CN117538781A - Intelligent detection device and method for energy storage battery based on SOC model - Google Patents
Intelligent detection device and method for energy storage battery based on SOC model Download PDFInfo
- Publication number
- CN117538781A CN117538781A CN202311556747.0A CN202311556747A CN117538781A CN 117538781 A CN117538781 A CN 117538781A CN 202311556747 A CN202311556747 A CN 202311556747A CN 117538781 A CN117538781 A CN 117538781A
- Authority
- CN
- China
- Prior art keywords
- energy storage
- storage battery
- video
- infrared
- soc
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 57
- 238000003331 infrared imaging Methods 0.000 claims abstract description 30
- 238000012360 testing method Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims abstract description 18
- 238000013528 artificial neural network Methods 0.000 claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims abstract description 7
- 238000000605 extraction Methods 0.000 claims description 24
- 238000007599 discharging Methods 0.000 claims description 20
- 239000013598 vector Substances 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 238000007600 charging Methods 0.000 claims description 11
- 238000003708 edge detection Methods 0.000 claims description 7
- 230000005855 radiation Effects 0.000 claims description 6
- 238000002474 experimental method Methods 0.000 claims description 4
- 238000010281 constant-current constant-voltage charging Methods 0.000 claims description 3
- 208000024891 symptom Diseases 0.000 claims description 2
- 230000008859 change Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003416 augmentation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000011282 treatment Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
- G01R31/387—Determining ampere-hour charge capacity or SoC
- G01R31/388—Determining ampere-hour charge capacity or SoC involving voltage measurements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/389—Measuring internal impedance, internal conductance or related variables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Secondary Cells (AREA)
Abstract
The invention provides an intelligent detection device and method for an energy storage battery based on an SOC model, wherein the device comprises the energy storage battery, a battery capacity-dividing testing device, an infrared imaging device and a video recognition and processing device; the positive electrode and the negative electrode of the energy storage battery are connected with a battery capacity-dividing testing device, the battery capacity-dividing testing device is used for monitoring the voltage and current states of the energy storage battery in the whole process, the infrared imaging device is arranged right in front of the energy storage battery and is used for monitoring the temperature states of the energy storage battery under the condition of normal charge and discharge, and the signal output ends of the battery capacity-dividing testing device and the infrared imaging device are connected with a video recognition and processing device; according to the invention, the infrared imaging video and the temperature data of the specific point on the surface of the energy storage battery are obtained through the infrared imaging device when the energy storage battery is normally charged and discharged, the video and the temperature data are trained and identified based on the neural network, and a related SOC model is established to realize quick and online detection of the SOC.
Description
Technical Field
The invention relates to the technical field of energy storage battery detection, in particular to an intelligent energy storage battery detection device and method based on an SOC model.
Background
The increasing shortage of traditional energy greatly promotes the development of new energy power generation. Because of randomness and intermittence of new energy power generation such as wind power, photovoltaic and the like, the supplied electric energy has great uncertainty. In order to ensure that the power grid stably operates, a light-discarding and wind-discarding strategy is adopted at present, so that a great deal of energy is wasted. The energy storage power station can quickly provide response, realizes self-digestion of energy, effectively solves some defects of new energy grid connection, and improves the safety and flexibility of the power grid. The energy storage power station is formed by combining a large number of energy storage batteries in series-parallel connection, the accurate estimation of the energy storage batteries SOC (State of Charge) can effectively avoid the overcharge and overdischarge of the batteries, the service life of the batteries is prolonged, a reliable basis is provided for a control strategy of the power grid energy conversion system, and the method has important significance for safe and stable operation of power grid side energy storage.
The current battery SOC detection method mainly comprises an ampere-hour method, an open-circuit voltage method and a discharge experiment method, and the problems of overlong detection time (several hours) and the like generally exist in the methods, so that the method is not suitable for on-line energy storage battery SOC detection.
Disclosure of Invention
In order to solve the defects, the invention provides an intelligent detection device and method for an energy storage battery based on an SOC model.
In order to achieve the above purpose, the invention is realized by the following technical scheme that the intelligent detection device for the energy storage battery comprises the energy storage battery, a battery capacity-dividing testing device, an infrared imaging device and a video identification and processing device; the positive electrode and the negative electrode of the energy storage battery are connected with a battery capacity-dividing testing device, the battery capacity-dividing testing device is used for monitoring the voltage and current states of the energy storage battery in the whole process, the infrared imaging device is arranged right in front of the energy storage battery and used for monitoring the temperature states of the energy storage battery under the condition of normal charge and discharge, and the signal output ends of the battery capacity-dividing testing device and the infrared imaging device are connected with a video recognition and processing device.
By adopting the technical scheme, the infrared imaging video and the temperature data of the specific point on the surface of the energy storage battery are obtained through the infrared imaging device when the energy storage battery is normally charged and discharged. Based on the neural network, training and identifying the video and the temperature data, establishing a related SOC model, continuously improving the detection speed and accuracy of the model through self-learning, and fully utilizing the temperature information of the energy storage battery during short-time charge and discharge to realize quick and online detection of the SOC.
Optionally, the battery capacity-dividing testing device adopts an EBC-X8 channel battery capacity-dividing cabinet, and comprises constant-current discharging, constant-current constant-voltage charging and circulating charging and discharging modes, so that an electrochemical performance experiment on the battery is completed, and voltage and current data of the energy storage battery are monitored in the whole process.
Optionally, the video recognition and processing device comprises an infrared video processing module, a feature extraction module and a temperature data acquisition module, wherein the infrared video processing module is connected with the feature extraction module and the temperature data acquisition module, the infrared video processing module is used for processing the acquired infrared video, the feature extraction module is used for extracting features of the video, representative feature vectors are mainly extracted from the video, and the temperature acquisition module is used for acquiring the temperature corresponding to the infrared video.
Optionally, the infrared imaging device includes infrared camera, infrared detector, treater and display, infrared camera is used for receiving and gathering the infrared radiation that is surveyed the object and launches, infrared detector is used for becoming the thermal radiation model electrical signal, the treater is used for handling the electrical signal, the display is used for turning into the visible light image with the electrical signal.
The invention also provides an intelligent detection method of the energy storage battery based on the SOC model, which comprises the following steps:
the video identification and processing device is combined with an open-circuit voltage method to acquire the SOC of the energy storage battery, and the energy storage batteries with different SOCs are classified and marked;
the video recognition and processing device controls the battery capacity-division testing device to charge and discharge the energy storage battery;
acquiring an infrared video and the surface temperature before the charging and discharging process of the energy storage battery through an infrared imaging device, and transmitting the infrared video and the surface temperature to a video identification and processing device;
the video identification and processing device performs key frame extraction, image enhancement and edge detection processing on the infrared video, and performs feature extraction on the processed video;
capturing temperature data of infrared videos of the energy storage batteries in different SOC states in the charging and discharging processes through a video identification and processing device;
constructing different SOC energy storage battery databases by using a large number of energy storage batteries in different SOC states to input a neural network for training, and creating an SOC model;
and judging whether the image generated by the infrared imaging device is in a normal discharging state or not through the SOC model, and if not, stopping discharging the energy storage battery.
Through adopting above-mentioned technical scheme, acquire the infrared imaging video and the temperature data of energy storage battery surface specific point when the normal charge and discharge of energy storage battery through infrared imaging device, train and discern video and temperature data based on neural network, establish relevant SOC model, through self-learning, constantly improve the detection rate and the accuracy of model, make full use of the temperature information when the energy storage battery short time charges and discharges realizes the quick, the on-line measuring to the SOC.
Optionally, the video recognition and processing device performs key frame extraction on the infrared video to extract frames containing important information and changes.
Optionally, the video recognition and processing device performs image augmentation on the infrared video.
Optionally, the video recognition and processing device performs feature extraction on the processed video.
Optionally, the video recognition and processing device performs feature extraction on the processed video to obtain a required feature vector.
Optionally, the symptom vector is a set of values extracted from the processed infrared video and used to represent key feature information contained in the video.
The invention provides an intelligent detection device and method for an energy storage battery based on an SOC model, which have the following beneficial effects:
1. the invention provides an intelligent detection device for an energy storage battery, which is used for acquiring infrared imaging video and temperature data of a specific point on the surface of the energy storage battery during normal charge and discharge of the energy storage battery through an infrared imaging device. Training and identifying videos and temperature data based on a neural network, establishing a related SOC model, continuously improving the detection speed and accuracy of the model through self-learning, and fully utilizing the temperature information of the energy storage battery during short-time charge and discharge to realize quick and online detection of the SOC;
2. the invention provides an intelligent detection method of an energy storage battery based on an SOC model. Based on the neural network, training and identifying the video and the temperature data, establishing a related SOC model, continuously improving the detection speed and accuracy of the model through self-learning, and fully utilizing the temperature information of the energy storage battery during short-time charge and discharge to realize quick and online detection of the SOC.
Drawings
Fig. 1 is a schematic structural diagram of an intelligent detection device for an energy storage battery according to an embodiment of the present invention.
Fig. 2 is a flowchart of an intelligent detection method of an energy storage battery based on an SOC model according to an embodiment of the present invention.
Detailed Description
The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are one embodiment of the present invention, not all other embodiments obtained by those skilled in the art without making creative efforts, and all other embodiments are within the scope of protection of the present invention.
As shown in fig. 1, the embodiment of the invention provides an intelligent detection device for an energy storage battery, which comprises the energy storage battery, a battery capacity-dividing testing device, an infrared imaging device, a video identification and processing device and an intelligent control device, wherein the battery capacity-dividing testing device, the infrared imaging device and the video identification and processing device are all connected with the intelligent control device; the positive electrode and the negative electrode of the energy storage battery are connected with the battery capacity-dividing testing device, the battery capacity-dividing testing device is used for monitoring the voltage and current states of the energy storage battery in the whole process, the infrared imaging device is arranged right in front of the energy storage battery, the temperature states of the energy storage battery under the condition of normal charge and discharge are monitored, and the signal output ends of the battery capacity-dividing testing device and the infrared imaging device are connected with the video identification and processing device.
The battery capacity-dividing testing device adopts an EBC-X8 channel battery capacity-dividing cabinet, comprises constant-current discharging, constant-current constant-voltage charging and circulating charging and discharging modes, completes an electrochemical performance experiment on the battery, and monitors voltage and current data of the energy storage battery in the whole process.
The video identification and processing device comprises an infrared video processing module, a feature extraction module and a temperature data acquisition module, wherein the infrared video processing module is connected with the feature extraction module and the temperature data acquisition module, the infrared video processing module is used for processing acquired infrared videos, the feature extraction module is used for carrying out feature extraction on the videos, representative feature vectors are mainly extracted from the videos, and the temperature acquisition module is used for acquiring temperatures corresponding to the infrared videos.
The infrared imaging device comprises an infrared camera, an infrared detector, a processor and a display, wherein the infrared camera is used for receiving and converging infrared radiation emitted by a measured object, the infrared detector is used for changing a thermal radiation model into an electric signal, the processor is used for processing the electric signal, and the display is used for converting the electric signal into a visible light image.
As shown in fig. 2, the invention further provides an intelligent detection method of the energy storage battery based on the SOC model, which comprises the following steps:
and the video identification and processing device is combined with an open-circuit voltage method to acquire the SOC of the energy storage battery, and the energy storage batteries with different SOCs are classified and marked.
The video recognition and processing device controls the battery capacity-division testing device to charge and discharge the energy storage battery; the video recognition and processing device is communicated with the battery capacity-division testing device through a control signal, the control device performs charge and discharge operation on the energy storage battery, and in addition, in the control process, the video recognition and processing device can monitor the voltage and current states of the battery in real time and detect whether abnormal values exist.
And acquiring infrared videos and the surface temperature before the charging and discharging process of the energy storage battery through an infrared imaging device, and transmitting the infrared videos and the surface temperature to a video identification and processing device.
The video recognition and processing device performs key frame extraction, image enhancement and edge detection processing on the infrared video, and performs feature extraction on the processed video.
And capturing temperature data of infrared videos of the energy storage batteries in different SOC states in the charging and discharging processes through the video identification and processing device.
Constructing different SOC energy storage battery databases by using a large number of energy storage batteries in different SOC states to input a neural network for training, and creating an SOC model; the video processing and identifying device inputs infrared video data in the database into the neural network, namely the LSTM model for training, and the temperature data of specific points on the surface of the battery are trained by using the Restnet model to jointly form the SOC model, wherein the specific flow is as follows: acquiring infrared videos and temperature data of specific points on the surface of the battery in the process of charging and discharging a large number of energy storage batteries, and corresponding the infrared videos and the temperature data with different SOCs (output values); performing key frame extraction, image enhancement, edge detection and other treatments on the infrared video, extracting effective feature vectors, and combining temperature data of specific points on the surface of the battery to form a training set and a testing set; the neural network is built through the training set to carry out model assumption, the obtained training set is continuously sent into the neural network to carry out model training, model parameters are obtained, the model parameters are optimized through training of a large number of test sets, and the evaluation accuracy of the SOC of the energy storage battery is continuously improved.
And judging whether the image generated by the infrared imaging device is in a normal discharging state or not through the SOC model, and if not, stopping discharging the energy storage battery.
In the process of shooting infrared video of the energy storage battery, the temperature of the battery rises as a change process, so that a lot of redundancies exist in the shot video data, and generally, the interference data existing in the infrared video mainly comprise three types: the method mainly aims at the problem that redundant frames exist in infrared video, and mainly comprises the following steps of extracting key frames of the video, wherein the method mainly comprises the following steps of: the invention uses the mode of combining the frame difference method and the background difference method to extract the video key frame to extract more information and reduce noise.
Besides, the infrared image is usually characterized by low spatial resolution, low contrast and blurred edges, so that the selection of a proper filtering algorithm to preprocess the infrared image is a key of video identification, and a Canny operator is an edge detection operator integrating multiple stages of filtering, enhancement, detection and the like, and aims to detect an optimal edge profile.
Edge detection is a method of image processing for capturing the position and shape of the boundary of an object in an image. In the infrared image, the edges represent temperature variations between different objects. Through edge detection, the boundary and the outline of an object in the infrared image can be effectively extracted, so that the change condition of the temperature in the battery charging and discharging process is better analyzed, and more accurate information is provided for subsequent feature extraction and SOC correlation analysis.
In the field of artificial intelligence, each piece of data input to a neural network is called a feature, and a segment of infrared video has a plurality of features. This vector of several dimensions is also called a feature vector; specifically, the feature vector is a set of values extracted from the processed infrared video and used to represent key feature information contained in the video. Specifically, during the charge and discharge of the battery, the feature vector may include features describing the temperature distribution and the trend of change, such as a temperature average value, a variance, a gradient, a texture, and the like, and may further include features describing time series, such as a frequency, an amplitude, a change speed, and the like of the temperature change. These feature vectors can be used for subsequent tasks such as feature analysis, classification, clustering, and prediction.
The invention uses long-term memory network (LSTM) to have long-time sequence modeling capability, can contact with long-distance context information of video sequence, acquires the feature vector in infrared video to train, obtains SOC evaluation model, and combines with temperature data of specific point of battery to further study correlation between SOC and temperature change in feature analysis to evaluate state and performance of battery.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. An intelligent detection device for an energy storage battery comprises the energy storage battery, a battery capacity-dividing testing device, an infrared imaging device and a video identification and processing device; the positive electrode and the negative electrode of the energy storage battery are connected with a battery capacity-dividing testing device, the battery capacity-dividing testing device is used for monitoring the voltage and current states of the energy storage battery in the whole process, the infrared imaging device is arranged right in front of the energy storage battery and used for monitoring the temperature states of the energy storage battery under the condition of normal charge and discharge, and the signal output ends of the battery capacity-dividing testing device and the infrared imaging device are connected with a video recognition and processing device.
2. The intelligent detection device for the energy storage battery according to claim 1, wherein the battery capacity-dividing testing device adopts an EBC-X8 channel battery capacity-dividing cabinet, comprises constant-current discharging, constant-current constant-voltage charging and circulating charging and discharging modes, finishes an electrochemical performance experiment on the battery, and monitors voltage and current data of the energy storage battery in the whole process.
3. The intelligent detection device for the energy storage battery according to claim 1, wherein the video recognition and processing device comprises an infrared video processing module, a feature extraction module and a temperature data acquisition module, the infrared video processing module is connected with the feature extraction module and the temperature data acquisition module, the infrared video processing module is used for processing acquired infrared videos, the feature extraction module is used for extracting features of the videos, representative feature vectors are mainly extracted from the videos, and the temperature acquisition module is used for acquiring temperatures corresponding to the infrared videos.
4. The intelligent detection device for the energy storage battery according to claim 1, wherein the infrared imaging device comprises an infrared camera, an infrared detector, a processor and a display, the infrared camera is used for receiving and converging infrared radiation emitted by an object to be detected, the infrared detector is used for changing a thermal radiation model into an electric signal, the processor is used for processing the electric signal, and the display is used for converting the electric signal into a visible light image.
5. The intelligent detection method of the energy storage battery based on the SOC model according to any one of claims 1 to 4, which is characterized by comprising the following steps:
detecting the voltage and current states of the energy storage battery through a battery capacity-division testing device, and sending the detected voltage and current data to a video identification and processing device;
the video identification and processing device is combined with an open-circuit voltage method to acquire the SOC of the energy storage battery, and the energy storage batteries with different SOCs are classified and marked;
the video recognition and processing device controls the battery capacity-division testing device to charge and discharge the energy storage battery;
acquiring an infrared video and the surface temperature before the charging and discharging process of the energy storage battery through an infrared imaging device, and transmitting the infrared video and the surface temperature to a video identification and processing device;
the video identification and processing device performs key frame extraction, image enhancement and edge detection processing on the infrared video, and performs feature extraction on the processed video;
capturing temperature data of infrared videos of the energy storage batteries in different SOC states in the charging and discharging processes through a video identification and processing device;
constructing different SOC energy storage battery databases by using a large number of energy storage batteries in different SOC states to input a neural network for training, and creating an SOC model;
and judging whether the image generated by the infrared imaging device is in a normal discharging state or not through the SOC model, and if not, stopping discharging the energy storage battery.
6. The intelligent detection method for the energy storage battery based on the SOC model according to claim 5, wherein the video recognition and processing device performs key frame extraction on the infrared video to extract frames containing important information and changes.
7. The intelligent detection method for the energy storage battery based on the SOC model of claim 5, wherein the video recognition and processing device performs image enhancement on the infrared video.
8. The intelligent detection method for the energy storage battery based on the SOC model of claim 5, wherein the video recognition and processing device performs feature extraction on the processed video.
9. The intelligent detection method for the energy storage battery based on the SOC model of claim 5, wherein the video recognition and processing device performs feature extraction on the processed video to obtain the required feature vector.
10. The method of claim 9, wherein the symptom vector is a set of values extracted from the processed infrared video and used for representing key feature information contained in the video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311556747.0A CN117538781A (en) | 2023-11-21 | 2023-11-21 | Intelligent detection device and method for energy storage battery based on SOC model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311556747.0A CN117538781A (en) | 2023-11-21 | 2023-11-21 | Intelligent detection device and method for energy storage battery based on SOC model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117538781A true CN117538781A (en) | 2024-02-09 |
Family
ID=89789556
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311556747.0A Pending CN117538781A (en) | 2023-11-21 | 2023-11-21 | Intelligent detection device and method for energy storage battery based on SOC model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117538781A (en) |
-
2023
- 2023-11-21 CN CN202311556747.0A patent/CN117538781A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | State of health estimation based on modified Gaussian process regression for lithium-ion batteries | |
| Yao et al. | Fault detection of the connection of lithium-ion power batteries based on entropy for electric vehicles | |
| CN108089133B (en) | Battery pack consistency detection method and detection device for energy storage system | |
| CN108957331B (en) | Battery performance detection method and battery performance detection system | |
| CN113466706B (en) | Lithium battery echelon utilization residual life prediction method based on convolutional neural network | |
| WO2023221589A1 (en) | Method, apparatus and system for detecting battery health state | |
| CN115063418B (en) | Power battery temperature detection method based on image recognition | |
| CN109613446A (en) | A kind of aging of lithium battery detection method based on time series analysis | |
| CN115792637A (en) | Lithium battery health state estimation method | |
| CN111487532B (en) | Retired battery screening method and system based on analytic hierarchy process and entropy method | |
| CN114646888A (en) | Assessment method and system for capacity attenuation of power battery | |
| CN109669133A (en) | A kind of dynamic lithium battery lifetime data backstage mining analysis method | |
| Mawonou et al. | Li-ion battery pack SoC estimation for electric vehicles | |
| US11380036B2 (en) | Method of establishing visual images of models of battery status | |
| CN114184972A (en) | Method and equipment for automatically estimating SOH (state of health) of battery by combining data driving with electrochemical mechanism | |
| CN117233622A (en) | New energy automobile power lithium battery performance detection test method | |
| CN117538781A (en) | Intelligent detection device and method for energy storage battery based on SOC model | |
| CN110826645A (en) | Adaboost algorithm-based lithium battery retirement detection method and system | |
| CN115144681A (en) | Electric bicycle indoor charging monitoring method and device, electronic equipment and medium | |
| Liu et al. | Prediction method for battery self-discharge voltage drop based on pre-classifier | |
| CN114137430A (en) | Estimation method for residual life of retired lithium battery | |
| Yang et al. | Remaining Useful Life Prediction of Lithium-ion Batteries with Limited Degradation History Using Random Forest | |
| Gupta et al. | Machine Learning based SoC Estimation for Li-Ion Battery | |
| CN116859172B (en) | Blind-pluggable multi-lithium battery charging and discharging system and detection method | |
| CN117148165B (en) | Testing and analyzing method and system for polymer lithium ion battery |
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 |