CN113173104A - New energy vehicle power battery early warning method and system - Google Patents
New energy vehicle power battery early warning method and system Download PDFInfo
- Publication number
- CN113173104A CN113173104A CN202110476497.4A CN202110476497A CN113173104A CN 113173104 A CN113173104 A CN 113173104A CN 202110476497 A CN202110476497 A CN 202110476497A CN 113173104 A CN113173104 A CN 113173104A
- Authority
- CN
- China
- Prior art keywords
- power battery
- safety
- vehicle
- insulation resistance
- 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
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000009413 insulation Methods 0.000 claims abstract description 116
- 238000012216 screening Methods 0.000 claims abstract description 15
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000010219 correlation analysis Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 231100000279 safety data Toxicity 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000006467 substitution reaction Methods 0.000 description 3
- 230000003213 activating effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
- B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L3/00—Electric devices on electrically-propelled vehicles for safety purposes; Monitoring operating variables, e.g. speed, deceleration or energy consumption
- B60L3/0023—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train
- B60L3/0046—Detecting, eliminating, remedying or compensating for drive train abnormalities, e.g. failures within the drive train relating to electric energy storage systems, e.g. batteries or capacitors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G06Q50/40—
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
- H01M10/486—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte for measuring temperature
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
- H01M2010/4278—Systems for data transfer from batteries, e.g. transfer of battery parameters to a controller, data transferred between battery controller and main controller
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Abstract
The invention provides a method and a system for early warning a power battery of a new energy vehicle, relating to the field of early warning of vehicles and solving the technical problem of how to improve the accuracy of the safety early warning of the power battery of the new energy vehicle, the method comprises the following steps of obtaining the safety related data of the power battery of the vehicle connected with a big data platform, screening the safety related data of the power battery to obtain the data related to the temperature of the power battery, the voltage of the power battery and the insulation resistance of the power battery, carrying out neural network training on the screened data to establish a safety prediction model of the power battery of the vehicle, obtaining the safety related data of the current power battery of the vehicle connected with the big data platform after establishing the model, substituting the safety related data into the safety prediction model of the power battery of the vehicle and outputting a safety early warning result, wherein the method establishes the safety prediction model of the power battery of the vehicle to accurately obtain the early warning result, therefore, the safety early warning accuracy of the power battery of the new energy vehicle is improved.
Description
Technical Field
The invention relates to the field of vehicle early warning, in particular to a new energy vehicle power battery early warning method and system.
Background
Along with the popularization of new energy vehicles, new energy vehicle safety accidents also happen occasionally, safety accidents caused by power batteries are increased gradually, and therefore safety problems of the power batteries are paid more and more attention, the safety problems of the power batteries comprise overhigh temperature of the power batteries, overlarge insulation resistance of the power batteries and overlarge voltage of the power batteries.
In order to solve the problem of timely alarming of a vehicle battery, Chinese patent application No. (CN201810037645.0) discloses an online safety early warning method of a power battery for an electric vehicle based on a cloud platform and a battery management system, wherein the method is based on information such as current, voltage, temperature and internal resistance of a single battery cell of the power battery collected by the battery management system, GPS (global positioning system) information of a power battery pack collected by a vehicle control unit and the like, a relevant safety model is established through analysis and prediction of big data by the cloud platform, and real-time online safety early warning prompt is carried out according to artificially set limit conditions.
Although the method can perform early warning when the power battery has a problem, the vehicle is required to upload data to the cloud platform, the existing cloud platform can generate wrong data when acquiring the data, and an accurate model cannot be established if the wrong data is used. Therefore, the accuracy of safety early warning of the vehicle power battery is influenced, and the experience of a driver is influenced.
Disclosure of Invention
The invention provides a new energy vehicle power battery early warning method and system aiming at the problems in the prior art, and solves the technical problem of how to improve the safety early warning accuracy of the new energy vehicle power battery.
The invention is realized by the following technical scheme: a new energy vehicle power battery early warning method comprises the following steps:
acquiring power battery safety related data of a vehicle connected with a big data platform;
screening the safety related data of the power battery to obtain data related to the temperature of the power battery, the voltage of the power battery and the insulation resistance of the power battery, and carrying out neural network training on the screened data to establish a safety prediction model of the power battery of the vehicle;
and after the model is established, obtaining the safety related data of the current power battery of the vehicle connected with the big data platform, substituting the safety related data into the safety prediction model of the vehicle power battery, and outputting a safety early warning result.
The big data platform obtains power battery safety related data of a vehicle connected with the big data platform, screens the power battery safety related data to obtain data including power battery temperature related data, power battery voltage related data and power battery insulation resistance related data, conducts neural network training on the screened data to establish a vehicle power battery safety prediction model, and after the model is established, the big data platform obtains current power battery safety related data of the vehicle connected with the big data platform and substitutes the current power battery safety related data into the vehicle power battery safety prediction model to output a safety early warning result. The method improves the early warning method of the new energy vehicle power battery by screening relevant safety data of the vehicle power battery and establishing a vehicle power battery safety prediction model, reduces the data processing amount of a big data platform by screening out the relevant safety data of the vehicle power battery which is not in conformity, and improves the accuracy of establishing the vehicle power battery safety prediction model by screening out the data which is not in conformity, therefore, the method greatly improves the accuracy of the early warning of the vehicle power battery safety, the method also establishes the vehicle power battery safety prediction model, the early warning result can be accurately obtained by establishing the vehicle power battery safety prediction model, the overhauling efficiency is improved, the accuracy of the early warning of the new energy vehicle power battery safety is improved, thereby the use experience of a driver is improved, the vehicle power battery safety prediction model is considered relatively comprehensively, the universality is strong, can be applied to most vehicles at present.
In the new energy vehicle power battery early warning method, the screening step comprises the steps of cleaning the power battery safety related data, removing abnormal data and null data, carrying out correlation analysis on the cleaned power battery safety related data to obtain data including power battery temperature correlation, power battery voltage correlation and power battery insulation resistance correlation, cleaning the power battery safety related data to reduce the calculated amount of a large data platform and improve the accuracy of a vehicle power battery safety prediction model, and carrying out correlation analysis to remove unnecessary calculation and reduce the calculated amount of the large data platform, so that the accuracy and the efficiency of new energy vehicle early warning are improved.
In the method for early warning the new energy vehicle power battery, the correlation analysis comprises the step of selecting the vehicle power battery safety number with the Pearson correlation coefficient larger than a preset coefficient value, and the Pearson correlation coefficient is a common method for correlation analysis, so that the accuracy of a vehicle power battery safety prediction model is improved, and the early warning accuracy of the new energy vehicle is improved.
In the method for early warning the power battery of the new energy vehicle, the step of establishing the vehicle power battery safety prediction model comprises the steps of establishing a power battery temperature prediction model, a power battery voltage prediction model and a power battery insulation resistance prediction model, and the establishment of a plurality of vehicle power battery safety prediction models can obtain more comprehensive early warning information, so that the early warning accuracy of the new energy vehicle is improved.
In the method for early warning the power battery of the new energy vehicle, the step of establishing the power battery temperature prediction model comprises the steps of comparing a temperature prediction value output by a preset algorithm according to the temperature related data of the power battery with a reference temperature, establishing the power battery temperature prediction model when the difference value between the temperature prediction value and the reference temperature is not greater than a preset error value, adjusting the weight and the bias until the difference value between the temperature prediction value and the reference temperature is not greater than the preset error value when the difference value between the temperature prediction value and the reference temperature is greater than the preset error value, and establishing the power battery temperature prediction model as
Wherein y1 is a real-time predicted value of temperature, j is 1 … m, m is the number of hidden layer nodes, i is 1 … n, n is the characteristic number of input data, x is the number of hidden layer nodes, and the likeiThe parameters are input for the temperature of the power battery,
in order to hide the layer weight parameters,
in order to hide the layer bias from view,
as output layer weight parameters, b0For output layer bias, fHAnd establishing a power battery temperature prediction model for activating a function, so that the accuracy of temperature detection is improved, and the accuracy of a vehicle power battery safety prediction model is improved, thereby improving the accuracy of early warning of the new energy vehicle.
In the method for early warning the power battery of the new energy vehicle, the step of establishing the power battery voltage prediction model comprises the steps of comparing a predicted voltage output by a preset algorithm according to the voltage related data of the power battery with a reference voltage, establishing the power battery voltage prediction model when the difference value between the predicted voltage and the reference voltage is not greater than a preset error value, adjusting the weight and the bias when the difference value between the predicted voltage and the reference voltage is greater than the preset error value until the difference value between the predicted voltage and the reference voltage is not greater than the preset error value, and establishing the power battery voltage prediction model as
Wherein y2 is the real-time predicted value of voltage, j is 1 … m, m is the number of hidden layer nodes, i is 1 … n, n is the characteristic number of input data, u is the number of hidden layer nodes, n is the number of hidden layer nodes, and the hidden layer nodes, where y is the number of the hidden layer, and the hidden layer number of the hidden layer, and the hidden layer, where the hidden layer number of the hidden layer, and the hidden layer number of the hidden layer number of the layer, and theiThe parameters are input for the voltage of the power battery,
in order to hide the layer weight parameters,
in order to hide the layer bias from view,
as output layer weight parameters, b0For output layer bias, fHAs a function of activationAnd establishing a power battery voltage prediction model to improve the accuracy of voltage detection and the accuracy of a vehicle power battery safety prediction model, thereby improving the accuracy of new energy vehicle early warning.
In the method for early warning the power battery of the new energy vehicle, the step of establishing the power battery insulation resistance prediction model comprises the steps of comparing an insulation resistance predicted value output by a preset algorithm according to the data related to the insulation resistance of the power battery with a reference insulation resistance, establishing the power battery insulation resistance prediction model when the difference value between the insulation resistance predicted value and the reference insulation resistance is not greater than a preset error value, adjusting the weight and the bias until the difference value between the insulation resistance predicted value and the reference insulation resistance is not greater than the preset error value when the difference value between the insulation resistance predicted value and the reference insulation resistance is greater than the preset error value, and establishing the power battery insulation resistance prediction model which comprises the step of adjusting the weight and the bias until the difference value between the insulation resistance predicted value and the reference insulation resistance is not greater than the preset error value
Wherein y3 is the real-time predicted value of the insulation resistance, j is 1 … m, m is the number of hidden layer nodes, i is 1 … n, n is the characteristic number of input data, r isiInputting parameters for the insulation resistance of the power battery,
in order to hide the layer weight parameters,
in order to hide the layer bias from view,
as output layer weight parameters, b0For output layer bias, fHAnd establishing a power battery insulation resistance prediction model for activating the function, so that the accuracy of insulation resistance detection is improved, and the accuracy of a vehicle power battery safety prediction model is improved, thereby improving the accuracy of new energy vehicle early warning.
In the method for early warning the power battery of the new energy vehicle, the step of outputting the safety early warning result comprises the steps of comparing y1 with a preset maximum allowable power battery working temperature yk when y1 is obtained, outputting a power battery temperature early warning when y1 is greater than yk, comparing y2 with a preset maximum allowable power battery working voltage yu when y2 is obtained, outputting a power battery voltage early warning when y2 is greater than yu, comparing y3 with a preset maximum allowable power battery working insulation resistance yr when y3 is obtained, outputting a power battery insulation resistance early warning when y3 is greater than yr, and outputting corresponding safety early warnings according to different power battery conditions to improve the accuracy of the output safety early warning.
In the method for early warning the power battery of the new energy vehicle, the data related to the temperature of the power battery comprises the insulation resistance of the power battery and the voltage of the power battery, the data related to the voltage of the power battery comprises the temperature of the power battery or the current of the power battery, the data related to the insulation resistance of the power battery comprises the voltage of the power battery or the current of the power battery, the required linear relation can be obtained more accurately by selecting the data with high correlation, and a corresponding model can be established when the linear relation is determined.
The invention also comprises the following scheme: the new energy vehicle power battery early warning system comprises a big data platform, an acquisition module for acquiring safety related data of a power battery and a control unit for receiving the data output by the acquisition module, the acquisition module is connected with the control unit, the control unit is wirelessly connected with the big data platform, the big data platform is used for screening after receiving data output by the control unit of a vehicle connected with the big data platform, obtaining data related to power battery temperature, power battery voltage and power battery insulation resistance, carrying out neural network training on the screened data to establish a vehicle power battery safety prediction model, and the big data platform is also used for acquiring current power battery safety related data of the vehicle connected with the big data platform after establishing the model, substituting the current power battery safety related data into the vehicle power battery safety prediction model and outputting a safety early warning result.
The acquisition module acquires power battery safety related data and outputs the data to the control unit, the control unit receives the power battery safety related data output by the acquisition model and outputs the data to the big data platform, the big data platform receives the power battery safety related data and then screens the power battery safety related data to obtain data including power battery temperature related data, power battery voltage related data and power battery insulation resistance related data, the big data platform conducts neural network training on the screened data to establish a vehicle power battery safety prediction model, the big data platform acquires current power battery safety related data of a vehicle connected with the big data platform after establishing the model, and the big data platform substitutes the model to output a safety early warning result. The system improves a new energy vehicle power battery early warning system by presetting a new energy vehicle power battery early warning method through a big data platform, the big data platform screens vehicle power battery safety related data and establishes a vehicle power battery safety prediction model, the system screens out non-conforming vehicle power battery safety related data to reduce the data processing amount of the big data platform, and screens out non-conforming data to improve the accuracy of establishing the new energy vehicle power battery safety prediction model, therefore, the system greatly improves the accuracy of predicting the internal resistance of the new energy vehicle power battery, the system also establishes the vehicle power battery safety prediction model, and the vehicle power battery safety prediction model can accurately obtain an early warning result, thereby improving the early warning accuracy of the new energy vehicle, and simultaneously improving the use experience of a driver and the convenience of maintenance of working personnel, the safety prediction model of the vehicle power battery is relatively comprehensive in consideration, strong in universality and applicable to most of vehicles at present.
Compared with the prior art, the new energy vehicle power battery early warning method and system have the following advantages:
1. according to the method, the safety prediction model of the vehicle power battery is established, so that the early warning result can be accurately obtained, the early warning accuracy of the new energy vehicle is improved, and meanwhile, the use experience of a driver and the overhaul convenience of workers can be improved.
2. The method screens out the non-conforming safety related data of the power battery of the vehicle to reduce the data processing amount of a big data platform, and screens out the non-conforming data to improve the accuracy of establishing a safety prediction model of the power battery of the new energy vehicle.
Drawings
FIG. 1 is a schematic diagram of the process steps of the present invention.
Fig. 2 is a schematic structural diagram of the present invention.
In the figure 1, an acquisition module; 2. a control unit; 3. a big data platform.
Detailed Description
In order to make the technical problems, technical solutions and advantages solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, the early warning method for the power battery of the new energy vehicle comprises the following steps:
collecting safety related data of a power battery, wherein the safety related data of the power battery comprises a vehicle identification number, data collection time, insulation resistance, a charge-discharge state, power battery current, power battery voltage, power battery temperature and speed, screening the safety related data of the power battery of the vehicle to obtain the temperature related data, the voltage related data and the insulation resistance related data of the power battery, cleaning the safety related data of the power battery to remove abnormal data and null data, wherein the abnormal data is data which has overlarge deviation with other data and does not accord with statistical rules, the null data is data which has no input value in the safety related data of the power battery, the data which has no input value comprises data which has no content, can not determine the content and has 0 content, and performing correlation analysis on the cleaned safety related data of the power battery to obtain the safety related data of the power battery including the temperature related data, the insulation resistance related data of the power battery, and the power battery voltage and the speed, The correlation analysis comprises selecting the safety-related data of the power battery of the vehicle with the Pearson correlation coefficient larger than a preset value, wherein the preset value range can be any number between 0.1 and 0.3, and is preferably 0.25 in the embodiment.
The method comprises the steps of carrying out neural network training on safety related data of the power battery to establish a vehicle power battery safety prediction model, wherein the establishment of the vehicle power battery safety prediction model comprises the establishment of a power battery temperature prediction model, a power battery voltage prediction model and a power battery insulation resistance prediction model, and a comprehensive vehicle power battery safety prediction model related to temperature, voltage and insulation resistance can also be established.
The step of establishing the power battery temperature prediction model comprises the steps of comparing a temperature prediction value output by the power battery temperature related data through a preset algorithm with a reference temperature, establishing the power battery temperature prediction model when the difference value between the temperature prediction value and the reference temperature is not greater than a preset error value, and adjusting the weight and the bias until the difference value between the temperature prediction value and the reference temperature is not greater than the preset error value when the difference value between the temperature prediction value and the reference temperature is greater than the preset error value.
The power battery temperature prediction model is
Wherein y1 is a real-time predicted value of temperature, j is 1 … m, m is the number of hidden layer nodes, i is 1 … n, n is the characteristic number of input data, x is the number of hidden layer nodes, and the likeiThe parameters are input for the temperature of the power battery,
in order to hide the layer weight parameters,
in order to hide the layer bias from view,
as output layer weight parameters, b0For output layer bias, fHIs an activation function.
Selecting and setting the number of hidden layer nodes, for example, selecting and setting the number of hidden layer nodes 20 in the embodiment, obtaining model parameters and temperature predicted values by a big data platform according to a preset algorithm according to the screened power battery temperature related data including power battery insulation resistance and power battery voltage data, comparing the temperature predicted values with reference temperatures by the big data platform, indicating that the parameter selection is unreasonable when the temperature predicted values are more than 1% different from the reference temperatures, adjusting hidden layer weight parameters, hidden layer bias, output layer weight parameters and output layer bias, repeating the above processes, and establishing a power battery temperature prediction model by taking the parameters selected at the moment as the parameters corresponding to the power battery temperature prediction model when the temperature predicted values are less than or equal to 1% different from the reference temperatures, the reference temperature is the temperature corresponding to the current vehicle power battery voltage and the power battery insulation resistance data in the power battery early warning related historical data acquired by the big data platform 3, namely the corresponding temperature is obtained by searching the historical data according to the current vehicle power battery temperature and the power battery current data, for example, the current power battery voltage is 14V, the power battery insulation resistance data is 20 Ω, the temperature corresponding to the power battery voltage of 14V and the power battery insulation resistance data of 20 Ω in the big data platform 3 historical data is checked through the data, the temperature is the reference temperature, and the reference temperature is selected to prevent the value output by the substitution model from having a large deviation with the current reference temperature of the vehicle power battery, so that the established model is not accurate enough.
The step of establishing the power battery voltage prediction model comprises the steps of comparing the prediction voltage output by the power battery voltage related data through a preset algorithm with the reference voltage, establishing the power battery voltage prediction model when the difference value of the prediction voltage and the reference voltage is not larger than a preset error value, and adjusting the weight and the bias until the difference value of the prediction voltage and the reference voltage is not larger than the preset error value when the difference value of the prediction voltage and the reference voltage is larger than the preset error value.
The power battery voltage prediction model is
Wherein y2 is the real-time predicted value of voltage, j is 1 … m, m is the number of hidden layer nodes, i is 1 … n, n is the characteristic number of input data, u is the number of hidden layer nodes, n is the number of hidden layer nodes, and the hidden layer nodes, where y is the number of the hidden layer, and the hidden layer number of the hidden layer, and the hidden layer, where the hidden layer number of the hidden layer, and the hidden layer number of the hidden layer number of the layer, and theiThe parameters are input for the voltage of the power battery,
in order to hide the layer weight parameters,
in order to hide the layer bias from view,
as output layer weight parameters, b0For output layer bias, fHIs an activation function.
Selecting and setting the number of hidden layer nodes, for example, selecting and setting the number of hidden layer nodes 20 in the embodiment, the big data platform compares the screened power battery voltage related data including the power battery temperature or the power battery current, obtaining model parameters and predicted voltage according to a preset algorithm by the power battery temperature or the power battery current, the big data platform compares the predicted voltage with the reference voltage, when the difference value between the predicted voltage and the reference voltage is greater than 1%, the parameter selection is unreasonable, the processes are repeated after adjusting the hidden layer weight parameter, the hidden layer bias, the output layer weight parameter and the output layer bias, when the difference value between the predicted voltage and the reference voltage is less than or equal to 1%, the selected parameter at the moment is used as the parameter corresponding to the power battery voltage prediction model to establish a power battery voltage prediction model, and the reference voltage is the power battery early warning related historical data acquired by the big data platform 3, the power battery early warning related data related to the current vehicle power is obtained by the big data platform 3 The voltage corresponding to the battery temperature and the power battery current data in the same state is obtained by searching historical data through the current vehicle power battery temperature and the power battery current data, for example, the current power battery temperature is 35 ℃, the power battery current data is 3A, the voltage corresponding to the power battery current data is 3A at the power battery temperature of 35 ℃ under the historical data of the large data platform 3 is checked through the data, the voltage is a reference voltage, and the reference voltage is selected to prevent a value output by the substitution model from having a larger deviation with the current reference voltage of the vehicle power battery, so that the established model is not accurate enough.
The step of establishing the power battery insulation resistance prediction model comprises the steps of comparing an insulation resistance predicted value output by the power battery insulation resistance relevant data through a preset algorithm with a reference insulation resistance, establishing the power battery insulation resistance prediction model when the difference value between the insulation resistance predicted value and the reference insulation resistance is not larger than a preset error value, and adjusting the weight and the offset until the difference value between the insulation resistance predicted value and the reference insulation resistance is not larger than the preset error value when the difference value between the insulation resistance predicted value and the reference insulation resistance is larger than the preset error value.
The power battery insulation resistance prediction model comprises
Wherein y3 is the real-time predicted value of the insulation resistance, j is 1 … m, m is the number of hidden layer nodes, i is 1 … n, n is the characteristic number of input data, r isiInputting parameters for the insulation resistance of the power battery,
in order to hide the layer weight parameters,
in order to hide the layer bias from view,
as output layer weight parameters, b0For output layer bias, fHIs an activation function.
Selecting and setting the number of hidden layer nodes, for example, selecting and setting the number of hidden layer nodes 20 in the embodiment, obtaining model parameters and insulation resistance predicted values according to a preset algorithm by a big data platform according to screened power battery insulation resistance related data including power battery voltage or power battery current, comparing the insulation resistance predicted values with reference insulation resistance by the big data platform, when the difference between the insulation resistance predicted values and the reference insulation resistance is more than 1%, indicating that the parameter selection is unreasonable, adjusting hidden layer weight parameters, hidden layer bias, output layer weight parameters and output layer bias, repeating the above processes, and when the difference between the insulation resistance predicted values and the reference insulation resistance is less than or equal to 1%, establishing a power battery insulation resistance prediction model by taking the selected parameters as corresponding parameters of the power battery insulation resistance prediction model, the reference insulation resistance is the insulation resistance corresponding to the power battery voltage and the power battery current data in the power battery early warning related historical data acquired by the big data platform 3 under the state of being the same as the current vehicle power battery voltage and the current data of the power battery, that is, the corresponding insulation resistance is obtained by searching the historical data through the current vehicle power battery voltage and the current data of the power battery, for example, the current power battery voltage is 10V, the current data of the power battery is 3A, the insulation resistance of the power battery voltage is 10V and the current data of the power battery is 3A under the condition of checking the historical data of the big data platform 3 through the data, the insulation resistance is the reference insulation resistance, and the reference insulation resistance is selected to prevent the value output by the substitution model from having larger deviation with the current reference insulation resistance of the vehicle power battery, so that the established model is not accurate enough.
The preset algorithm of the invention comprises a Bayesian regularization algorithm, which belongs to the prior art, in the embodiment, the Bayesian regularization algorithm is used for obtaining power battery safety related data and model parameters according to input power battery safety related data of a vehicle after selecting the number of hidden layer nodes, obtaining a temperature predicted value and power battery temperature prediction model parameters according to input power battery insulation resistance and power battery voltage data in establishing a power battery temperature prediction model, obtaining a predicted voltage and power battery voltage prediction model parameters according to input power battery temperature or power battery current in establishing a power battery voltage prediction model, obtaining an insulation resistance predicted value and power battery insulation resistance prediction model parameters according to input power battery voltage or power battery current in establishing a power battery insulation resistance prediction model, this is one of the methods used for neural network modeling, and other methods having the same or similar functions may also be used.
The method comprises the steps of obtaining safety related data of a current power battery of a vehicle connected with a big data platform after a model is established, substituting the safety related data into a vehicle power battery safety prediction model, and outputting a safety early warning result, wherein the step of outputting the safety early warning result comprises the steps of comparing y1 with a preset maximum allowable power battery working temperature yk when y1 is obtained, outputting a power battery temperature early warning when y1 is larger than yk, comparing y2 with a preset maximum allowable power battery working voltage yu when y2 is obtained, outputting a power battery voltage early warning when y2 is larger than yu, comparing y3 with a preset maximum allowable power battery working insulation resistance yr when y3 is obtained, outputting a power battery insulation resistance early warning when y3 is larger than yr, substituting the vehicle battery prediction model into the vehicle battery prediction model at the same time, and outputting one or more safety early warning results.
yk is selected from a table preset by the large data platform according to the actual location of the vehicle, and is the maximum allowable operating temperature of the power battery of the vehicle, and when the output temperature exceeds the maximum value, the power battery of the vehicle is damaged, so that a maximum allowable vehicle operating temperature value yk is set.
yu is selected from a table preset by the large data platform according to the actual location of the vehicle, the maximum voltage allowed to operate by the power battery of the vehicle is the maximum voltage, and when the output voltage exceeds the maximum value, the power battery of the vehicle is damaged, so that a maximum voltage allowed for the operation of the vehicle yu is set.
yr is selected from a table preset by the actual location of the vehicle by the large data platform, and is the maximum insulation resistance allowed by the vehicle power battery to operate, and when the output insulation resistance exceeds the maximum value, the vehicle power battery is damaged, so that a maximum insulation resistance value yr allowed by the vehicle to operate is set.
When the vehicle has a demand for early warning of the power battery, the big data platform 3 collects safety related data of one or more power batteries of the vehicle connected with the big data platform and then screens out temperature related data of the power battery, voltage related data of the power battery and insulation resistance related data of the power battery, and the big data platform 3 takes the temperature related data of the power battery as an input parameter x of a temperature prediction model of the power batteryiSubstituting the real-time temperature prediction model into a power battery temperature prediction model to obtain a real-time temperature prediction value y1, comparing the real-time temperature prediction value y1 with a preset maximum power battery working temperature value yk by a big data platform 3, outputting a power battery temperature normal signal to a control unit by the big data platform when y1 is smaller than or equal to yk, and outputting a power battery temperature early warning signal to a vehicle by the big data platform when y1 is larger than ykAnd the unit 2 and the control unit 2 control a display unit or an alarm unit on the vehicle to give an alarm, the display unit comprises a display screen, the alarm unit comprises a vehicle-mounted loudspeaker, and a worker can perform key overhaul on the power battery temperature-related component.
The big data platform also takes the voltage related data of the power battery as an input parameter u of the voltage prediction model of the power batteryiThe method comprises the steps of substituting a power battery voltage prediction model to obtain a voltage real-time prediction value y2, comparing a voltage temperature real-time prediction value y2 with the maximum voltage yu allowed by the preset power battery of a vehicle through a big data platform, outputting a voltage normal signal to a control unit through the big data platform when y2 is smaller than or equal to yu, outputting a power battery voltage early warning signal to the control unit 2 of the vehicle through the big data platform when y2 is larger than yu, controlling the display unit or an alarm unit on the vehicle to give an alarm through the control unit 2, enabling the display unit to comprise a display screen, enabling the alarm unit to comprise a vehicle-mounted loudspeaker, and enabling a worker to overhaul power battery voltage related components in a key mode.
The big data platform also takes the relevant data of the insulation resistance of the power battery as an input parameter r of a prediction model of the insulation resistance of the power batteryiThe method comprises the steps of substituting a power battery insulation resistance prediction model, obtaining an insulation resistance prediction value y3, comparing a real-time insulation resistance prediction value y3 with the maximum insulation resistance yr allowed by the work of a power battery preset by a vehicle by a big data platform, outputting a power battery insulation resistance normal signal to a control unit by the big data platform when y3 is smaller than or equal to yr, outputting a power battery insulation resistance early warning signal to the control unit of the vehicle by the big data platform when y2 is larger than yr, controlling the display unit or the warning unit on the vehicle to give an alarm by the control unit 2, wherein the display unit comprises a display screen, the warning unit comprises a vehicle-mounted loudspeaker, and a worker can overhaul related components of the insulation resistance of the power battery in a key mode.
The power battery temperature prediction model, the power battery voltage prediction model and the power battery insulation resistance prediction model established by the big data platform 3 can be one or two or three.
The big data platform 3 can carry out power battery safety early warning on the vehicle connected with the big data platform, and can carry out safety early warning on any one of the vehicles and also can carry out safety early warning on all vehicles.
And when the safety related data of the vehicle power battery is updated, updating the safety prediction model of the vehicle power battery to obtain a new safety prediction model of the vehicle power battery.
The existing neural network comprises an input layer, a hidden layer and an output layer, data input by the input layer is output at the output layer through calculation of the hidden layer and the output layer, the neural network training is a process of establishing a model and is also an existing method for finding parameters of the hidden layer and the output layer of the neural network, and the existing neural network training is usually carried out in a mode of obtaining an error function through forward calculation and reducing a reverse derivative gradient.
The method improves the early warning method of the new energy vehicle power battery by screening relevant safety data of the vehicle power battery and establishing a vehicle power battery safety prediction model, reduces the data processing amount of a big data platform by screening out the relevant safety data of the vehicle power battery which is not in conformity, and improves the accuracy of establishing the new energy vehicle power battery safety prediction model by screening out the data which is not in conformity.
As shown in FIG. 2, the new energy vehicle power battery early warning system comprises an acquisition module 1, a control unit 2 and a big data platform 3, wherein the acquisition module 1 is connected with the control unit 2, and the control unit 2 is in wireless connection with the big data platform 3.
The acquisition module 1 acquires power battery safety related data and outputs the data to the control unit 2, the control unit 2 receives the data output by the acquisition model and outputs the data to the big data platform 3, the big data platform 3 receives power battery safety related data of a vehicle connected with the big data platform and screens the data to obtain data including power battery temperature, power battery voltage and power battery insulation resistance, the big data platform 3 conducts neural network training on the screened data to establish a vehicle power battery safety prediction model, the big data platform 3 acquires current power battery safety related data of the vehicle connected with the big data platform after establishing the model, and the data are substituted into the vehicle power battery safety prediction model to output a safety early warning result.
The system improves the early warning system of the new energy vehicle power battery by presetting the early warning method of the new energy vehicle power battery by the big data platform, the big data platform 3 screens the safety related data of the vehicle power battery and establishes a vehicle power battery safety prediction model, the system screens out the non-conforming safety related data of the vehicle power battery to reduce the data processing amount of the big data platform, and screening out the non-conforming data improves the accuracy of establishing a new energy vehicle power battery safety prediction model, therefore, the system greatly improves the accuracy of predicting the internal resistance of the new energy vehicle power battery, establishes a vehicle power battery safety prediction model, can accurately obtain the early warning result, therefore, the accuracy of early warning of the new energy vehicle is improved, and meanwhile the use experience of a driver and the convenience of overhauling of workers can be improved.
The acquisition module 1 comprises a temperature sensor for acquiring temperature, a voltmeter for acquiring voltage of the power battery and an insulation resistance sensor for acquiring insulation resistance of the power battery.
The big data platform 3 is a background server and can be connected with the control unit 2 of the vehicle, namely a vehicle-mounted computer, which can be a T-box, to obtain the safety related data of the power battery of the vehicle.
The specific embodiments described herein are merely illustrative of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (10)
1. The method for early warning the power battery of the new energy vehicle is characterized by comprising the following steps:
acquiring power battery safety related data of a vehicle connected with the big data platform (3);
screening the safety related data of the power battery to obtain data related to the temperature of the power battery, the voltage of the power battery and the insulation resistance of the power battery, and carrying out neural network training on the screened data to establish a safety prediction model of the power battery of the vehicle;
and after the model is established, the safety related data of the current power battery of the vehicle connected with the big data platform (3) is obtained and substituted into the safety prediction model of the vehicle power battery, and then a safety early warning result is output.
2. The method for early warning the power battery of the new energy vehicle as claimed in claim 1, wherein the screening step comprises the steps of cleaning the safety-related data of the power battery, removing abnormal data and null data, and performing correlation analysis on the cleaned safety-related data of the power battery to obtain data related to the temperature of the power battery, the voltage of the power battery and the insulation resistance of the power battery.
3. The new energy vehicle power battery early warning method as claimed in claim 2, wherein the correlation analysis includes selecting power battery safety-related data with a pearson correlation coefficient greater than a preset coefficient value.
4. The method for early warning the power battery of the new energy vehicle as claimed in claim 3, wherein the step of establishing the vehicle power battery safety prediction model comprises establishing a power battery temperature prediction model, a power battery voltage prediction model and a power battery insulation resistance prediction model.
5. The new energy vehicle power battery early warning method according to claim 4, characterized in that the step of establishing the power battery temperature prediction model comprises the step of outputting a temperature prediction value output by a preset algorithm according to power battery temperature related data and parametersAnd (4) comparing the reference temperature with the reference temperature, establishing a power battery temperature prediction model when the difference value between the predicted temperature value and the reference temperature is not greater than a preset error value, adjusting the weight and the bias when the difference value between the predicted temperature value and the reference temperature is greater than the preset error value until the difference value between the predicted temperature value and the reference temperature is not greater than the preset error value, wherein the power battery temperature prediction model is
Wherein y1 is a real-time predicted value of temperature, j is 1 … m, m is the number of hidden layer nodes, i is 1 … n, n is the characteristic number of input data, x is the number of hidden layer nodes, and the likeiThe parameters are input for the temperature of the power battery,
in order to hide the layer weight parameters,
in order to hide the layer bias from view,
as output layer weight parameters, b0For output layer bias, fHIs an activation function.
6. The new energy vehicle power battery early warning method as claimed in claim 5, wherein the step of establishing the power battery voltage prediction model includes comparing a predicted voltage output by the power battery voltage related data through a preset algorithm with a reference voltage, establishing the power battery voltage prediction model when a difference between the predicted voltage and the reference voltage is not greater than a preset error value, adjusting the weight and the bias until the difference between the predicted voltage and the reference voltage is not greater than the preset error value when the difference between the predicted voltage and the reference voltage is greater than the preset error value, and establishing the power battery voltage prediction model as
Wherein y2 is the real-time predicted value of voltage, j is 1 … m, m is the number of hidden layer nodes, i is 1 … n, and n is the outputInput data characteristic number, uiThe parameters are input for the voltage of the power battery,
in order to hide the layer weight parameters,
in order to hide the layer bias from view,
as output layer weight parameters, b0For output layer bias, fHIs an activation function.
7. The method according to claim 6, wherein the step of establishing the power battery insulation resistance prediction model comprises comparing an insulation resistance prediction value output by a preset algorithm according to the power battery insulation resistance related data with a reference insulation resistance, establishing the power battery insulation resistance prediction model when a difference between the insulation resistance prediction value and the reference insulation resistance is not greater than a preset error value, adjusting the weight and the bias until the difference between the insulation resistance prediction value and the reference insulation resistance is not greater than the preset error value when the difference between the insulation resistance prediction value and the reference insulation resistance is greater than the preset error value, and establishing the power battery insulation resistance prediction model comprising
Wherein y3 is the real-time predicted value of the insulation resistance, j is 1 … m, m is the number of hidden layer nodes, i is 1 … n, n is the characteristic number of input data, r isiInputting parameters for the insulation resistance of the power battery,
in order to hide the layer weight parameters,
in order to hide the layer bias from view,
as output layer weight parameters, b0For output layer bias, fHIs an activation function.
8. The new energy vehicle power battery early warning method as claimed in claim 7, wherein the step of outputting the safety early warning result comprises comparing y1 with a preset power battery operation allowable maximum temperature yk when y1 is obtained, outputting a power battery temperature early warning when y1 is greater than yk, comparing y2 with a preset power battery operation allowable maximum voltage yu when y2 is obtained, outputting a power battery voltage early warning when y2 is greater than yu, comparing y3 with a preset power battery operation allowable maximum insulation resistance yr when y3 is obtained, and outputting a power battery insulation resistance early warning when y3 is greater than yr.
9. The new energy vehicle power battery early warning method as claimed in any one of claims 1 to 8, wherein the power battery temperature related data comprises power battery insulation resistance and power battery voltage, the power battery voltage related data comprises power battery temperature or power battery current, and the power battery insulation resistance related data comprises power battery voltage or power battery current.
10. The new energy vehicle power battery early warning system comprises a big data platform (3) which is connected with a vehicle and can acquire data on the vehicle, and is characterized by further comprising an acquisition module (1) for acquiring safety-related data of the power battery and a control unit (2) which is arranged on the vehicle and used for receiving the data output by the acquisition module (1), wherein the acquisition module (1) is connected with the control unit (2), the control unit (2) is wirelessly connected with the big data platform (3), the big data platform (3) is used for receiving the safety-related data of the power battery of the vehicle output by the control unit (2) of the vehicle connected with the big data platform, and screening the received data to obtain data which comprise the temperature correlation of the power battery, the voltage correlation of the power battery and the insulation resistance correlation of the power battery, and carrying out neural network training on the screened data to establish a vehicle power battery safety prediction model, wherein the big data platform (3) is also used for acquiring the current power battery safety related data of the vehicle connected with the big data platform after the model is established, substituting the data into the vehicle power battery safety prediction model and outputting a safety early warning result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110476497.4A CN113173104B (en) | 2021-04-29 | 2021-04-29 | New energy vehicle power battery early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110476497.4A CN113173104B (en) | 2021-04-29 | 2021-04-29 | New energy vehicle power battery early warning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113173104A true CN113173104A (en) | 2021-07-27 |
| CN113173104B CN113173104B (en) | 2022-11-22 |
Family
ID=76925441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110476497.4A Active CN113173104B (en) | 2021-04-29 | 2021-04-29 | New energy vehicle power battery early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113173104B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113844266A (en) * | 2021-08-20 | 2021-12-28 | 云度新能源汽车有限公司 | Method and storage device for predicting and identifying faults of power battery |
| CN114295986A (en) * | 2021-12-03 | 2022-04-08 | 广西电网有限责任公司北海供电局 | Storage battery state monitoring module |
| CN114995164A (en) * | 2022-08-03 | 2022-09-02 | 武汉维泰信息科技有限公司 | New energy automobile safety early warning method and device based on Internet of things |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107069122A (en) * | 2017-04-01 | 2017-08-18 | 山东省科学院自动化研究所 | A kind of Forecasting Methodology of electrokinetic cell remaining life |
| CN108556647A (en) * | 2018-01-16 | 2018-09-21 | 上海应用技术大学 | The safety on line method for early warning of Prospect of EVS Powered with Batteries based on cloud platform and battery management system |
| CN111008728A (en) * | 2019-11-01 | 2020-04-14 | 深圳供电局有限公司 | Method for predicting short-term output of distributed photovoltaic power generation system |
| CN111007401A (en) * | 2019-12-16 | 2020-04-14 | 国网江苏省电力有限公司电力科学研究院 | Electric vehicle battery fault diagnosis method and device based on artificial intelligence |
| US20200153264A1 (en) * | 2017-07-25 | 2020-05-14 | Semiconductor Energy Laboratory Co., Ltd. | Power storage system, electronic device, vehicle, and estimation method |
| CN111381165A (en) * | 2018-12-28 | 2020-07-07 | 重庆峘能电动车科技有限公司 | Vehicle power battery monitoring method, device and platform |
| CN111572350A (en) * | 2020-05-29 | 2020-08-25 | 北京经纬恒润科技有限公司 | Electric automobile fire-starting early warning method and device |
-
2021
- 2021-04-29 CN CN202110476497.4A patent/CN113173104B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107069122A (en) * | 2017-04-01 | 2017-08-18 | 山东省科学院自动化研究所 | A kind of Forecasting Methodology of electrokinetic cell remaining life |
| US20200153264A1 (en) * | 2017-07-25 | 2020-05-14 | Semiconductor Energy Laboratory Co., Ltd. | Power storage system, electronic device, vehicle, and estimation method |
| CN108556647A (en) * | 2018-01-16 | 2018-09-21 | 上海应用技术大学 | The safety on line method for early warning of Prospect of EVS Powered with Batteries based on cloud platform and battery management system |
| CN111381165A (en) * | 2018-12-28 | 2020-07-07 | 重庆峘能电动车科技有限公司 | Vehicle power battery monitoring method, device and platform |
| CN111008728A (en) * | 2019-11-01 | 2020-04-14 | 深圳供电局有限公司 | Method for predicting short-term output of distributed photovoltaic power generation system |
| CN111007401A (en) * | 2019-12-16 | 2020-04-14 | 国网江苏省电力有限公司电力科学研究院 | Electric vehicle battery fault diagnosis method and device based on artificial intelligence |
| CN111572350A (en) * | 2020-05-29 | 2020-08-25 | 北京经纬恒润科技有限公司 | Electric automobile fire-starting early warning method and device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113844266A (en) * | 2021-08-20 | 2021-12-28 | 云度新能源汽车有限公司 | Method and storage device for predicting and identifying faults of power battery |
| CN114295986A (en) * | 2021-12-03 | 2022-04-08 | 广西电网有限责任公司北海供电局 | Storage battery state monitoring module |
| CN114995164A (en) * | 2022-08-03 | 2022-09-02 | 武汉维泰信息科技有限公司 | New energy automobile safety early warning method and device based on Internet of things |
| CN114995164B (en) * | 2022-08-03 | 2022-12-02 | 武汉维泰信息科技有限公司 | New energy automobile safety early warning method and device based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113173104B (en) | 2022-11-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113173104B (en) | New energy vehicle power battery early warning method and system | |
| CN110492186B (en) | Power battery module management method based on cloud control technology | |
| JP4414470B1 (en) | Generating reference values for vehicle fault diagnosis | |
| JP4928532B2 (en) | Vehicle fault diagnosis device | |
| CN107037370B (en) | Electric vehicle remaining power calculation method based on monitoring data | |
| CN107291991B (en) | Early defect early warning method for wind turbine generator based on dynamic network sign | |
| CN111823952A (en) | Battery cell temperature diagnosis method, storage medium and electronic equipment | |
| CN113191547B (en) | New energy vehicle power battery charging optimization method and system | |
| CN114239734B (en) | Distributed vehicle-mounted health management system | |
| CN114254818A (en) | Low-voltage distribution network cascading failure early warning method based on risk assessment model | |
| CN110942221A (en) | Transformer substation fault rapid repairing method based on Internet of things | |
| CN113159435B (en) | Method and system for predicting remaining driving mileage of new energy vehicle | |
| Wang et al. | Prognostics and health management system for electric vehicles with a hierarchy fusion framework: concepts, architectures, and methods | |
| CN114036647A (en) | Power battery safety risk assessment method based on real vehicle data | |
| CN113505932A (en) | Power battery capacity algorithm based on big data technology evaluation | |
| CN114487839A (en) | Early warning method and device for battery | |
| CN114692926A (en) | Safety evaluation method, system and equipment for vehicle battery and readable storage medium | |
| CN115848176A (en) | Electric vehicle charging early warning method and system based on A-LSTM algorithm | |
| CN113212244B (en) | New energy vehicle power battery life prediction method and system | |
| CN111381165A (en) | Vehicle power battery monitoring method, device and platform | |
| CN115469226A (en) | Real-time safety early warning method for electric vehicle power battery based on operation big data | |
| CN113986893A (en) | Active early warning system and method based on generator car risk identification | |
| CN111624985A (en) | Gas turbine control system sensor fault diagnosis method | |
| CN113448301A (en) | Fault diagnosis method and system based on OBD system | |
| CN117691722B (en) | Lithium battery charging safety monitoring and early warning method and system |
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 |