CN117022032B - New energy automobile electricity taking method and system based on display screen - Google Patents
New energy automobile electricity taking method and system based on display screen Download PDFInfo
- Publication number
- CN117022032B CN117022032B CN202311305860.1A CN202311305860A CN117022032B CN 117022032 B CN117022032 B CN 117022032B CN 202311305860 A CN202311305860 A CN 202311305860A CN 117022032 B CN117022032 B CN 117022032B
- Authority
- CN
- China
- Prior art keywords
- target
- feature
- electric quantity
- change parameter
- battery
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000005611 electricity Effects 0.000 title claims abstract description 55
- 238000012423 maintenance Methods 0.000 claims abstract description 53
- 230000005856 abnormality Effects 0.000 claims abstract description 52
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 238000004891 communication Methods 0.000 claims abstract description 32
- 230000003993 interaction Effects 0.000 claims abstract description 30
- 230000002457 bidirectional effect Effects 0.000 claims abstract description 28
- 230000008859 change Effects 0.000 claims description 272
- 230000004927 fusion Effects 0.000 claims description 69
- 230000007246 mechanism Effects 0.000 claims description 39
- 230000006870 function Effects 0.000 claims description 29
- 238000000605 extraction Methods 0.000 claims description 22
- 238000007726 management method Methods 0.000 claims description 21
- 238000003860 storage Methods 0.000 claims description 16
- 238000004458 analytical method Methods 0.000 claims description 14
- 230000010354 integration Effects 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 13
- 230000009466 transformation Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000035772 mutation Effects 0.000 claims description 8
- 238000011282 treatment Methods 0.000 claims description 7
- 230000002068 genetic effect Effects 0.000 claims description 6
- 238000004146 energy storage Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000012800 visualization Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 11
- 230000008569 process Effects 0.000 description 20
- 230000002159 abnormal effect Effects 0.000 description 15
- 238000012545 processing Methods 0.000 description 8
- 230000009471 action Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 208000032953 Device battery issue Diseases 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000001351 cycling effect Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 230000002708 enhancing effect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000009021 linear effect Effects 0.000 description 3
- 230000002035 prolonged effect Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000009022 nonlinear effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
- B60L53/66—Data transfer between charging stations and vehicles
-
- 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
- B60L53/10—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 characterised by the energy transfer between the charging station and the vehicle
- B60L53/14—Conductive energy transfer
-
- 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
- B60L58/12—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries responding to state of charge [SoC]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Secondary Cells (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention relates to the field of new energy automobiles, and discloses a new energy automobile electricity taking method and system based on a display screen, which are used for realizing intelligent monitoring and operation and maintenance of new energy automobile electricity taking. The method comprises the following steps: when the target new energy vehicle is in a power taking mode, acquiring first battery electric quantity information through a BMS management system, and sending the first battery electric quantity information to a power taking device controller through a CAN communication protocol; calculating first residual electric quantity information; the first residual electric quantity information is sent to a socket controller of the power taking equipment through a CAN communication protocol, and is visualized through a man-machine interaction display screen; converting direct current into alternating current through a DC/AC bidirectional inversion module and outputting the alternating current to target alternating current load equipment to acquire second battery electric quantity information; and calculating second residual electric quantity information according to the second battery electric quantity information, detecting power taking abnormality, and carrying out abnormality warning on a power taking abnormality detection result through a man-machine interaction display screen.
Description
Technical Field
The invention relates to the field of new energy automobiles, in particular to a new energy automobile electricity taking method and system based on a display screen.
Background
With the popularization and development of new energy automobiles, battery management and charging technologies are becoming more and more important. The user needs to know the state and the remaining capacity of the vehicle battery in real time to ensure that the battery can be effectively used for outdoor power supply when needed. In addition, in order to improve the convenience of use of the new energy automobile, it is necessary to use electric power equipment in the open air or in a temporary place, and thus a convenient method of converting battery energy into alternating current is required to supply various electric appliances and tools.
However, conventional battery management and power extraction methods often do not provide sufficient real-time information, and it is often difficult for a user to accurately understand the state of the battery and the amount of power available. In addition, the lack of efficient battery performance analysis and power extraction anomaly detection methods results in battery damage or performance degradation, increasing maintenance costs and safety risks.
Disclosure of Invention
The invention provides a new energy automobile electricity taking method and system based on a display screen, which are used for realizing intelligent monitoring and operation and maintenance of new energy automobile electricity taking.
The invention provides a new energy automobile power taking method based on a display screen, which comprises the following steps of:
When a target new energy vehicle is in a power-taking mode, acquiring first battery electric quantity information of a target battery module in the target new energy vehicle through a preset BMS management system, and sending the first battery electric quantity information to a preset power-taking equipment controller through a preset CAN communication protocol;
receiving the first battery electric quantity information through the power taking device controller, and calculating first residual electric quantity information of the target battery module according to the first battery electric quantity information;
the first residual electric quantity information is sent to a power taking device socket controller through the CAN communication protocol, and the first residual electric quantity information is visualized through a man-machine interaction display screen of the power taking device controller;
converting the direct current of the target battery module into alternating current through a DC/AC bidirectional inversion module, outputting the alternating current to corresponding target alternating current load equipment, and simultaneously acquiring second battery electric quantity information corresponding to the target battery module;
and calculating second residual capacity information of the target battery module according to the second battery capacity information, detecting power taking abnormality of the second residual capacity information to obtain a power taking abnormality detection result, and carrying out abnormality warning on the power taking abnormality detection result through the man-machine interaction display screen.
With reference to the first aspect, in a first implementation manner of the first aspect of the present invention, the method for powering a new energy automobile based on a display screen further includes:
if the electricity taking abnormality detection result is that the electricity taking abnormality is caused, acquiring a battery electric quantity change parameter data set and a battery state change parameter data set of a target battery module in the target new energy vehicle through a BMS management system;
inputting the battery electric quantity change parameter data set into a first automatic encoder for parameter feature extraction to obtain a plurality of initial electric quantity change parameter features, and inputting the battery state change parameter data set into a second automatic encoder for parameter feature extraction to obtain a plurality of initial state change parameter features;
inputting the initial electric quantity change parameter characteristics into a first full-connection layer for characteristic integration to obtain target electric quantity change parameter characteristics, and inputting the initial state change parameter characteristics into a second full-connection layer for characteristic integration to obtain target state change parameter characteristics;
performing multi-angle feature enhancement on the initial electric quantity change parameter features and the initial state change parameter features to obtain target enhancement features;
Performing feature fusion on the target electric quantity change parameter feature and the target enhancement feature through a first attention mechanism layer to obtain a fusion electric quantity change feature, and performing feature fusion on the target state change parameter feature and the target enhancement feature through a second attention mechanism layer to obtain a fusion state change feature;
performing feature interaction on the fusion electric quantity change feature and the fusion state change feature through a gating mechanism layer, determining corresponding weight and fusion mode, and performing feature splicing on the fusion electric quantity change feature and the fusion state change feature according to the weight and the fusion mode to obtain target splicing features;
and inputting the target splicing characteristics into a third full-connection layer for battery module electricity taking performance analysis, obtaining electricity taking performance prediction data, and matching the corresponding target battery module operation and maintenance scheme according to the electricity taking performance prediction data.
With reference to the first aspect, in a second implementation manner of the first aspect of the present invention, the inputting the battery power change parameter data set into the first automatic encoder performs parameter feature extraction to obtain a plurality of initial power change parameter features, and inputting the battery state change parameter data set into the second automatic encoder performs parameter feature extraction to obtain a plurality of initial state change parameter features, including:
Performing parameter classification on the battery electric quantity change parameter data set to obtain a plurality of target battery electric quantity change parameter data, and performing parameter classification on the battery state change parameter data set to obtain a plurality of target battery state change parameter data;
respectively inputting the plurality of target battery power change parameter data into a first automatic encoder, wherein the first automatic encoder comprises a first bidirectional threshold cycle unit; simultaneously, respectively inputting the plurality of target battery state change parameter data into a second automatic encoder, wherein the second automatic encoder comprises a second bidirectional threshold cycle unit;
extracting features of the target battery electric quantity change parameter data through a first layer of threshold circulating units in the first bidirectional threshold circulating units to obtain a plurality of first forward hidden coding features, and extracting features of the target battery electric quantity change parameter data through a second layer of threshold circulating units in the first bidirectional threshold circulating units to obtain a plurality of first backward hidden coding features; meanwhile, extracting features of the plurality of target battery state change parameter data through a third layer of threshold circulating units in the second bi-directional threshold circulating units to obtain a plurality of second forward hidden coding features, and extracting features of the plurality of target battery state change parameter data through a fourth layer of threshold circulating units in the second bi-directional threshold circulating units to obtain a plurality of second backward hidden coding features;
And respectively connecting the plurality of first forward hidden coding features and the corresponding plurality of first backward hidden coding features to obtain a plurality of initial electric quantity change parameter features, and respectively connecting the plurality of second forward hidden coding features and the corresponding plurality of second backward hidden coding features to obtain a plurality of initial state change parameter features.
With reference to the first aspect, in a third implementation manner of the first aspect of the present invention, inputting the plurality of initial electrical quantity change parameter features into a first full-connection layer for feature integration to obtain a target electrical quantity change parameter feature, and inputting the plurality of initial state change parameter features into a second full-connection layer for feature integration to obtain a target state change parameter feature includes:
inputting the initial electric quantity change parameter characteristics into a first full-connection layer respectively, and setting a first weight of each initial electric quantity change parameter characteristic through the first full-connection layer; simultaneously, the initial state change parameter characteristics are respectively input into a second full-connection layer, and a second weight of each initial state change parameter characteristic is set through the second full-connection layer;
Performing weighted operation on the plurality of initial electric quantity change parameter features according to the first weight to obtain a plurality of weighted electric quantity change parameter features, and performing weighted operation on the plurality of initial state change parameter features according to the second weight to obtain a plurality of weighted state change parameter features;
and carrying out nonlinear transformation on the plurality of weighted electric quantity change parameter characteristics through a preset first ReLU function to obtain target electric quantity change parameter characteristics, and carrying out nonlinear transformation on the plurality of weighted state change parameter characteristics through a preset second ReLU function to obtain target state change parameter characteristics.
With reference to the first aspect, in a fourth implementation manner of the first aspect of the present invention, the performing multi-angle feature enhancement on the multiple initial power change parameter features and the multiple initial state change parameter features to obtain a target enhancement feature includes:
initializing the characteristic population of the plurality of initial electric quantity change parameter characteristics and the plurality of initial state change parameter characteristics through a preset genetic algorithm to obtain an initial multi-angle characteristic population, wherein the initial multi-angle characteristic population comprises: a plurality of first candidate multi-angle features;
Respectively calculating a first characteristic fitness index D1 corresponding to each first candidate multi-angle characteristic, and acquiring a first fitness index threshold F and a second fitness index threshold X, wherein the first fitness index threshold F is smaller than the second fitness index threshold X;
performing group segmentation on the plurality of first candidate multi-angle features according to the first feature fitness index D1, the first fitness index threshold F and the second fitness index threshold X;
if the first characteristic adaptability index D1 is smaller than the first adaptability index threshold F, determining that the corresponding first candidate multi-angle characteristic is an uninfected group, if the first adaptability index threshold F is smaller than the first characteristic adaptability index D1 and smaller than the second adaptability index threshold X, determining that the corresponding first candidate multi-angle characteristic is an easily-infected group, and if the second adaptability index threshold X is smaller than the first characteristic adaptability index D1, determining that the corresponding first candidate multi-angle characteristic is an infected group;
performing propagation, mutation and cross treatment on the non-infected population and the easily infected population, and performing mutation and cross treatment on the infected population to obtain a plurality of second candidate multi-angle features;
and respectively calculating a second characteristic fitness index D2 of each second candidate multi-angle characteristic, and carrying out optimization enhancement characteristic solution on the plurality of second candidate multi-angle characteristics according to the second characteristic fitness index D2 to obtain target enhancement characteristics.
With reference to the first aspect, in a fifth implementation manner of the first aspect of the present invention, the feature fusion is performed on the target electric quantity change parameter feature and the target enhancement feature by the first attention mechanism layer to obtain a fused electric quantity change feature, and the feature fusion is performed on the target state change parameter feature and the target enhancement feature by the second attention mechanism layer to obtain a fused state change feature, where the feature fusion includes:
calculating a first attention score between the target power change parameter feature and the target enhancement feature by a first attention mechanism layer, and calculating a second attention score between the target state change parameter feature and the target enhancement feature by a second attention mechanism layer;
the first attention score is subjected to weight calculation through a preset first softmax function to obtain a first attention weight, and the second attention score is subjected to weight calculation through a preset second softmax function to obtain a second attention weight;
and carrying out feature weighted fusion on the target electric quantity change parameter feature and the target enhancement feature according to the first attention weight to obtain a fusion electric quantity change feature, and carrying out feature weighted fusion on the target state change parameter feature and the target enhancement feature according to the second attention weight to obtain a fusion state change feature.
With reference to the first aspect, in a sixth implementation manner of the first aspect of the present invention, inputting the target splicing feature into the third full connection layer to perform battery module electricity taking performance analysis, to obtain electricity taking performance prediction data, and matching a corresponding target battery module operation and maintenance scheme according to the electricity taking performance prediction data, where the method includes:
inputting target splicing characteristics into a third full-connection layer, and calculating the performance of the energy storage battery pack through a Sigmoid function in the third full-connection layer to obtain electricity taking performance prediction data, wherein the electricity taking performance prediction data comprise battery capacity, residual service life and electricity taking efficiency;
acquiring a battery pack operation and maintenance scheme list, and constructing a mapping relation between each candidate battery pack operation and maintenance scheme and electricity taking performance prediction data in the battery pack operation and maintenance scheme list;
and carrying out mapping matching on the electricity taking performance prediction data and the battery pack operation and maintenance scheme list according to the mapping relation to obtain a target battery module operation and maintenance scheme corresponding to the target new energy vehicle.
The second aspect of the invention provides a new energy automobile power taking system based on a display screen, which comprises:
The acquisition module is used for acquiring first battery electric quantity information of a target battery module in the target new energy vehicle through a preset BMS management system when the target new energy vehicle is in a power taking mode, and transmitting the first battery electric quantity information to a preset power taking equipment controller through a preset CAN communication protocol;
the calculation module is used for receiving the first battery electric quantity information through the power taking device controller and calculating first residual electric quantity information of the target battery module according to the first battery electric quantity information;
the visualization module is used for sending the first residual electric quantity information to a power taking device socket controller through the CAN communication protocol, and visualizing the first residual electric quantity information through a man-machine interaction display screen of the power taking device controller;
the conversion module is used for converting the direct current of the target battery module into alternating current through the DC/AC bidirectional inversion module, outputting the alternating current to corresponding target alternating current load equipment, and simultaneously acquiring second battery electric quantity information corresponding to the target battery module;
the detection module is used for calculating second residual electric quantity information of the target battery module according to the second battery electric quantity information, carrying out power taking abnormality detection on the second residual electric quantity information to obtain a power taking abnormality detection result, and carrying out abnormality warning on the power taking abnormality detection result through the man-machine interaction display screen.
The third aspect of the invention provides a new energy automobile electricity taking device based on a display screen, comprising: a memory and at least one processor, the memory having instructions stored therein; and the at least one processor calls the instruction in the memory so that the new energy automobile power taking equipment based on the display screen executes the new energy automobile power taking method based on the display screen.
A fourth aspect of the present invention provides a computer-readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform the above-described display-screen-based power extraction method for a new energy vehicle.
According to the technical scheme provided by the invention, when a target new energy vehicle is in a power taking mode, the BMS management system is used for collecting first battery electric quantity information, and the first battery electric quantity information is sent to the power taking equipment controller through the CAN communication protocol; calculating first residual electric quantity information; the first residual electric quantity information is sent to a socket controller of the power taking equipment through a CAN communication protocol, and is visualized through a man-machine interaction display screen; converting direct current into alternating current through a DC/AC bidirectional inversion module and outputting the alternating current to target alternating current load equipment to acquire second battery electric quantity information; according to the battery power information, the second residual power information is calculated, abnormal power taking detection is carried out, abnormal power taking detection results are subjected to abnormal alarm through a human-computer interaction display screen, and the battery state and the residual power are allowed to be monitored in real time by a user through the BMS and CAN communication protocol. Through the man-machine interaction display screen, the user can intuitively know the condition of the vehicle battery, and the convenience and the visibility of operation are improved. With an automatic encoder and attention mechanism, the method can accurately analyze the performance of the battery. The multi-angle feature enhancement is provided, and the battery performance problem can be identified more accurately, so that false alarm and missing alarm are reduced, and the reliability of fault diagnosis is improved. By detecting the power taking abnormality in the battery performance analysis process, the method can timely identify the battery problem and generate an abnormality alarm. This helps the user take quick action, reduces the risk of battery failure, and improves the safety and reliability of the vehicle. The battery module operation and maintenance scheme is matched according to the battery performance data, so that the use of the battery is optimized, the service life of the battery is prolonged, the sustainability of the battery is improved, and the maintenance cost is reduced. By converting direct current into alternating current, a user is enabled to use the power equipment outdoors or in a temporary location. This increases the versatility of the battery, enhancing the user experience. By utilizing the automatic encoder and the attention mechanism technology, the intelligent analysis and the abnormality detection of the battery performance are realized, and the operation burden of a user is reduced. In addition, the matching of the operation and maintenance schemes of the battery module is also automatic, so that a user can more easily select a scheme suitable for requirements, and further intelligent monitoring and operation and maintenance of the new energy automobile power taking process are realized.
Drawings
Fig. 1 is a schematic diagram of an embodiment of a new energy automobile power-taking method based on a display screen in an embodiment of the invention;
fig. 2 is a flowchart of a method for generating a target battery module operation and maintenance scheme according to an embodiment of the present invention;
FIG. 3 is a flow chart of feature integration in an embodiment of the invention;
FIG. 4 is a flow chart of multi-angle feature enhancement in an embodiment of the present invention;
FIG. 5 is a schematic diagram of an embodiment of a new energy automobile power taking system based on a display screen according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a new energy automobile power taking device based on a display screen in an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a new energy automobile power taking method and system based on a display screen, which are used for realizing intelligent monitoring and operation and maintenance of new energy automobile power taking. The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a specific flow of an embodiment of the present invention is described below, referring to fig. 1, and an embodiment of a new energy automobile power taking method based on a display screen in the embodiment of the present invention includes:
s101, when a target new energy vehicle is in a power-taking mode, acquiring first battery electric quantity information of a target battery module in the target new energy vehicle through a preset BMS management system, and sending the first battery electric quantity information to a preset power-taking equipment controller through a preset CAN communication protocol;
it can be understood that the execution subject of the present invention may be a new energy automobile power taking system based on a display screen, and may also be a terminal or a server, which is not limited herein. The embodiment of the invention is described by taking a server as an execution main body as an example.
In particular, a Battery Management System (BMS) is a critical component that is located in a target new energy vehicle. A BMS is a system specifically designed to monitor and manage batteries, which is capable of monitoring the voltage, current, temperature, and other critical parameters of the batteries in real time. When the vehicle is in the power-on mode, the BMS may start a process of collecting battery information. The BMS monitors various parameters of the battery module through the sensors and the internal circuit. Wherein battery charge information is a core parameter that indicates the current state of charge of the battery. The BMS periodically reads this information and stores it in an internal memory for subsequent transmission. The CAN communication protocol follows. Controller Area Network (CAN) is a communication protocol that is widely used in automobiles and other embedded systems. CAN communication is used to transmit battery charge information from the BMS to the power take-off controller. The power take-off control is typically a control unit located in the battery charging device or the power take-off apparatus. It CAN receive and interpret the CAN message and take appropriate action based on the received battery charge information. For example, if the target vehicle needs to power an outdoor activity, the controller may activate the battery charging device to provide the required power.
S102, receiving first battery electric quantity information through a power taking device controller, and calculating first residual electric quantity information of a target battery module according to the first battery electric quantity information;
specifically, the power extraction device controller needs to be able to receive the first battery level information from the BMS. This is typically accomplished by the CAN communication protocol or other suitable means of communication. The BMS periodically transmits battery level information to the controller for real-time monitoring. When the power take device controller receives the first battery level information, it will parse the data. The charge information typically includes parameters such as voltage, current, state of charge, etc. of the battery. These parameters are key information required for calculating the remaining power. The battery power taking device controller may calculate the first remaining power information of the target battery module using the voltage and current data of the battery according to the first battery power information. This calculation is typically done based on the energy capacity of the battery and the change in charge/discharge state. A simple calculation formula is as follows: residual capacity (Wh) =battery capacity (Wh) -integral (current x time). Here, integration is the accumulation of current over time. The power taking device controller typically displays the calculated first remaining power information on the user interface in a visual manner. This may be a display screen, a smart phone application or an on-line dashboard. The user can view the remaining capacity of the battery at any time so as to better manage the use of the battery.
S103, sending the first residual electric quantity information to a power taking device socket controller through a CAN communication protocol, and visualizing the first residual electric quantity information through a man-machine interaction display screen of the power taking device controller;
it should be noted that the power taking device controller needs to implement a CAN communication protocol to receive the first remaining power information from the Battery Management System (BMS). The BMS encodes the calculated power data into a CAN message and transmits it to the power taking device outlet controller. After receiving the CAN message, the socket controller of the power taking device needs to perform data analysis to extract the first residual electric quantity information. This may be accomplished by parsing the data fields of the CAN message and then storing the charge data in the memory of the controller for later use. In order to enable the user to easily understand the electric quantity information, the power taking device socket controller needs a visual interface of personal computer interaction. This may be a liquid crystal display, touch screen or interface to a smartphone application. User-friendliness and readability should be considered when designing the interface to ensure that the user can quickly understand the power information. And displaying the first residual electric quantity information on the interface in a visual form. This may be a percentage of the remaining battery capacity, estimated range, or other power indicator of interest to the user. In addition, graphical elements, warnings and notifications may be added to provide more information and feedback.
S104, converting the direct current of the target battery module into alternating current through the DC/AC bidirectional inversion module, outputting the alternating current to corresponding target alternating current load equipment, and simultaneously acquiring second battery electric quantity information corresponding to the target battery module;
specifically, the system needs to obtain a dc power supply from the target battery module. This may be accomplished through a battery connector or a charging port. Batteries typically provide a dc power supply, but in practical applications the voltage and current will vary, so that appropriate voltage and current regulation circuitry is required to match the inverter requirements. The DC/AC bidirectional inversion module in the system converts direct current power supply into alternating current power supply. In this process, the inverter needs to consider the requirements of the output voltage, frequency and waveform to meet the requirements of the target ac load device. The inverter should also have bi-directional capability to reverse power flow back to the battery for charging when needed. The electric energy that has been converted into alternating current may be directly connected to a target alternating current load device such as an electric water heater, an air conditioner, an electric furnace, or the like. The inverter should be able to provide sufficient power and voltage to meet the requirements of the load device. And a second battery power monitor or BMS is arranged on the battery module and used for monitoring the state of the battery in real time. The monitor can measure parameters such as voltage, current, temperature, and electric quantity of the battery. The second battery level monitor communicates battery information to the system controller via an appropriate communication protocol (e.g., CAN or Modbus). The system controller is responsible for monitoring the operating state of the inverter, including parameters such as output power, current and voltage. It is also responsible for communicating with a second battery level monitor to obtain second battery level information for the battery. The controller needs to comprehensively consider the state of the battery and the requirements of the target load device to ensure that the battery is not overdischarged or undercharged.
S105, calculating second residual capacity information of the target battery module according to the second battery capacity information, detecting power taking abnormality of the second residual capacity information to obtain a power taking abnormality detection result, and carrying out abnormality warning on the power taking abnormality detection result through a man-machine interaction display screen.
Specifically, the second battery level information is obtained by a Battery Management System (BMS) or a dedicated battery level monitor. Such information typically includes parameters such as voltage, current, temperature, and charge of the battery. The second battery charge information may be transmitted to the system controller via CAN communication or other communication protocol. The system controller calculates second remaining power information of the target battery module using an appropriate algorithm according to the second battery power information. This calculation typically takes into account the capacity of the battery, the charge/discharge state, and the historical performance of the battery. The power taking abnormality detection involves real-time monitoring and analyzing the second remaining power information to detect potential abnormal conditions. The abnormality includes overdischarge of the battery, abnormality of the battery voltage, overrun of the current, and the like. The system controller uses predefined rules or machine learning algorithms to detect these anomalies. If a power take abnormality is detected, the system controller will generate an abnormality alert. This alert may include a text message, an audible alarm, a flashing warning light, or other form of notification. The alarm may also indicate which parts are abnormal and what action to take. The abnormal alarm information is visually presented to a user or operator through a man-machine interaction display screen. Specific information of abnormality such as abnormality type, battery state, remaining power change, etc. can be displayed on the display screen. The user can view the information on the display screen at any time to know the battery state.
In the embodiment of the invention, when a target new energy vehicle is in a power taking mode, acquiring first battery electric quantity information through a BMS management system, and sending the first battery electric quantity information to a power taking device controller through a CAN communication protocol; calculating first residual electric quantity information; the first residual electric quantity information is sent to a socket controller of the power taking equipment through a CAN communication protocol, and is visualized through a man-machine interaction display screen; converting direct current into alternating current through a DC/AC bidirectional inversion module and outputting the alternating current to target alternating current load equipment to acquire second battery electric quantity information; according to the battery power information, the second residual power information is calculated, abnormal power taking detection is carried out, abnormal power taking detection results are subjected to abnormal alarm through a human-computer interaction display screen, and the battery state and the residual power are allowed to be monitored in real time by a user through the BMS and CAN communication protocol. Through the man-machine interaction display screen, the user can intuitively know the condition of the vehicle battery, and the convenience and the visibility of operation are improved. With an automatic encoder and attention mechanism, the method can accurately analyze the performance of the battery. The multi-angle feature enhancement is provided, and the battery performance problem can be identified more accurately, so that false alarm and missing alarm are reduced, and the reliability of fault diagnosis is improved. By detecting the power taking abnormality in the battery performance analysis process, the method can timely identify the battery problem and generate an abnormality alarm. This helps the user take quick action, reduces the risk of battery failure, and improves the safety and reliability of the vehicle. The battery module operation and maintenance scheme is matched according to the battery performance data, so that the use of the battery is optimized, the service life of the battery is prolonged, the sustainability of the battery is improved, and the maintenance cost is reduced. By converting direct current into alternating current, a user is enabled to use the power equipment outdoors or in a temporary location. This increases the versatility of the battery, enhancing the user experience. By utilizing the automatic encoder and the attention mechanism technology, the intelligent analysis and the abnormality detection of the battery performance are realized, and the operation burden of a user is reduced. In addition, the matching of the operation and maintenance schemes of the battery module is also automatic, so that a user can more easily select a scheme suitable for requirements, and further intelligent monitoring and operation and maintenance of the new energy automobile power taking process are realized.
In a specific embodiment, as shown in fig. 2, the process of executing the new energy automobile power taking method based on the display screen may specifically further include the following steps:
s201, if the electricity taking abnormality detection result is the electricity taking abnormality, acquiring a battery electric quantity change parameter data set and a battery state change parameter data set of a target battery module in a target new energy vehicle through a BMS management system;
s202, inputting a battery electric quantity change parameter data set into a first automatic encoder for parameter feature extraction to obtain a plurality of initial electric quantity change parameter features, and inputting a battery state change parameter data set into a second automatic encoder for parameter feature extraction to obtain a plurality of initial state change parameter features;
s203, inputting a plurality of initial electric quantity change parameter characteristics into a first full-connection layer for characteristic integration to obtain target electric quantity change parameter characteristics, and inputting a plurality of initial state change parameter characteristics into a second full-connection layer for characteristic integration to obtain target state change parameter characteristics;
s204, performing multi-angle feature enhancement on the initial electric quantity change parameter features and the initial state change parameter features to obtain target enhancement features;
s205, carrying out feature fusion on the target electric quantity change parameter feature and the target enhancement feature through a first attention mechanism layer to obtain a fusion electric quantity change feature, and carrying out feature fusion on the target state change parameter feature and the target enhancement feature through a second attention mechanism layer to obtain a fusion state change feature;
S206, performing feature interaction on the fusion electric quantity change features and the fusion state change features through a gating mechanism layer, determining corresponding weights and fusion modes, and performing feature splicing on the fusion electric quantity change features and the fusion state change features according to the weights and the fusion modes to obtain target splicing features;
s207, inputting the target splicing characteristics into the third full-connection layer for battery module electricity taking performance analysis, obtaining electricity taking performance prediction data, and matching the corresponding target battery module operation and maintenance scheme according to the electricity taking performance prediction data.
Specifically, when the power taking abnormality detection result is abnormal, the server first needs to acquire a battery power change parameter data set and a battery state change parameter data set of a target battery module in the target new energy vehicle from the BMS management system. These data include changes in battery charge over time and various parameters related to battery status. The useful features are extracted in order to transform the raw data into a form that can be processed by the machine learning model. In this procedure, two automatic encoders are used, a first automatic encoder and a second automatic encoder, respectively, for extracting features in the power change parameter data set and the state change parameter data set. An automatic encoder is an unsupervised learning algorithm for learning a representation of data. And integrating the extracted characteristics by using a full connection layer behind each automatic encoder to obtain the target electric quantity change parameter characteristics and the target state change parameter characteristics. These features will be used for further processing in subsequent steps. To enhance the expressive power of the features, the features may be handled through different angles. This may include performing dimension reduction, normalization, etc. on the features to ensure that the features are on the same scale. And fusing the target electric quantity change parameter characteristics and the target enhancement characteristics through the attention mechanism layer to obtain fused electric quantity change characteristics. Likewise, the target state change parameter feature and the target enhancement feature are fused by the attention mechanism layer to obtain a fused state change feature. The attention mechanism allows the model to focus on different parts of the input features to better learn useful information. And carrying out characteristic interaction on the fusion electric quantity change characteristics and the fusion state change characteristics through a gating mechanism layer. This step helps the model understand the relationship between the two features and determine their contribution to the final performance prediction. And inputting the target splicing characteristics into the third full-connection layer to analyze the electricity taking performance of the battery module. This fully-connected layer will learn how to predict the power-taking performance of the battery module from the characteristics, which may include information on the remaining capacity of the battery, available endurance, charging time, etc. And matching the corresponding operation and maintenance scheme of the target battery module according to the electricity taking performance prediction data. This may include suggesting that the user stop taking power, going to a charging station for charging, reducing loads, etc., to protect the battery and ensure safety. Consider, for example, the case of an electric vehicle. When the vehicle is abnormal in the power taking mode, the system can acquire the electric quantity change and state change data of the battery of the vehicle from the BMS. These data include battery voltage, current, temperature, SOC (battery state), and information of the speed, driving behavior, etc. of the vehicle. By means of an automatic encoder, the system extracts characteristics related to the performance of the battery. These features are fused and interacted through an attention mechanism and a gating mechanism to obtain a prediction of the battery power taking performance. If the system detects that the battery is not meeting the expected travel demand, it may generate an abnormal alert advising the driver to go to the nearest charging station or take other action to ensure that the battery is not depleted.
In a specific embodiment, the process of executing step S202 may specifically include the following steps:
(1) Performing parameter classification on the battery electric quantity change parameter data set to obtain a plurality of target battery electric quantity change parameter data, and performing parameter classification on the battery state change parameter data set to obtain a plurality of target battery state change parameter data;
(2) Respectively inputting a plurality of target battery power change parameter data into a first automatic encoder, wherein the first automatic encoder comprises a first bidirectional threshold cycle unit; simultaneously, respectively inputting a plurality of target battery state change parameter data into a second automatic encoder, wherein the second automatic encoder comprises a second bidirectional threshold cycle unit;
(3) Extracting features of the plurality of target battery electric quantity change parameter data through a first layer of threshold circulating units in the first bidirectional threshold circulating units to obtain a plurality of first forward hidden coding features, and extracting features of the plurality of target battery electric quantity change parameter data through a second layer of threshold circulating units in the first bidirectional threshold circulating units to obtain a plurality of first backward hidden coding features; meanwhile, extracting features of the plurality of target battery state change parameter data through a third layer of threshold circulating units in the second bidirectional threshold circulating units to obtain a plurality of second forward hidden coding features, and extracting features of the plurality of target battery state change parameter data through a fourth layer of threshold circulating units in the second bidirectional threshold circulating units to obtain a plurality of second backward hidden coding features;
(4) And respectively connecting the plurality of first forward hidden coding features and the corresponding plurality of first backward hidden coding features to obtain a plurality of initial electric quantity change parameter features, and respectively connecting the plurality of second forward hidden coding features and the corresponding plurality of second backward hidden coding features to obtain a plurality of initial state change parameter features.
Specifically, the battery power change parameter data set and the battery state change parameter data set are preprocessed. This includes data cleaning, denoising, normalization, etc. operations to ensure the quality and consistency of the data. The data set also needs to be divided into a number of categories, each category representing a type of battery or state parameter. Parameters in a dataset typically comprise a number of different characteristics, such as voltage, current, temperature, etc. These parameters are classified according to their type. For example, the battery charge amount variation parameter may include SOC (battery state) of the battery, battery charge/discharge state, and the like. The battery state change parameter may include a temperature change, a battery internal resistance change, and the like. Classification facilitates grouping parameters in a dataset for subsequent processing. To extract useful features, two automatic encoders are used, a first automatic encoder and a second automatic encoder, respectively. An automatic encoder is a neural network architecture for learning a compressed representation, i.e., coding features, of input data. The first automatic encoder includes a first bi-directional threshold cycle unit for processing battery level change parameter data. This automatic encoder will learn how to extract features related to battery level variations; the second automatic encoder includes a second bi-directional threshold cycling unit for processing battery state change parameter data. This automatic encoder will learn how to extract features related to battery state changes. In each automatic encoder, the data is processed using a threshold loop unit to extract forward and backward concealment coding features, respectively. These features contain important information in the data such as trends, periodicity, etc. A first layer threshold cycle unit in the first bidirectional threshold cycle unit is used for extracting a plurality of first forward hidden coding features; the second layer threshold circulating unit in the first bidirectional threshold circulating unit is used for extracting a plurality of first backward hidden coding features; a third layer of threshold circulation unit in the second bidirectional threshold circulation unit is used for extracting a plurality of second forward hidden coding features; a fourth layer of threshold cycling units in the second bi-directional threshold cycling unit is used for extracting a plurality of second backward hidden coding features. And connecting the forward and backward hidden coding features together to obtain a plurality of initial electric quantity change parameter features and a plurality of initial state change parameter features. These features will contain different aspects and patterns in the data, providing more information for subsequent data analysis and modeling. For example, assuming that the server has an electric car, it is necessary to analyze the change in the power and the change in the state of its battery. A battery level change parameter data set and a battery state change parameter data set are acquired from a BMS system of the automobile. The battery charge amount variation parameter data includes a battery SOC (battery state), a voltage variation, and the like, and the battery state variation parameter data includes a temperature variation, a current variation, and the like. Using the first automatic encoder, the server extracts features related to battery level changes. For example, the automatic encoder learns the periodic variation of the SOC, the trend of the battery voltage, and the like. Meanwhile, using the second automatic encoder, the server extracts characteristics related to the battery state change, such as a periodic change in temperature, a peak value of current, and the like. And connecting the characteristics together to obtain a plurality of initial electric quantity change parameter characteristics and a plurality of initial state change parameter characteristics. These features may be used for further analysis such as battery performance prediction, anomaly detection, etc. This procedure can help the server to better understand the behavior of the battery, improving the efficiency and reliability of battery management.
In a specific embodiment, as shown in fig. 3, the process of performing step S203 may specifically include the following steps:
s301, inputting a plurality of initial electric quantity change parameter characteristics into a first full-connection layer respectively, and setting a first weight of each initial electric quantity change parameter characteristic through the first full-connection layer; simultaneously, respectively inputting a plurality of initial state change parameter characteristics into a second full-connection layer, and setting a second weight of each initial state change parameter characteristic through the second full-connection layer;
s302, carrying out weighting operation on a plurality of initial electric quantity change parameter characteristics according to a first weight to obtain a plurality of weighted electric quantity change parameter characteristics, and carrying out weighting operation on a plurality of initial state change parameter characteristics according to a second weight to obtain a plurality of weighted state change parameter characteristics;
s303, performing nonlinear transformation on the plurality of weighted electric quantity change parameter features through a preset first ReLU function to obtain target electric quantity change parameter features, and performing nonlinear transformation on the plurality of weighted state change parameter features through a preset second ReLU function to obtain target state change parameter features.
Specifically, in the neural network, features first need to be input into the fully connected layer. For the charge variation parameter features, they are input to the first fully connected layer, respectively, and a first weight of each initial charge variation parameter feature is set by the layer. For the state change parameter features, they are input to the second fully connected layer, respectively, and a second weight for each initial state change parameter feature is set by this layer. These weights are the learnable parameters of the neural network model that will determine the weight of each feature in the final target feature. And carrying out weighting operation on the plurality of initial electric quantity change parameter characteristics by using a first weight set in the first full-connection layer to obtain a plurality of weighted electric quantity change parameter characteristics. And similarly, carrying out weighting operation on the plurality of initial state change parameter characteristics by using a second weight set in the second full connection layer to obtain a plurality of weighted state change parameter characteristics. This step allows the model to assign different importance to each feature to better capture patterns and information in the data. In neural networks, nonlinear activation functions are typically introduced to increase the expressive power of the model. In this flow, a preset first ReLU function is used to perform nonlinear transformation on the multiple weighted power variation parameter features to obtain a target power variation parameter feature. And simultaneously, carrying out nonlinear transformation on the plurality of weighted state change parameter characteristics by using a preset second ReLU function to obtain target state change parameter characteristics. ReLU (Rectified Linear Unit) is a commonly used activation function that changes the negative number to zero, leaving the positive number unchanged, introducing non-linear properties. For example, assume that a server is processing battery data for an electric vehicle. The server has extracted a plurality of initial charge variation parameter features and a plurality of initial state variation parameter features, including information on battery SOC, voltage, temperature, current, etc. For the electric quantity change parameter characteristics, the server respectively inputs the electric quantity change parameter characteristics into a first full-connection layer, and a first weight is set for each characteristic. For example, for SOC, the first weight may represent the extent to which the parameter affects battery performance. In the first fully connected layer, these features will be combined in a weighted manner. For the state change parameter characteristics, the server inputs the state change parameter characteristics to a second full connection layer respectively, and sets a second weight for each characteristic. For example, for temperature changes, the second weight may represent the extent to which the parameter affects the battery state. In the second fully connected layer, these features will be combined in a weighted manner. Then, the server uses a preset ReLU function to perform nonlinear transformation on the weighted electric quantity change parameter characteristics to obtain target electric quantity change parameter characteristics. This transformation may capture complex relationships between features and non-linear patterns. And similarly, the server uses a preset ReLU function to carry out nonlinear transformation on the weighted state change parameter characteristics to obtain target state change parameter characteristics. This transformation may help the server better understand the impact of the change in state parameters on battery performance.
In a specific embodiment, as shown in fig. 4, the process of executing step S204 may specifically include the following steps:
s401, initializing a feature population of a plurality of initial electric quantity change parameter features and a plurality of initial state change parameter features through a preset genetic algorithm to obtain an initial multi-angle feature population, wherein the initial multi-angle feature population comprises: a plurality of first candidate multi-angle features;
s402, respectively calculating a first characteristic fitness index D1 corresponding to each first candidate multi-angle characteristic, and acquiring a first fitness index threshold F and a second fitness index threshold X, wherein the first fitness index threshold F is smaller than the second fitness index threshold X;
s403, performing group segmentation on a plurality of first candidate multi-angle features according to a first feature fitness index D1, a first fitness index threshold F and a second fitness index threshold X;
s404, if the first characteristic adaptability index D1 is smaller than the first adaptability index threshold F, determining that the corresponding first candidate multi-angle characteristic is an uninfected group, if the first adaptability index threshold F is smaller than the first characteristic adaptability index D1 and smaller than the second adaptability index threshold X, determining that the corresponding first candidate multi-angle characteristic is an easily-infected group, and if the second adaptability index threshold X is smaller than the first characteristic adaptability index D1, determining that the corresponding first candidate multi-angle characteristic is an infected group;
S405, carrying out propagation, mutation and cross treatment on non-infected groups and easily-infected groups, and carrying out mutation and cross treatment on the infected groups to obtain a plurality of second candidate multi-angle features;
s406, respectively calculating a second characteristic fitness index D2 of each second candidate multi-angle characteristic, and carrying out optimization enhancement characteristic solution on a plurality of second candidate multi-angle characteristics according to the second characteristic fitness index D2 to obtain target enhancement characteristics.
Specifically, the server initializes a feature population. The feature population includes a plurality of initial power change parameter features and a plurality of initial state change parameter features. These features are considered individuals in the genetic algorithm and constitute a population. For each first candidate multi-angle feature, a corresponding first feature fitness index D1 needs to be calculated. The index is used to measure the quality or relevance of the features, and the specific manner in which the index is calculated will vary from problem to problem. Meanwhile, a first fitness index threshold F and a second fitness index threshold X need to be determined, where F is smaller than X. These thresholds help determine whether a feature belongs to an uninfected, susceptible, or infected population. Dividing the first candidate multi-angle features into different groups according to the comparison of the calculated D1 value and the thresholds F and X: if D1< F, determining the corresponding first candidate multi-angle feature as an uninfected population; if F < D1< X, determining the corresponding first candidate multi-angle feature as an easy-to-infect group; if D1> X, the corresponding first candidate multi-angle feature is determined to be an infected population. This population segmentation process helps identify which features are dominant in the genetic algorithm, which are suboptimal, and which are unsuitable for solving the problem. For uninfected and susceptible populations, propagation, mutation and crossover treatments were performed. These operations are the core of genetic algorithms, which generate new feature combinations by simulating the process of biological evolution. During propagation, individuals may combine in some way to create new individuals. During mutation, certain characteristics of an individual may change randomly. In the crossover process, the features of the two individuals are interchanged to create a new combination. For each second candidate multi-angle feature, a corresponding second feature fitness index D2 needs to be calculated. This index is usually related to the specific requirements of the problem, concerning the degree of differentiation, classification performance, etc. of the features. And carrying out optimization enhancement feature solution on the plurality of second candidate multi-angle features based on the second feature fitness index D2. The goal of this process is to select the feature combination with the best performance to improve the expressive power of the features and adaptability to the problem.
In a specific embodiment, the process of executing step S205 may specifically include the following steps:
(1) Calculating a first attention score between the target power change parameter feature and the target enhancement feature through the first attention mechanism layer, and calculating a second attention score between the target state change parameter feature and the target enhancement feature through the second attention mechanism layer;
(2) The first attention score is subjected to weight calculation through a preset first softmax function to obtain a first attention weight, and the second attention score is subjected to weight calculation through a preset second softmax function to obtain a second attention weight;
(3) And carrying out feature weighted fusion on the target electric quantity change parameter feature and the target enhancement feature according to the first attention weight to obtain a fusion electric quantity change feature, and carrying out feature weighted fusion on the target state change parameter feature and the target enhancement feature according to the second attention weight to obtain a fusion state change feature.
In particular, the attention mechanism is a technique for dynamically adjusting feature weights, enabling models to focus on different portions of the input data. First, a first attention score between a target power change parameter feature and a target enhancement feature is calculated through a first attention mechanism layer. A second attention score between the target state change parameter feature and the target enhancement feature is calculated by a second attention mechanism layer. In calculating the attention weight, a softmax function is typically used to convert the attention score into a weight. The softmax function can map the score to a range between 0 and 1 and ensure that the sum of all weights is 1. In this flow, a first attention score is weighted using a first softmax function to obtain a first attention weight. And simultaneously, calculating the weight of the second attention score by using a second softmax function to obtain a second attention weight. These weights are then applied to a weighted fusion of features. Specifically, feature weighted fusion is performed on the target power change parameter feature and the target enhancement feature according to the first attention weight, so that a fused power change feature is obtained. And simultaneously, carrying out feature weighted fusion on the target state change parameter feature and the target enhancement feature according to the second attention weight to obtain a fusion state change feature. For example, assume that a server is handling a problem predicting battery performance, where there are multiple battery parameters (e.g., SOC, voltage, current) and multiple state parameters (e.g., internal resistance, state of health). The server wishes to determine which parameters have the greatest impact on battery performance through an attention mechanism in order to better predict battery life. At the first attention mechanism layer, the server calculates an attention score between the target power change parameter characteristics (e.g., current and SOC) and the target enhancement characteristics. These scores represent the extent to which each battery parameter affects the change in charge. For example, if the impact of SOC on the power change is large, the corresponding attention score may be high. At the second attentiveness-mechanism-layer, the server calculates an attentiveness score between the target state-change parameter characteristics (e.g., internal resistance and state of health) and the target enhancement characteristics. These scores represent the extent to which each state parameter affects the state change. For example, if the internal resistance has a greater impact on the state change, the corresponding attention score may be higher. The first attention score is translated into a first attention weight using a first softmax function, while the second attention score is translated into a second attention weight using a second softmax function. These weights determine the extent to which each feature contributes in the final fusion. And carrying out feature weighted fusion on the target electric quantity change parameter feature and the target enhancement feature based on the first and second attention weights to obtain a fusion electric quantity change feature. And meanwhile, carrying out feature weighted fusion on the target state change parameter features and the target enhancement features to obtain fusion state change features. These fusion features include battery parameters and state parameters with high impact, which can be used to more accurately predict battery performance.
In a specific embodiment, the process of executing step S207 may specifically include the following steps:
(1) Inputting the target splicing characteristics into a third full-connection layer, and calculating the performance of the energy storage battery pack to the target splicing characteristics through a Sigmoid function in the third full-connection layer to obtain electricity taking performance prediction data, wherein the electricity taking performance prediction data comprise battery capacity, residual service life and electricity taking efficiency;
(2) Acquiring a battery pack operation and maintenance scheme list, and constructing a mapping relation between each candidate battery pack operation and maintenance scheme and electricity taking performance prediction data in the battery pack operation and maintenance scheme list;
(3) And carrying out mapping matching on the electricity taking performance prediction data and the battery pack operation and maintenance scheme list according to the mapping relation to obtain a target battery module operation and maintenance scheme corresponding to the target new energy vehicle.
Specifically, the target stitching feature is input into the third fully connected layer. The fully connected layer typically includes a plurality of neurons for further processing and combining features to calculate the performance of the energy storage battery. The server uses the Sigmoid function to calculate electricity taking performance prediction data of the energy storage battery pack. These predictive data typically include key performance indicators of battery capacity, remaining life, and power efficiency. The server obtains a battery pack operation and maintenance scheme list. This list contains various battery pack operation and maintenance schemes including different operation and maintenance strategies aimed at optimizing the performance and life of the battery. These schemes involve charging strategies, discharging strategies, temperature control, etc. Then, the server constructs a mapping relation between each candidate battery pack operation and maintenance scheme and electricity taking performance prediction data. The server determines how each battery pack operation and maintenance scheme affects the power take performance prediction data. This can be determined experimentally, by simulation. And then, the server performs mapping matching on the electricity taking performance prediction data and the battery pack operation and maintenance scheme list. And the server finds the most suitable battery pack operation and maintenance scheme according to the predicted performance data so as to achieve a specific performance target. For example, assuming that the server is handling an electric vehicle battery management system, it is necessary to select the best operating and maintenance scheme for the battery to optimize the performance and life of the battery. The server has trained a neural network model that accepts battery parameters and state parameters as inputs, outputting performance metrics such as battery capacity, remaining life, and power efficiency. Inputting the target spliced features to a third full-connection layer, and performing linear combination and nonlinear conversion on the features according to the weights and the deviations of the model. And transforming the result by using a Sigmoid function to obtain electricity taking performance prediction data. For example, the model predicts a battery capacity of 100kWh, a remaining life of 5 years, and a power extraction efficiency of 95%. The server has obtained a number of battery pack operation and maintenance schemes including different charging strategies and temperature control strategies, as well as different maintenance plans. Through simulation and experimentation, the server determines the impact of each battery pack operation and maintenance scheme on performance. For example, the server knows that a certain charging strategy will increase battery capacity, but decrease remaining life. These influencing relationships will help the server build the mapping. And the server performs mapping matching on the electricity taking performance prediction data and the battery pack operation and maintenance scheme list. In this example, the model of the server predicts a battery capacity of 100kWh and a remaining lifetime of 5 years. The server looks up the battery pack operation and maintenance scheme list and finds the operation and maintenance scheme most suitable for the performance indexes. A particular charging strategy and temperature control strategy is matched to these performance metrics.
The method for powering up the new energy automobile based on the display screen in the embodiment of the present invention is described above, and the following describes a new energy automobile power-up system based on the display screen in the embodiment of the present invention, referring to fig. 5, and an embodiment of the new energy automobile power-up system based on the display screen in the embodiment of the present invention includes:
the acquisition module 501 is configured to acquire, when a target new energy vehicle is in a power taking mode, first battery power information of a target battery module in the target new energy vehicle through a preset BMS management system, and send the first battery power information to a preset power taking device controller through a preset CAN communication protocol;
the calculating module 502 is configured to receive the first battery power information through the power taking device controller, and calculate first remaining power information of the target battery module according to the first battery power information;
the visualization module 503 is configured to send the first remaining capacity information to a power taking device socket controller through the CAN communication protocol, and visualize the first remaining capacity information through a man-machine interaction display screen of the power taking device controller;
the conversion module 504 is configured to convert the direct current of the target battery module into alternating current through the DC/AC bidirectional inversion module, output the alternating current to a corresponding target alternating current load device, and obtain second battery power information corresponding to the target battery module;
The detection module 505 is configured to calculate second remaining capacity information of the target battery module according to the second battery capacity information, perform power taking abnormality detection on the second remaining capacity information, obtain a power taking abnormality detection result, and perform abnormality alarm on the power taking abnormality detection result through the man-machine interaction display screen.
Through the cooperative cooperation of the components, when the target new energy vehicle is in the power taking mode, the BMS management system collects first battery electric quantity information and sends the first battery electric quantity information to the power taking device controller through the CAN communication protocol; calculating first residual electric quantity information; the first residual electric quantity information is sent to a socket controller of the power taking equipment through a CAN communication protocol, and is visualized through a man-machine interaction display screen; converting direct current into alternating current through a DC/AC bidirectional inversion module and outputting the alternating current to target alternating current load equipment to acquire second battery electric quantity information; according to the battery power information, the second residual power information is calculated, abnormal power taking detection is carried out, abnormal power taking detection results are subjected to abnormal alarm through a human-computer interaction display screen, and the battery state and the residual power are allowed to be monitored in real time by a user through the BMS and CAN communication protocol. Through the man-machine interaction display screen, the user can intuitively know the condition of the vehicle battery, and the convenience and the visibility of operation are improved. With an automatic encoder and attention mechanism, the method can accurately analyze the performance of the battery. The multi-angle feature enhancement is provided, and the battery performance problem can be identified more accurately, so that false alarm and missing alarm are reduced, and the reliability of fault diagnosis is improved. By detecting the power taking abnormality in the battery performance analysis process, the method can timely identify the battery problem and generate an abnormality alarm. This helps the user take quick action, reduces the risk of battery failure, and improves the safety and reliability of the vehicle. The battery module operation and maintenance scheme is matched according to the battery performance data, so that the use of the battery is optimized, the service life of the battery is prolonged, the sustainability of the battery is improved, and the maintenance cost is reduced. By converting direct current into alternating current, a user is enabled to use the power equipment outdoors or in a temporary location. This increases the versatility of the battery, enhancing the user experience. By utilizing the automatic encoder and the attention mechanism technology, the intelligent analysis and the abnormality detection of the battery performance are realized, and the operation burden of a user is reduced. In addition, the matching of the operation and maintenance schemes of the battery module is also automatic, so that a user can more easily select a scheme suitable for requirements, and further intelligent monitoring and operation and maintenance of the new energy automobile power taking process are realized.
The above fig. 5 describes the new energy automobile power taking system based on the display screen in the embodiment of the present invention in detail from the angle of the modularized functional entity, and the following describes the new energy automobile power taking device based on the display screen in the embodiment of the present invention in detail from the angle of hardware processing.
Fig. 6 is a schematic structural diagram of a new energy automobile power taking device based on a display screen, where the new energy automobile power taking device 600 based on the display screen may generate relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 610 (e.g., one or more processors) and a memory 620, one or more storage media 630 (e.g., one or more mass storage devices) storing application programs 633 or data 632. Wherein the memory 620 and the storage medium 630 may be transitory or persistent storage. The program stored on the storage medium 630 may include one or more modules (not shown), each of which may include a series of instruction operations on the display-based power extraction device 600 for a new energy vehicle. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the display-based power delivery device 600 for a new energy vehicle.
The display-based new energy automobile power harvesting device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input/output interfaces 660, and/or one or more operating systems 631, such as Windows Server, mac OS X, unix, linux, freeBSD, and the like. It will be appreciated by those skilled in the art that the display-based power extraction device structure of the new energy vehicle illustrated in fig. 6 is not limiting and may include more or fewer components than illustrated, or may be combined with certain components or a different arrangement of components.
The invention also provides new energy automobile power taking equipment based on the display screen, which comprises a memory and a processor, wherein the memory stores computer readable instructions, and when the computer readable instructions are executed by the processor, the processor executes the steps of the new energy automobile power taking method based on the display screen in the embodiments.
The invention also provides a computer readable storage medium, which can be a nonvolatile computer readable storage medium, and can also be a volatile computer readable storage medium, wherein the computer readable storage medium stores instructions, and when the instructions run on a computer, the instructions cause the computer to execute the steps of the new energy automobile power-taking method based on the display screen.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. The new energy automobile power taking method based on the display screen is characterized by comprising the following steps of:
when a target new energy vehicle is in a power-taking mode, acquiring first battery electric quantity information of a target battery module in the target new energy vehicle through a preset BMS management system, and sending the first battery electric quantity information to a preset power-taking equipment controller through a preset CAN communication protocol;
receiving the first battery electric quantity information through the power taking device controller, and calculating first residual electric quantity information of the target battery module according to the first battery electric quantity information;
The first residual electric quantity information is sent to a power taking device socket controller through the CAN communication protocol, and the first residual electric quantity information is visualized through a man-machine interaction display screen of the power taking device controller;
converting the direct current of the target battery module into alternating current through a DC/AC bidirectional inversion module, outputting the alternating current to corresponding target alternating current load equipment, and simultaneously acquiring second battery electric quantity information corresponding to the target battery module;
calculating second residual capacity information of the target battery module according to the second battery capacity information, detecting power taking abnormality of the second residual capacity information to obtain a power taking abnormality detection result, and carrying out abnormality warning on the power taking abnormality detection result through the man-machine interaction display screen; if the electricity taking abnormality detection result is that electricity taking abnormality is caused, acquiring a battery electric quantity change parameter data set and a battery state change parameter data set of a target battery module in the target new energy vehicle through a BMS management system; inputting the battery electric quantity change parameter data set into a first automatic encoder for parameter feature extraction to obtain a plurality of initial electric quantity change parameter features, and inputting the battery state change parameter data set into a second automatic encoder for parameter feature extraction to obtain a plurality of initial state change parameter features; inputting the initial electric quantity change parameter characteristics into a first full-connection layer for characteristic integration to obtain target electric quantity change parameter characteristics, and inputting the initial state change parameter characteristics into a second full-connection layer for characteristic integration to obtain target state change parameter characteristics; performing multi-angle feature enhancement on the initial electric quantity change parameter features and the initial state change parameter features to obtain target enhancement features; performing feature fusion on the target electric quantity change parameter feature and the target enhancement feature through a first attention mechanism layer to obtain a fusion electric quantity change feature, and performing feature fusion on the target state change parameter feature and the target enhancement feature through a second attention mechanism layer to obtain a fusion state change feature; performing feature interaction on the fusion electric quantity change feature and the fusion state change feature through a gating mechanism layer, determining corresponding weight and fusion mode, and performing feature splicing on the fusion electric quantity change feature and the fusion state change feature according to the weight and the fusion mode to obtain target splicing features; and inputting the target splicing characteristics into a third full-connection layer for battery module electricity taking performance analysis, obtaining electricity taking performance prediction data, and matching the corresponding target battery module operation and maintenance scheme according to the electricity taking performance prediction data.
2. The method for power-taking of a new energy automobile based on a display screen according to claim 1, wherein the steps of inputting the battery power change parameter data set into a first automatic encoder for parameter feature extraction to obtain a plurality of initial power change parameter features, and inputting the battery state change parameter data set into a second automatic encoder for parameter feature extraction to obtain a plurality of initial state change parameter features include:
performing parameter classification on the battery electric quantity change parameter data set to obtain a plurality of target battery electric quantity change parameter data, and performing parameter classification on the battery state change parameter data set to obtain a plurality of target battery state change parameter data;
respectively inputting the plurality of target battery power change parameter data into a first automatic encoder, wherein the first automatic encoder comprises a first bidirectional threshold cycle unit; simultaneously, respectively inputting the plurality of target battery state change parameter data into a second automatic encoder, wherein the second automatic encoder comprises a second bidirectional threshold cycle unit;
extracting features of the target battery electric quantity change parameter data through a first layer of threshold circulating units in the first bidirectional threshold circulating units to obtain a plurality of first forward hidden coding features, and extracting features of the target battery electric quantity change parameter data through a second layer of threshold circulating units in the first bidirectional threshold circulating units to obtain a plurality of first backward hidden coding features; meanwhile, extracting features of the plurality of target battery state change parameter data through a third layer of threshold circulating units in the second bi-directional threshold circulating units to obtain a plurality of second forward hidden coding features, and extracting features of the plurality of target battery state change parameter data through a fourth layer of threshold circulating units in the second bi-directional threshold circulating units to obtain a plurality of second backward hidden coding features;
And respectively connecting the plurality of first forward hidden coding features and the corresponding plurality of first backward hidden coding features to obtain a plurality of initial electric quantity change parameter features, and respectively connecting the plurality of second forward hidden coding features and the corresponding plurality of second backward hidden coding features to obtain a plurality of initial state change parameter features.
3. The method for power-taking of a new energy automobile based on a display screen according to claim 2, wherein the inputting the plurality of initial power change parameter features into the first fully-connected layer for feature integration to obtain a target power change parameter feature, and inputting the plurality of initial state change parameter features into the second fully-connected layer for feature integration to obtain a target state change parameter feature comprises:
inputting the initial electric quantity change parameter characteristics into a first full-connection layer respectively, and setting a first weight of each initial electric quantity change parameter characteristic through the first full-connection layer; simultaneously, the initial state change parameter characteristics are respectively input into a second full-connection layer, and a second weight of each initial state change parameter characteristic is set through the second full-connection layer;
Performing weighted operation on the plurality of initial electric quantity change parameter features according to the first weight to obtain a plurality of weighted electric quantity change parameter features, and performing weighted operation on the plurality of initial state change parameter features according to the second weight to obtain a plurality of weighted state change parameter features;
and carrying out nonlinear transformation on the plurality of weighted electric quantity change parameter characteristics through a preset first ReLU function to obtain target electric quantity change parameter characteristics, and carrying out nonlinear transformation on the plurality of weighted state change parameter characteristics through a preset second ReLU function to obtain target state change parameter characteristics.
4. The method for powering a new energy automobile based on a display screen according to claim 3, wherein the performing multi-angle feature enhancement on the plurality of initial power change parameter features and the plurality of initial state change parameter features to obtain a target enhancement feature includes:
initializing the characteristic population of the plurality of initial electric quantity change parameter characteristics and the plurality of initial state change parameter characteristics through a preset genetic algorithm to obtain an initial multi-angle characteristic population, wherein the initial multi-angle characteristic population comprises: a plurality of first candidate multi-angle features;
Respectively calculating a first characteristic fitness index D1 corresponding to each first candidate multi-angle characteristic, and acquiring a first fitness index threshold F and a second fitness index threshold X, wherein the first fitness index threshold F is smaller than the second fitness index threshold X;
performing group segmentation on the plurality of first candidate multi-angle features according to the first feature fitness index D1, the first fitness index threshold F and the second fitness index threshold X;
if the first characteristic adaptability index D1 is smaller than the first adaptability index threshold F, determining that the corresponding first candidate multi-angle characteristic is an uninfected group, if the first adaptability index threshold F is smaller than the first characteristic adaptability index D1 and smaller than the second adaptability index threshold X, determining that the corresponding first candidate multi-angle characteristic is an easily-infected group, and if the second adaptability index threshold X is smaller than the first characteristic adaptability index D1, determining that the corresponding first candidate multi-angle characteristic is an infected group;
performing propagation, mutation and cross treatment on the non-infected population and the easily infected population, and performing mutation and cross treatment on the infected population to obtain a plurality of second candidate multi-angle features;
and respectively calculating a second characteristic fitness index D2 of each second candidate multi-angle characteristic, and carrying out optimization enhancement characteristic solution on the plurality of second candidate multi-angle characteristics according to the second characteristic fitness index D2 to obtain target enhancement characteristics.
5. The method for powering a new energy automobile based on a display screen according to claim 4, wherein the feature fusion is performed on the target power change parameter feature and the target enhancement feature by the first attention mechanism layer to obtain a fused power change feature, and the feature fusion is performed on the target state change parameter feature and the target enhancement feature by the second attention mechanism layer to obtain a fused state change feature, and the method comprises:
calculating a first attention score between the target power change parameter feature and the target enhancement feature by a first attention mechanism layer, and calculating a second attention score between the target state change parameter feature and the target enhancement feature by a second attention mechanism layer;
the first attention score is subjected to weight calculation through a preset first softmax function to obtain a first attention weight, and the second attention score is subjected to weight calculation through a preset second softmax function to obtain a second attention weight;
and carrying out feature weighted fusion on the target electric quantity change parameter feature and the target enhancement feature according to the first attention weight to obtain a fusion electric quantity change feature, and carrying out feature weighted fusion on the target state change parameter feature and the target enhancement feature according to the second attention weight to obtain a fusion state change feature.
6. The method for power taking of a new energy automobile based on a display screen according to claim 5, wherein the inputting the target splicing feature into the third full connection layer for power taking performance analysis of the battery module, obtaining power taking performance prediction data, and matching the corresponding target battery module operation and maintenance scheme according to the power taking performance prediction data, comprises:
inputting target splicing characteristics into a third full-connection layer, and calculating the performance of the energy storage battery pack through a Sigmoid function in the third full-connection layer to obtain electricity taking performance prediction data, wherein the electricity taking performance prediction data comprise battery capacity, residual service life and electricity taking efficiency;
acquiring a battery pack operation and maintenance scheme list, and constructing a mapping relation between each candidate battery pack operation and maintenance scheme and electricity taking performance prediction data in the battery pack operation and maintenance scheme list;
and carrying out mapping matching on the electricity taking performance prediction data and the battery pack operation and maintenance scheme list according to the mapping relation to obtain a target battery module operation and maintenance scheme corresponding to the target new energy vehicle.
7. The utility model provides a new energy automobile power taking system based on display screen which characterized in that, new energy automobile power taking system based on display screen includes:
The acquisition module is used for acquiring first battery electric quantity information of a target battery module in the target new energy vehicle through a preset BMS management system when the target new energy vehicle is in a power taking mode, and transmitting the first battery electric quantity information to a preset power taking equipment controller through a preset CAN communication protocol;
the calculation module is used for receiving the first battery electric quantity information through the power taking device controller and calculating first residual electric quantity information of the target battery module according to the first battery electric quantity information;
the visualization module is used for sending the first residual electric quantity information to a power taking device socket controller through the CAN communication protocol, and visualizing the first residual electric quantity information through a man-machine interaction display screen of the power taking device controller;
the conversion module is used for converting the direct current of the target battery module into alternating current through the DC/AC bidirectional inversion module, outputting the alternating current to corresponding target alternating current load equipment, and simultaneously acquiring second battery electric quantity information corresponding to the target battery module;
the detection module is used for calculating second residual electric quantity information of the target battery module according to the second battery electric quantity information, carrying out power taking abnormality detection on the second residual electric quantity information to obtain a power taking abnormality detection result, and carrying out abnormality warning on the power taking abnormality detection result through the man-machine interaction display screen; if the electricity taking abnormality detection result is that electricity taking abnormality is caused, acquiring a battery electric quantity change parameter data set and a battery state change parameter data set of a target battery module in the target new energy vehicle through a BMS management system; inputting the battery electric quantity change parameter data set into a first automatic encoder for parameter feature extraction to obtain a plurality of initial electric quantity change parameter features, and inputting the battery state change parameter data set into a second automatic encoder for parameter feature extraction to obtain a plurality of initial state change parameter features; inputting the initial electric quantity change parameter characteristics into a first full-connection layer for characteristic integration to obtain target electric quantity change parameter characteristics, and inputting the initial state change parameter characteristics into a second full-connection layer for characteristic integration to obtain target state change parameter characteristics; performing multi-angle feature enhancement on the initial electric quantity change parameter features and the initial state change parameter features to obtain target enhancement features; performing feature fusion on the target electric quantity change parameter feature and the target enhancement feature through a first attention mechanism layer to obtain a fusion electric quantity change feature, and performing feature fusion on the target state change parameter feature and the target enhancement feature through a second attention mechanism layer to obtain a fusion state change feature; performing feature interaction on the fusion electric quantity change feature and the fusion state change feature through a gating mechanism layer, determining corresponding weight and fusion mode, and performing feature splicing on the fusion electric quantity change feature and the fusion state change feature according to the weight and the fusion mode to obtain target splicing features; and inputting the target splicing characteristics into a third full-connection layer for battery module electricity taking performance analysis, obtaining electricity taking performance prediction data, and matching the corresponding target battery module operation and maintenance scheme according to the electricity taking performance prediction data.
8. The utility model provides a new energy automobile electricity taking device based on display screen which characterized in that, new energy automobile electricity taking device based on display screen includes: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the display-based new energy automobile power extraction device to perform the display-based new energy automobile power extraction method of any one of claims 1-6.
9. A computer readable storage medium having instructions stored thereon, wherein the instructions when executed by a processor implement the new energy vehicle power extraction method based on a display screen of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311305860.1A CN117022032B (en) | 2023-10-10 | 2023-10-10 | New energy automobile electricity taking method and system based on display screen |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311305860.1A CN117022032B (en) | 2023-10-10 | 2023-10-10 | New energy automobile electricity taking method and system based on display screen |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117022032A CN117022032A (en) | 2023-11-10 |
| CN117022032B true CN117022032B (en) | 2023-12-29 |
Family
ID=88639527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311305860.1A Active CN117022032B (en) | 2023-10-10 | 2023-10-10 | New energy automobile electricity taking method and system based on display screen |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117022032B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107009901A (en) * | 2017-03-31 | 2017-08-04 | 武汉理工大学 | A kind of SCM Based electric automobile combination electronic instrument |
| CN111674276A (en) * | 2020-06-11 | 2020-09-18 | 国网重庆市电力公司营销服务中心 | Electric automobile ordered charging control method and system |
| CN112297950A (en) * | 2020-11-09 | 2021-02-02 | 中国第一汽车股份有限公司 | Charging and discharging human-computer interaction control method and device, vehicle and storage medium |
| JP2021152804A (en) * | 2020-03-24 | 2021-09-30 | 富士フイルムビジネスイノベーション株式会社 | Information processing device and computer program |
| CN113779892A (en) * | 2021-09-27 | 2021-12-10 | 中国人民解放军国防科技大学 | Wind speed and wind direction prediction method |
-
2023
- 2023-10-10 CN CN202311305860.1A patent/CN117022032B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107009901A (en) * | 2017-03-31 | 2017-08-04 | 武汉理工大学 | A kind of SCM Based electric automobile combination electronic instrument |
| JP2021152804A (en) * | 2020-03-24 | 2021-09-30 | 富士フイルムビジネスイノベーション株式会社 | Information processing device and computer program |
| CN111674276A (en) * | 2020-06-11 | 2020-09-18 | 国网重庆市电力公司营销服务中心 | Electric automobile ordered charging control method and system |
| CN112297950A (en) * | 2020-11-09 | 2021-02-02 | 中国第一汽车股份有限公司 | Charging and discharging human-computer interaction control method and device, vehicle and storage medium |
| CN113779892A (en) * | 2021-09-27 | 2021-12-10 | 中国人民解放军国防科技大学 | Wind speed and wind direction prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117022032A (en) | 2023-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110492186B (en) | Power battery module management method based on cloud control technology | |
| WO2018133230A1 (en) | Control method and apparatus for micro-grid system | |
| CN109596913B (en) | Charging pile fault cause diagnosis method and device | |
| CN112700032A (en) | Fault prediction system and method for low-voltage direct-current power distribution and utilization system | |
| CN107870306A (en) | A kind of lithium battery charge state prediction algorithm based under deep neural network | |
| CN107404139A (en) | Charging pile detection means and system | |
| WO2023185601A1 (en) | Method and device for determining state of health information of battery, and battery system | |
| CN110472772B (en) | Overheating early warning method for isolating switch and overheating early warning system for isolating switch | |
| CN104483633B (en) | Lead-acid accumulator monitoring system | |
| CN108146267A (en) | Charging system, charger, electric vehicle, rechargeable battery safety protecting method | |
| CN116643178B (en) | SOC estimation method and related device of battery management system | |
| US20220382771A1 (en) | Battery information processing system and battery information processing method | |
| CN113682184A (en) | Charging detection method, device and system for electric automobile | |
| CN113547919A (en) | Remote fault monitoring method and system for fuel cell vehicle | |
| CN112349981A (en) | Battery management system | |
| CN113326585B (en) | Energy efficiency abnormality early warning method and device for gas boiler and computer equipment | |
| KR102431909B1 (en) | Recycled battery evaluation system and method thereof | |
| CN117022032B (en) | New energy automobile electricity taking method and system based on display screen | |
| CN115280356A (en) | Management system, management method, server device, program, battery information providing system, and battery information providing method | |
| CN116923188A (en) | Charging protection system of new energy vehicle | |
| CN116031508A (en) | Lithium ion battery management system and method based on deep learning | |
| CN114002609A (en) | Power operation real-time supervision early warning system based on thing networking | |
| CN112083340B (en) | Storage battery performance detection method and device, storage medium and terminal | |
| CN111337764A (en) | Charging pile fault diagnosis system and method and storage medium | |
| CN117955248B (en) | Energy storage power station battery state monitoring system, method, device and storage medium |
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 |