operation parameters of each subsystem of the fuel cell engine test system is determined, and the operation parameters of each subsystem of the fuel cell engine test system are determined with high Reliability, long life, and good adaptability to low-temperature environments are used as the optimization goals, and a multi-objective optimization function is built, and the NSGA-II algorithm is used to complete the multi-objective optimization. The invention adopts the NSGA-II algorithm to solve the multi-objective problem of the parameters of the fuel cell engine test system and obtains the Pareto optimal solution, which not only enables the fuel cell engine test system to obtain high efficiency and high performance, but also provides multiple sets of parameters for the testers. To optimize the solution, testers can choose different parameter combinations according to different needs.

Description

Optimal Scheduling Method of Fuel Cell Engine Test System

technical field

The invention relates to the field of optimal scheduling of fuel cell engines, in particular to an optimal scheduling method of a fuel cell engine test system.

Background technique

New energy vehicles use unconventional vehicle fuels as power sources. Its appearance reduces people's demand for traditional vehicles and brings new solutions to energy problems and environmental pollution problems. There are many types of new energy vehicles. Among them, fuel cell vehicles have become the key research and development targets of major car companies due to their advantages of low pollution, high efficiency, low noise and high reliability. A fuel cell engine is a power generation device that directly converts hydrogen and oxygen into electrical energy through electrochemical reaction. The operation of a fuel cell engine does not involve combustion, has no mechanical loss, and has a high energy conversion rate. The products are only electricity, heat and water. Smooth and low noise. With the rapid development of fuel cell technology, its power and performance are rapidly improved, and the development of fuel cell engine test systems has attracted more and more attention. At present, due to technical confidentiality reasons, the published literature is mainly about a certain performance of the fuel cell test system.

SUMMARY OF THE INVENTION

The main purpose of the invention is to optimize the fuel cell engine test system through the NSGA-II algorithm. The optimization of the fuel cell engine test system mainly adjusts the fuel cell by adjusting the hydrogen feed, air feed and cooling and heat dissipation energy, so as to achieve the optimization effect. .

In order to solve the above-mentioned technical problems, a technical scheme adopted in the present invention is:

Provided is an optimal scheduling method for a fuel cell engine test system, the steps comprising:

(1) Collect historical data when the fuel cell engine test system is running, and preprocess the collected historical data to remove abnormal data;

(2) According to the basic parameters and operating conditions of the fuel cell engine test system, the preprocessed data are classified according to different operating conditions to form the operating data of each operating condition;

(3) Establish a multi-objective optimization function and model the fuel cell engine system;

(4) Perform parameter fitting on the operating data under different working conditions to obtain the objective function under different working conditions;

(5) Use the NSGA-II algorithm to solve the multi-objective optimization model, obtain the Pareto optimal solution set, determine the optimal parameters of each subsystem, and optimize and control the fuel cell engine test system according to the optimal parameters.

In a preferred embodiment of the present invention, the specific steps of preprocessing the collected historical data include:

(a) remove missing and duplicate data;

(b) Converting data of different types of parameters, so that there is a mutual influence relationship between the parameters;

准则剔除误差较大的异常数据。(c) Utilize 3

The criterion excludes abnormal data with large error.

In a preferred embodiment of the present invention, the operating conditions of the fuel cell engine test system include idle speed conditions, full power conditions, and low temperature conditions.

In a preferred embodiment of the present invention, the subsystems of the fuel cell engine test system include a gas gas supply system, a circulating cooling water system, an exhaust gas emission system, an electronic load system, a safety system, a sensor measurement system, a test platform monitoring system, an auxiliary Power source system.

In a preferred embodiment of the present invention, in step (3), the fuel cell engine test system is modeled, with high reliability, long life, and good adaptability to low temperature environments as the optimization goals, and each sub-system of the fuel cell engine test system is optimized The system output is the decision variable, and the multi-objective optimization model of the fuel cell engine system is established with the threshold of each decision variable and the numerical relationship between the operating parameters as constraints.

In a preferred embodiment of the present invention, the specific steps of parameter fitting are: according to the hydrogen supply function relationship, the air supply function relationship and the cooling and heat dissipation function relationship, the operating data under different working conditions are analyzed by nonlinear least squares method. Fitting to obtain the coefficients of the objective function, so as to obtain the objective function under different working conditions.

，In a preferred embodiment of the present invention, the hydrogen supply function relationship

,

为氢气计量比，

为单电池节数，

为目标电流；in,

is the hydrogen stoichiometric ratio,

is the number of single battery cells,

is the target current;

，Air supply function relationship

,

为氢气计量比，

为单电池节数，

为目标电流；in,

is the hydrogen stoichiometric ratio,

is the number of single battery cells,

is the target current;

，Cooling heat dissipation function relationship

,

表示内循环水流量，

表示水定压比热容，

表示内循环水电池出口温度，

表示内循环水电池进口温度，

表示外循环水流量，

表示外循环水换热器进口温度，

表示外循环水换热器出口温度。in,

Represents the internal circulating water flow,

represents the specific heat capacity of water at constant pressure,

Indicates the outlet temperature of the internal circulating water battery,

Indicates the inlet temperature of the internal circulating water battery,

represents the external circulating water flow,

Indicates the inlet temperature of the external circulating water heat exchanger,

Indicates the outlet temperature of the external circulating water heat exchanger.

In a preferred embodiment of the present invention, in step (5), the specific flow of the NSGA-II algorithm optimization is: using the NSGA-II algorithm to solve the multi-objective optimization model

Define the NSGA-II optimization algorithm;

The parent population is obtained by random initialization, and the ordinal values of all individuals are obtained and sorted through non-dominated sorting, and the crowding distance between individuals with the same ordinal value is calculated at the same time;

Using the selection, crossover and mutation operators of the genetic algorithm, taking the order value and crowding distance of each individual as a reference, the offspring population is obtained through evolution;

In order to expand the optimization space, the elite strategy combines the child population with the parent population, and then performs non-dominant sorting and crowding distance calculation on it, and finally obtains the next generation population by pruning the population to ensure that the best individual can evolve to next generation, so that it will not be lost;

After the next generation population is obtained, it is judged whether the maximum evolutionary algebra is reached, and once the set evolutionary cycle algebra is reached, the calculation is terminated and the optimal solution is output.

In a preferred embodiment of the present invention, the step of initializing the population includes setting population size, evolutionary algebra, Pareto ratio, number of independent variables, number of objective functions, and setting upper and lower population limits.

The beneficial effects of the present invention are: using the NSGA-II algorithm to solve the multi-objective problem of the parameters of the fuel cell engine test system to obtain the Pareto optimal solution, which not only enables the fuel cell engine test system to obtain high efficiency and high performance, but also provides a high level of performance for the test system. The personnel provide multiple sets of parameter optimization schemes, and testers can choose different parameter combinations according to different needs.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, under the premise of no creative work, other drawings can also be obtained from these drawings, wherein:

1 is a schematic flowchart of a preferred embodiment of an optimal scheduling method for a fuel cell engine test system of the present invention;

FIG. 2 is a flowchart of the NSGA-II optimization algorithm in a preferred embodiment of the optimal scheduling method of the fuel cell engine test system of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Referring to Figures 1-2, embodiments of the present invention include:

An optimal scheduling method for a fuel cell engine test system, the specific steps of which are:

Step 1. Collect historical data when the fuel cell engine test system is running, and perform data preprocessing on the collected historical data.

The preprocessing of the data is carried out according to the following steps. First, if the collected data is missing or duplicated, the data will be deleted. Second, if the collected data types are different, the data will be converted with the help of functional relationships. There is a correlation between the data. Finally, the collected historical data is analyzed for error, and the abnormal data with large error is eliminated by using the 3σ criterion to improve the accuracy of the historical data.

Step 2. The operating conditions of the fuel cell engine test system mainly include idle speed conditions, full power conditions, and low temperature conditions. The fuel cell engine test system mainly includes a gas supply system, a circulating cooling water system, an exhaust gas emission system, an electronic load system, a safety system, a sensor measurement system, a test platform monitoring system, and an auxiliary power source.

According to the basic parameters and operating conditions of the fuel cell engine test system described above, the preprocessed historical data are classified according to different operating conditions to form historical operating data of each operating condition.

Step 3. In order to establish a multi-objective optimization function including high reliability, long life and good adaptability to low temperature environment, model the fuel cell engine test system, and use high reliability, long life and good adaptability to low temperature environment as the fuel cell engine The main optimization objective of the test system is to establish a multi-objective optimization model of the fuel cell engine test system with the output of each subsystem of the fuel cell engine test system as the decision variable, and the threshold value of each decision variable and the numerical relationship between the operating parameters as the constraint condition. .

Step 4. Through the hydrogen supply function relationship, the air supply function relationship and the cooling and heat dissipation function relationship, the parameters under different working conditions are fitted by the nonlinear least squares method, so as to obtain various coefficients of the objective function, and finally obtain different working conditions. the objective function in the case.

，其中

表示氢气计量比，

代表单电池节数，

为目标电流；The hydrogen supply function relationship is

,in

represents the hydrogen metering ratio,

represents the number of single battery cells,

is the target current;

，其中

表示氢气计量比，

代表单电池节数，

为目标电流；The air supply function relationship is

,in

represents the hydrogen metering ratio,

represents the number of single battery cells,

is the target current;

，其中

表示内循环水流量，

表示水定压比热容，

表示内循环水电池出口温度，

表示内循环水电池进口温度，

表示外循环水流量，

表示外循环水换热器进口温度，

表示外循环水换热器出口温度。The cooling and heat dissipation function relationship is

,in

Represents the internal circulating water flow,

represents the specific heat capacity of water at constant pressure,

Indicates the outlet temperature of the internal circulating water battery,

Indicates the inlet temperature of the internal circulating water battery,

represents the external circulating water flow,

Indicates the inlet temperature of the external circulating water heat exchanger,

Indicates the outlet temperature of the external circulating water heat exchanger.

Step 5. As shown in Figure 2, use the NSGA-II algorithm to solve the multi-objective optimization model, obtain the Pareto optimal solution set, and determine the optimal parameters of each subsystem.

The optimization process of the NSGA-II algorithm is as follows: first, define the NSGA-II optimization algorithm; secondly, the parent population is obtained by random initialization, and the ordinal values of all individuals are obtained and sorted through non-dominated sorting. Calculate the crowding distance; use the selection, crossover and mutation operators of the genetic algorithm again, and use the order value and crowding distance of each individual as a reference to obtain the offspring population through evolution; finally, in order to expand the optimization space, the elite strategy will The generation population is combined with the parent population, and the non-dominant sorting and crowding distance calculation are performed on it, and then the next generation population is obtained by pruning the population, which can ensure that the best individual can evolve to the next generation, so that it will not be lost; After the next generation population is obtained, it is judged whether the maximum evolutionary algebra is reached. Once the set evolutionary cycle algebra is reached, the calculation is terminated and the optimal solution is output.

Initializing the population includes setting the population size, evolutionary algebra, Pareto ratio, the number of independent variables, the number of objective functions, and setting the upper and lower limits of the population.

In this embodiment, the NSGA-II algorithm is used to coordinate the relationship between various objective functions, and to find an optimal solution set that makes each objective function reach a relatively large (or relatively small) function value as much as possible.

The beneficial effect of the optimal scheduling method for the fuel cell engine test system of the present invention is that the NSGA-II algorithm is used to solve the multi-objective problem of the fuel cell engine test system parameters, and the Pareto optimal solution is obtained, which not only enables the fuel cell engine test system to obtain High efficiency and high performance, and also provide testers with multiple sets of parameter optimization solutions, testers can choose different parameter combinations according to different needs.

The above descriptions are only the embodiments of the present invention, and are not intended to limit the scope of the patent of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the description of the present invention, or directly or indirectly applied in other related technical fields, are all applicable. Similarly, it is included in the scope of patent protection of the present invention.

Claims (9)

1. An optimal scheduling method for a fuel cell engine test system is characterized by comprising the following steps:

(1) collecting historical data of a fuel cell engine test system during operation, preprocessing the collected historical data, and removing abnormal data;

(2) classifying the preprocessed data according to different working conditions according to basic parameters and the operating working conditions of a fuel cell engine test system to form operating data of each working condition;

(3) establishing a multi-objective optimization function, and modeling a fuel cell engine system;

(4) performing parameter fitting on the operation data under different working conditions to obtain target functions under different working conditions;

(5) and solving the multi-objective optimization model by using an NSGA-II algorithm to obtain a Pareto optimal solution set, determining the optimal parameters of each subsystem, and optimally regulating and controlling the fuel cell engine test system according to the optimal parameters.

2. The optimized scheduling method of a fuel cell engine test system as claimed in claim 1, wherein the specific step of preprocessing the collected historical data comprises:

(a) deleting missing and repeated data;

(b) converting data of different types of parameters to enable the parameters to have a mutual influence relationship;

(c) by using 3

And rejecting abnormal data with large errors according to the criterion.

3. The method of claim 1, wherein the operating conditions of the fuel cell engine test system include idle, full power, and low temperature conditions.

4. The method of claim 1, wherein the subsystems of the fuel cell engine test system include a gas supply system, a recirculating cooling water system, an exhaust system, an electronic load system, a safety system, a sensor measurement system, a test platform monitoring system, and an auxiliary power source system.

5. The optimal scheduling method for a fuel cell engine test system as claimed in claim 1, wherein in the step (3), the fuel cell engine test system is modeled to establish the fuel cell engine system multi-objective optimization model with high reliability, long service life and good adaptability to low-temperature environment as optimization objectives, each subsystem output quantity of the fuel cell engine test system is used as a decision variable, and a numerical relationship between a threshold value and an operation parameter of each decision variable is used as a constraint condition.

6. The optimal scheduling method of a fuel cell engine test system according to claim 1, wherein the specific steps of parameter fitting are: and performing parameter fitting on the operation data under different working conditions by adopting a nonlinear least square method through the hydrogen supply functional relation, the air supply functional relation and the cooling and heat dissipation functional relation to obtain each coefficient of the objective function, so as to obtain the objective function under different working conditions.

7. The optimized scheduling method of a fuel cell engine testing system of claim 6,

hydrogen supply function relationship

，

Wherein,

the hydrogen gas is used as the metering ratio of the hydrogen gas,

the number of the single cell sections is,

is a target current;

air supply function relationship

，

Wherein,

the hydrogen gas is used as the metering ratio of the hydrogen gas,

the number of the single cell sections is,

is a target current;

cooling heat dissipation function relationship

，

Wherein,

the flow rate of the internal circulation water is shown,

it represents the specific heat capacity of water at constant pressure,

represents the outlet temperature of the internal circulation water cell,

represents the inlet temperature of the internal circulation water cell,

the flow rate of the external circulation water is shown,

the temperature of the inlet of the external circulating water heat exchanger is shown,

the outside circulation water heat exchanger outlet temperature is indicated.

8. The optimal scheduling method of the fuel cell engine test system according to claim 1, wherein in the step (5), the specific process of the NSGA-II algorithm optimization is as follows: multi-objective optimization model solved by using NSGA-II algorithm

Defining an NSGA-II optimization algorithm;

randomly initializing to obtain a parent population, obtaining sequence values of all individuals through non-dominated sorting, sorting the sequence values, and calculating the crowding distance between the individuals with the same sequence value;

utilizing selection, crossing and mutation operators of a genetic algorithm, taking the sequence value and the crowding distance of each individual as references, and obtaining offspring populations through evolution;

in order to expand the optimizing space, the elite strategy combines the offspring population and the parent population, then performs non-dominated sorting and congestion distance calculation on the offspring population and finally prunes the population to obtain the next generation population so as to ensure that the best individual can evolve to the next generation and not be lost;

and after obtaining the next generation population, judging whether the maximum evolution algebra is reached, and once the maximum evolution algebra is reached, stopping calculating and outputting the optimal solution.

9. The fuel cell engine test system optimized scheduling method of claim 8, wherein the step of initializing a population includes setting a population size, an evolutionary algebra, a pareto ratio, a number of independent variables, a number of objective functions, and setting a population upper limit and a population lower limit.

Images