CN111157898A - New energy vehicle online battery fault detection and analysis method and device - Google Patents
New energy vehicle online battery fault detection and analysis method and device Download PDFInfo
- Publication number
- CN111157898A CN111157898A CN202010015475.3A CN202010015475A CN111157898A CN 111157898 A CN111157898 A CN 111157898A CN 202010015475 A CN202010015475 A CN 202010015475A CN 111157898 A CN111157898 A CN 111157898A
- Authority
- CN
- China
- Prior art keywords
- fault
- sensor
- battery
- 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.)
- Pending
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
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- 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
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Secondary Cells (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
A long-time memory neural network model (LSTM), a support vector machine model (SVM) and two softmax multi-classification models aiming at sensor faults and vehicle battery faults respectively are established, during detection, sensor data are subjected to fault diagnosis through the LSTM model, then the sensor faults and the vehicle battery faults are distinguished through the SVM model, and then classification and positioning of sensor or vehicle battery fault types are carried out through the two softmax multi-classification models respectively, so that online and accurate fault detection is achieved. Through distinguishing and judging sensor faults and vehicle battery self faults, the requirements for fault type classification models can be well reduced, the classification precision is further increased, the fault types can be more accurately distinguished, the higher distinguishing degree of fault severity grade is facilitated, the vehicle can be better overhauled and maintained in time, the driving safety and comfort are improved, and the accident occurrence rate is reduced.
Description
Technical Field
The invention relates to the field of automobile fault detection, in particular to a new energy vehicle online battery fault detection analysis method and device.
Background
The new energy automobile comprises a pure electric automobile, a fuel cell automobile, a hybrid electric automobile and the like, along with the development and progress of the manufacturing technology and process of the new energy automobile, more and more people select and use the new energy automobile, the safety guarantee cannot be ignored at the moment, and the fault detection is an important and indispensable ring. In the past, after the vehicle cannot be normally used, a vehicle owner drives the vehicle to a maintenance shop to perform post-repair and maintenance, but the perceived fault usually misses the best repair opportunity and has great potential safety hazard. Because the high-frequency fault of the electric automobile mainly occurs on the battery system, the fault of the battery system can often cause major accidents such as the ignition of the automobile and the like. In view of this, performing online real-time fault analysis on the battery operation data of the new energy automobile is an urgent problem to be solved in the industry.
Disclosure of Invention
The invention mainly aims to overcome the defects in the prior art and provide an online battery fault detection analysis method and a detection device for new energy vehicle battery operation parameter data.
In order to achieve the purpose, the invention adopts the following technical scheme:
an online battery fault detection and analysis method for a new energy vehicle comprises the following steps:
s1, establishing and training a long-term memory neural network (LSTM) model according to the historical time flow data of the sensor; establishing and training a Support Vector Machine (SVM) model according to historical fault data; establishing and training two softmax multi-classification models respectively aiming at sensor faults and vehicle battery faults according to historical fault type data;
s2, judging whether a fault exists or not by utilizing the real-time running parameter data of the vehicle acquired by each sensor in real time through the long-time and short-time memory neural network model, and executing the next step if the fault exists;
s3, determining whether the fault is a sensor fault or a vehicle battery fault through the support vector machine model, executing a step S4 when the fault is the sensor fault, and executing a step S5 when the fault is the vehicle battery fault;
s4, judging the fault type of the fault through a softmax multi-classification model aiming at the sensor fault;
and S5, judging the fault type of the fault through a softmax multi-classification model aiming at the fault of the vehicle battery.
Further:
in step S1, the establishing and training of the long-term and short-term memory neural network model specifically includes: for each item of sensor data, historical data [ x ] of the previous n moments1,x2,…,xn]For input, obtaining the prediction output of the neural network at the current moment through long-time and short-time memory, and training to obtain the long-time and short-time memory neural network model by taking the difference between the minimum true value and the predicted value as a training target function; in step S2, the predicted value and the actual measured value of the long-time memory neural network model are compared, and if the difference is greater than a preset threshold, it is determined that a fault exists, otherwise, no fault exists.
The selection of the preset threshold takes into account that the noise level of the sensor output is greater than the variance of the sensor noise. For example, selecting the threshold to be three times the variance of the sensor noise results in 8 LSTM trained models for 8 items of data.
In step S1, the establishing and training of the support vector machine model specifically includes: the training of the support vector machine model takes fault data and fault parts thereof, namely label values, as input, two classifications of sensor faults and vehicle battery faults are carried out, and the distance between a maximized dividing plane and two fault class samples is taken as a target function to obtain the support vector machine model through training; in step S3, the sensor data is used as input, and the fault classification is obtained by the support vector machine model.
In step S1, the step of maximizing the distance between the segmentation plane and the two fault category samples specifically includes: minimizing loss function
In step S1, the building and training of two softmax multi-classification models for a sensor fault and a vehicle battery fault respectively specifically includes: the multi-classification model aiming at the sensor faults takes the historical data of the current sensor as input, the multi-classification model aiming at the vehicle battery faults takes the data of all sensors at the historical moment as input, the input data passes through a multilayer feedforward neural network, the probability of the maximized real type is taken as an objective function, and two softmax multi-classification models respectively aiming at the sensor faults and the vehicle battery faults are obtained through training; in steps S4 and S5, the softmax multi-class model is output with the type having the highest probability value as the final fault type.
The softmax multi-classification model comprises an input layer, three hidden layers and an output layer.
The sensor fault types comprise complete failure faults, fixed deviation faults, drift deviation faults and precision reduction faults, a Softmax multi-classification model aiming at the sensor faults takes data of n historical time points of a fault sensor as input, and the fault types are obtained through the hidden layer and the output layer; and/or
The vehicle battery fault type comprises a single battery overvoltage fault, a battery consistency difference fault, a temperature difference overlarge fault, a battery voltage jump fault, an SOC jump fault and a high-voltage insulation overlow fault, and data of all sensors at n historical time points are used as input of a softmax multi-classification model aiming at the vehicle battery fault, and the fault type is obtained through the hidden layer and the output layer.
The vehicle operating parameter data includes: the battery pack comprises a battery cell voltage/a battery cell voltage highest value/a battery cell voltage lowest value/a total voltage measured by a voltage sensor, a battery highest temperature value/a battery lowest temperature value measured by a temperature sensor, a battery charging and discharging current measured by a current sensor and a vehicle speed measured by a speed sensor.
The utility model provides a new energy vehicle operation data online fault detection device, includes:
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 provided by the invention, accumulated historical data is utilized, accurate and reliable vehicle operation fault detection and classification models are established, wherein the accurate and reliable vehicle operation fault detection and classification models comprise a long-time short-term memory neural network model (LSTM), a support vector machine model (SVM) and two softmax multi-classification models aiming at sensor faults and vehicle battery faults respectively, vehicle real-time operation parameter data collected by a sensor is utilized during detection, fault diagnosis is carried out through the LSTM model firstly in combination with the established models, then the sensor faults and the vehicle battery faults are distinguished through the SVM model, and then classification and positioning of the sensor or the vehicle battery fault types are carried out through the two softmax multi-classification models respectively, so that online and accurate fault detection is realized. According to the invention, through distinguishing and judging the sensor fault and the vehicle battery self fault, the requirement on a fault type classification model can be well reduced, and the classification precision is further increased, so that the fault type can be more accurately distinguished, and the higher distinguishing degree of the fault severity grade is facilitated, so that the vehicle can be better overhauled and maintained in time, the driving safety and comfort are improved, and the accident occurrence rate is reduced.
Drawings
Fig. 1 is a schematic flow chart of a new energy vehicle battery data online fault detection method according to an embodiment of the invention.
Fig. 2 is a block diagram of an LSTM network in one embodiment of the invention.
FIG. 3 is a diagram illustrating SVM model classification according to an embodiment of the present invention.
FIG. 4 is a diagram of a softmax multi-class model of a sensor fault in an embodiment of the invention.
FIG. 5 is a diagram of a softmax multi-class model of a vehicle battery failure in an embodiment of the 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 flow chart of a new energy vehicle battery data online fault detection method according to an embodiment of the invention. Referring to fig. 1 to 5, an embodiment of the present invention provides an online battery fault detection and analysis method for a new energy vehicle, including the following steps:
s1, establishing and training a long-term memory neural network (LSTM) model according to the historical time flow data of the sensor; establishing and training a Support Vector Machine (SVM) model according to historical fault data; establishing and training two softmax multi-classification models respectively aiming at sensor faults and vehicle battery faults according to historical fault type data;
s2, judging whether a fault exists or not by utilizing the real-time running parameter data of the vehicle, which are acquired by each sensor in real time, through the long-time and short-time memory neural network (LSTM), and executing the next step if the fault exists;
s3, judging through the support vector machine model (SVM), determining whether the fault is a sensor fault or a vehicle battery fault, executing a step S4 when the fault is the sensor fault, and executing a step S5 when the fault is the vehicle battery fault;
s4, judging the fault type of the fault through a softmax multi-classification model A aiming at the sensor fault;
and S5, judging the fault type of the fault through the softmax multi-classification model B aiming at the vehicle battery fault.
Features and advantages of particular embodiments of the present invention are described further below in conjunction with the following figures.
Due to the characteristics of the new energy vehicle, it is possible to provide a large amount of vehicle battery operation data in real time for battery status and failure analysis. The embodiment of the invention provides a new energy vehicle data online fault detection and analysis method based on data, and the method is described in detail with reference to fig. 1.
(1) And establishing and training a long-term memory neural network (LSTM) model according to historical sensor time flow data.
(2) And establishing and training a Support Vector Machine (SVM) model according to the historical fault data.
(3) And establishing and training two softmax multi-classification models respectively aiming at the sensor fault and the vehicle battery fault according to the historical fault type data.
(4) Judging whether a fault exists through an LSTM network according to the sensor data uploaded in real time; if the faults exist, judging through an SVM model to determine that the faults exist as sensor faults or vehicle battery faults; and after the fault part is determined, the specific fault type is determined through a softmax multi-classification model.
In some embodiments, the sensor data includes the following 8 items: the battery cell voltage/the highest value of the battery cell voltage/the lowest value of the battery cell voltage/the total voltage measured by the voltage sensor, the highest temperature value/the lowest temperature value of the battery measured by the temperature sensor, the charge and discharge current of the battery measured by the current sensor and the vehicle speed measured by the speed sensor. In the fault detection process, vehicle parameter data uploaded by a vehicle sensor in real time are analyzed, and whether a fault exists is judged through an LSTM network long-term and short-term memory neural network; if the fault exists, judging through a support vector machine model to determine that the fault is a sensor fault or a vehicle battery fault; and after the fault part is determined, the specific fault type is determined through a softmax multi-classification model. Furthermore, the system can perform real-time alarm in addition to the online fault detection of the vehicle data, timely and effectively remind a driver of overhauling and maintaining the whole vehicle, thereby improving the driving safety and reducing the accident rate.
In some embodiments, the LSTM network training takes data from several previous sensor moments as input, predicts data output for the current moment, and the objective function is to minimize the difference between the true and predicted values to obtain the LSTM network for each type of sensor. The fault detection by using the LSTM specifically comprises the steps of comparing a predicted value and a real measured value of the LSTM, and if a difference value is larger than a set threshold value, determining that a fault exists, otherwise, determining that the fault does not exist. Wherein the threshold value is selected taking into account the noise level of the sensor output, i.e. a variance slightly larger than the sensor noise, to reduce false alarms caused by noise.
Specifically, for each item of sensor data, the historical data [ x ] of the previous n historical time instants1,x2,…,xn]For input, for example, the previous 8 historical moments, the predicted output at the current moment is obtained through the LSTM network as shown in fig. 2, and the model is obtained through the training of the minimized predicted output and the real output. And after the model is established, comparing the predicted value and the real measured value of the LSTM model when the model is applied online, and if the difference value is greater than a set threshold value, determining that a fault exists, otherwise, determining that the fault does not exist. Wherein the threshold value is selected to take into account the noise level of the sensor output, i.e. greater than the variance of the sensor noise, to reduce false alarms caused by noise. Wherein, the threshold is selected to be three times the variance of the sensor noise, and 8 LSTM trained models respectively aiming at 8 items of data can be obtained.
In some embodiments, the training of the support vector machine SVM model takes the fault data as input, and performs two classifications of sensor fault and vehicle battery fault, where the objective function is to maximize the distance between the segmentation plane and two fault class samples to obtain the SVM model, see fig. 3.
Specifically, if a certain item of data has a fault, the fault data is judged sequentially through a Support Vector Machine (SVM) model, and the fault data is determined to be a sensor fault or a vehicle battery fault. In the training stage of the SVM model, the sensor data of faults and fault parts (namely label values) thereof are taken as input, and the model is obtained by maximizing the distance between a division plane and two fault class samples, namely a minimized loss function
In the application stage, sensor data is used as input to obtain fault classification of the sensor data.
In some embodiments, two softmax multi-classification models are established, respectively a multi-classification model for sensor faults and a multi-classification model for vehicle battery faults. The multi-classification model for the sensor faults takes the historical data of the current sensor as input, and the multi-classification model for the vehicle battery faults takes the historical data of all the sensors as input. The input data passes through a multilayer feedforward neural network, the target function is the probability of maximizing the real category, and a softmax multi-classification model of two types of faults is obtained.
Specifically, for sensor faults with sensor fault parts, a softmax multi-classification model for the sensor faults is established, and the sensor faults are classified by using the model during online detection. The sensor fault types comprise four types of faults such as complete failure fault, fixed deviation fault, drift deviation fault and accuracy reduction. Referring to fig. 4, the softmax multi-classification model for the sensor fault includes an input layer, three hidden layers, and an output layer, and the data of 8 historical time points of the faulty sensor are used as input, and the classification is obtained through the hidden layers and the softmax output layer. In the training phase, a softmax multi-classification model for sensor failure is obtained by maximizing the probability of the true class. In the application phase, the category with the maximum probability value is taken as the final fault category through a softmax multi-classification model aiming at the sensor fault.
Specifically, for the vehicle battery fault of which the fault part is the vehicle battery, a softmax multi-classification model for the vehicle battery fault is established, and the vehicle battery fault is classified by using the model during online detection. The vehicle battery fault types comprise six faults, namely a single battery overvoltage fault, a battery consistency difference fault, an excessive temperature difference fault, a battery voltage jump fault, an SOC jump fault, a high-voltage insulation over-low fault and the like. Referring to fig. 5, the softmax multi-classification model for the vehicle battery fault includes an input layer, a three-layer hidden layer, and an output layer, and the category is obtained through the hidden layer and the softmax output layer by taking 8 items of the sensor data of 8 history points as input. In the training phase, a softmax multi-classification model for vehicle battery faults is obtained by maximizing the probability of the true class. In the application phase, the category with the maximum probability value is taken as the final fault category through a softmax multi-classification model aiming at the vehicle battery fault.
According to the detection method of the embodiment, whether the input of the integral model is faulty or not, whether the fault part is a sensor fault or a vehicle battery fault, and which type the specific type of the fault belongs to are sequentially determined.
Through experimental verification of the detection method of the embodiment, the fault detection rate of the detection method of the embodiment of the invention is improved by 5% compared with the fault detection rate of the method without sensor fault/vehicle battery fault distinguishing, and the feasibility and the effectiveness of the invention are further verified.
According to the technical scheme provided by the invention, accumulated historical data is utilized, accurate and reliable fault detection and classification models are built, the fault detection and classification models comprise a long-time memory neural network model (LSTM), a support vector machine model (SVM) and two softmax multi-classification models respectively aiming at sensor faults and vehicle battery faults, parameter data in vehicle operation are collected, and online and accurate fault detection is realized by combining the built models. According to the invention, through distinguishing and judging the sensor fault and the vehicle battery self fault, the requirement on a fault type classification model can be well reduced, and the classification precision is further increased, so that the fault type can be more accurately distinguished, and the higher distinguishing degree of the fault severity grade is facilitated, so that the vehicle can be better overhauled and maintained in time, the driving safety and comfort are improved, and the accident occurrence rate is reduced.
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. The new energy vehicle online battery fault detection and analysis method is characterized by comprising the following steps:
s1, establishing and training a long-term memory neural network (LSTM) model according to the historical time flow data of the sensor; establishing and training a Support Vector Machine (SVM) model according to historical fault data; establishing and training two softmax multi-classification models respectively aiming at sensor faults and vehicle battery faults according to historical fault type data;
s2, judging whether a fault exists or not by utilizing the real-time running parameter data of the vehicle acquired by each sensor in real time through the long-time and short-time memory neural network model, and executing the next step if the fault exists;
s3, determining whether the fault is a sensor fault or a vehicle battery fault through the support vector machine model, executing a step S4 when the fault is the sensor fault, and executing a step S5 when the fault is the vehicle battery fault;
s4, judging the fault type of the fault through a softmax multi-classification model aiming at the sensor fault;
and S5, judging the fault type of the fault through a softmax multi-classification model aiming at the fault of the vehicle battery.
2. The new energy vehicle online battery fault detection and analysis method according to claim 1, wherein in step S1, the establishing and training of the long-term and short-term memory neural network model specifically comprises: for each item of sensor data, historical data [ x ] of the previous n moments1,x2,…,xn]For input, obtaining the prediction output of the neural network at the current moment through long-time and short-time memory, and training to obtain the long-time and short-time memory neural network model by taking the difference between the minimum true value and the predicted value as a training target function; in step S2, the predicted value and the actual measured value of the long-time memory neural network model are compared, and if the difference is greater than a preset threshold, it is determined that a fault exists, otherwise, no fault exists.
3. The new energy vehicle online battery fault detection analysis method of claim 2, wherein the selection of the preset threshold takes into account a noise level of the sensor output that is greater than a variance of the sensor noise.
4. The new energy vehicle online battery fault detection and analysis method according to any one of claims 1 to 3, wherein in step S1, the establishing and training of the support vector machine model specifically includes: the training of the support vector machine model takes fault data and fault parts thereof, namely label values, as input, two classifications of sensor faults and vehicle battery faults are carried out, and the distance between a maximized dividing plane and two fault class samples is taken as a target function to obtain the support vector machine model through training; in step S3, the sensor data is used as input, and the fault classification is obtained by the support vector machine model.
5. The new energy vehicle online battery fault detection and analysis method according to claim 4, wherein in step S1, maximizing the distance between the segmentation plane and the two fault category samples specifically comprises: minimizing loss function
6. The new energy vehicle online battery fault detection and analysis method according to any one of claims 1 to 5, wherein in the step S1, establishing and training two softmax multi-classification models respectively aiming at the sensor fault and the vehicle battery fault specifically comprises: the multi-classification model aiming at the sensor faults takes the historical data of the current sensor as input, the multi-classification model aiming at the vehicle battery faults takes the data of all sensors at the historical moment as input, the input data passes through a multilayer feedforward neural network, the probability of the maximized real type is taken as an objective function, and two softmax multi-classification models respectively aiming at the sensor faults and the vehicle battery faults are obtained through training; in steps S4 and S5, the softmax multi-class model is output with the type having the highest probability value as the final fault type.
7. The new energy vehicle online battery fault detection analysis method of claim 6, wherein the softmax multi-classification model comprises an input layer, a three-layer hidden layer, and an output layer.
8. The new energy vehicle online battery fault detection and analysis method according to claim 7, wherein the sensor fault types include a complete failure fault, a fixed deviation fault, a drift deviation fault and a precision reduction fault, and the Softmax multi-classification model for the sensor fault takes data of n historical time points of a faulty sensor as input, and obtains the fault types through the hidden layer and the output layer; and/or
The vehicle battery fault type comprises a single battery overvoltage fault, a battery consistency difference fault, a temperature difference overlarge fault, a battery voltage jump fault, an SOC jump fault and a high-voltage insulation overlow fault, and data of all sensors at n historical time points are used as input of a softmax multi-classification model aiming at the vehicle battery fault, and the fault type is obtained through the hidden layer and the output layer.
9. The new energy vehicle online battery fault detection analysis method according to any one of claims 1 to 8, wherein the vehicle operation parameter data includes: the battery pack comprises a battery cell voltage/a battery cell voltage highest value/a battery cell voltage lowest value/a total voltage measured by a voltage sensor, a battery highest temperature value/a battery lowest temperature value measured by a temperature sensor, a battery charging and discharging current measured by a current sensor and a vehicle speed measured by a speed sensor.
10. The utility model provides a new energy vehicle operation data online fault detection device which characterized in that includes:
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 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010015475.3A CN111157898A (en) | 2020-01-07 | 2020-01-07 | New energy vehicle online battery fault detection and analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010015475.3A CN111157898A (en) | 2020-01-07 | 2020-01-07 | New energy vehicle online battery fault detection and analysis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111157898A true CN111157898A (en) | 2020-05-15 |
Family
ID=70561852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010015475.3A Pending CN111157898A (en) | 2020-01-07 | 2020-01-07 | New energy vehicle online battery fault detection and analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111157898A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111830934A (en) * | 2020-07-17 | 2020-10-27 | 中车大连电力牵引研发中心有限公司 | Electric locomotive fault source positioning method and device |
| CN112363059A (en) * | 2020-11-02 | 2021-02-12 | 山东大学 | Battery fault diagnosis method and system based on GM (1, 1) gray model |
| CN112630660A (en) * | 2020-12-14 | 2021-04-09 | 湖北工业大学 | Battery fault identification method based on support vector machine |
| CN112804336A (en) * | 2020-10-29 | 2021-05-14 | 浙江工商大学 | Fault detection method, device, system and computer readable storage medium |
| CN114243063A (en) * | 2021-12-17 | 2022-03-25 | 华中科技大学 | Fault positioning method and diagnosis method for solid oxide fuel cell system |
| WO2022162060A1 (en) * | 2021-01-27 | 2022-08-04 | TWAICE Technologies GmbH | Big data for fault identification in battery systems |
| CN114996661A (en) * | 2022-08-04 | 2022-09-02 | 山东佳力通汽车有限公司 | Refrigerator car temperature monitoring method and system |
| CN116087782A (en) * | 2022-11-09 | 2023-05-09 | 苏州首帆电子科技有限公司 | Automobile battery fault early warning method, system, device and storage medium |
| CN117516927A (en) * | 2024-01-05 | 2024-02-06 | 四川省机械研究设计院(集团)有限公司 | Gearbox fault detection method, system, equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108027407A (en) * | 2015-08-06 | 2018-05-11 | 密执安州立大学董事会 | Fault-tolerant voltage measurement method |
| CN108303264A (en) * | 2017-01-13 | 2018-07-20 | 华为技术有限公司 | A kind of car fault diagnosis method based on cloud, device and its system |
| CN108544925A (en) * | 2018-04-02 | 2018-09-18 | 北京理工大学 | Battery management system |
| CN109143094A (en) * | 2018-06-29 | 2019-01-04 | 上海科列新能源技术有限公司 | A kind of abnormal deviation data examination method and device of power battery |
| US20190011506A1 (en) * | 2016-01-20 | 2019-01-10 | Mitsubishi Electric Corporation | Malfunction detection apparatus capable of detecting actual malfunctioning device not due to abnormal input values |
| CN110133508A (en) * | 2019-04-24 | 2019-08-16 | 上海博强微电子有限公司 | The safe early warning method of electric automobile power battery |
| CN110146817A (en) * | 2019-05-13 | 2019-08-20 | 上海博强微电子有限公司 | The diagnostic method of lithium battery failure |
| CN110224673A (en) * | 2019-05-14 | 2019-09-10 | 太原理工大学 | A kind of solar photovoltaic cell panel fault detection method based on deep learning |
| CN110263846A (en) * | 2019-06-18 | 2019-09-20 | 华北电力大学 | The method for diagnosing faults for being excavated and being learnt based on fault data depth |
| CN110441695A (en) * | 2019-08-07 | 2019-11-12 | 南京佑创汽车研究院有限公司 | A kind of battery pack multiple faults error comprehensive diagnosis method combined based on model and signal processing |
| CN111025153A (en) * | 2018-10-09 | 2020-04-17 | 上海汽车集团股份有限公司 | Electric vehicle battery fault diagnosis method and device |
-
2020
- 2020-01-07 CN CN202010015475.3A patent/CN111157898A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108027407A (en) * | 2015-08-06 | 2018-05-11 | 密执安州立大学董事会 | Fault-tolerant voltage measurement method |
| US20190011506A1 (en) * | 2016-01-20 | 2019-01-10 | Mitsubishi Electric Corporation | Malfunction detection apparatus capable of detecting actual malfunctioning device not due to abnormal input values |
| CN108303264A (en) * | 2017-01-13 | 2018-07-20 | 华为技术有限公司 | A kind of car fault diagnosis method based on cloud, device and its system |
| US20190333291A1 (en) * | 2017-01-13 | 2019-10-31 | Huawei Technologies Co., Ltd. | Cloud-Based Vehicle Fault Diagnosis Method, Apparatus, and System |
| CN108544925A (en) * | 2018-04-02 | 2018-09-18 | 北京理工大学 | Battery management system |
| CN109143094A (en) * | 2018-06-29 | 2019-01-04 | 上海科列新能源技术有限公司 | A kind of abnormal deviation data examination method and device of power battery |
| CN111025153A (en) * | 2018-10-09 | 2020-04-17 | 上海汽车集团股份有限公司 | Electric vehicle battery fault diagnosis method and device |
| CN110133508A (en) * | 2019-04-24 | 2019-08-16 | 上海博强微电子有限公司 | The safe early warning method of electric automobile power battery |
| CN110146817A (en) * | 2019-05-13 | 2019-08-20 | 上海博强微电子有限公司 | The diagnostic method of lithium battery failure |
| CN110224673A (en) * | 2019-05-14 | 2019-09-10 | 太原理工大学 | A kind of solar photovoltaic cell panel fault detection method based on deep learning |
| CN110263846A (en) * | 2019-06-18 | 2019-09-20 | 华北电力大学 | The method for diagnosing faults for being excavated and being learnt based on fault data depth |
| CN110441695A (en) * | 2019-08-07 | 2019-11-12 | 南京佑创汽车研究院有限公司 | A kind of battery pack multiple faults error comprehensive diagnosis method combined based on model and signal processing |
Non-Patent Citations (5)
| Title |
|---|
| FREEMAN RUFUS JR.ET AL.: "《Health Monitoring Algorithms for Space Application Batteries》", 《2008 INTERNATIONAL CONFERENCE ON PROGNOSTICS AND HEALTH MANAGEMENT》 * |
| 张传雷等: "《基于图像分析的植物及其病虫害识别方法研究》", 31 October 2018, 中国经济出版社 * |
| 李业波等: "航空发动机传感器故障与部件故障诊断技术", 《北京航空航天大学学报》 * |
| 王快妮: "《支持向量机鲁棒性模型与算法研究 第一版》", 31 August 2019 * |
| 许朝雄等: "固体氧化物燃料电池多工况特征提取与多故障识别", 《化工自动化及仪表》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111830934A (en) * | 2020-07-17 | 2020-10-27 | 中车大连电力牵引研发中心有限公司 | Electric locomotive fault source positioning method and device |
| CN112804336A (en) * | 2020-10-29 | 2021-05-14 | 浙江工商大学 | Fault detection method, device, system and computer readable storage medium |
| CN112363059A (en) * | 2020-11-02 | 2021-02-12 | 山东大学 | Battery fault diagnosis method and system based on GM (1, 1) gray model |
| CN112630660A (en) * | 2020-12-14 | 2021-04-09 | 湖北工业大学 | Battery fault identification method based on support vector machine |
| WO2022162060A1 (en) * | 2021-01-27 | 2022-08-04 | TWAICE Technologies GmbH | Big data for fault identification in battery systems |
| CN114243063A (en) * | 2021-12-17 | 2022-03-25 | 华中科技大学 | Fault positioning method and diagnosis method for solid oxide fuel cell system |
| CN114243063B (en) * | 2021-12-17 | 2024-05-14 | 华中科技大学 | Solid oxide fuel cell system fault positioning method and diagnosis method |
| CN114996661A (en) * | 2022-08-04 | 2022-09-02 | 山东佳力通汽车有限公司 | Refrigerator car temperature monitoring method and system |
| CN116087782A (en) * | 2022-11-09 | 2023-05-09 | 苏州首帆电子科技有限公司 | Automobile battery fault early warning method, system, device and storage medium |
| CN116087782B (en) * | 2022-11-09 | 2024-02-02 | 苏州首帆电子科技有限公司 | Automobile battery fault early warning method, system, device and storage medium |
| CN117516927A (en) * | 2024-01-05 | 2024-02-06 | 四川省机械研究设计院(集团)有限公司 | Gearbox fault detection method, system, equipment and storage medium |
| CN117516927B (en) * | 2024-01-05 | 2024-04-05 | 四川省机械研究设计院(集团)有限公司 | Gearbox fault detection method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111157898A (en) | New energy vehicle online battery fault detection and analysis method and device | |
| CN106154182B (en) | A kind of lithium battery method for diagnosing faults based on improvement D-S evidence theory | |
| CN114559819B (en) | Electric automobile battery safety early warning method based on signal processing | |
| CN102252843B (en) | Assessment method for rolling bearing performance variation | |
| CN106353690A (en) | Method for diagnosing lithium battery faults by Petri net | |
| CN109604186A (en) | Power battery performance flexibility assesses method for separating | |
| CN107229017B (en) | A kind of wind generating set pitch control battery abnormal failure prediction technique | |
| CN109947898B (en) | Equipment fault testing method based on intellectualization | |
| CN112327168A (en) | XGboost-based electric vehicle battery consumption prediction method | |
| CN112101597A (en) | Electric vehicle leasing operation platform vehicle fault pre-judging system, method and device | |
| CN113791350B (en) | Battery fault prediction method | |
| CN111680875A (en) | Unmanned aerial vehicle state risk fuzzy comprehensive evaluation method based on probability baseline model | |
| CN110794308A (en) | Method and device for predicting train battery capacity | |
| CN112700156A (en) | Construction method of new energy automobile operation safety performance evaluation system | |
| CN111641236B (en) | Dynamic threshold power battery charging voltage state judgment method based on big data AI | |
| CN111680712B (en) | Method, device and system for predicting oil temperature of transformer based on similar time in day | |
| CN110610326B (en) | Driving management system based on driving data | |
| CN113459867A (en) | Electric vehicle charging process fault early warning method based on adaptive deep confidence network | |
| Wang et al. | Prognostics and health management system for electric vehicles with a hierarchy fusion framework: concepts, architectures, and methods | |
| CN114460481A (en) | Energy storage battery thermal runaway early warning method based on Bi-LSTM and attention mechanism | |
| CN114036647A (en) | Power battery safety risk assessment method based on real vehicle data | |
| CN116061690A (en) | Safety early warning method and device in electric automobile charging process | |
| CN114997748A (en) | New energy automobile operation safety risk prediction method and system based on model fusion | |
| CN117341476B (en) | Battery differential pressure fault early warning method and system | |
| CN114734873B (en) | Power battery monomer thermal runaway early warning method based on cloud online data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200515 |
|
| RJ01 | Rejection of invention patent application after publication |