CN111190062A - Vehicle electric control system safety analysis method and device based on neural network - Google Patents
Vehicle electric control system safety analysis method and device based on neural network Download PDFInfo
- Publication number
- CN111190062A CN111190062A CN201911399392.2A CN201911399392A CN111190062A CN 111190062 A CN111190062 A CN 111190062A CN 201911399392 A CN201911399392 A CN 201911399392A CN 111190062 A CN111190062 A CN 111190062A
- Authority
- CN
- China
- Prior art keywords
- neural network
- control system
- electric control
- prediction model
- data
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/005—Testing of electric installations on transport means
- G01R31/006—Testing of electric installations on transport means on road vehicles, e.g. automobiles or trucks
- G01R31/007—Testing of electric installations on transport means on road vehicles, e.g. automobiles or trucks using microprocessors or computers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
A vehicle electric control system safety analysis method and device based on a neural network comprises the following steps: acquiring historical working condition data and labels of a vehicle electric control system to obtain a training set; determining a topological structure of the BP neural network, wherein the topological structure comprises an input layer, a hidden layer, an output layer and a softmax layer; training by using the training set and establishing a BP neural network prediction model; and inputting the working condition data acquired in real time from the electric control system of the electric vehicle to be tested into the BP neural network prediction model, and carrying out safety analysis on the electric control system of the electric vehicle to be tested. Compared with the existing safety detection method for the vehicle electric control system, the safety detection method can quickly finish the analysis and evaluation of the safety of the vehicle electric control system, and has the advantages of quickness, high timeliness, non-destructiveness and repeatability.
Description
Technical Field
The invention relates to the field of vehicle detection safety analysis, in particular to a method and a device for analyzing the safety of a vehicle electric control system based on a neural network.
Background
The new energy automobile is developed later in China, and according to the needs of industry development, the Ministry of science and technology starts from fifteen, and bulletins and outgoing detection methods of the new energy automobile are continuously supported through important projects of the new energy automobile, so that the progress of relevant detection technologies of the new energy automobile in China is promoted. At present, announcement detection and factory detection of new energy automobiles form a complete detection process and system, and a plurality of industrial standards are established.
At present, in the aspects of standards such as universality, safety, interchangeability, technical conditions, test methods and the like of the whole new energy automobile and key parts, 42 new energy automobile standard items (including 6 electric motorcycles) are published, wherein 35 new energy automobile standard items are published, and 7 new energy automobile industry standard items are published. The standard comprises 11 pure new energy vehicles, 6 hybrid vehicles, 4 fuel cell vehicles, 6 electric motorcycles, 8 power batteries, 2 motors and controllers and 5 related energy supply and charging according to technical lines.
However, in the current detection of a new energy automobile, the new energy automobile needs to be disassembled to independently detect the functions and structures of each module, and for example, factory inspection needs to perform tests such as needling, wading, overcharge and overheating on a battery, a long-time test is needed, and it is difficult to generate a detection report in place in a short time.
Disclosure of Invention
The invention provides a safety analysis method and a safety analysis device for an electric control system of a new energy vehicle, aiming at the defects of the safety analysis aspect of the electric control system in the annual inspection of the new energy vehicle, and the safety analysis method and the safety analysis device are used for realizing nondestructive rapid safety inspection of the electric control system.
In order to achieve the purpose, the invention adopts the following technical scheme:
a safety analysis method for a vehicle electric control system based on a neural network comprises the following steps:
s1, acquiring historical working condition data and label data representing safety of the vehicle electric control system to obtain a training set;
s2, determining a topological structure of a BP neural network prediction model, wherein the topological structure of the BP neural network prediction model comprises an input layer, a hidden layer, an output layer and a softmax layer, each node of the input layer corresponds to different types of working condition data of a vehicle electric control system, and a judgment result of the safety of the vehicle electric control system is output through the output layer and the softmax layer;
s3, inputting the data of the training set into the BP neural network prediction model for training to obtain final model parameters, and completing the establishment of the BP neural network prediction model;
and S4, inputting the working condition data acquired in real time from the electric control system of the electric vehicle to be tested into the trained BP neural network prediction model, and carrying out safety analysis on the electric control system of the electric vehicle to be tested through the BP neural network prediction model.
Further:
the number of the nodes of the input layer of the BP neural network prediction model is 18, the number of the nodes of the hidden layer is 3, the number of the nodes of the output layer is 2, and the 2 nodes of the output layer are converted into two kinds of probabilities that the system is safe or unsafe through a softmax layer.
In step S3, a stochastic gradient descent method is used to train the BP neural network prediction model.
In step S3, the training process includes:
initializing model parameters, wherein the model parameters comprise weights and biases of 18 nodes of the input layer and 3 nodes of the hidden layer, and the initialization method is to randomly generate parameters;
inputting the working condition data and the label data of the training set into the BP neural network prediction model, obtaining a regression result through neural network operation, converting the regression result into the safe and unsafe probabilities of a vehicle electric control system through the softmax layer in the neural network, selecting the probability with high probability as a current training result, comparing the current training result with a real value to obtain an error, solving a partial derivative of the parameters of each layer of each pair of neural networks by taking the error, updating the parameters along the negative gradient direction of the partial derivative, and continuously training and iterating until the error is smaller than a set error threshold value or the iteration number is larger than a set value.
In step S1, the collected operating condition data includes the following three types of data: the first type of data is output deviation of a controller of the vehicle electric control system and indication deviation of an instrument, the second type of data is controller communication data of the vehicle electric control system, and the third type of data is controller response data of the vehicle electric control system; and step S4, inputting the controller display deviation, the instrument display deviation, the controller communication data and the controller response deviation which are acquired by real-time detection of the vehicle electric control system into the trained input layer of the BP neural network prediction model, and outputting the corresponding safety of the electric control system from the output layer after prediction analysis is carried out through the BP neural network prediction model.
The first type of data includes one or more of:
1) residual driving range display value error;
2) error of the running distance of the rotary drum;
3) displaying errors of the rotating speed of the motor;
4) vehicle speed display error;
5) electric quantity display error;
6) the temperature shows the error.
The second type of data comprises:
the communication function between any two of a CAN network communication system, a vehicle control unit (ECU), a Battery Management System (BMS) and a motor controller is 1 in normal communication and 0 in abnormal communication;
the third type of data includes one or more of:
1) deviation between the input data of the accelerator pedal and the output rotating speed of the motor;
2) the brake pedal input data is offset from the braking force of the brake system.
The vehicle electric control system is a vehicle electric control system of a new energy automobile, and the new energy automobile comprises a pure electric automobile, a fuel cell automobile and a hybrid electric automobile.
A vehicle electric control system safety analysis device based on a neural network comprises:
the training set acquisition unit is used for acquiring historical working condition data and label data representing safety of the vehicle electric control system to obtain a training set;
the BP neural network prediction model topological structure determining unit is used for determining a topological structure of a BP neural network prediction model, wherein the topological structure of the BP neural network prediction model comprises an input layer, a hidden layer, an output layer and a softmax layer, each node of the input layer corresponds to different types of working condition data of a vehicle electric control system, and a judgment result of the safety of the vehicle electric control system is output through the output layer and the softmax layer;
the BP neural network prediction model training unit is used for inputting the data of the training set into the BP neural network prediction model for training to obtain final model parameters and complete the establishment of the BP neural network prediction model;
the safety analysis unit is used for inputting the working condition data acquired in real time from the electric control system of the electric vehicle to be tested into the trained BP neural network prediction model and carrying out safety analysis on the electric control system of the electric vehicle to be tested through the BP neural network prediction model
A computer-readable storage medium storing a computer program which, when executed by a processor, implements the method.
A vehicle electric control system safety analysis device based on a neural network comprises:
a processor;
a computer-readable storage medium storing a computer program which, when executed by the processor, implements the method.
The invention has the following beneficial effects:
according to the technical scheme, a safety evaluation model of the vehicle electric control system can be established by collecting factory detection and annual inspection data of the new energy vehicle electric control system as learning samples and combining a neural network training method; the safety of the vehicle electric control system can be quickly analyzed and evaluated by reading the characteristic data of the vehicle electric control system under the working condition and inputting the characteristic data into the evaluation model, and the method has the advantages of quickness, high timeliness, non-destructiveness and repeatability.
Drawings
FIG. 1 is a schematic diagram of a vehicle electronic control system;
FIG. 2 is a schematic flow chart of a method for analyzing the safety of a vehicle electric control system based on a neural network according to an embodiment of the present invention;
fig. 3 is a topology structure diagram of a BP neural network prediction model according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail below. It should be emphasized that the following description is merely exemplary in nature and is not intended to limit the scope of the invention or its application.
Fig. 1 is a schematic configuration diagram of a typical vehicle electronic control system. Fig. 2 is a schematic flow chart of a safety analysis method for a vehicle electronic control system based on a neural network according to an embodiment of the present invention (where the network topology is schematic). Referring to fig. 2, an embodiment of the present invention provides a method for analyzing a safety of a vehicle electronic control system based on a neural network, including the following steps:
s1, acquiring and obtaining historical working condition data and label data (labels for short) representing safety of the vehicle electric control system to obtain a training set;
s2, determining the topological structure of the BP neural network prediction model; fig. 3 is a topological structure diagram of a BP neural network prediction model according to an embodiment of the present invention, where the topological structure of the BP neural network prediction model includes an input layer, a hidden layer, an output layer, and a softmax layer, where each node of the input layer corresponds to different types of operating condition data of a vehicle electronic control system, and a determination result of the safety of the vehicle electronic control system is output through the output layer and the softmax layer;
s3, inputting the data of the training set into the BP neural network prediction model for training to obtain final model parameters, and completing the establishment of the BP neural network prediction model;
and S4, inputting the working condition data acquired in real time from the electric control system of the electric vehicle to be tested into the trained BP neural network prediction model, and carrying out safety analysis on the electric control system of the electric vehicle to be tested through the BP neural network prediction model.
When the treatment is actually carried out, the treatment,
fig. 3 is a topology structure diagram of a BP neural network prediction model according to a preferred embodiment of the present invention. In a preferred embodiment, the number of nodes of the input layer of the BP neural network prediction model is 18, the number of nodes of the hidden layer is 3, the number of nodes of the output layer is 2, and the output layer is followed by a softmax layer, which corresponds to two probabilities of determining that the system is safe or unsafe.
In a preferred embodiment, in step S3, the training of the BP neural network prediction model is performed by using a stochastic gradient descent method.
In a preferred embodiment, in step S3, the training process includes:
initializing model parameters, wherein the model parameters comprise weights and biases of 18 nodes of the input layer and 3 nodes of the hidden layer, and the initialization method is to randomly generate parameters;
inputting the working condition data and the label data of the training set into the BP neural network prediction model, obtaining a regression result through correlation matrix operation based on a neural network, converting the regression result into the safe and unsafe probabilities of a vehicle electric control system through the softmax layer in the neural network, selecting the probability with high probability as a current training result, comparing the current training result with a real value to obtain an error, solving a partial derivative of the parameter of each layer of each pair of neural networks by taking the error, updating the parameter along the negative gradient direction of the partial derivative, and iterating through continuous training until the error is smaller than a set error threshold value or the iteration number is larger than a set value.
In a preferred embodiment, in step S1, the collected operating condition data includes the following three types of data: the first type of data is output deviation of a controller of the vehicle electric control system and indication deviation of an instrument, the second type of data is controller communication data of the vehicle electric control system, and the third type of data is controller response data of the vehicle electric control system; and step S4, inputting the controller display deviation, the instrument display deviation, the controller communication data and the controller response deviation which are acquired by real-time detection of the vehicle electric control system into the trained input layer of the BP neural network prediction model, and outputting the corresponding safety of the electric control system from the output layer after prediction analysis is carried out through the BP neural network prediction model.
In a preferred embodiment, the first type of data comprises one or more of:
1) residual driving range display value error;
2) error of the running distance of the rotary drum;
3) displaying errors of the rotating speed of the motor;
4) vehicle speed display error;
5) electric quantity display error;
6) the temperature shows the error.
The second type of data comprises:
the communication function between any two of a CAN network communication system, a vehicle control unit (ECU), a Battery Management System (BMS) and a motor controller is 1 in normal communication and 0 in abnormal communication;
the third type of data includes one or more of:
1) deviation between the input data of the accelerator pedal and the output rotating speed of the motor;
2) the brake pedal input data is offset from the braking force of the brake system.
The vehicle electric control system is a vehicle electric control system of a new energy automobile, and the new energy automobile comprises a pure electric automobile, a fuel cell automobile, a hybrid electric automobile and the like.
The embodiment of the invention also provides a vehicle electric control system safety analysis device based on the neural network, which comprises the following steps: the system comprises a training set acquisition unit, a BP neural network prediction model topological structure determination unit, a BP neural network prediction model training unit and a safety analysis unit, wherein the training set acquisition unit is used for acquiring historical working condition data and label data representing safety of a vehicle electric control system to obtain a training set; the BP neural network prediction model topological structure determining unit is used for determining a topological structure of a BP neural network prediction model, the topological structure of the BP neural network prediction model comprises an input layer, a hidden layer, an output layer and a softmax layer, wherein each node of the input layer corresponds to different types of working condition data of a vehicle electric control system, and a judgment result of the safety of the vehicle electric control system is output through the output layer and the softmax layer; the BP neural network prediction model training unit inputs the data of the training set into the BP neural network prediction model for training to obtain final model parameters, and the establishment of the BP neural network prediction model is completed; the safety analysis unit is used for inputting the working condition data acquired in real time from the electric vehicle electric control system to be tested into the trained BP neural network prediction model, and carrying out safety analysis on the electric vehicle electric control system to be tested through the BP neural network prediction model.
The embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the method.
The embodiment of the invention also provides a vehicle electric control system safety analysis device based on the neural network, which comprises the following steps: a processor and a computer readable storage medium storing a computer program which, when executed by the processor, implements the method.
The following further describes a safety analysis method of a vehicle electric control system according to a specific embodiment of the present invention with reference to the drawings.
As shown in fig. 2, a method for analyzing safety of an electric control system of a new energy vehicle based on a neural network according to a specific embodiment includes the following steps:
a. data related to the electric control system are extracted from a new energy electric vehicle working condition database and comprise three types, wherein the first type is controller output deviation and instrument indication deviation, the second type is controller communication data, and the third type is controller response data. These data serve as the training data set for the method.
b. Determining the topological structure of the BP neural network prediction model: it contains a total of four layers: the data processing system comprises an input layer, a hidden layer, an output layer and a softmax layer, wherein the number of nodes of the input layer is the type of the data in the step a, and the total number of the nodes is 18; the number of hidden layer nodes is 3; the number of output layer nodes is 2; the softmax layer converts a regression result obtained by matrix operation of the front part of the neural network into the safe and unsafe probability of the electric control system; the specific structure is shown in fig. 3;
c. inputting the training set in the step a into a neural network model for training, wherein a specific algorithm adopts a random gradient descent method, and the training process comprises the following steps:
firstly, initializing model parameters, including the weights and the biases of 21 nodes, wherein the initialization method is a random generation parameter.
secondly, performing matrix multiplication and addition on training data and parameters through matrix operation to obtain a regression result, converting the regression result into the probability of failure through a softmax layer, comparing the training result of iteration with a real value to obtain an error, solving a partial derivative of the error on the parameters of each layer of the neural network, updating the parameters along the negative direction of the partial derivative, performing parameter correction through continuous iteration to enable the calculation result of the model to be continuously close to the real value, and obtaining final model parameters when the final error is smaller than a certain threshold value or the iteration reaches a certain number of times to complete the establishment of the prediction model.
d. When the trained neural network is used for detecting the new energy vehicle electric control system in real time, the acquired controller display deviation, the instrument display deviation, the controller communication data and the controller response deviation are input into an input layer of the neural network, and the output layer outputs the corresponding safety of the electric control system, so that the safety analysis of the electric control system is realized.
The three types of data in the step a mainly comprise:
the first type of data controller output deviation and instrument indication deviation can include:
1) residual driving range display value error;
2) error of the running distance of the rotary drum;
3) displaying errors of the rotating speed of the motor;
4) vehicle speed display error;
5) electric quantity display error;
6) the temperature shows the error.
The second type of data controller communication data for summarizing whether the communication between the communication systems of the vehicle is normal may include:
1) the communication function among a CAN network communication system, a vehicle control unit (ECU), a Battery Management System (BMS) and a motor controller is 1 in normal communication and 0 in abnormal communication;
a third type of data controller response bias may include:
1) and (3) deviation between the input data of the accelerator pedal and the output rotating speed of the motor, if the data transmitted from the pedal end is that the motor is accelerated to 1000r/min, the motor is accelerated to 3000 r/min.
2) The brake pedal input data and the brake system brake force deviation, such as pedal end incoming data is 3000N brake force, and the brake system applies 5000N brake force.
Based on the judged faults of the electric control system in the database, the electric control system is divided into three types according to three types of data: 1) the controller outputs and the instrument displays faults; 2) a controller communication failure; 3) the controller responds to the fault and corresponds to the three types of data respectively.
In some specific embodiments, the safety evaluation of the new energy automobile electric control system is performed by the following method:
1. and acquiring working condition data of the electric control system, wherein each piece of data comprises 18 fields and a safety label.
2. Determining the topological structure of the neural network model, wherein the topological structure comprises an input layer (18 nodes), a hidden layer (3 nodes), an output layer (2 nodes) and a softmax layer (probability transformation). Firstly, initializing model parameters, including the weight and the offset of 21 nodes, inputting labels and working condition data into a neural network model, performing matrix operation to obtain a regression result, inputting the regression result into a softmax layer to obtain the final safety probability, selecting the result with the high probability, comparing the result with a real value to obtain an error, taking a partial derivative of the error on each parameter, updating the parameter along the negative gradient direction of the partial derivative, and continuously iterating until the error is smaller than a threshold value or the iteration times are larger than a set value, wherein the method is also called a gradient descent method.
And then after the neural network model is trained, the model is convenient to migrate by storing parameters of the model, and the trained neural network is utilized to carry out safety analysis on the electric vehicle electric control system by inputting real-time acquired working condition data.
The background of the present invention may contain background information related to the problem or environment of the present invention and does not necessarily describe the prior art. Accordingly, the inclusion in the background section is not an admission of prior art by the applicant.
The foregoing is a more detailed description of the invention in connection with specific/preferred embodiments and is not intended to limit the practice of the invention to those descriptions. It will be apparent to those skilled in the art that various substitutions and modifications can be made to the described embodiments without departing from the spirit of the invention, and these substitutions and modifications should be considered to fall within the scope of the invention. In the description herein, references to the description of the term "one embodiment," "some embodiments," "preferred embodiments," "an example," "a specific example," or "some examples" or the like are intended to 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. Various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction. Although embodiments of the present invention and their advantages have been described in detail, it should be understood that various changes, substitutions and alterations can be made herein without departing from the scope of the claims.
Claims (10)
1. A safety analysis method for a vehicle electric control system based on a neural network is characterized by comprising the following steps:
s1, acquiring historical working condition data and label data representing safety of the vehicle electric control system to obtain a training set;
s2, determining a topological structure of a BP neural network prediction model, wherein the topological structure of the BP neural network prediction model comprises an input layer, a hidden layer, an output layer and a softmax layer, each node of the input layer corresponds to different types of working condition data of a vehicle electric control system, and a judgment result of the safety of the vehicle electric control system is output through the output layer and the softmax layer;
s3, inputting the data of the training set into the BP neural network prediction model for training to obtain final model parameters, and completing the establishment of the BP neural network prediction model;
and S4, inputting the working condition data acquired in real time from the electric control system of the electric vehicle to be tested into the trained BP neural network prediction model, and carrying out safety analysis on the electric control system of the electric vehicle to be tested through the BP neural network prediction model.
2. The neural network-based vehicle electric control system security analysis method according to claim 1, wherein the number of nodes of the input layer of the BP neural network prediction model is 18, the number of nodes of the hidden layer is 3, the number of nodes of the output layer is 2, and the 2 nodes of the output layer are converted into two probabilities that the system is safe or unsafe through a softmax layer.
3. A safety analysis method for a vehicle electric control system based on a neural network as claimed in claim 1 or 2, characterized in that in step S3, a stochastic gradient descent method is adopted to train the BP neural network prediction model.
4. A safety analysis method for vehicle electric control system based on neural network as claimed in any one of claims 1 to 3, characterized in that in step S3, the training process includes:
initializing model parameters, wherein the model parameters comprise weights and biases of 18 nodes of the input layer and 3 nodes of the hidden layer, and the initialization method is to randomly generate parameters;
inputting the working condition data and the label data of the training set into the BP neural network prediction model, obtaining a regression result through neural network operation, converting the regression result into the safe and unsafe probabilities of a vehicle electric control system through the softmax layer in the neural network, selecting the probability with high probability as a current training result, comparing the current training result with a real value to obtain an error, solving a partial derivative of the parameters of each layer of each pair of neural networks by taking the error, updating the parameters along the negative gradient direction of the partial derivative, and continuously training and iterating until the error is smaller than a set error threshold value or the iteration number is larger than a set value.
5. The neural network-based vehicle electric control system safety analysis method according to any one of claims 1 to 4, wherein in the step S1, the collected operating condition data includes the following three types of data: the first type of data is output deviation of a controller of the vehicle electric control system and indication deviation of an instrument, the second type of data is controller communication data of the vehicle electric control system, and the third type of data is controller response data of the vehicle electric control system; and step S4, inputting the controller display deviation, the instrument display deviation, the controller communication data and the controller response deviation which are acquired by real-time detection of the vehicle electric control system into the trained input layer of the BP neural network prediction model, and outputting the corresponding safety of the electric control system from the output layer after prediction analysis is carried out through the BP neural network prediction model.
6. The neural network-based vehicle electrical control system security analysis method of claim 5,
the first type of data includes one or more of:
1) residual driving range display value error;
2) error of the running distance of the rotary drum;
3) displaying errors of the rotating speed of the motor;
4) vehicle speed display error;
5) electric quantity display error;
6) the temperature shows the error.
The second type of data comprises:
the communication function between any two of a CAN network communication system, a vehicle control unit (ECU), a Battery Management System (BMS) and a motor controller is 1 in normal communication and 0 in abnormal communication;
the third type of data includes one or more of:
1) deviation between the input data of the accelerator pedal and the output rotating speed of the motor;
2) the brake pedal input data is offset from the braking force of the brake system.
7. The safety analysis method for the vehicle electric control system based on the neural network as claimed in any one of claims 1 to 6, wherein the vehicle electric control system is a vehicle electric control system of a new energy automobile, and the new energy automobile comprises a pure electric automobile, a fuel cell automobile and a hybrid electric automobile.
8. A vehicle electric control system safety analysis device based on a neural network is characterized by comprising the following components:
the training set acquisition unit is used for acquiring historical working condition data and label data representing safety of the vehicle electric control system to obtain a training set;
the BP neural network prediction model topological structure determining unit is used for determining a topological structure of a BP neural network prediction model, wherein the topological structure of the BP neural network prediction model comprises an input layer, a hidden layer, an output layer and a softmax layer, each node of the input layer corresponds to different types of working condition data of a vehicle electric control system, and a judgment result of the safety of the vehicle electric control system is output through the output layer and the softmax layer;
the BP neural network prediction model training unit is used for inputting the data of the training set into the BP neural network prediction model for training to obtain final model parameters and complete the establishment of the BP neural network prediction model;
and the safety analysis unit is used for inputting the working condition data acquired in real time from the electric control system of the electric vehicle to be tested into the trained BP neural network prediction model and carrying out safety analysis on the electric control system of the electric vehicle to be tested through the BP neural network prediction model.
9. A computer-readable storage medium, characterized in that it stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 7.
10. A vehicle electric control system safety analysis device based on a neural network is characterized by comprising the following components:
a processor;
a computer-readable storage medium storing a computer program which, when executed by the processor, implements the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911399392.2A CN111190062B (en) | 2019-12-30 | 2019-12-30 | Vehicle electric control system safety analysis method and device based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911399392.2A CN111190062B (en) | 2019-12-30 | 2019-12-30 | Vehicle electric control system safety analysis method and device based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111190062A true CN111190062A (en) | 2020-05-22 |
| CN111190062B CN111190062B (en) | 2022-02-11 |
Family
ID=70707964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911399392.2A Active CN111190062B (en) | 2019-12-30 | 2019-12-30 | Vehicle electric control system safety analysis method and device based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111190062B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000062135A1 (en) * | 1999-04-09 | 2000-10-19 | Abb Automation Inc. | Digital controller redundancy using neural network fault detection |
| JP2005349908A (en) * | 2004-06-09 | 2005-12-22 | Honda Motor Co Ltd | Failure detecting method of electronic controlling system of vehicle |
| CN101930234A (en) * | 2010-04-20 | 2010-12-29 | 天津大学 | Vehicle-mounted master controller for vehicle-mounted information system and control system thereof |
| CN105955240A (en) * | 2016-06-01 | 2016-09-21 | 深圳市欧克勒亚科技有限公司 | Vehicle electric control system fault quick retrieval method |
| CN106249599A (en) * | 2016-09-28 | 2016-12-21 | 河南理工大学 | A kind of network control system fault detection method based on neural network prediction |
| CN107194053A (en) * | 2017-05-16 | 2017-09-22 | 歌拉瑞电梯股份有限公司 | A kind of Intelligent elevator control system operation troubles Forecasting Methodology |
| CN107330529A (en) * | 2017-06-05 | 2017-11-07 | 上海理工大学 | Heavy-duty mill roll loads the failure risk appraisal procedure of intelligent robot |
| CN109444575A (en) * | 2018-10-23 | 2019-03-08 | 长兴昇阳科技有限公司 | Motor driving system runs health state evaluation system and method |
| CN109784479A (en) * | 2019-01-16 | 2019-05-21 | 上海西井信息科技有限公司 | Restrictor bar neural network based is anti-to pound method, system, equipment and storage medium |
| CN110210381A (en) * | 2019-05-30 | 2019-09-06 | 盐城工学院 | A kind of adaptive one-dimensional convolutional neural networks intelligent failure diagnosis method of domain separation |
-
2019
- 2019-12-30 CN CN201911399392.2A patent/CN111190062B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000062135A1 (en) * | 1999-04-09 | 2000-10-19 | Abb Automation Inc. | Digital controller redundancy using neural network fault detection |
| JP2005349908A (en) * | 2004-06-09 | 2005-12-22 | Honda Motor Co Ltd | Failure detecting method of electronic controlling system of vehicle |
| CN101930234A (en) * | 2010-04-20 | 2010-12-29 | 天津大学 | Vehicle-mounted master controller for vehicle-mounted information system and control system thereof |
| CN105955240A (en) * | 2016-06-01 | 2016-09-21 | 深圳市欧克勒亚科技有限公司 | Vehicle electric control system fault quick retrieval method |
| CN106249599A (en) * | 2016-09-28 | 2016-12-21 | 河南理工大学 | A kind of network control system fault detection method based on neural network prediction |
| CN107194053A (en) * | 2017-05-16 | 2017-09-22 | 歌拉瑞电梯股份有限公司 | A kind of Intelligent elevator control system operation troubles Forecasting Methodology |
| CN107330529A (en) * | 2017-06-05 | 2017-11-07 | 上海理工大学 | Heavy-duty mill roll loads the failure risk appraisal procedure of intelligent robot |
| CN109444575A (en) * | 2018-10-23 | 2019-03-08 | 长兴昇阳科技有限公司 | Motor driving system runs health state evaluation system and method |
| CN109784479A (en) * | 2019-01-16 | 2019-05-21 | 上海西井信息科技有限公司 | Restrictor bar neural network based is anti-to pound method, system, equipment and storage medium |
| CN110210381A (en) * | 2019-05-30 | 2019-09-06 | 盐城工学院 | A kind of adaptive one-dimensional convolutional neural networks intelligent failure diagnosis method of domain separation |
Non-Patent Citations (2)
| Title |
|---|
| YAN WANG 等: "Transformer Fault Diagnosis Based on Back-Propagation Neural Network Optimized by Cuckoo Search Algorithm", 《2017 IEEE 3RD INTERNATIONAL CONFERENCE ON CONTROL SCIENCE AND SYSTEMS ENGINEERING》 * |
| 王书提 等: "基于BP神经网络的电控发动机故障诊断", 《现代电子技术》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111190062B (en) | 2022-02-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110865628B (en) | New energy automobile electric control system fault prediction method based on working condition data | |
| Hong et al. | Vehicle energy system active defense: a health assessment of lithium‐ion batteries | |
| Wang et al. | A data-driven method for battery charging capacity abnormality diagnosis in electric vehicle applications | |
| Wang et al. | Model based insulation fault diagnosis for lithium-ion battery pack in electric vehicles | |
| CN111208445A (en) | Power battery abnormal monomer identification method and system | |
| CN112068004A (en) | Method and device for determining battery abnormity and battery charging remaining time | |
| CN105846780A (en) | Decision tree model-based photovoltaic assembly fault diagnosis method | |
| CN112858917B (en) | Battery system multi-fault diagnosis method based on genetic algorithm optimization neural network | |
| CN110568360B (en) | Lithium battery aging diagnosis method based on fuzzy logic algorithm | |
| CN109655754A (en) | A kind of cell performance evaluation method based on charging process multidimensional sublevel | |
| CN109470946B (en) | Power generation equipment fault detection method and system | |
| CN111191824B (en) | Power battery capacity attenuation prediction method and system | |
| Zhao et al. | Electric vehicle battery fault diagnosis based on statistical method | |
| CN116572747B (en) | Battery fault detection method, device, computer equipment and storage medium | |
| Jafari et al. | Prediction of the battery state using the digital twin framework based on the battery management system | |
| CN113095173A (en) | Photovoltaic system fault arc detection method with Adaboost fused with multiple classifiers | |
| Wang et al. | Prognostics and health management system for electric vehicles with a hierarchy fusion framework: concepts, architectures, and methods | |
| CN112684349A (en) | Analysis method, verification method, device, equipment and medium for battery monomer failure | |
| CN114662954A (en) | Vehicle performance evaluation system | |
| CN112816881A (en) | Battery differential pressure abnormality detection method, battery differential pressure abnormality detection device and computer storage medium | |
| Liu et al. | Reliability analysis and evaluation of a brake system based on competing risk | |
| Liu et al. | Prediction study of the heavy vehicle driving state based on digital twin model | |
| CN111751729B (en) | Method for determining the state of a rechargeable battery of a vehicle | |
| CN111190062B (en) | Vehicle electric control system safety analysis method and device based on neural network | |
| CN109886439A (en) | Electronic-control vehicle remote diagnosis system and its diagnostic method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |