CN112459890A - Heat management system and heat management method and device based on neural network - Google Patents
Heat management system and heat management method and device based on neural network Download PDFInfo
- Publication number
- CN112459890A CN112459890A CN201910840612.4A CN201910840612A CN112459890A CN 112459890 A CN112459890 A CN 112459890A CN 201910840612 A CN201910840612 A CN 201910840612A CN 112459890 A CN112459890 A CN 112459890A
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- engine
- thermal management
- cooling liquid
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01P—COOLING OF MACHINES OR ENGINES IN GENERAL; COOLING OF INTERNAL-COMBUSTION ENGINES
- F01P7/00—Controlling of coolant flow
- F01P7/14—Controlling of coolant flow the coolant being liquid
- F01P7/16—Controlling of coolant flow the coolant being liquid by thermostatic control
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01P—COOLING OF MACHINES OR ENGINES IN GENERAL; COOLING OF INTERNAL-COMBUSTION ENGINES
- F01P2037/00—Controlling
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F01—MACHINES OR ENGINES IN GENERAL; ENGINE PLANTS IN GENERAL; STEAM ENGINES
- F01P—COOLING OF MACHINES OR ENGINES IN GENERAL; COOLING OF INTERNAL-COMBUSTION ENGINES
- F01P2050/00—Applications
- F01P2050/22—Motor-cars
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The application provides a thermal management system, and a thermal management method and device based on a neural network, wherein the method comprises the following steps: obtaining working condition parameters of vehicle running and inputting the working condition parameters into a target neural network model; obtaining the predicted temperature of the cooling liquid in the engine through the target neural network model; and controlling a thermal management system in the engine to regulate the temperature of the cooling liquid according to the predicted temperature of the cooling liquid so as to realize regulation according to the predicted temperature of the cooling liquid and improve the stability of the thermal management system.
Description
Technical Field
The invention relates to the technical field of vehicles, in particular to a thermal management system and a neural network-based thermal management method and device.
Background
The vehicle can produce a large amount of heat in the running process, the produced heat can also change correspondingly along with the change of working environment and working condition, and in order to ensure the optimal running state of the vehicle, the heat is usually radiated to the environment in a cooling fan forced cooling mode, so that all devices are kept in the working range of normal temperature. However, the related art has the problems that the control system has slow response speed, and the error of central control can cause the information of the whole system to delay or even collapse, thus easily causing the vehicle to heat up too fast and reducing the service life of the engine and the accessories thereof.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, the first objective of the present invention is to provide a neural network-based engine thermal management method to implement adjustment according to the predicted temperature of the coolant, so as to improve the stability of the thermal management system.
The second purpose of the invention is to provide a heat management device of the engine based on the neural network.
A third object of the invention is to propose a thermal management system.
A fourth object of the invention is to propose a computer-readable storage medium.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides a method for thermal management of an engine based on a neural network, including the following steps: obtaining working condition parameters of vehicle running and inputting the working condition parameters into a target neural network model; obtaining the predicted temperature of the cooling liquid in the engine through the target neural network model; and controlling a thermal management system in the engine to regulate the temperature of the cooling liquid according to the predicted temperature of the cooling liquid.
According to an embodiment of the invention, before the obtaining of the operating condition parameters of the vehicle running and inputting the operating condition parameters into the neural network model, the method further comprises the following steps: establishing an initial neural network model, inputting the sample working condition parameters and the test result of each sample working condition parameter into the initial neural network model for training until the output error of the trained neural network model is less than a set error value, and obtaining the target neural network model.
According to an embodiment of the present invention, the inputting the sample condition parameters and the test result of each sample condition parameter into the initial neural network model for training includes: obtaining a prediction result of the target neural network model; and comparing the prediction result with the test result so as to correct the weight value of the hidden layer in the target neural network model according to the comparison result.
According to one embodiment of the invention, the controlling a thermal management system in the engine to adjust the temperature of the coolant according to the predicted temperature of the coolant comprises: and controlling the flow of the cooling liquid of the heat exchanger according to the target cooling liquid temperature for each heat exchanger.
According to the heat management method provided by the embodiment of the invention, the operation condition of the engine can be accurately matched through the target neural network model, and the optimal coolant temperature is selected, so that the problem of inaccurate temperature control of the traditional heat management system is solved; meanwhile, the heat exchangers are respectively controlled, so that the defect that the whole system is crashed due to paralysis of an integrated control center is overcome, and the normal operation of the engine is effectively guaranteed.
In order to achieve the above object, a second aspect of the present invention provides a thermal management device for an engine based on a neural network, including: the acquisition module is used for acquiring the working condition parameters of vehicle running and inputting the working condition parameters into the target neural network model; the neural network model is used for acquiring the predicted temperature of the cooling liquid in the engine through the target neural network model; and the control module is used for controlling a thermal management system in the engine to regulate the temperature of the cooling liquid according to the predicted temperature of the cooling liquid.
According to one embodiment of the invention, an initial neural network model is established, sample working condition parameters and test results of each sample working condition parameter are input into the initial neural network model for training, and the target neural network model is obtained until the output error of the trained neural network model is smaller than a set error value.
According to an embodiment of the invention, the neural network model is further configured to: obtaining a prediction result of the target neural network model; and comparing the prediction result with the test result so as to correct the weight value of the hidden layer in the target neural network model according to the comparison result.
According to an embodiment of the present invention, the control module is further configured to: and controlling the flow of the cooling liquid of the heat exchanger according to the target cooling liquid temperature for each heat exchanger.
In order to achieve the purpose, the embodiment of the third aspect of the invention provides a thermal management system of an engine, which comprises the thermal management device of the engine based on the neural network.
In order to achieve the above object, a fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the heat pipe method of the neural network-based engine.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of a method for thermal management of a neural network based engine in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of a method for thermal management of a neural network based engine according to one embodiment of the present invention;
FIG. 3 is a block schematic diagram of a neural network based engine thermal management apparatus according to an embodiment of the present invention;
FIG. 4 is a block diagram representation of a thermal management system for an engine according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The following describes a thermal management system, a neural network-based thermal management method and an apparatus according to an embodiment of the present invention with reference to the drawings.
FIG. 1 is a flow chart of a method for thermal management of a neural network based engine according to an embodiment of the present invention. As shown in fig. 1, a method for thermal management of an engine based on a neural network according to an embodiment of the present invention includes the following steps:
s101: and acquiring the running condition parameters of the vehicle, and inputting the running condition parameters into the target neural network model.
Before acquiring the operating condition parameters of the vehicle, and inputting the operating condition parameters into the target neural network model, the method further includes:
establishing an initial neural network model, inputting the sample working condition parameters and the test result of each sample working condition parameter into the initial neural network model for training until the output error of the trained neural network model is less than the set error value, and obtaining a target neural network model.
Specifically, first, vehicle speed, external wind speed, and at least one coolant temperature in the engine, and at least one heat exchanger temperature are selected as variables, wherein the coolant temperature in the engine can be selected to be 5, and the heat exchangers can be three, such as a warm air heat exchanger, a transmission heat exchanger, and a radiator heat exchanger. Therefore, the number of variables was 10, and an orthogonal experiment was performed on the variables in 10. Meanwhile, the automobile power and the torque under different working conditions and the engine thermal efficiency are measured as variable parameters, wherein the different working conditions can comprise: starting, accelerating, constant speed, decelerating, turning, ascending and descending, parking, no load, full load and overload. And carrying out normalization processing on the data used by the variable and the variable parameter, selecting a network structure and parameters from the normalized time delay data, and establishing an initial neural network model.
It should be understood that the normalization process is to accelerate the convergence of the training neural network model and accelerate the learning speed of the neural network model, and also because the node transformation function in the neural network model takes values between 0 and 1, the normalization data process is a linear transformation of the raw data, and finally the raw data is mapped between 0 and 1, wherein the transformation function is
In the formula xmax、xminThe maximum and minimum values of the input variables, x the input variables, and x' the normalized values.
Then, variables as input data are input into an input layer of the initial neural network model, and are transferred to the hidden layer by the input layer. The hidden layer is processed through the weight and the excitation function, and the processed result is transmitted to the output layer.
Further, the sample condition parameters and the test result of each sample condition parameter are input into the initial neural network model for training, as shown in fig. 2, including:
s201: and obtaining a prediction result of the target neural network model.
S202: and comparing the prediction result with the test result, and correcting the weight value of the hidden layer in the target neural network model according to the comparison result.
The weight parameters of the neural network model comprise a network weight, an initial value of a threshold value and a learning rate, and in order to ensure that the weight of each neuron can be adjusted at the position where the change of an activation function is maximum, the network weight and the initial value of the threshold value can be specified between (-1, 1) by a Matlab matrix random function. In order to ensure the stability of the system, the learning rate is selected at the lower limit of the threshold, and the calculation precision and the maximum learning times are given at the same time.
Specifically, the number n of sets of input layers is set, using
Calculating the value of each unit of each layer, wherein aiIs the value of each cell of the i-th layer, ωiIs the weight of the ith layer, and f is the activation function and is the neuron threshold of the next layer. In the calculation process, the output value of each node is weighted according to the output values of all nodes on the upper layer, the weight values of the current node and all nodes on the upper layer and the threshold value of the current node, and then is used as a dependent variable of an activation function to train the initial neural network model.
And inputting the given variable serving as input data into an input layer and transmitting the variable to a hidden layer from the input layer, processing the hidden layer through a weight and an excitation function, transmitting a result obtained after processing to an output layer, wherein the output result of the output layer is a prediction result, comparing the prediction result with a correct result of an orthogonal test, and calculating to obtain an error.
Further, an error function is calculated
Partial derivative delta of output layer neuronstWherein, yjAs a prediction result of the output layer, tjCalculating the correction weight value by using the partial derivative result until the global error is reached for the correct result of the orthogonal test
When the number of learning volume is less than the threshold value or reaches the set maximum number, the training is finished.
It should be understood that after training is completed, the neural network model also needs to be detected. The trained neural network model is tested with test data to verify the fit and predictive power of the network. If the error of the detection result is smaller than the set standard value, the neural network model can be used as a target neural network model to predict the temperature of the cooling liquid, and if the error of the detection result is larger than the set standard value, the initial neural network model needs to be reestablished.
S102: and acquiring the predicted temperature of the cooling liquid in the engine through the target neural network model.
In particular, the objective function may be built following a least squares method to minimize the sum of the mean error between the predicted and target properties, e.g.
Wherein S is the mean square error, ΩtAs a weight, XtIn the form of an actual value of the value,
is a predicted value.
In order to improve the prediction accuracy of the neural network model, different weights can be set for the automobile power, the torque and the engine thermal efficiency, the weight with high prediction accuracy is adjusted to the upper threshold limit, and the weight with low prediction accuracy is adjusted to the lower threshold limit.
It should be understood that, in the embodiment of the present invention, the target neural network model has three layers, namely, an input layer, a hidden layer and an output layer, wherein neurons of the input layer correspond to variables in the sample working condition one to one, that is, the input neurons are vehicle speed, external wind speed, three heat exchanger temperatures, and five engine internal temperatures; correspondingly, the neurons of the output layer correspond to variable parameters one by one, namely the output neurons are the automobile power, the torque and the engine thermal efficiency under different working conditions. Neurons in the hidden layer are determined by empirical formula calculation and trial and error adjustment. The activation function may be an S-type activation function, and the output layer may be a linear transformation function. The target neural network model adopts an error back propagation learning algorithm and a gradient search technology, and meets the target of minimum mean square error between actual output and expected output.
In the training process by using the sample working condition parameters, the sample working condition parameters can be randomly divided into two parts, one part is a training sample library, the other part is a testing sample library, the two parts are grouped according to the proportion of E/100 to multiplied by E100 (preferably E/F to 85/15 multiplied by 100%), when a testing sample set is selected, the data of the testing sample set should be between the maximum value and the minimum value of the testing data in the training sample as much as possible, so that the prediction is an interpolation value with the training, and the prediction result is more accurate.
S103: and controlling a thermal management system in the engine to regulate the temperature of the cooling liquid according to the predicted temperature of the cooling liquid.
The predicted temperature of the coolant is the predicted temperature of the coolant in the heat exchanger, that is, the temperature of the coolant in the heat exchanger is controlled to reach the predicted temperature, so that the heat exchanger exchanges heat with the engine by using the coolant, and stable operation of the engine is ensured.
Specifically, controlling a thermal management system in the engine to regulate the temperature of the coolant according to the predicted temperature of the coolant includes: and controlling the flow of the cooling liquid of the heat exchanger according to the target cooling liquid temperature for each heat exchanger.
It should be noted that, in the engine thermal management system according to the embodiment of the present invention, at least three heat exchangers may be provided, including a warm air heat exchanger, a transmission heat exchanger, and a radiator heat exchanger, and a control device may be respectively provided for each heat exchanger to control the flow rate of the coolant flowing through the heat exchanger, so as to adjust the temperature of the coolant, thereby effectively avoiding the defect that the integrated control center is broken down to cause the breakdown of the entire system, that is, when any control device fails, the heat exchange amount of other heat exchangers can be ensured, thereby ensuring the normal operation of the engine.
It should be further noted that, in the embodiment of the present invention, the thermal management system of the engine includes a cold vehicle cycle and a normal cycle, the cold vehicle cycle is that after a cold vehicle is parked, the coolant circulates in the engine through the water pump and the thermostat, and the thermostat is automatically turned on or off according to the running state of the engine. The heat management system of the engine also comprises an electronic water pump and a stepless speed regulation electronic water pump for driving the circulation of the cooling liquid.
Specifically, after the predicted temperature is obtained through the target neural network model, the flow rate of the coolant of the heat exchanger can be adjusted by controlling the electronic water pump and the thermostat, for example, when the current temperature of the heat exchanger of the radiator is higher than or equal to the predicted temperature, which means that the temperature of the coolant entering the engine is higher than the required temperature, the engine is not cooled enough to ensure that the engine is in an optimal operation state, and the flow rate of the coolant can be increased by controlling the electronic water pump and/or the thermostat; when the current temperature of the radiator heat exchanger is lower than the predicted temperature, which means that the temperature of the coolant entering the engine is lower than the required temperature, the temperature of the coolant can be over-cooled to influence the operation of the engine, and the flow of the cold liquid level can be reduced by controlling the electronic water pump and/or the thermostat. The electronic water pump and the thermostat control the flow by reading the temperature of the three heat exchangers of the radiator, the warm air and the speed changer, and meanwhile, the actuators of the three heat exchangers can also adjust the flow opening and match the flow of the water pump. For example, when the current temperature of the warm air heat exchanger is higher than or equal to the predicted temperature, the warm air heat exchanger can increase the valve opening to help the cooling liquid to circulate quickly, so that the cooling liquid with lower temperature enters the engine to help the heat dissipation of the engine. When the current temperature of the warm air heat exchanger is lower than the predicted temperature, the warm air heat exchanger can reduce the opening of the valve and reduce the flow rate of the cooling liquid, so that the temperature of the engine is ensured. When the current temperature of the transmission heat exchanger is higher than or equal to the predicted temperature, the transmission heat exchanger can increase the valve opening degree to help the cooling liquid to circulate quickly, so that the cooling liquid with lower temperature enters the transmission to help the heat dissipation of the transmission. When the current temperature of the transmission heat exchanger is lower than the predicted temperature, the transmission heat exchanger can reduce the opening degree of the valve and reduce the flow rate of the cooling liquid, so that the proper working temperature of the transmission is ensured. The three heat exchangers are adopted to respectively control the flow of the cooling liquid, so that the problem that one temperature sensing element or one actuating element fails to work, the engine is insufficiently cooled or overheated, and the engine runs badly and even fails can be avoided.
In conclusion, the heat management method provided by the embodiment of the invention can accurately match the engine operation condition and select the optimal coolant temperature through the target neural network model, so that the problem of inaccurate temperature control of the traditional heat management system is solved; meanwhile, the heat exchangers are respectively controlled, so that the defect that the whole system is crashed due to paralysis of an integrated control center is overcome, and the normal operation of the engine is effectively guaranteed.
In order to realize the embodiment, the invention further provides a heat management device of the engine based on the neural network.
FIG. 3 is a block diagram of a neural network based engine thermal management apparatus according to an embodiment of the present invention. As shown in fig. 3, the neural network based engine thermal management apparatus 100 includes: an acquisition module 10, a neural network model 20 and a control module 30.
The acquisition module 10 is used for acquiring working condition parameters of vehicle running and inputting the working condition parameters into the target neural network model; the neural network model 20 is used for obtaining the predicted temperature of the cooling liquid in the engine through the target neural network model; the control module 30 is configured to control a thermal management system in the engine to regulate the temperature of the coolant based on the predicted temperature of the coolant.
Further, still include: establishing an initial neural network model, inputting the sample working condition parameters and the test result of each sample working condition parameter into the initial neural network model for training until the output error of the trained neural network model is less than a set error value, and obtaining the target neural network model.
Further, the neural network model 20 is further configured to: obtaining a prediction result of the target neural network model; and comparing the prediction result with the test result so as to correct the weight value of the hidden layer in the target neural network model according to the comparison result.
Further, the control module 30 is further configured to: and controlling the flow of the cooling liquid of the heat exchanger according to the target cooling liquid temperature for each heat exchanger.
It should be noted that the foregoing explanation of the embodiment of the thermal management method for the neural network-based engine is also applicable to the thermal management device for the neural network-based engine of this embodiment, and details are not repeated here.
In order to implement the embodiment, the invention further provides a thermal management system of an engine, as shown in fig. 4, the thermal management system 200 of the engine comprises the aforementioned neural network-based thermal management device 100 of the engine.
In order to implement the above embodiments, the present invention also proposes a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the heat pipe method of a neural network based engine as described above.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A method for thermal management of an engine based on a neural network, comprising the steps of:
obtaining working condition parameters of vehicle running and inputting the working condition parameters into a target neural network model;
obtaining the predicted temperature of the cooling liquid in the engine through the target neural network model;
and controlling a thermal management system in the engine to regulate the temperature of the cooling liquid according to the predicted temperature of the cooling liquid.
2. The method according to claim 1, wherein before obtaining the operating condition parameters of the vehicle and inputting the operating condition parameters into the neural network model, the method further comprises:
establishing an initial neural network model, inputting the sample working condition parameters and the test result of each sample working condition parameter into the initial neural network model for training until the output error of the trained neural network model is less than a set error value, and obtaining the target neural network model.
3. The method according to claim 2, wherein the inputting the sample operating condition parameters and the test results of each sample operating condition parameter into the initial neural network model for training comprises:
obtaining a prediction result of the target neural network model;
and comparing the prediction result with the test result so as to correct the weight value of the hidden layer in the target neural network model according to the comparison result.
4. The method of claim 1, wherein controlling a thermal management system in the engine to adjust the temperature of the coolant based on the predicted temperature of the coolant comprises:
and controlling the flow of the cooling liquid of the heat exchanger according to the target cooling liquid temperature for each heat exchanger.
5. A neural network-based thermal management apparatus for an engine, comprising:
the acquisition module is used for acquiring the working condition parameters of vehicle running and inputting the working condition parameters into the target neural network model;
the neural network model is used for acquiring the predicted temperature of the cooling liquid in the engine through the target neural network model;
and the control module is used for controlling a thermal management system in the engine to regulate the temperature of the cooling liquid according to the predicted temperature of the cooling liquid.
6. The thermal management device of claim 5, further comprising:
establishing an initial neural network model, inputting the sample working condition parameters and the test result of each sample working condition parameter into the initial neural network model for training until the output error of the trained neural network model is less than a set error value, and obtaining the target neural network model.
7. The thermal management apparatus of claim 6, wherein the neural network model is further configured to:
obtaining a prediction result of the target neural network model;
and comparing the prediction result with the test result so as to correct the weight value of the hidden layer in the target neural network model according to the comparison result.
8. The thermal management apparatus of claim 5, wherein the control module is further configured to:
and controlling the flow of the cooling liquid of the heat exchanger according to the target cooling liquid temperature for each heat exchanger.
9. A thermal management system for an engine, comprising the neural network-based thermal management apparatus for an engine according to any one of claims 5 to 8.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the heat pipe method of a neural network-based engine as set forth in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910840612.4A CN112459890A (en) | 2019-09-06 | 2019-09-06 | Heat management system and heat management method and device based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910840612.4A CN112459890A (en) | 2019-09-06 | 2019-09-06 | Heat management system and heat management method and device based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112459890A true CN112459890A (en) | 2021-03-09 |
Family
ID=74807722
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910840612.4A Pending CN112459890A (en) | 2019-09-06 | 2019-09-06 | Heat management system and heat management method and device based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112459890A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113064371A (en) * | 2021-03-23 | 2021-07-02 | 博鼎汽车科技(山东)有限公司 | Ship engine heat management system controlled by monitor and implementation method thereof |
| CN113419419A (en) * | 2021-06-24 | 2021-09-21 | 上海电机学院 | Heat management system of new energy automobile |
| CN113947021A (en) * | 2021-10-20 | 2022-01-18 | 重庆金康赛力斯新能源汽车设计院有限公司 | Thermal management control method and thermal management control device |
| CN114076042A (en) * | 2020-08-11 | 2022-02-22 | 郑州宇通客车股份有限公司 | Engine heat management method and vehicle adopting same |
| CN114704370A (en) * | 2021-06-30 | 2022-07-05 | 天津大学 | Parameter online learning and MPC-based energy efficiency optimization algorithm for thermal management system |
| WO2023071164A1 (en) * | 2021-10-26 | 2023-05-04 | 宁德时代新能源科技股份有限公司 | Heat management method and system, and domain controller and storage medium |
| CN117647932A (en) * | 2024-01-25 | 2024-03-05 | 上海碳索能源服务股份有限公司 | Method, system, terminal and medium for constructing cooling pump flow prediction model |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19902923A1 (en) * | 1999-01-26 | 2000-08-03 | Daimler Chrysler Ag | Internal combustion engine cooling system functional monitoring involves deriving anticipated temp. from neural network trained with input parameters representing engine states |
| CN106870099A (en) * | 2017-03-09 | 2017-06-20 | 山东大学 | A kind of control method of the motor vehicle driven by mixed power heat management system based on fixed road spectrum |
| CN108644002A (en) * | 2018-07-18 | 2018-10-12 | 龙城电装（常州）有限公司 | A kind of water-cooled engine Intelligent heat management system |
| CN109515165A (en) * | 2018-11-30 | 2019-03-26 | 北京新能源汽车股份有限公司 | Motor cooling constant temperature control method and device |
-
2019
- 2019-09-06 CN CN201910840612.4A patent/CN112459890A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE19902923A1 (en) * | 1999-01-26 | 2000-08-03 | Daimler Chrysler Ag | Internal combustion engine cooling system functional monitoring involves deriving anticipated temp. from neural network trained with input parameters representing engine states |
| CN106870099A (en) * | 2017-03-09 | 2017-06-20 | 山东大学 | A kind of control method of the motor vehicle driven by mixed power heat management system based on fixed road spectrum |
| CN108644002A (en) * | 2018-07-18 | 2018-10-12 | 龙城电装（常州）有限公司 | A kind of water-cooled engine Intelligent heat management system |
| CN109515165A (en) * | 2018-11-30 | 2019-03-26 | 北京新能源汽车股份有限公司 | Motor cooling constant temperature control method and device |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114076042A (en) * | 2020-08-11 | 2022-02-22 | 郑州宇通客车股份有限公司 | Engine heat management method and vehicle adopting same |
| CN113064371A (en) * | 2021-03-23 | 2021-07-02 | 博鼎汽车科技(山东)有限公司 | Ship engine heat management system controlled by monitor and implementation method thereof |
| CN113419419A (en) * | 2021-06-24 | 2021-09-21 | 上海电机学院 | Heat management system of new energy automobile |
| CN114704370A (en) * | 2021-06-30 | 2022-07-05 | 天津大学 | Parameter online learning and MPC-based energy efficiency optimization algorithm for thermal management system |
| CN114704370B (en) * | 2021-06-30 | 2023-10-13 | 天津大学 | Thermal management system energy efficiency optimization algorithm based on parameter online learning and MPC |
| CN113947021A (en) * | 2021-10-20 | 2022-01-18 | 重庆金康赛力斯新能源汽车设计院有限公司 | Thermal management control method and thermal management control device |
| WO2023071164A1 (en) * | 2021-10-26 | 2023-05-04 | 宁德时代新能源科技股份有限公司 | Heat management method and system, and domain controller and storage medium |
| CN117647932A (en) * | 2024-01-25 | 2024-03-05 | 上海碳索能源服务股份有限公司 | Method, system, terminal and medium for constructing cooling pump flow prediction model |
| CN117647932B (en) * | 2024-01-25 | 2024-05-07 | 上海碳索能源服务股份有限公司 | Method, system, terminal and medium for constructing cooling pump flow prediction model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112459890A (en) | Heat management system and heat management method and device based on neural network | |
| CN108790696B (en) | Temperature control method, temperature control device, electronic equipment and storage medium | |
| CN108736109B (en) | Battery thermal management system and battery temperature adjusting method | |
| JP6687144B1 (en) | Abnormality detection device for engine cooling water circulation system | |
| CN108340771B (en) | Cooling fan and active grille shutter control | |
| CN114335625B (en) | Fuel cell stack temperature control method, device, model predictive controller and system | |
| CN111005799B (en) | Water temperature control method and device, thermal management system and storage medium | |
| CN113139338B (en) | Temperature prediction method, temperature prediction device and vehicle | |
| JP6968282B2 (en) | Causal analysis of powertrain management | |
| CN115774929A (en) | Electric automobile thermal management control system and method considering energy conservation and battery life | |
| US11541777B2 (en) | System and method for controlling vehicle thermal management apparatus | |
| CN115195528A (en) | Energy management system for electric automobile | |
| CN117117397B (en) | Battery thermal management simulation method, device, system and storage medium | |
| CN109763889B (en) | Engine coolant control system and method using model predictive control | |
| JP2020183816A (en) | Heat source system, target operation capacity estimation method and target operation capacity estimation program | |
| CN116931624A (en) | Training method of learning model, temperature control method, device and electronic equipment | |
| JP2023132568A (en) | Machine learning device, cooling temperature estimation device, cooling circuit control device, low temperature circuit, on-vehicle temperature control device and computer program | |
| US10961897B2 (en) | Methods of controlling electrical coolant valve for internal combustion engine | |
| CN113108444B (en) | Expansion valve opening degree control method and device and air conditioner | |
| Choi et al. | Deep Q-Network-Based Controller for Cabin Cooling System of Electric Vehicles | |
| CN115470689A (en) | Vehicle thermal management model generation method, vehicle thermal management test method and device | |
| EP4227754B1 (en) | Estimates of cooling or heating power | |
| CN117739482A (en) | Control method, device and equipment for air conditioner tail end fan and storage medium | |
| CN116540547A (en) | Electronic water valve opening fuzzy control method and system based on working condition prediction | |
| US9719406B2 (en) | Engine out coolant temperature correction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210309 |
|
| WD01 | Invention patent application deemed withdrawn after publication |