CN113895272A - Electric vehicle alternating current charging state monitoring and fault early warning method based on deep learning - Google Patents
Electric vehicle alternating current charging state monitoring and fault early warning method based on deep learning Download PDFInfo
- Publication number
- CN113895272A CN113895272A CN202111203161.7A CN202111203161A CN113895272A CN 113895272 A CN113895272 A CN 113895272A CN 202111203161 A CN202111203161 A CN 202111203161A CN 113895272 A CN113895272 A CN 113895272A
- Authority
- CN
- China
- Prior art keywords
- alternating current
- current charging
- data
- electric vehicle
- early warning
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000012544 monitoring process Methods 0.000 title claims abstract description 34
- 238000013135 deep learning Methods 0.000 title claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 238000013136 deep learning model Methods 0.000 claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000011156 evaluation Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 16
- 230000004913 activation Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 241000288673 Chiroptera Species 0.000 claims description 3
- 241000288105 Grus Species 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000013450 outlier detection Methods 0.000 claims description 3
- 238000005295 random walk Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 206010000369 Accident Diseases 0.000 claims description 2
- 230000002457 bidirectional effect Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 125000004122 cyclic group Chemical group 0.000 claims 2
- 230000001172 regenerating effect Effects 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 4
- 238000012300 Sequence Analysis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 239000000178 monomer Substances 0.000 description 3
- 230000000306 recurrent effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- B60L53/00—Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
- B60L53/60—Monitoring or controlling charging stations
-
- 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
-
- 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
- B60L3/12—Recording operating variables ; Monitoring of operating variables
-
- 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
-
- 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
- Y02T10/7072—Electromobility specific charging systems or methods for batteries, ultracapacitors, supercapacitors or double-layer capacitors
-
- 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
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/12—Electric charging stations
-
- 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
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/16—Information or communication technologies improving the operation of electric vehicles
- Y02T90/167—Systems integrating technologies related to power network operation and communication or information technologies for supporting the interoperability of electric or hybrid vehicles, i.e. smartgrids as interface for battery charging of electric vehicles [EV] or hybrid vehicles [HEV]
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S30/00—Systems supporting specific end-user applications in the sector of transportation
- Y04S30/10—Systems supporting the interoperability of electric or hybrid vehicles
- Y04S30/12—Remote or cooperative charging
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The invention designs an electric vehicle alternating current charging state monitoring and fault early warning method based on deep learning, which comprises the steps of firstly, carrying out state monitoring on various parameters of the electric vehicle alternating current charging, and storing the parameters into a database; secondly, dividing data in the database into historical data and real-time data, and preprocessing the historical data and the real-time data; then, a CNN-BiGRU deep learning model is designed to fully learn the normal alternating current charging historical data, an alternating current charging prediction model of the electric automobile is constructed, and the hyper-parameters of the model are optimized by adopting a bat algorithm; then, an evaluation standard of the model prediction precision is formulated to evaluate the accuracy of the model prediction, residual error analysis is carried out on the model prediction value through a sliding window method, and a fault early warning threshold value and a fault early warning rule which are suitable for alternating current charging of the electric automobile are determined; and finally, applying the trained CNN-BiGRU prediction model to real-time alternating current charging monitoring of the electric automobile to realize fault early warning of the electric automobile.
Description
Technical Field
The invention belongs to the technical field of equipment fault early warning, and particularly relates to an electric vehicle alternating current charging state monitoring and fault early warning method based on deep learning.
Background
In recent years, with the increasing preservation quantity of traditional fuel automobiles, the energy crisis and the environmental pollution are increasingly aggravated, and the electric automobile industry is vigorously developed at home and abroad. With the continuous development of the electric automobile industry, the safety problem of the electric automobile is more and more emphasized by people. The range of the safety problem of the electric automobile is very wide, and the safety problem comprises the aspects of the safety of the whole automobile, the charging safety, the information safety and the like. The alternating current charging of the electric automobile has the advantages of low cost and prolonged service life of the power battery, and is widely applied at present, so that the research on the safety and the reliability of the alternating current charging of the electric automobile is very necessary. The power battery is used as a power source of the electric vehicle, and the ac charging safety problem is particularly important, because once the power battery fails in the ac charging process, the power battery is very likely to cause the electric vehicle to catch fire, thereby causing serious economic loss and even possibly causing casualties. Therefore, in the alternating current charging process of the electric automobile, the alternating current charging data of the power battery is dynamically monitored, the occurrence of faults is effectively predicted in time, and measures are taken to ensure the safety of the alternating current charging, so that the method has important significance.
At present, research results of safety analysis and dynamic early warning methods in the alternating-current charging process of the electric automobile are relatively few, but fault early warning methods based on deep learning are widely applied to other industries. The Convolutional Neural Network (CNN) can effectively learn deep features from a large sample, avoid a complex feature extraction process, and can fully mine alternating current charging data of the electric vehicle. The bidirectional gating circulation Unit BiGRU (Bi-directional Gated Recurrent Unit, BiGRU) has the characteristic of time series prediction, can give consideration to both the AC charging history and the future time data of the electric vehicle, can utilize deep features extracted by CNN more deeply, and can improve the data extraction, analysis and generalization capability of the model.
According to the national standard, the alternating current charging data of the electric automobile is acquired, and the electric automobile alternating current charging state monitoring and fault early warning method based on deep learning is provided. According to the method, CNN is used for fully mining monitored alternating current charging historical data of the electric vehicle, deep features hidden in the alternating current charging data are extracted, the deep features are input into a BiGRU, time sequence analysis is carried out on the deep features, and a charging prediction model for normal alternating current of the electric vehicle is constructed. And searching the hyper-parameters such as the learning rate, the iteration times, the number of hidden units and the like of the CNN-BiGRU deep learning model by using a bat algorithm so as to enhance the prediction accuracy of the alternating current charging prediction model. And analyzing the quality of the prediction effect of the alternating-current charging prediction model by establishing an evaluation standard of the model prediction precision. And analyzing and processing the prediction residual error of the alternating current charging model by adopting a sliding window analysis method, and determining a good fault early warning threshold value. The alternating-current charging prediction model with good prediction effect, the early warning rule and the threshold value are applied to the real-time monitoring of the alternating-current charging of the electric automobile, and the fault early warning in the alternating-current charging process of the electric automobile is realized.
Disclosure of Invention
The invention provides an electric vehicle alternating current charging state monitoring and fault early warning method based on deep learning, aiming at the safety problem existing in the electric vehicle alternating current charging fault early warning, and aiming at solving the defects of the existing method. According to the method, CNN is used for fully mining monitored alternating current charging historical data of the electric vehicle, deep features hidden in the alternating current charging data are extracted and input into a BiGRU, time sequence analysis is carried out on the deep features, and a charging prediction model for normal alternating current of the electric vehicle is constructed. And searching the hyper-parameters such as the learning rate, the iteration times, the number of hidden units and the like of the CNN-BiGRU deep learning model by using a bat algorithm so as to enhance the prediction accuracy of the alternating current charging prediction model. And analyzing the quality of the prediction effect of the alternating-current charging prediction model by establishing an evaluation standard of the model prediction precision. And analyzing and processing the prediction residual error of the alternating current charging model by adopting a sliding window analysis method, and determining a good fault early warning threshold value. The alternating-current charging prediction model with good prediction effect, the early warning rule and the threshold value are applied to the real-time monitoring of the alternating-current charging of the electric automobile, and the fault early warning in the alternating-current charging process of the electric automobile is realized. In order to achieve the above purpose, the invention provides the following scheme: the electric vehicle alternating current charging state monitoring and fault early warning method based on deep learning specifically comprises the following steps:
step 1: monitoring the state of various parameters of the alternating current charging process of the electric automobile, and storing the monitoring data into a database;
step 2: dividing alternating current charging data in a database into historical data and real-time data, and preprocessing the historical data and the real-time data;
and step 3: designing a CNN-BiGRU deep learning model, fully learning normal alternating current charging historical data of the electric automobile, and constructing a prediction model of alternating current charging of the electric automobile;
and 4, step 4: optimizing the hyper-parameters of the alternating current charging prediction model of the electric automobile by adopting a bat algorithm;
and 5: an evaluation standard of the output precision of the prediction model is formulated for evaluating the accuracy of the prediction model;
step 6: residual error analysis is carried out on the predicted value of the model through a sliding window method, and a fault early warning threshold value and a fault early warning rule which are suitable for alternating current charging of the electric automobile are determined;
and 7: acquiring real-time alternating current charging data of the electric automobile on line;
and 8: inputting the real-time alternating current charging data into a trained prediction model to obtain a prediction output value;
and step 9: calculating residual mean and standard deviation of the predicted output value by a sliding window method;
step 10: and when the residual mean value and the standard deviation exceed the set threshold value at the same time, carrying out fault early warning and stopping the alternating current charging of the electric automobile.
In step 1, the state monitoring of each parameter in the ac charging process of the electric vehicle includes, but is not limited to, parameter information such as rated capacity of a power battery of the entire vehicle, rated voltage of the power battery of the entire vehicle, maximum allowable individual voltage, maximum allowable ac charging current, nominal total energy of the power battery of the entire vehicle, maximum allowable ac charging voltage, maximum allowable temperature, initial SOC of the power battery of the entire vehicle, initial voltage of the power battery of the entire vehicle, ac voltage required by the power battery of the entire vehicle, ac current required by the power battery of the entire vehicle, measured value of the ac charging voltage, measured value of the ac charging current, maximum individual voltage of the power battery of the entire vehicle, current SOC of the power battery of the entire vehicle, and maximum temperature of the power battery of the entire vehicle.
In step 2 of the invention, the AC charging data is preprocessed, which specifically comprises the following operations:
(1) performing outlier detection on the data, and deleting abnormal data in the data;
(2) filling missing values in the data by an interpolation method;
(3) and (4) normalizing the data by using a range normalization method, wherein the range of the processed data is [0,1 ].
The invention designs a CNN-BiGRU deep learning model in step 3, wherein the CNN has the following calculation formula:
ct＝f(WCNN*nt+bCNN)
in the formula, WCNNRepresenting the weight coefficient of a filter in the convolution of the alternating current charging data of the electric automobile, namely a convolution kernel; n istRepresenting the alternating current charging data of the electric vehicle at the time t; is a convolution operation; bCNNA deviation coefficient representing convolution operation of alternating current charging data of the electric vehicle; c. CtThe alternating current charging data sequence of the electric automobile is extracted after convolution; f represents an activation function of convolution operation of the alternating current charging data of the electric automobile.
In step 3, the invention designs a CNN-BiGRU deep learning model, wherein the BiGRU is composed of a forward hidden gate control circulation Unit (Gated Recurrent Unit, GRU)
The GRU has the calculation formula as follows:
rt＝σ(Wrxt+Urht-1+br)
zt＝σ(Wzxt+Uzht-1+bz)
ht＝tanh(Wh1xt+(rt⊙ht-1)Wh2+bh)
ht＝(1-zt)⊙ht-1+zt⊙ht
yt＝σ(Wo⊙ht)
in the formula, rtTo reset the gate; z is a radical oftTo update the door; h istThe GRU hidden state is used for AC charging of the electric vehicle at the time t; y istPredicting and outputting the alternating current charging of the electric automobile at the time t; σ and tanh are activation functions; wr、Wz、Ur、Uz、Wh1And Wh2Weighting parameters of deep features of the alternating current charging data of the electric vehicle; br、bzAnd bhDeviation parameters of deep characteristics of the alternating current charging data of the electric vehicle; as a Hadamard product; h istAnd (4) a GRU candidate state for AC charging of the electric vehicle at the time t. The BiGRU calculation formula is as follows:
in the formula, wtThe output weight of the GRU of the forward hidden layer of the deep layer characteristics of the AC charging data of the electric vehicle at the time t; v. oftOutputting weights of backward hidden layer GRUs of deep features of the electric vehicle alternating current charging data at the time t; h istThe hidden state of the BiGRU is charged for the electric vehicle at the time t; btIs htThe corresponding offset.
In step 4 of the present invention, a bat algorithm is adopted to optimize the hyper-parameters of the prediction model, the bat algorithm is an optimization algorithm for searching the specific target position by simulating the pulse echo of the bat, and assuming that the search space of the bat algorithm is d-dimension, the updated formula at the next moment is:
lm＝lmin+(lmax-lmin)ξ
in the formula (I), the compound is shown in the specification,
searching the position and the speed of the m-th value bat in the space for the time t; lmThe frequency emitted by the mth bat; x is the number ofbestRepresenting a current global optimal solution; lmax、lminSending out the maximum value and the minimum value of the frequency for the bat algorithm; xi is in the middle of 0,1]The random number of (2).
For local search, once a solution is selected among the current best solutions, a new local solution is generated using a random walk method, which has the formula:
xnew＝xold+ψAt
in which ψ e [ -1,1 [ ]]The random number of (2); x is the number ofoldRandomly selecting one of the current optimal solutions; a. thetIs the average value of bats population loudness.
In the optimization process of the bat algorithm, the loudness A gradually decreases along with the approach of the optimal solution, the pulse frequency R continuously increases, and the sound wave loudness of the ith bat algorithm
Frequency of sum
The update formula is as follows:
wherein, alpha belongs to (0,1) and is the attenuation coefficient of the sound wave loudness; gamma > 0, which is a pulse frequency enhancement coefficient;
is the initial pulse frequency of the ith bat. For any of α and γ, when t → ∞,
when in use
When the bat finds a prey, sound waves are not emitted temporarily, and only after the position of the bat is optimized, the loudness and frequency of the pulses are updated, which implies that the bat moves towards an optimal solution method.
In the step 5 of the invention, the evaluation standard of the output accuracy of the prediction model is formulated by adopting the root mean square error eRMSE(Root Mean Square Error，eRMSE) And the mean absolute percentage error eMAPE(Mean Absolute Percentage Error，eMAPE) The two error measurement modes are used as indexes for evaluating the accuracy of the alternating current charging prediction model, and the calculation formula is as follows:
in the formula, yiAnd
respectively actual electric vehicle alternating current charging data and predicted electric vehicle alternating current at the ith momentCharging data; n is the number of all samples as a test set. e.g. of the typeRMSEAnd eMAPEThe smaller the value, the more accurate the predicted electric vehicle ac charging data.
In step 6 of the invention, residual error analysis is carried out on the model predicted value by a sliding window method, and a proper fault early warning threshold value and rule are determined, so that the influence of error alternating current charging data on residual error change in the data transmission process can be eliminated, and error early warning can be effectively avoided. When the width of the sliding window is N, the calculation formula of the mean value and the standard deviation of the residual error under the window is as follows:
in the formula, eiIs the residual error of the ith sample point in the sliding window. Analyzing and processing the residual error of the normal alternating current charging data by utilizing a sliding window to obtain the maximum value of the average absolute value of the normal alternating current charging residual errors
And the maximum value S of the residual standard deviationmaxThe calculation formula of the early warning threshold is as follows:
SY＝k2Smax
in the formula, k1And k2The value of the scaling factor is determined by the type of the AC-charged electric vehicle and the battery capacity. And when the mean value and the standard deviation both exceed the calculated early warning threshold value, carrying out fault early warning.
In step 10, the fault early warning in the alternating current charging process of the electric automobile is realized, and when the residual mean value and the standard deviation exceed the set threshold value at the same time, the fault early warning is carried out, the alternating current charging of the electric automobile is cut off, and the fire accident is prevented.
The beneficial effect of this application lies in: according to the method for monitoring the alternating current charging state of the electric vehicle and early warning the fault based on deep learning, after the alternating current charging data of the electric vehicle are preprocessed, a CNN-BiGRU deep learning model is designed to deeply learn the alternating current charging data of the electric vehicle, and a normal alternating current charging prediction model of the electric vehicle is constructed; according to the method and the device, the CNN is adopted to carry out deep mining on the alternating current charging data, the deep features of the alternating current charging data are extracted, and the time sequence analysis is carried out on the deep features by utilizing the advantages of the BiGRU analysis history and the future data, so that the training time of the model is shortened, and the prediction accuracy of the model is improved. The super-parameters of the CNN-BiGRU deep learning model are determined by using the bat algorithm, so that the accuracy of predicting the alternating current charging data of the electric vehicle can be further enhanced; the method and the device for determining the fault early warning of the electric automobile adopt a sliding window analysis method to determine the rule and the threshold value of the fault early warning of the electric automobile, not only can early warn the fault of the alternating current charging process of the electric automobile in advance, but also can eliminate the error early warning caused by error data in the data transmission process.
Drawings
FIG. 1 is a schematic flow chart of an electric vehicle AC charging state monitoring and fault early warning method based on deep learning according to the present invention;
FIG. 2 is a diagram of a CNN-BiGRU deep learning model structure designed by the present invention;
FIG. 3 is a diagram of a GRU network architecture in accordance with the present invention;
FIG. 4 is a flow chart of CNN-BiGRU deep learning model parameter optimization based on bat algorithm;
fig. 5 is a block diagram of an electric vehicle ac charging state monitoring and fault early warning method based on deep learning according to the present invention.
Detailed Description
Specific embodiments of the present invention will be described in more detail below with reference to the accompanying drawings of the specification. The procedures, conditions, experimental methods and the like for carrying out the present invention are general knowledge and common general knowledge in the art except for the contents specifically mentioned below, and the present invention is not particularly limited.
Fig. 1 is a schematic flow chart of an electric vehicle ac charging state monitoring and fault early warning method based on deep learning according to the present invention. As shown in fig. 1, the method for monitoring the ac charging state and early warning the fault of the electric vehicle based on deep learning of the present invention includes the following steps:
step 1: the method comprises the steps of carrying out state monitoring on various parameters in the alternating current charging process of the electric automobile, and monitoring state information such as rated capacity of a power battery of the whole automobile, rated voltage of the power battery of the whole automobile, maximum allowable monomer voltage, maximum allowable alternating current charging current, rated total energy of the power battery of the whole automobile, maximum allowable alternating current charging voltage, maximum allowable temperature, initial SOC of the power battery of the whole automobile, initial voltage of the power battery of the whole automobile, alternating current voltage required by the power battery of the whole automobile, alternating current charging voltage measured value, alternating current charging current measured value, maximum monomer voltage of the power battery of the whole automobile, current SOC of the power battery of the whole automobile, maximum temperature of the power battery monomer of the whole automobile and the like.
Step 2: and dividing the alternating current charging data in the database into historical data and real-time charging data, and preprocessing the historical data and the real-time charging data. Specifically, the historical normal alternating current charging data is used for constructing an alternating current normal charging prediction model of the electric vehicle, and the real-time alternating current charging data is used for online fault early warning.
The preprocessing of the data comprises the following operations:
(1) performing outlier detection on the data, and deleting abnormal data in the data;
(2) filling missing values in the data by an interpolation method;
(3) and (3) carrying out normalization processing on the data by using a range normalization method, wherein the processed data range is [0,1], and a calculation formula is as follows.
In the formula, xmin，xmaxRespectively, are data set samplesMinimum and maximum values of group data, xoutIs the result of normalizing the input data x.
And step 3: and fully utilizing the normal alternating current charging historical data by using the CNN-BiGRU deep learning network model to construct an alternating current charging prediction model of the electric automobile.
The CNN network structure in the CNN-BiGRU deep learning model is shown in the CNN network structure in fig. 2, and the calculation formula is as follows:
ct＝f(WCNN*nt+bCNN)
in the formula, WCNNRepresenting the weight coefficient of a filter in the convolution of the alternating current charging data of the electric automobile, namely a convolution kernel; n istRepresenting the alternating current charging data of the electric vehicle at the time t; is a convolution operation; bCNNA deviation coefficient representing convolution operation of alternating current charging data of the electric vehicle; c. CtThe alternating current charging data sequence of the electric automobile is extracted after convolution; f represents an activation function of convolution operation of the alternating current charging data of the electric automobile.
The BiGRU is transformed based on the GRU, has strong memory capacity, can effectively retain historical input data, and compared with the unidirectional GRU, the BiGRU can give consideration to the influence of historical and future charging data on the current moment, so that the historical alternating current charging data of the electric automobile can be deeply analyzed. The CNN-BiGRU deep learning model has the advantages of both CNN and BiGRU networks, and the model structure is shown in FIG. 2.
GRU update gate ztAnd a reset gate rtThe system comprises an update gate, a reset gate and a network structure, wherein the update gate represents the influence degree of charging data of an electric vehicle at the previous moment on the current moment, the reset gate represents the neglected degree of the charging data of the electric vehicle at the previous moment, the network structure is shown in fig. 3, and the specific calculation formula is as follows:
rt＝σ(Wrxt+Urht-1+br)
zt＝σ(Wzxt+Uzht-1+bz)
ht＝tanh(Wh1xt+(rt⊙ht-1)Wh2+bh)
ht＝(1-zt)⊙ht-1+zt⊙ht
yt＝σ(Wo⊙ht)
in the formula, rtTo reset the gate; z is a radical oftTo update the door; h istThe GRU hidden state is used for AC charging of the electric vehicle at the time t; y istPredicting and outputting the alternating current charging of the electric automobile at the time t; σ and tanh are activation functions; wr、Wz、Ur、Uz、Wh1And Wh2Weighting parameters of deep features of the alternating current charging data of the electric vehicle; br、bzAnd bhDeviation parameters of deep characteristics of the alternating current charging data of the electric vehicle; as a Hadamard product; h istGRU candidate state for AC charging of electric vehicle at time t, which is provided by reset gate rtGRU hidden state h for alternating current charging of electric automobile at time t-1t-1And the input x of the alternating current charging of the electric automobile at the current momenttAnd (4) controlling together.
As shown in the BiGRU network structure in FIG. 2, the BiGRU is composed of a forward hidden layer GRU and a backward hidden layer GRU which are connected with each other, and the charging output of the electric vehicle at the time t and the output of the forward hidden layer GRU
And the output of backward hidden layer GRU
The result of the linear superposition is calculated as follows:
in the formula, wtThe output weight of the GRU of the forward hidden layer of the deep layer characteristics of the AC charging data of the electric vehicle at the time t; v. oftOutputting weights of backward hidden layer GRUs of deep features of the electric vehicle alternating current charging data at the time t; h istThe hidden state of the BiGRU is charged for the electric vehicle at the time t; btIs htThe corresponding offset.
And 4, step 4: and optimizing the hyper-parameters of the CNN-BiGRU deep learning model by adopting a bat algorithm. The CNN-BiGRU deep learning model sets different learning rates, iteration times and the number of hidden layer units, and the obtained prediction performance has larger difference. The structure of the current CNN-BiGRU deep learning model is usually obtained by selecting a plurality of groups of different learning rates, iteration times and the number of hidden layer units for debugging and comparison according to experience, which usually needs to consume a large amount of time and energy. To solve the problem, the invention proposes to solve the hyper-parameters of the model by using the bat algorithm, and the flow chart is shown in fig. 3, and specifically the method comprises the following steps:
step 4.1: initializing parameters of the bat algorithm, and setting the hyper-parameters of the model as an optimized object of the bat algorithm;
step 4.2: setting the position, speed and fitness value of the bat;
step 4.3: finding out the best one of all the bat fitness values, and updating the speed and the position of the bat, wherein if the search space of the bat algorithm is d-dimension, the updated formula at the next moment is as follows:
lm＝lmin+(lmax-lmin)ξ
in the formula (I), the compound is shown in the specification,
searching the position and the speed of the m-th value bat in the space for the time t; lmThe frequency emitted by the mth bat; x is the number ofbestRepresenting a current global optimal solution; lmax、lminSending out the maximum value and the minimum value of the frequency for the bat algorithm; xi is in the middle of 0,1]The random number of (2).
For local search, once a solution is selected among the current best solutions, a new local solution is generated using a random walk method, which has the formula:
xnew＝xold+ψAt
in which ψ e [ -1,1 [ ]]The random number of (2); x is the number ofoldRandomly selecting one of the current optimal solutions; a. thetIs the average value of bats population loudness.
In the optimization process of the bat algorithm, the loudness A gradually decreases along with the approach of the optimal solution, the pulse frequency R continuously increases, and the sound wave loudness of the ith bat algorithm
Frequency of sum
The update formula is as follows:
wherein, alpha belongs to (0,1) and is the attenuation coefficient of the sound wave loudness; gamma > 0, which is a pulse frequency enhancement coefficient;
is the initial pulse frequency of the ith bat. For any of α and γ, when t → ∞When the temperature of the water is higher than the set temperature,
when in use
When the bat finds a prey, sound waves are not emitted temporarily, and only after the position of the bat is optimized, the loudness and frequency of the pulses are updated, which implies that the bat moves towards an optimal solution method.
Step 4.4: repeating the step 4.3 until the requirement of the set optimal solution is met or the maximum iteration times is reached, and outputting the optimal solution;
step 4.5: and transmitting the solved optimal hyper-parameter to a CNN-BiGRU deep learning model, wherein the whole process is shown in figure 3.
And 5: making an evaluation standard of model prediction accuracy by adopting eRMSEAnd eMAPEThe two error measurement modes are used as indexes for evaluating the accuracy of the alternating current charging prediction model, and the calculation formula is as follows:
in the formula, yiAnd
respectively obtaining actual electric vehicle alternating current charging data and predicted electric vehicle alternating current charging data at the ith moment; n is the number of all samples as a test set. e.g. of the typeRMSEAnd eMAPEThe smaller the value, the more accurate the predicted electric vehicle ac charging data.
Step 6: residual error analysis is carried out on the model predicted value through a sliding window method, a proper fault early warning threshold value and a proper fault early warning rule are determined, the influence of error alternating current charging data on residual error change in the data transmission process can be eliminated, and error early warning can be effectively avoided. When the width of the sliding window is N, the calculation formula of the mean value and the standard deviation of the residual error under the window is as follows:
in the formula, eiIs the residual error of the ith sample point in the sliding window. Analyzing and processing the residual error of the normal alternating current charging data by utilizing a sliding window to obtain the maximum value of the average absolute value of the normal alternating current charging residual errors
And the maximum value S of the residual standard deviationmaxThe calculation formula of the early warning threshold is as follows:
SY＝k2Smax
in the formula, k1And k2The value of the scaling factor is determined by the type of the AC-charged electric vehicle and the battery capacity. And when the mean value and the standard deviation both exceed the calculated early warning threshold value, carrying out fault early warning.
And 7: acquiring real-time alternating current charging data of the electric automobile on line;
and 8: inputting the real-time alternating current charging data into a trained prediction model to obtain a prediction output value;
and step 9: calculating residual mean and standard deviation of the predicted output value by a sliding window method;
step 10: and when the residual mean value and the standard deviation exceed the set threshold value at the same time, carrying out fault early warning and stopping the alternating current charging of the electric automobile.
Although the present invention has been disclosed in the preferred embodiments above, the present invention is not limited thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention is subject to the scope defined by the claims.
Claims (9)
1. The method for monitoring the alternating current charging state of the electric vehicle and early warning the fault based on deep learning is characterized by comprising three parts of state monitoring, data preprocessing, offline model training and online fault early warning, and specifically comprises the following steps:
step 1: monitoring the state of various parameters of the alternating current charging process of the electric automobile, and storing the monitoring data into a database;
step 2: dividing alternating current charging data in a database into historical data and real-time data, and preprocessing the historical data and the real-time data;
and step 3: designing a CNN-BiGRU deep learning model, fully learning normal alternating current charging historical data of the electric automobile, and constructing a prediction model of alternating current charging of the electric automobile;
and 4, step 4: optimizing the hyper-parameters of the alternating current charging prediction model of the electric automobile by adopting a bat algorithm;
and 5: an evaluation standard of the output precision of the prediction model is formulated for evaluating the accuracy of the prediction model;
step 6: residual error analysis is carried out on the predicted value of the model through a sliding window method, and a fault early warning threshold value and a fault early warning rule which are suitable for alternating current charging of the electric automobile are determined;
and 7: acquiring real-time alternating current charging data of the electric automobile on line;
and 8: inputting the real-time alternating current charging data into a trained prediction model to obtain a prediction output value;
and step 9: calculating residual mean and standard deviation of the predicted output value by a sliding window method;
step 10: and when the residual mean value and the standard deviation exceed the set threshold value at the same time, carrying out fault early warning and stopping the alternating current charging of the electric automobile.
2. The deep learning-based alternating current charging state monitoring and fault early warning method for the electric vehicle as claimed in claim 1, the method is characterized in that various parameters for monitoring the state of the alternating current charging of the electric automobile in the step 1 include, but are not limited to, rated capacity of a power battery of the whole automobile, rated voltage of the power battery of the whole automobile, maximum allowable single voltage, maximum allowable alternating current charging current, nominal total energy of the power battery of the whole automobile, maximum allowable alternating current charging voltage, maximum allowable temperature, initial SOC of the power battery of the whole automobile, initial voltage of the power battery of the whole automobile, required alternating current of the power battery of the whole automobile, measured value of the alternating current charging voltage, measured value of the alternating current charging current, maximum single voltage of the power battery of the whole automobile, current SOC of the power battery of the whole automobile, maximum temperature of the single power battery of the whole automobile and the like.
3. The deep learning-based electric vehicle alternating current charging state monitoring and fault early warning method according to claim 1, wherein the alternating current charging data is preprocessed in the step 2, and the method specifically comprises the following operations:
(1) performing outlier detection on the data, and deleting abnormal data in the data;
(2) filling missing values in the data by an interpolation method;
(3) and (4) normalizing the data by using a range normalization method, wherein the range of the processed data is [0,1 ].
4. The deep learning-based electric vehicle alternating current charging state monitoring and fault early warning method according to claim 1, wherein the step 3 is designed to be a CNN-BiGRU deep learning model, wherein CNN (Convolutional Neural Networks, CNN) is a Convolutional Neural network, and a calculation formula of the Convolutional Neural network is as follows:
ct＝f(WCNN*nt+bCNN)
in the formula, WCNNRepresenting the weight coefficient of a filter in the convolution of the alternating current charging data of the electric automobile, namely a convolution kernel; n istElectric vehicle alternating current charging data representing time t(ii) a Is a convolution operation; bCNNA deviation coefficient representing convolution operation of alternating current charging data of the electric vehicle; c. CtThe alternating current charging data sequence of the electric automobile is extracted after convolution; f represents an activation function of convolution operation of the alternating current charging data of the electric automobile.
5. The deep learning-based ac charging status monitoring and fault warning method for electric vehicle as claimed in claim 1, wherein step 3 uses a CNN-BiGRU deep learning model, wherein BiGRU (Bi-directional Gated regenerative Unit, BiGRU) is a bidirectional Gated cyclic Unit consisting of a forward and a backward hidden Gated cyclic Unit (GRU)
The GRU has the calculation formula as follows:
rt＝σ(Wrxt+Urht-1+br)
zt＝σ(Wzxt+Uzht-1+bz)
ht＝tanh(Wh1xt+(rt⊙ht-1)Wh2+bh)
ht＝(1-zt)⊙ht-1+zt⊙ht
yt＝σ(Wo⊙ht)
in the formula, rtTo reset the gate; z is a radical oftTo update the door; h istThe GRU hidden state is used for AC charging of the electric vehicle at the time t; y istPredicting and outputting the alternating current charging of the electric automobile at the time t; σ and tanh are activation functions; wr、Wz、Ur、Uz、Wh1And Wh2Weighting parameters of deep features of the alternating current charging data of the electric vehicle; br、bzAnd bhDeviation parameters of deep characteristics of the alternating current charging data of the electric vehicle; as a Hadamard product; h istGRU candidate state for AC charging of electric vehicle at time tState. The BiGRU calculation formula is as follows:
in the formula, wtThe output weight of the GRU of the forward hidden layer of the deep layer characteristics of the AC charging data of the electric vehicle at the time t; v. oftOutputting weights of backward hidden layer GRUs of deep features of the electric vehicle alternating current charging data at the time t; h istThe hidden state of the BiGRU is charged for the electric vehicle at the time t; btIs htThe corresponding offset.
6. The deep learning-based ac charging status monitoring and fault early warning method for electric vehicle as claimed in claim 1, wherein the step 4 employs a bat algorithm to optimize the hyper-parameters of the prediction model, the bat algorithm is an optimized algorithm for simulating the pulse echo of the bat to search the specific target location, assuming that the search space of the bat algorithm is d-dimension, the updated formula at the next moment is:
lm＝lmin+(lmax-lmin)ξ
in the formula (I), the compound is shown in the specification,
searching the position and the speed of the m-th value bat in the space for the time t; lmThe frequency emitted by the mth bat; x is the number ofbestRepresenting a current global optimal solution; lmax、lminSending out the maximum value and the minimum value of the frequency for the bat algorithm; xi is in the middle of 0,1]The random number of (2).
For local search, once a solution is selected among the current best solutions, a new local solution is generated using a random walk method, which has the formula:
xnew＝xold+ψAt
in which ψ e [ -1,1 [ ]]The random number of (2); x is the number ofoldRandomly selecting one of the current optimal solutions; a. thetIs the average value of bats population loudness.
In the optimization process of the bat algorithm, the loudness A gradually decreases along with the approach of the optimal solution, the pulse frequency R continuously increases, and the sound wave loudness of the ith bat algorithm
Sum frequency ri t+1The update formula is as follows:
ri t+1＝ri 0[1-exp(-γt)]
wherein, alpha belongs to (0,1) and is the attenuation coefficient of the sound wave loudness; gamma > 0, which is a pulse frequency enhancement coefficient; r isi 0Is the initial pulse frequency of the ith bat. For any of α and γ, when t → ∞,
when in use
When the bat finds a prey, sound waves are not emitted temporarily, and only after the position of the bat is optimized, the loudness and frequency of the pulses are updated, which implies that the bat moves towards an optimal solution method.
7. The deep learning-based alternating current charging state monitoring and fault early warning method for the electric vehicle as claimed in claim 1, wherein the step 5 of establishing the evaluation standard of the output accuracy of the prediction model adopts the root mean square error eRMSE(Root Mean Square Error，eRMSE) And the mean absolute percentage error eMAPE(Mean Absolute Percentage Error，eMAPE) The two error measurement modes are used as indexes for evaluating the accuracy of the alternating current charging prediction model, and the calculation formula is as follows:
in the formula, yiAnd
respectively obtaining an actual value and a predicted value of the electric vehicle alternating current charging at the ith moment; n is the number of all samples as a test set. e.g. of the typeRMSEAnd eMAPEThe smaller the value, the more accurate the predicted electric vehicle ac charging data.
8. The deep learning-based electric vehicle alternating current charging state monitoring and fault early warning method according to claim 1, wherein the model prediction value is subjected to residual error analysis by a sliding window method in the step 6, and a proper fault early warning threshold value and rule are determined, so that the influence of error alternating current charging data on residual error change in a data transmission process can be eliminated, and error early warning can be effectively avoided. When the width of the sliding window is N, the calculation formula of the mean value and the standard deviation of the residual error under the window is as follows:
in the formula, eiIs the residual error of the ith sample point in the sliding window. Analyzing and processing the residual error of the normal alternating current charging data by utilizing a sliding window to obtain the maximum value of the average absolute value of the normal alternating current charging residual errors
And the maximum value S of the residual standard deviationmaxThe calculation formula of the early warning threshold is as follows:
SY＝k2Smax
in the formula, k1And k2The value of the scaling factor is determined by the type of the AC-charged electric vehicle and the battery capacity. And when the mean value and the standard deviation both exceed the calculated early warning threshold value, carrying out fault early warning.
9. The method for monitoring the alternating-current charging state and early warning the fault of the electric vehicle based on the deep learning as claimed in claim 1, wherein the fault early warning in the alternating-current charging process of the electric vehicle is realized in the step 10, and when the residual mean value and the standard deviation exceed the set threshold value at the same time, the fault early warning is carried out, the alternating-current charging of the electric vehicle is cut off, and the occurrence of fire accidents is prevented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111203161.7A CN113895272A (en) | 2021-10-15 | 2021-10-15 | Electric vehicle alternating current charging state monitoring and fault early warning method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111203161.7A CN113895272A (en) | 2021-10-15 | 2021-10-15 | Electric vehicle alternating current charging state monitoring and fault early warning method based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113895272A true CN113895272A (en) | 2022-01-07 |
Family
ID=79192320
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111203161.7A Pending CN113895272A (en) | 2021-10-15 | 2021-10-15 | Electric vehicle alternating current charging state monitoring and fault early warning method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113895272A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114372417A (en) * | 2022-01-12 | 2022-04-19 | 青岛科技大学 | Electric vehicle battery health state and remaining life evaluation method based on charging network |
| CN114579644A (en) * | 2022-05-06 | 2022-06-03 | 中国汽车技术研究中心有限公司 | Method, apparatus and medium for battery efficient charging data identification based on deep learning |
| CN114758483A (en) * | 2022-04-14 | 2022-07-15 | 江苏国电南自海吉科技有限公司 | Dynamic intelligent early warning method for power equipment based on cosine similarity |
| CN115958957A (en) * | 2023-01-03 | 2023-04-14 | 重庆大学 | Method and system for predicting charging overheating fault of power battery of electric automobile |
| CN117289141A (en) * | 2023-11-22 | 2023-12-26 | 深圳市麦迪瑞科技有限公司 | Electric bicycle charging state monitoring method based on artificial intelligence |
| CN117426758A (en) * | 2023-12-20 | 2024-01-23 | 武汉纺织大学 | Intelligent clothing system and method based on multi-sensing information fusion |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107103397A (en) * | 2017-06-26 | 2017-08-29 | 广东工业大学 | A kind of traffic flow forecasting method based on bat algorithm, apparatus and system |
| CN107725283A (en) * | 2017-09-19 | 2018-02-23 | 江苏方天电力技术有限公司 | A kind of fan trouble detection method based on depth belief network model |
| CN110866314A (en) * | 2019-10-22 | 2020-03-06 | 东南大学 | Method for predicting residual life of rotating machinery of multilayer bidirectional gate control circulation unit network |
| 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 |
| CN112986827A (en) * | 2021-04-12 | 2021-06-18 | 山东凯格瑞森能源科技有限公司 | Fuel cell residual life prediction method based on deep learning |
| US20210256265A1 (en) * | 2020-02-13 | 2021-08-19 | Stats Llc | Dynamically Predicting Shot Type Using a Personalized Deep Neural Network |
| CN113459867A (en) * | 2021-07-19 | 2021-10-01 | 青岛科技大学 | Electric vehicle charging process fault early warning method based on adaptive deep confidence network |
-
2021
- 2021-10-15 CN CN202111203161.7A patent/CN113895272A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107103397A (en) * | 2017-06-26 | 2017-08-29 | 广东工业大学 | A kind of traffic flow forecasting method based on bat algorithm, apparatus and system |
| CN107725283A (en) * | 2017-09-19 | 2018-02-23 | 江苏方天电力技术有限公司 | A kind of fan trouble detection method based on depth belief network model |
| CN110866314A (en) * | 2019-10-22 | 2020-03-06 | 东南大学 | Method for predicting residual life of rotating machinery of multilayer bidirectional gate control circulation unit network |
| US20210256265A1 (en) * | 2020-02-13 | 2021-08-19 | Stats Llc | Dynamically Predicting Shot Type Using a Personalized Deep Neural Network |
| 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 |
| CN112986827A (en) * | 2021-04-12 | 2021-06-18 | 山东凯格瑞森能源科技有限公司 | Fuel cell residual life prediction method based on deep learning |
| CN113459867A (en) * | 2021-07-19 | 2021-10-01 | 青岛科技大学 | Electric vehicle charging process fault early warning method based on adaptive deep confidence network |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114372417A (en) * | 2022-01-12 | 2022-04-19 | 青岛科技大学 | Electric vehicle battery health state and remaining life evaluation method based on charging network |
| CN114758483A (en) * | 2022-04-14 | 2022-07-15 | 江苏国电南自海吉科技有限公司 | Dynamic intelligent early warning method for power equipment based on cosine similarity |
| CN114579644A (en) * | 2022-05-06 | 2022-06-03 | 中国汽车技术研究中心有限公司 | Method, apparatus and medium for battery efficient charging data identification based on deep learning |
| CN115958957A (en) * | 2023-01-03 | 2023-04-14 | 重庆大学 | Method and system for predicting charging overheating fault of power battery of electric automobile |
| CN115958957B (en) * | 2023-01-03 | 2023-12-22 | 重庆大学 | Method and system for predicting charging overheat faults of power battery of electric automobile |
| CN117289141A (en) * | 2023-11-22 | 2023-12-26 | 深圳市麦迪瑞科技有限公司 | Electric bicycle charging state monitoring method based on artificial intelligence |
| CN117426758A (en) * | 2023-12-20 | 2024-01-23 | 武汉纺织大学 | Intelligent clothing system and method based on multi-sensing information fusion |
| CN117426758B (en) * | 2023-12-20 | 2024-04-05 | 武汉纺织大学 | Intelligent clothing system and method based on multi-sensing information fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113895272A (en) | Electric vehicle alternating current charging state monitoring and fault early warning method based on deep learning | |
| CN112731159B (en) | Method for pre-judging and positioning battery faults of battery compartment of energy storage power station | |
| CN109492193B (en) | Abnormal network data generation and prediction method based on deep machine learning model | |
| CN112926273B (en) | Method for predicting residual life of multivariate degradation equipment | |
| CN110221225B (en) | Spacecraft lithium ion battery cycle life prediction method | |
| CN111539515B (en) | Complex equipment maintenance decision method based on fault prediction | |
| CN108960303B (en) | Unmanned aerial vehicle flight data anomaly detection method based on LSTM | |
| CN111813084B (en) | Mechanical equipment fault diagnosis method based on deep learning | |
| CN110689171A (en) | Turbine health state prediction method based on E-LSTM | |
| CN113895271A (en) | Deep learning-based electric vehicle high-power direct-current charging state monitoring and fault early warning method | |
| CN112488235A (en) | Elevator time sequence data abnormity diagnosis method based on deep learning | |
| CN110570013B (en) | Single-station online wave period data prediction diagnosis method | |
| CN113705094A (en) | Ship fuel oil pipeline fault prediction method based on PSO-GRU | |
| CN112949930A (en) | PA-LSTM network-based road motor vehicle exhaust high-emission early warning method | |
| CN116541790A (en) | New energy vehicle health assessment method and device based on multi-feature fusion | |
| CN116595319A (en) | Prediction method and system applied to rail transit motor health state evaluation | |
| CN115422687A (en) | Service life prediction method of rolling bearing | |
| CN115982141A (en) | Characteristic optimization method for time series data prediction | |
| CN107689015A (en) | A kind of improved power system bad data recognition method | |
| CN114021758A (en) | Operation and maintenance personnel intelligent recommendation method and device based on fusion of gradient lifting decision tree and logistic regression | |
| CN114036647A (en) | Power battery safety risk assessment method based on real vehicle data | |
| CN116653608B (en) | Electric automobile charging protection and control method, device and storage medium | |
| CN112014757A (en) | Battery SOH estimation method integrating capacity increment analysis and genetic wavelet neural network | |
| CN116680598A (en) | Fault diagnosis and residual life prediction method for intelligent distribution box of construction site | |
| CN115828744A (en) | White light LED fault on-line diagnosis and service life prediction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |