A fuel cell cooling fan control method and system

The BP neural network model adjusts the working number and duty cycle signals of the fuel cell cooling fan, which solves the problem of inaccurate temperature control in the existing technology, achieves a more accurate heat dissipation effect, and extends the service life of the fuel cell.

CN115472877BActive Publication Date: 2025-01-03ZHONGTONG BUS HLDG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202211173883.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-09-26
Publication Date
2025-01-03
Estimated Expiration
2042-09-26

AI Technical Summary

Technical Problem

In the prior art, the temperature control method of the fuel cell cooling fan may easily lead to inaccurate duty cycle control, and the fuel cell cannot be effectively maintained within a suitable temperature range, affecting its stability and durability.

Method used

Using the temperature control model based on BP neural network, the ratio of the coolant temperature of the fuel cell outlet and the target temperature is obtained, the working quantity and duty cycle signal of the cooling fan are adjusted, and the weight is optimized by using the cross entropy loss function to achieve more accurate heat dissipation. control.

Benefits of technology

It improves the heat dissipation effect, ensures that the fuel cell operates within the appropriate temperature range, extends its life, and makes up for the duty cycle error of the cooling fan in the linear state through real-time monitoring and adjustment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115472877B_ABST
    Figure CN115472877B_ABST
Patent Text Reader

Abstract

The present invention relates to a fuel cell cooling fan control method and system, wherein the fuel cell cooling fan control method comprises the following steps: obtaining the outlet coolant temperature of the fuel cell as the input temperature, using a trained temperature control model, and determining the number of cooling fans to work based on the ratio of the obtained outlet coolant temperature and the target temperature; based on the obtained outlet coolant temperature, using the trained temperature control model, obtaining a cooling fan duty cycle signal corresponding to the target temperature, and the cooling fan outputs a corresponding speed based on the duty cycle signal; if the obtained outlet coolant temperature exceeds the range of the target temperature, using the trained temperature control model to adjust the weights, obtaining an updated cooling fan duty cycle signal and the number of cooling fans to work. On the basis of the linear heat dissipation relationship, a neural network weight is added for PWM regulation, and the heat dissipation effect is further improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a fuel cell cooling fan control method and system. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] During the operation of the vehicle fuel cell system, heat is continuously generated due to chemical reactions. The accumulation of heat will cause the water content of the proton exchange membrane to decrease, and long-term operation will affect the stability and durability of the fuel cell system. In order to extend the life of the fuel cell and make it work within a suitable temperature range, the existing technology controls the PWM (i.e., duty cycle) signal of the cooling fan through the fuel cell temperature to change the speed of the cooling fan, thereby controlling the cooling fan to effectively dissipate heat.

[0004] The existing heat dissipation method is to set the temperature at the outlet of the fuel cell stack - the cooling fan PWM curve to be linearly related. This temperature control method easily leads to inaccurate control of the cooling fan duty cycle, and the fuel cell cannot operate in a suitable temperature range. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a fuel cell cooling fan control method and system, which adds neural network weights for PWM regulation on the basis of the linear heat dissipation relationship, and further improves the heat dissipation effect.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A first aspect of the present invention provides a fuel cell cooling fan control method, comprising the following steps:

[0008] The outlet coolant temperature of the fuel cell is obtained as the input temperature, and the trained temperature control model is used to determine the working number of the cooling fan based on the ratio of the outlet coolant temperature obtained and the target temperature;

[0009] Based on the obtained outlet coolant temperature, the trained temperature control model is used to obtain a cooling fan duty cycle signal corresponding to the target temperature, and the cooling fan outputs a corresponding speed based on the duty cycle signal;

[0010] If the obtained outlet coolant temperature exceeds the target temperature range, the trained temperature control model is used to adjust the weights to obtain an updated cooling fan duty cycle signal and the number of cooling fan operations.

[0011] When the vehicle key is in the ON position, the motor controller temperature is not greater than the first set temperature, the motor temperature is not greater than the second set temperature, the power module temperature is not greater than the third set temperature, and the fuel cell temperature is not greater than the fourth set temperature, the cooling fan is enabled to 0.

[0012] When the vehicle key is in the ON position, the motor controller temperature is greater than the first set temperature, the motor temperature is greater than the second set temperature, the power module temperature is greater than the third set temperature, and the fuel cell temperature is greater than the fourth set temperature, the cooling fan enable is 1.

[0013] When the vehicle is high voltage ready and has no faults, it switches from pure electric mode to fuel cell mode. The fuel cell responds to the target power and increases to the target output power. During the process of reaching the target power, the fuel cell system temperature is linearly related to the cooling fan PWM.

[0014] The temperature control model has a BP neural network, including an input layer, a hidden layer and an output layer. The coolant temperature at the fuel cell outlet is taken as the input variable, and the number of working hours and duty cycle signal of the cooling fan are taken as the output variables. The hidden layer receives the data from the input layer and performs weighted summation and output calculation. The output of the hidden layer is also used as the input data of the output layer, and weighted summation and output calculation are also performed to obtain the final simulation output.

[0015] The duty cycle signal of the set interval and the corresponding temperature value are obtained to form key data, and a BP neural network is constructed based on the key data.

[0016] Based on the ratio of the obtained outlet coolant temperature and the target temperature, the number of cooling fans working is determined, specifically: the fuel cell outlet coolant temperature is used as the input temperature. If the input temperature is not greater than the target temperature, the number of cooling fans working = input temperature / target temperature*total number of cooling fans; if the input temperature is greater than the target temperature, the number of cooling fans working = target temperature / input temperature*total number of cooling fans.

[0017] The trained temperature control model is used to adjust the weights to obtain the updated cooling fan duty cycle signal and the number of cooling fan operations, specifically:

[0018] The weights connect the input and output of the BP neural network, optimize the data fitting, and use the cross entropy loss function to adjust the weights. If the output solution of the cross entropy loss function is smaller than the input solution, the adjusted weights are closer to the target temperature value, thus better satisfying the heat dissipation effect.

[0019] A second aspect of the present invention provides a fuel cell cooling fan control system, comprising:

[0020] The fan quantity determination module is configured to: obtain the outlet coolant temperature of the fuel cell as an input temperature, and determine the working quantity of the cooling fans based on the ratio of the outlet coolant temperature obtained and the target temperature by using the trained temperature control model;

[0021] The duty cycle signal determination module is configured to: obtain a cooling fan duty cycle signal corresponding to a target temperature based on the obtained outlet coolant temperature and using a trained temperature control model, and the cooling fan outputs a corresponding rotation speed based on the duty cycle signal;

[0022] The heat dissipation effect evaluation module is configured as follows: if the obtained outlet coolant temperature exceeds the target temperature range, the weights are adjusted using the trained temperature control model to obtain an updated cooling fan duty cycle signal and the number of cooling fan operations.

[0023] A third aspect of the present invention provides a controller for executing the above-mentioned fuel cell cooling fan control method.

[0024] Compared with the prior art, one or more of the above technical solutions have the following beneficial effects:

[0025] Using the trained temperature control model, when the coolant temperature at the fuel cell outlet and the target temperature are determined but the correspondence between the two is fuzzy, the simulated number of cooling fans working and the duty cycle are compared and evaluated with the target cooling effect by setting weights, and then the weights are adjusted to make it closer to the preset target temperature value. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0027] Figure 1 is a schematic diagram of a cooling fan control process provided by one or more embodiments of the present invention;

[0028] Figure 2 It is a schematic diagram of the structure of a cooling fan control system provided by one or more embodiments of the present invention. DETAILED DESCRIPTION

[0029] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0030] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0031] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0032] As described in the background technology, the existing heat dissipation method is to set the temperature at the outlet of the fuel cell stack - the cooling fan PWM curve to be in a linear relationship. This temperature control method is prone to inaccurate control of the cooling fan duty cycle, and the fuel cell cannot operate in a suitable temperature range. Therefore, the following embodiment provides a fuel cell cooling fan control method and system to further improve the control accuracy, use a BP neural network algorithm to adjust the duty cycle in real time, and monitor the temperature in real time to compensate for the cooling fan duty cycle error in the linear state.

[0033] Embodiment 1:

[0034] like Figure 1-2 As shown, a fuel cell cooling fan control method includes:

[0035] The outlet coolant temperature of the fuel cell is obtained as the input temperature, and the trained temperature control model is used to determine the working number of the cooling fan based on the ratio of the outlet coolant temperature obtained and the target temperature;

[0036] Based on the obtained outlet coolant temperature, the trained temperature control model is used to obtain a cooling fan duty cycle signal corresponding to the target temperature, and the cooling fan outputs a corresponding speed based on the duty cycle signal;

[0037] If the obtained outlet coolant temperature exceeds the target temperature range, the trained temperature control model is used to adjust the weights to obtain an updated cooling fan duty cycle signal and the number of cooling fan operations.

[0038] Specifically:

[0039] When the vehicle key is in the ON position, if the motor controller temperature is detected to be less than 85°C, the motor temperature is less than 100°C, the DCDC (power module) temperature is less than 80°C, and the fuel cell temperature is less than 50°C, the cooling fan is enabled to 0;

[0040] The vehicle key is in the ON position. If the motor controller temperature is detected to be greater than 85°C, the motor temperature is greater than 100°C, the DCDC temperature is greater than 80°C, and the fuel cell temperature is greater than 50°C, the cooling fan enable is 1;

[0041] When the vehicle is high voltage ready and has no faults, press the EV-FC switch, the vehicle switches from pure electric mode to fuel cell mode, and the fuel cell responds to the target power and gradually increases to the target output power;

[0042] In the process of reaching the target power, the temperature of the fuel cell system also increases, and the temperature is linearly related to the cooling fan PWM. In the process of the fuel cell system temperature rising from 50°C to 80°C, the cooling fan PWM increases from 0% to 90%;

[0043] Furthermore, a temperature sensor is installed at the outlet of the fuel cell stack water path to monitor the water temperature at the outlet in real time. When the temperature is higher than the preset value, the cooling fan status and the number of fans in operation are adjusted in time.

[0044] Furthermore, the actual PWM value of the cooling fan is based on the above linear control and combined with the BP neural network algorithm to control the PWM of the fan in real time;

[0045] Furthermore, the fuel cell temperature depends not only on the fuel cell current, power, etc., but also on the fuel cell operating time. The larger the value of the above variables, the more heat is generated and the greater the heat dissipation demand.

[0046] In this embodiment:

[0047] S1: The integrated cooling system has multiple cooling fans, for example, it can be composed of 6 fans. The temperature of the coolant at the fuel cell outlet is read by a temperature sensor, and the number of cooling fans and PWM are controlled according to different temperature ranges;

[0048] The real-time temperature data of the coolant at the outlet of the fuel cell system is collected by a temperature sensor;

[0049] The number of fans working and PWM are proportional to the temperature. The higher the temperature, the greater the number of fans working and PWM. In this embodiment, the number of fans working is 1-6, and the fan PWM is 0-90%.

[0050] S2: Linear data processing of fuel cell system temperature and cooling fan PWM, which can find some matching points based on the linear relationship and provide and apply them to the intelligent cooling temperature control model;

[0051] The temperature of the fuel cell system is proportional to the cooling fan PWM. When the temperature of the fuel cell system rises from 50°C to 80°C, the cooling fan PWM rises from 0% to 90%.

[0052] In the process of temperature-PWM change, several key data points are selected to form an intelligent heat dissipation temperature control model. The key data points in this embodiment are: the PWM signal and the corresponding temperature value at every 10% interval, that is, at 10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, and the data points formed with the corresponding temperature values, and neural network training is performed on them;

[0053] The intelligent temperature control model consists of three layers of data of the BP neural network, namely the input layer, hidden layer and output layer. The fuel cell temperature is used as the input variable, and the number of cooling fans running and PWM are used as the output variables.

[0054] The hidden layer receives the data from the input layer, performs weighted summation and output calculation, and the output of the hidden layer is also used as the input data of the output layer, and also performs weighted summation and output calculation to obtain the final simulation output. The relationship between the layers is the Sigmoid(x) function:

[0055]

[0056] Where x is the output of the previous layer, Sigmoid(x) is the input of the next layer, and the value range of the S function [0,1] represents the fan duty cycle.

[0057] In addition, the number of cooling fans working is determined according to the ratio of the input temperature to the target temperature: if the input temperature is less than the target temperature, the calculation method is: input temperature / target temperature*6; if the input temperature is greater than the target temperature, the calculation method is: target temperature / input temperature*6.

[0058] S3: Evaluate the heat dissipation effect of the integrated fan based on the intelligent heat dissipation temperature control model of the fuel cell system;

[0059] The temperature at the outlet of the fuel cell stack is collected to predict whether the temperature is in a controllable range. The judgment basis in this embodiment is that the upper limit of the fuel cell outlet temperature is set to 80°C. If it is uncontrollable, the weight is adjusted and the output value is recalculated. The weight in this embodiment connects the input and output of the BP neural network to optimize the data fitting.

[0060] The cross entropy loss function is used to adjust the weights, and the function expression is:

[0061]

[0062] Among them, p is the target output, q is the algorithm output, and the smaller the value of H(p,q), the closer the algorithm output is to the target output. The loss function is used to adjust the weight value. If the loss function H2 < the loss function H1, the adjusted weight value is more satisfactory for the heat dissipation effect and is closer to the target temperature value.

[0063] The above method is based on the linear growth relationship between the PWM of the cooling fan of the fuel cell system and the temperature of the fuel cell system. However, this control method is relatively rough and not precise enough to accurately reflect the actual change relationship. The BP neural network can set weights to compare and evaluate the simulated number of cooling fans and duty cycle with the target cooling effect when the input and output are determined and the input relationship is fuzzy, and then adjust the weights to make it closer to the preset target value.

[0064] Embodiment 2:

[0065] A fuel cell cooling fan control system, comprising:

[0066] The fan quantity determination module is configured to: obtain the outlet coolant temperature of the fuel cell as an input temperature, and determine the working quantity of the cooling fans based on the ratio of the outlet coolant temperature obtained and the target temperature by using the trained temperature control model;

[0067] The duty cycle signal determination module is configured to: obtain a cooling fan duty cycle signal corresponding to a target temperature based on the obtained outlet coolant temperature and using a trained temperature control model, and the cooling fan outputs a corresponding rotation speed based on the duty cycle signal;

[0068] The heat dissipation effect evaluation module is configured as follows: if the obtained outlet coolant temperature exceeds the target temperature range, the weights are adjusted using the trained temperature control model to obtain an updated cooling fan duty cycle signal and the number of cooling fan operations.

[0069] After the temperature control model is trained by the BP neural network, when the input and output quantities are determined and the input relationship is fuzzy, the simulated number of working fans and duty cycle can be compared and evaluated with the target cooling effect by setting weights, and then the weights can be adjusted to make them closer to the preset target values.

[0070] Embodiment three:

[0071] A controller is provided, which carries the fuel cell cooling fan control system of the second embodiment and executes the fuel cell cooling fan control method of the first embodiment.

[0072] After the temperature control model is trained by the BP neural network, when the input and output quantities are determined and the input relationship is fuzzy, the simulated number of working fans and duty cycle can be compared and evaluated with the target cooling effect by setting weights, and then the weights can be adjusted to make them closer to the preset target values.

[0073] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A fuel cell cooling fan control method, characterized in that: The following steps are involved: The outlet coolant temperature of the fuel cell is obtained as the input temperature, and the trained temperature control model is used to determine the working number of the cooling fan based on the ratio of the outlet coolant temperature obtained and the target temperature; Based on the obtained outlet coolant temperature, the trained temperature control model is used to obtain a cooling fan duty cycle signal corresponding to the target temperature, and the cooling fan outputs a corresponding speed based on the duty cycle signal; If the obtained outlet coolant temperature exceeds the target temperature range, the trained temperature control model is used to adjust the weights to obtain an updated cooling fan duty cycle signal and the number of cooling fan operations; The trained temperature control model is used to adjust the weights to obtain the updated cooling fan duty cycle signal and the number of cooling fan operations, specifically: The weights connect the input and output of the BP neural network, optimize the data fitting, and use the cross entropy loss function to adjust the weights. If the output solution of the cross entropy loss function is smaller than the input solution, the adjusted weights are closer to the target temperature value, thus better satisfying the heat dissipation effect.

2. A fuel cell cooling fan control method as claimed in claim 1, characterized in that: When the vehicle key is in the ON position, the motor controller temperature is not greater than the first set temperature, the motor temperature is not greater than the second set temperature, the power module temperature is not greater than the third set temperature, and the fuel cell temperature is not greater than the fourth set temperature, the cooling fan enable is 0.

3. A fuel cell cooling fan control method as claimed in claim 1, characterized in that: When the vehicle key is in the ON position, the motor controller temperature is greater than the first set temperature, the motor temperature is greater than the second set temperature, the power module temperature is greater than the third set temperature, and the fuel cell temperature is greater than the fourth set temperature, the cooling fan enable is 1.

4. A fuel cell cooling fan control method as claimed in claim 1, characterized in that: When the vehicle is high voltage ready and has no faults, it switches from pure electric mode to fuel cell mode. The fuel cell responds to the target power and increases to the target output power. During the process of reaching the target power, the fuel cell system temperature is linearly related to the cooling fan PWM.

5. A fuel cell cooling fan control method as claimed in claim 1, characterized in that: The temperature control model has a BP neural network, including an input layer, a hidden layer and an output layer. The coolant temperature at the fuel cell outlet is taken as an input variable, and the number of working hours and duty cycle signals of the cooling fan are taken as output variables. The hidden layer receives data from the input layer and performs weighted summation and output calculation. The output of the hidden layer is also used as input data of the output layer, and weighted summation and output calculation are also performed to obtain the final simulation output.

6. A fuel cell cooling fan control method as claimed in claim 5, characterized in that: Key data are formed according to the duty cycle signal of the set interval and the corresponding temperature value, and a BP neural network is constructed based on the key data.

7. A fuel cell cooling fan control method as claimed in claim 1, characterized in that: The operation quantity of the cooling fan is determined based on the ratio of the obtained outlet coolant temperature to the target temperature, specifically: The coolant temperature at the fuel cell outlet is used as the input temperature. If the input temperature is not greater than the target temperature, the number of cooling fans = input temperature / target temperature*total number of cooling fans. If the input temperature is greater than the target temperature, the number of cooling fans working = target temperature / input temperature*total number of cooling fans.

8. A fuel cell cooling fan control system, using a fuel cell cooling fan control method according to any one of claims 1 to 7, characterized in that: include The fan quantity determination module is configured to: obtain the outlet coolant temperature of the fuel cell as an input temperature, and determine the working quantity of the cooling fans based on the ratio of the outlet coolant temperature obtained and the target temperature by using the trained temperature control model; The duty cycle signal determination module is configured to: obtain a cooling fan duty cycle signal corresponding to a target temperature based on the obtained outlet coolant temperature and using a trained temperature control model, and the cooling fan outputs a corresponding rotation speed based on the duty cycle signal; The heat dissipation effect evaluation module is configured as follows: if the obtained outlet coolant temperature exceeds the target temperature range, the weights are adjusted using the trained temperature control model to obtain an updated cooling fan duty cycle signal and the number of cooling fan operations.

9. A controller, characterized in that: Execute the fuel cell cooling fan control method as described in any one of claims 1 to 7.