CN117438631B - Intelligent production line of liquid cooling energy storage battery pack - Google Patents
Intelligent production line of liquid cooling energy storage battery pack Download PDFInfo
- Publication number
- CN117438631B CN117438631B CN202311388455.0A CN202311388455A CN117438631B CN 117438631 B CN117438631 B CN 117438631B CN 202311388455 A CN202311388455 A CN 202311388455A CN 117438631 B CN117438631 B CN 117438631B
- Authority
- CN
- China
- Prior art keywords
- mica sheet
- energy storage
- self
- feature map
- attention
- 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
- 238000004146 energy storage Methods 0.000 title claims abstract description 138
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 63
- 239000007788 liquid Substances 0.000 title claims abstract description 61
- 238000001816 cooling Methods 0.000 title claims abstract description 56
- 239000010445 mica Substances 0.000 claims abstract description 191
- 229910052618 mica group Inorganic materials 0.000 claims abstract description 191
- 230000007547 defect Effects 0.000 claims abstract description 51
- 238000001514 detection method Methods 0.000 claims abstract description 37
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 claims abstract description 16
- 229910052782 aluminium Inorganic materials 0.000 claims abstract description 16
- 238000003466 welding Methods 0.000 claims abstract description 16
- 238000001125 extrusion Methods 0.000 claims abstract description 14
- 230000000007 visual effect Effects 0.000 claims description 38
- 239000013598 vector Substances 0.000 claims description 28
- 238000005728 strengthening Methods 0.000 claims description 18
- 238000009826 distribution Methods 0.000 claims description 12
- 230000002950 deficient Effects 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 12
- 238000013527 convolutional neural network Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000000605 extraction Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 8
- 238000003908 quality control method Methods 0.000 description 8
- 230000008901 benefit Effects 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 238000011176 pooling Methods 0.000 description 6
- 238000010248 power generation Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 238000002360 preparation method Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 239000002826 coolant Substances 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000009413 insulation Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000017525 heat dissipation Effects 0.000 description 2
- 238000011056 performance test Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 1
- BNOODXBBXFZASF-UHFFFAOYSA-N [Na].[S] Chemical compound [Na].[S] BNOODXBBXFZASF-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000001627 detrimental effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003792 electrolyte Substances 0.000 description 1
- 238000011990 functional testing Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 229910001416 lithium ion Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 239000007773 negative electrode material Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 238000012858 packaging process Methods 0.000 description 1
- 239000007774 positive electrode material Substances 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/04—Construction or manufacture in general
- H01M10/0404—Machines for assembling batteries
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M50/00—Constructional details or processes of manufacture of the non-active parts of electrochemical cells other than fuel cells, e.g. hybrid cells
- H01M50/50—Current conducting connections for cells or batteries
- H01M50/502—Interconnectors for connecting terminals of adjacent batteries; Interconnectors for connecting cells outside a battery casing
- H01M50/514—Methods for interconnecting adjacent batteries or cells
- H01M50/516—Methods for interconnecting adjacent batteries or cells by welding, soldering or brazing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Secondary Cells (AREA)
Abstract
The invention discloses an intelligent production line of a liquid-cooled energy storage battery pack, which stores an energy storage battery in an energy storage roller line body; using the intelligent battery sorting equipment to grade the energy storage batteries to obtain the energy storage batteries after grade; performing defect detection on the mica sheet by using the defect detection equipment to obtain the mica sheet meeting the preset requirements; placing the energy storage batteries and the mica sheets meeting the preset requirements into a battery box one by one after the grading, and extruding by using the extrusion tooling table to obtain a battery pack; and carrying out aluminum row positioning, aluminum row welding and wire harness assembly on the battery pack by using the intelligent laser welder to obtain the liquid cooling energy storage battery pack. In this way, the performance and safety of the battery pack can be improved.
Description
Technical Field
The invention relates to the technical field of intelligent production, in particular to an intelligent production line of a liquid cooling energy storage battery pack.
Background
The liquid cooling energy storage battery pack is energy storage equipment for controlling the temperature of a battery by utilizing a liquid cooling system, and has the advantages of high power density, high efficiency, long service life and the like. The liquid cooling energy storage battery pack is widely applied to the fields of new energy automobiles, wind power generation, energy storage power stations and the like.
However, many challenges exist in the production process of liquid-cooled energy storage battery packs, such as battery grading, aluminum row welding, etc., which affect the performance and safety of the battery pack. In order to meet market demands, improving production efficiency and reducing cost, how to intelligentize the production process of the liquid-cooled energy storage battery pack is an important technical problem.
Disclosure of Invention
The embodiment of the invention provides an intelligent production line of a liquid-cooled energy storage battery pack, which stores energy storage batteries in an energy storage roller line body; using the intelligent battery sorting equipment to grade the energy storage batteries to obtain the energy storage batteries after grade; performing defect detection on the mica sheet by using the defect detection equipment to obtain the mica sheet meeting the preset requirements; placing the energy storage batteries and the mica sheets meeting the preset requirements into a battery box one by one after the grading, and extruding by using the extrusion tooling table to obtain a battery pack; and carrying out aluminum row positioning, aluminum row welding and wire harness assembly on the battery pack by using the intelligent laser welder to obtain the liquid cooling energy storage battery pack. In this way, the performance and safety of the battery pack can be improved.
The embodiment of the invention also provides an intelligent production line of the liquid cooling energy storage battery pack, which comprises the following steps: energy storage cylinder line body, intelligent battery sorting facilities, defect detection equipment, extrusion tool table and intelligent laser welding machine, its characterized in that, the intelligent production line of liquid cooling energy storage battery group operates with following step:
storing an energy storage battery in the energy storage roller wire body;
Using the intelligent battery sorting equipment to grade the energy storage batteries to obtain the energy storage batteries after grade;
Performing defect detection on the mica sheet by using the defect detection equipment to obtain the mica sheet meeting the preset requirements;
Placing the energy storage batteries and the mica sheets meeting the preset requirements into a battery box one by one after the grading, and extruding by using the extrusion tooling table to obtain a battery pack; and
And carrying out aluminum row positioning, aluminum row welding and wire harness assembly on the battery pack by using the intelligent laser welder to obtain the liquid cooling energy storage battery pack.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a flow chart of an intelligent production line of a liquid-cooled energy storage battery pack according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a system architecture of an intelligent production line of a liquid-cooled energy storage battery pack according to an embodiment of the present invention.
Fig. 3 is a flowchart illustrating the substeps of step 130 in the intelligent production line of the liquid-cooled energy storage battery pack according to an embodiment of the present invention.
Fig. 4 is a block diagram of an intelligent production system for a liquid-cooled energy storage battery pack according to an embodiment of the present invention.
Fig. 5 is an application scenario diagram of an intelligent production line of a liquid-cooled energy storage battery pack provided in an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
Unless defined otherwise, all technical and scientific terms used in the embodiments of the invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the present invention is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present invention.
In describing embodiments of the present invention, unless otherwise indicated and limited thereto, the term "connected" should be construed broadly, for example, it may be an electrical connection, or may be a communication between two elements, or may be a direct connection, or may be an indirect connection via an intermediate medium, and it will be understood by those skilled in the art that the specific meaning of the term may be interpreted according to circumstances.
It should be noted that, the term "first\second\third" related to the embodiment of the present invention is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that embodiments of the invention described herein may be practiced in sequences other than those illustrated or described herein.
With the continuous deepening of global carbon emission reduction trend, the new energy industry is vigorously developed. The world demand for energy is more intense, and who has mastered the energy has mastered more initiative. Therefore, the large-scale energy storage power station and the distributed energy storage are raised, the market pays more attention to the safety and energy efficiency of the energy storage, and the liquid cooling technology has the advantages of high heat conductivity, more uniform heat dissipation, lower energy consumption, small occupied area and the like, is more and more concerned by the industry, and the market acceptance is rapidly improved. Zhejiang Boshi new energy technology limited company is one of manufacturers of energy storage and liquid cooling system temperature control in early China, and is continuously put into talents, technologies, resources and the like in the liquid cooling industry, so that a liquid cooling and energy storage intelligent pipeline is generated on the premise of great importance.
This intelligent assembly line reaches the leading level of trade, and intelligent equipment operation is applied to many posts, greatly reduced cost of labor and effectively improve production efficiency, adds the CTP technique that the trade was led to run on liquid cooling energy storage system's basis, makes the product of this assembly line production reach advantages such as little volume under the strong joint hand, low energy consumption, heat conduction efficiency height. The technology progress is better promoted, and the energy storage industry system is increased.
The liquid cooling energy storage battery pack is energy storage equipment for controlling the temperature of a battery by utilizing a liquid cooling system and consists of a liquid cooling system and the battery pack. Liquid cooling systems are typically composed of components such as coolant, circulation pumps, radiators, and pipes. The function of the device is to conduct heat generated by the battery pack to the radiator through the circulating coolant, and then to radiate the heat to the external environment through the radiator, so as to keep the temperature of the battery pack within a safe range.
The battery pack is a core part of a liquid-cooled energy storage battery pack and is generally composed of a plurality of battery cells. The battery cells are the basic units of the battery pack, which are assembled into the battery pack in a serial or parallel manner, to provide desired voltage and capacity. Common battery types for liquid cooled energy storage batteries include lithium ion batteries, sodium sulfur batteries, and the like.
Liquid cooled energy storage batteries have several advantages over air cooled batteries. First, the liquid cooling system can more effectively control the temperature of the battery, and provide better heat management capability, thereby improving the working efficiency and the service life of the battery. Secondly, the liquid cooling system can realize higher power density, so that the battery pack has higher output power. In addition, the liquid cooling energy storage battery pack has better safety performance, and can better cope with abnormal conditions such as overheating of the battery.
The liquid cooling energy storage battery pack is widely applied to the fields of new energy automobiles, wind power generation, energy storage power stations and the like. In the new energy automobile, the liquid cooling energy storage battery pack can provide high power output and longer endurance mileage, and meets the requirements of the electric automobile on energy density and charge and discharge performance. In wind power generation and energy storage power stations, the liquid cooling energy storage battery pack can balance supply and demand differences of power grids and provide reliable energy storage and peak shaving functions.
The liquid cooling energy storage battery pack is one of core energy systems of the electric automobile, and because the electric automobile has requirements on high power output and long endurance mileage, the liquid cooling system can effectively control the temperature of the battery and provide better heat management capability, thereby improving the working efficiency and the service life of the battery. The liquid cooling energy storage battery pack can provide a reliable power source for the electric automobile and meet the requirements of users on high performance and long endurance.
The liquid cooling energy storage battery pack plays an important role in a wind power generation energy storage system, the wind power generation has instability, the liquid cooling energy storage battery pack can balance supply and demand differences of a power grid, store redundant electric energy and release the electric energy when needed, and reliable energy storage and peak shaving functions are provided. The liquid cooling system can ensure that the battery pack keeps working stably under the conditions of high temperature and high power output, and improves the reliability and performance of the wind power generation energy storage system.
The liquid cooling energy storage battery pack is also widely applied to an energy storage power station, and the energy storage power station can balance load fluctuation of a power grid and provide standby power and peak regulation and frequency modulation services. The liquid cooling energy storage battery pack has the characteristics of high power density and high efficiency, can quickly respond to the power grid demand, provides stable and reliable energy storage and discharge capacity, and contributes to the stable operation of the power system.
Liquid-cooled energy storage batteries have also found applications in other fields, such as solar energy storage systems, power grid backup power supplies, industrial energy storage, and the like. With the continuous development and popularization of application of new energy technology, the liquid cooling energy storage battery pack can play an important role in the energy field continuously, and support is provided for sustainable energy transformation and energy storage. The production process of the liquid-cooled energy storage battery pack generally comprises the following main steps: first, it is necessary to prepare a battery cell, which is a basic unit constituting a battery pack, and the preparation process of the battery cell includes the preparation of positive and negative electrode materials, the preparation of an electrolyte, and the assembly of the battery cell. These steps are typically performed in a clean room or clean environment to ensure the quality and performance of the battery. Then, after the preparation of the battery cells is completed, the design and assembly of the battery pack is performed, which involves the connection and assembly of the battery cells to form the desired voltage and capacity. During the assembly process, attention is paid to the arrangement and connection manner of the battery cells to ensure the performance and safety of the battery pack. Then, the liquid cooling energy storage battery pack needs to be integrated with a liquid cooling system to control the temperature of the battery, and the liquid cooling system comprises components such as a coolant, a circulating pump, a radiator, a pipeline and the like. During the integration process, the various components of the liquid cooling system need to be connected to the battery pack and ensure circulation of coolant and efficient operation of the radiator. Then, after the integration of the battery pack and the liquid cooling system is completed, functional test and debugging are required to ensure the normal operation of the battery pack and the effective operation of the liquid cooling system. In the testing and debugging process, the battery pack is subjected to charge and discharge testing, temperature control testing and the like so as to verify the performance and stability of the battery pack. Next, in the production process, quality control and inspection are performed to ensure the quality and safety of the battery pack, including appearance inspection, electrical performance test, safety performance test, etc. of the battery pack and the liquid cooling system. Only through strict quality control and inspection, the production of the liquid cooling energy storage battery pack meeting the requirements can be ensured. The final step is to package and prepare the finished liquid-cooled energy storage battery pack for shipment. During the packaging process, the battery pack needs to be properly protected from damage during transportation and storage. Meanwhile, related factory files and certificates are required to be prepared so as to ensure compliance and traceability of products.
In one embodiment of the present invention, fig. 1 is a flowchart of an intelligent production line of a liquid-cooled energy storage battery pack provided in the embodiment of the present invention. As shown in fig. 1, an intelligent production line of a liquid-cooled energy storage battery pack according to an embodiment of the present invention includes: energy storage cylinder line body, intelligent battery sorting facilities, defect detection equipment, extrusion tool table and intelligent laser welding machine, its characterized in that, the intelligent production line of liquid cooling energy storage battery group operates with following step: 110, storing an energy storage battery in the energy storage roller wire body; 120, grading the energy storage battery by using the intelligent battery sorting equipment to obtain the graded energy storage battery; 130, performing defect detection on the mica sheet by using the defect detection equipment to obtain the mica sheet meeting the preset requirements; 140, placing the energy storage batteries and the mica sheets meeting the preset requirements into a battery box one by one after the grading, and extruding by using the extrusion tooling table to obtain a battery pack; and 150, performing aluminum row positioning, aluminum row welding and wire harness assembly on the battery pack by using the intelligent laser welder to obtain the liquid cooling energy storage battery pack.
In one embodiment of the invention, the intelligent assembly line consists of an energy storage roller line body, intelligent battery sorting equipment, a battery transfer channel, an extrusion tool table, an intelligent laser welder and the like, and the intelligent management system can realize independent station operation and combined operation of each station of the assembly line and can adapt to various specifications and types of liquid cooling energy storage pack boxes.
The functional advantages of this intelligent assembly line include:
1. The intelligent sorting of the battery cells greatly improves the consistency of the module configuration.
2. The CTP technology is added, so that the liquid cooling PACK has higher energy integration and more uniform heat dissipation under the same volume, and meanwhile, the module manufacturing procedure is greatly reduced, and the production line productivity is greatly improved.
3. The visual recognition system is added, so that the failure rate of the module is greatly reduced, the position of the module is scanned and positioned, the preparation work is carried out for the subsequent welding process, the repeated operation is reduced, and the productivity is improved
4. The high-power laser welding equipment can adapt to welding work of various materials with various thicknesses, and is automatically calibrated and positioned, thereby being safer and more efficient
5. The intelligent control of the whole line system can realize single-station, multi-station coordination configuration and adaptation to various product specifications
Then, most liquid cooling production lines on the market of the present order are reformed transform by original forced air cooling line, adopt the module form to install, compare the expense manual work, production efficiency is lower, can produce multichannel transport process in the middle, has great potential safety hazard. The traditional production line has lower intelligent degree and low productivity, and the manual operation has larger quality potential safety hazard. Most of the existing liquid cooling energy storage PACKs are 1P48S and 1P52S, the length of the commercial module type 1P52S is basically more than 1200mm, the internal width of the container is 2352mm, and the application of the standard container without the passageway double door cannot be met.
The invention discloses a liquid cooling energy storage battery PACK line CTP scheme assembly line, which relates to the field of energy storage equipment and mainly comprises an energy storage roller line body, intelligent battery sorting equipment, a battery transfer channel, an extrusion tooling table, an intelligent laser welder and the like
The intelligent battery sorting equipment can divide the battery into 4 gears according to gears by detecting the internal resistance voltage of the battery, and then inputs the battery into the corresponding channel through the intelligent transfer equipment, so that the configuration consistency of the battery pack is ensured.
The CTP technology is that batteries and mica sheets are placed into a battery box one by one, and the battery pack is integrally formed through an extrusion tool.
The CCS technology is characterized in that an insulating PC sheet is subjected to plastic suction molding, a battery is connected with an aluminum row and a temperature control wire harness is collected and integrated, and the working efficiency of a production line is greatly improved.
The intelligent welding machine automatically recognizes and positions the battery cell polar columns through a vision capturing system, forms a spectrum, is matched with a CCS to tightly connect the battery cells in sequence, and completes the procedures of aluminum row positioning, aluminum row welding, wire harness assembly and the like at one time.
The upper and lower intelligent circulation production line is matched with the infrared induction and vision system through the lifting table, so that the production line can automatically and reciprocally work.
The intelligent control system controls each station through the PLC, so that single-station operation of the assembly line can be realized, multiple working stations can be combined to operate, and the intelligent control system is suitable for assembly of each machine type and iterative use of subsequent products.
In particular, mica sheets play a role in heat insulation and insulation in the liquid-cooled energy storage battery pack, and are important to the performance and safety of the battery pack. Specifically, if the mica sheet has defects such as cracks, bubbles, impurities, etc., the insulation performance of the mica sheet may be reduced, and even a fault may be induced during use, resulting in degradation of the performance of the battery pack or potential safety hazard. Furthermore, if the quality of the mica sheet is unstable, undetected mica sheets may be used to produce a battery pack, resulting in increased variability between products. This may result in some battery packs having good performance while others have poor performance, which is detrimental to uniform quality control and market competitiveness of the product. However, conventional mica sheet detection methods may require manual operations, are time consuming and are susceptible to the level of skill and subjective factors of the operator. In contrast, the technical concept of the invention is to automatically detect defects of mica sheets by utilizing an artificial intelligence technology and a visual detection technology based on deep learning.
Fig. 2 is a schematic diagram of a system architecture of an intelligent production line of a liquid-cooled energy storage battery pack according to an embodiment of the present invention. Fig. 3 is a flowchart illustrating the substeps of step 130 in the intelligent production line of the liquid-cooled energy storage battery pack according to an embodiment of the present invention. As shown in fig. 2 and 3, performing defect detection on the mica sheet by using the defect detection device to obtain a mica sheet meeting predetermined requirements, including: 131, acquiring a visual image of the mica sheet acquired by a camera; 132, extracting shallow layer features, middle layer features and deep layer features of the visual image of the mica sheet to obtain a mica sheet shallow layer feature map, a mica sheet middle layer feature map and a mica sheet deep layer feature map; 133, performing feature interaction on the mica sheet shallow feature map, the mica sheet middle layer feature map and the mica sheet deep feature map to obtain a self-attention enhanced mica sheet multi-scale image feature map; and, 134, determining whether the mica sheet is defective based on the self-care enhanced mica sheet multi-scale image feature map.
In step 131, proper mounting and calibration of the camera is ensured to obtain a clear, accurate visual image of the mica sheet. The attention points comprise selection of the position and the angle of a camera, control of illumination conditions and stability of image acquisition, and acquisition of high-quality mica sheet visual images is a basis for subsequent analysis and detection.
In the step 132, features of different levels are extracted from the mica sheet visual image using a deep learning method, such as Convolutional Neural Network (CNN). Shallow features typically include low-level features such as edges, textures, etc., middle-level features include higher-level shape and structure information, while deep features contain more abstract and semantic features, extraction of which can be done through pre-trained CNN models, or custom network design and training according to specific tasks.
In the step 133, the different levels of features of the mica sheet are interacted and integrated using a self-attention mechanism (self-attention) to obtain a self-attention enhanced multi-scale image feature map of the mica sheet. The self-attention mechanism can learn the relativity and importance among the features and perform weighted fusion on the features so as to improve the expression capacity and the distinguishing degree of the features. Therefore, the local and global information of the mica sheet can be better captured, and the accuracy and the robustness of defect detection are improved.
In step 134, a classification or detection algorithm, such as a Support Vector Machine (SVM), convolutional Neural Network (CNN), or object detection algorithm (e.g., faster R-CNN, YOLO, etc.), is used to detect defects on the mica sheet based on the self-care enhanced multi-scale image feature map of the mica sheet. Through training the model, can distinguish normal and defective mica sheet to confirm whether there is the defect, can help improving production efficiency, reduce the work load of manual detection, and improve product quality and uniformity.
Based on this, in the technical scheme of the invention, the implementation process of using the intelligent battery sorting equipment to sort the energy storage batteries to obtain the energy storage batteries after being sorted comprises the following steps: first, a visual image of a mica sheet acquired by a camera is acquired.
The method is characterized in that the step of acquiring the visual image of the mica sheet acquired by the camera is one of key steps in the production process of the liquid-cooled energy-storage battery pack, and the step is used for acquiring the visual information of the mica sheet and providing a basis for subsequent defect detection and quality control.
Visual images of the mica sheet are acquired through the camera, appearance characteristics and detail information of the mica sheet can be acquired in real time, and the images can contain the visual characteristics of the mica sheet such as shape, color, texture and the like, and possible defects or anomalies. By analyzing and processing these visual images, it is possible to help detect and determine whether a mica sheet has defects, thereby evaluating and controlling the quality of the product.
Defects such as cracks, breakage, foreign matters and the like on the mica sheet can be detected and identified through analysis and processing of the visual images of the mica sheet, and whether defects exist can be accurately judged through comparison of visual characteristic differences of normal mica sheets and defective mica sheets. Defects in mica sheets can negatively impact the performance and safety of liquid-cooled energy storage batteries. The defective mica sheet can be screened and removed in the production process by analyzing and detecting the visual image of the mica sheet, so that the quality and the reliability of the product are improved. The visual images of the mica sheets are acquired by using the camera, so that automatic defect detection and quality control can be realized, and the production efficiency can be improved compared with manual inspection. By rapidly and accurately acquiring the visual information of the mica sheet, high-speed continuous image processing and analysis can be realized, so that the production speed is increased.
The acquisition of the visual image of the mica sheet acquired by the camera is an important step in the production process of the liquid cooling energy storage battery pack, plays a key role in determining whether the mica sheet has defects or not, and can realize automatic defect detection and quality control by analyzing and processing the visual image of the mica sheet, thereby improving the production efficiency and the product quality.
And then, extracting the shallow layer characteristics, the middle layer characteristics and the deep layer characteristics of the visual image of the mica sheet to obtain a mica sheet shallow layer characteristic diagram, a mica sheet middle layer characteristic diagram and a mica sheet deep layer characteristic diagram. It should be appreciated that shallow features can capture detailed information of the image, such as edges, textures, etc., to help distinguish between the surface structure and defect type of the mica sheet; the middle layer features can capture local information of the image, such as shape, contour and the like, and help to locate the defect position and range of the mica sheet; deep features can capture global information of the image, such as semantics, scenes, etc., and help to understand the overall quality and properties of the mica sheet.
Shallow features typically include low-level image features, such as edges, textures, colors, etc., that are extracted from the original pixel information of the input image, with a low level of abstraction. Shallow features may be sufficient for some simple image processing tasks, but may not be sufficient to provide adequate expressive power and discrimination in complex tasks.
The middle layer features are feature representations extracted from the middle layer of the deep neural network, and have higher abstract degree and semantic meaning than the shallow layer features. The mid-level features may capture higher levels of shape, structure, and local information while still retaining some spatial resolution. Middle layer features exhibit good performance in many computer vision tasks, such as object detection, image segmentation, and the like.
Deep features are feature representations extracted in deeper layers of the deep neural network, and the features have higher abstract degrees and semantic meanings, so that more complex image features and semantic information can be captured. Deep features are generally extracted in the latter layers of the network, and through multiple nonlinear transformation and pooling operations, have a larger receptive field and a higher level of semantic information. Deep features exhibit great expressive power and robustness in many computer vision tasks.
In extracting visual features of the mica sheet, a deep neural network model, such as a Convolutional Neural Network (CNN), may be used to sequentially extract shallow, middle and deep features of the mica sheet from shallow to deep by layer-by-layer feature extraction. These features can be used for subsequent tasks such as feature interaction, defect detection, quality control, etc., to enhance the understanding and analysis capabilities of the mica sheet.
In a specific example of the invention, the process of extracting the shallow layer feature, the middle layer feature and the deep layer feature of the visual image of the mica sheet to obtain a mica sheet shallow layer feature map, a mica sheet middle layer feature map and a mica sheet deep layer feature map is implemented by passing the visual image of the mica sheet through an image multi-scale feature extractor based on a pyramid network to obtain a mica sheet shallow layer feature map, a mica sheet middle layer feature map and a mica sheet deep layer feature map.
A pyramid network is a network structure for multi-scale feature extraction of images by downsampling (or upsampling) and feature extraction multiple times on different scales of an input image to obtain feature representations of the image at different levels. Such multi-scale feature representations may better capture details and overall information of the image, improving understanding and expressive power of the image content.
The basic idea of a pyramid network is to enable the network to perform feature extraction in different receptive fields by constructing feature maps of multiple scales. In image processing, the pyramid network structure includes:
the pyramid convolution network extracts features of different scales by performing convolution operations on the different scales. Typically, the bottom layer of the network corresponds to the original input image, while the upper layer corresponds to the downsampled image, and the feature map of each layer may extract higher level features through convolution and pooling operations.
The pyramid pooling network obtains features of different scales by pooling operations on different scales. On each scale, the network divides the input image into a plurality of areas, and performs pooling operation on each area to obtain a feature vector with a fixed length. These feature vectors may then be stitched or combined to form a feature representation of the entire image.
The visual image of the mica sheet can be input into a network through an image multi-scale feature extractor based on a pyramid network, and shallow layer features, middle layer features and deep layer features of the mica sheet can be extracted on different scales. The specific implementation process comprises the following steps: the visual image of the mica sheet is taken as an input and can be a color image or a gray image. Through the pyramid network structure, the input image is subjected to downsampling and feature extraction for multiple times on different scales, and the feature extraction on each scale can use convolution operation, pooling operation or other feature extraction methods. On each scale, the image representation subjected to feature extraction is converted into a feature map, the shallow feature map corresponds to a lower receptive field and abstraction level, the middle feature map corresponds to a medium receptive field and abstraction level, and the deep feature map corresponds to a higher receptive field and abstraction level. And taking the obtained shallow layer characteristic diagram, middle layer characteristic diagram and deep layer characteristic diagram as the output of a network for subsequent defect detection, quality control or other tasks.
Through the image multi-scale feature extractor of the pyramid network, the feature representation of the mica sheet on different levels can be obtained, so that more comprehensive and rich visual information is provided, and whether the mica sheet has defects or not can be judged more accurately.
And then, carrying out feature interaction on the mica sheet shallow feature map, the mica sheet middle layer feature map and the mica sheet deep feature map to obtain a self-attention reinforced mica sheet multi-scale image feature map. That is, the multi-scale feature distribution of the mica sheet is fully utilized, and the three are polymerized and feature expression enhanced, so that the self-attention enhanced multi-scale image feature map of the mica sheet has more excellent feature expression capability.
In a specific example of the present invention, the encoding process for performing feature interaction on the shallow feature map of the mica sheet, the middle feature map of the mica sheet, and the deep feature map of the mica sheet to obtain the self-attention enhanced multi-scale image feature map of the mica sheet includes: firstly, the shallow layer feature map of the mica sheet, the middle layer feature map of the mica sheet and the deep layer feature map of the mica sheet are aggregated along the channel dimension to obtain a multi-scale image feature map of the mica sheet; and then the multi-scale image feature map of the mica sheet is improved by a self-attention module to obtain a multi-scale image feature map of the self-attention reinforced mica sheet.
In particular, in the solution of the present invention, it is considered that the conventional self-attention model, although being able to interact well with features of different spatial locations, depends on the input itself. Wherein pairs K, Q of features are learned independently without exploring the relationship between them. This severely limits the self-attention learning capabilities for feature maps in visual characterization learning. To alleviate this problem, improvements to the self-attention module, i.e., enhancement of the feature expression of mica sheets by the improved self-attention module, are desired.
Specifically, in the encoding process of the improved self-attention module, K, Q features are spliced, the starting point is to make full use of information among K, Q features, self-attention learning is effectively promoted, and the representing capability of the mica sheet multi-scale image feature map is enhanced. More specifically, improvements to the self-attention model are presented in: the input features are converted into Q, K, V through linear transformation by three different weight matrixes, dot product operation is not carried out between Q and K, splicing operation is carried out on the two weight matrixes, normalization processing is carried out on the two weight matrixes, correlation operation is carried out on the two weight matrixes and the value of the position with the largest correlation is removed from a value library, residual operation is carried out on the obtained characteristic value and the value of K, the last Softmax layer of a traditional self-attention model is removed, design of a residual network is used for reference, and the input characteristic K value is fused with an attention matrix output by the residual network to obtain the final characteristic value. The improvement can reduce the calculated amount, increase the learning of the context information, strengthen the connection between local features, remove redundant information and strengthen the visual representation capability.
In one embodiment of the present invention, determining whether the mica sheet is defective based on the self-care enhanced mica sheet multi-scale image feature map includes: expanding the self-attention-strengthening mica sheet multi-scale image feature map to obtain a self-attention-strengthening mica sheet multi-scale image feature vector; performing feature distribution optimization on the self-attention-strengthening mica sheet multi-scale image feature vector to obtain an optimized self-attention-strengthening mica sheet multi-scale image feature vector; and passing the optimized self-attention-strengthening mica sheet multi-scale image feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the mica sheet has defects or not.
In the technical scheme of the application, when the visual image of the mica sheet passes through the image multi-scale feature extractor based on the pyramid network, the shallow layer feature image of the mica sheet, the middle layer feature image of the mica sheet and the deep layer feature image of the mica sheet can express image semantic features at different depths based on different scales of the pyramid network, so that when the multi-scale image feature image of the mica sheet is obtained by improving a self-attention module, each feature matrix of the multi-scale image feature image of the mica sheet can be weighted based on a self-attention mechanism to strengthen the overall feature distribution of some feature matrices of the multi-scale image feature image of the self-attention reinforced mica sheet. Here, if the image semantic features of each feature matrix of the multi-scale image feature map of the mica sheet are represented as foreground object features, background distribution noise is introduced while performing self-attention weighted enhancement of the image semantic features of different depths and different scales, and since the improved self-attention module performs vector-matrix aggregation high-rank distribution representation, image semantic space heterogeneous distribution of the high-dimensional features of each feature matrix of the multi-scale image feature map of the self-attention enhanced mica sheet based on different feature scales, feature depths and attention weights is also introduced, so that image semantic space probability density mapping errors of the image semantic features of each feature matrix of the multi-scale image feature map of the self-attention enhanced mica sheet are caused, which may cause poor convergence of probability density distribution of regression probability of each feature value of the multi-scale image feature map of the self-attention enhanced mica sheet when the multi-scale image feature map of the self-attention enhanced mica sheet is subjected to class probability regression mapping by a classifier, and affect accuracy of classification results obtained by the classifier.
Therefore, preferably, when the self-attention enhanced mica sheet multi-scale image feature map is subjected to classification training through a classifier, each feature value of the self-attention enhanced mica sheet multi-scale image feature vector obtained by expanding the self-attention enhanced mica sheet multi-scale image feature map is optimized, which is specifically expressed as:
Wherein V is the multi-scale image feature vector of the self-attention enhanced mica sheet, V i and V j are the ith and jth feature values of the multi-scale image feature vector of the self-attention enhanced mica sheet, and Is the global feature mean of the self-attention enhanced mica sheet multiscale image feature vector, and v' i is the ith feature value of the optimized self-attention enhanced mica sheet multiscale image feature vector.
Specifically, for the local probability density mismatch of probability density distribution in a probability space caused by image semantic space probability density mapping errors of the self-attention-strengthening mica sheet multi-scale image feature vector in a high-dimensional feature space, global self-consistent relation of coding behaviors of the high-dimensional feature manifold of the self-attention-strengthening mica sheet multi-scale image feature vector in the probability space is simulated by regularized global self-consistent class coding so as to adjust error landscapes of feature manifolds in a high-dimensional open space domain, self-consistent matching class coding of the high-dimensional feature manifold of the self-attention-strengthening mica sheet multi-scale image feature vector to explicit probability space embedding is realized, and therefore the convergence of probability density distribution of regression probability of the self-attention-strengthening mica sheet multi-scale image feature vector is improved, and the accuracy of classification results obtained by a classifier is improved.
Further, the optimized self-attention-strengthening mica sheet multi-scale image feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the mica sheet has defects.
The optimized self-attention mechanism is applied to the multi-scale image feature map of the mica sheet, and classification is carried out by combining with the classifier, so that the accuracy and the effect of the defect detection of the mica sheet can be effectively improved. The multi-scale feature map enhanced by the self-attention mechanism is input into a classifier for classification. The classifier may be a conventional machine learning algorithm, such as a Support Vector Machine (SVM) or Random Forest (Random Forest), or a deep learning model, such as a Convolutional Neural Network (CNN) or a Recurrent Neural Network (RNN). And obtaining a classification result of whether the mica sheet has defects or not according to the output of the classifier. The classification result may be a two-classification (defect present/defect not present) or a multi-classification (different types of defects present).
In summary, an intelligent production line of a liquid-cooled energy storage battery pack according to an embodiment of the present invention is illustrated, which utilizes an artificial intelligence technology and a visual detection technology based on deep learning to automatically detect defects of mica sheets.
Fig. 4 is a block diagram of an intelligent production system for a liquid-cooled energy storage battery pack according to an embodiment of the present invention. As shown in fig. 4, the intelligent production system 200 of the liquid-cooled energy storage battery pack includes: energy storage cylinder line body, intelligent battery sorting facilities, defect detection equipment, extrusion tool table and intelligent laser welding machine, its characterized in that, the intelligent production system of liquid cooling energy storage battery group operates with following module: a storage module 210, configured to store an energy storage battery in the energy storage roller line body; a grading module 220, configured to grade the energy storage battery by using the intelligent battery sorting device to obtain a graded energy storage battery; a defect detection module 230, configured to perform defect detection on the mica sheet using the defect detection device to obtain a mica sheet that meets a predetermined requirement; the extrusion module 240 is configured to put the energy storage battery and the mica sheets meeting the predetermined requirements into a battery box one by one after the energy storage battery is graded, and extrude the battery box by using the extrusion tooling table to obtain a battery pack; and an assembly module 250, configured to use the intelligent laser welder to perform aluminum row positioning, aluminum row welding and wire harness assembly on the battery pack to obtain a liquid cooling energy storage battery pack.
It will be appreciated by those skilled in the art that the specific operation of the steps in the above-described intelligent production system for a liquid-cooled energy storage battery pack has been described in detail in the above description of the intelligent production line for a liquid-cooled energy storage battery pack with reference to fig. 1 to 3, and thus, repeated descriptions thereof will be omitted.
As described above, the intelligent production system 200 of the liquid-cooled energy storage battery pack according to the embodiment of the present invention may be implemented in various terminal devices, for example, a server for intelligent production of the liquid-cooled energy storage battery pack, or the like. In one example, the intelligent production system 200 of the liquid-cooled energy storage battery pack according to an embodiment of the present invention may be integrated into the terminal device as a software module and/or hardware module. For example, the intelligent production system 200 of the liquid-cooled energy storage battery pack may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the intelligent production system 200 of the liquid-cooled energy storage battery pack can also be one of a plurality of hardware modules of the terminal device.
Alternatively, in another example, the intelligent production system 200 of the liquid-cooled energy storage battery pack and the terminal device may be separate devices, and the intelligent production system 200 of the liquid-cooled energy storage battery pack may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information in a agreed data format.
Fig. 5 is an application scenario diagram of an intelligent production line of a liquid-cooled energy storage battery pack provided in an embodiment of the present invention. As shown in fig. 5, in the application scene, first, a visual image (e.g., C as illustrated in fig. 5) of the mica sheet (e.g., M as illustrated in fig. 5) acquired by a camera is acquired; the acquired visual image of the mica sheet is then input into a server (e.g., S as illustrated in fig. 5) that deploys an intelligent production algorithm for the liquid-cooled energy storage battery pack, wherein the server is capable of processing the visual image of the mica sheet based on the intelligent production algorithm for the liquid-cooled energy storage battery pack to determine whether the mica sheet is defective.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (5)
1.An intelligent production line for a liquid-cooled energy storage battery pack, comprising: energy storage cylinder line body, intelligent battery sorting facilities, defect detection equipment, extrusion tool table and intelligent laser welding machine, its characterized in that, the intelligent production line of liquid cooling energy storage battery group operates with following step:
storing an energy storage battery in the energy storage roller wire body;
Using the intelligent battery sorting equipment to grade the energy storage batteries to obtain the energy storage batteries after grade;
Performing defect detection on the mica sheet by using the defect detection equipment to obtain the mica sheet meeting the preset requirements;
Placing the energy storage batteries and the mica sheets meeting the preset requirements into a battery box one by one after the grading, and extruding by using the extrusion tooling table to obtain a battery pack; and
Performing aluminum row positioning, aluminum row welding and wire harness assembly on the battery pack by using the intelligent laser welder to obtain a liquid cooling energy storage battery pack;
The defect detection device is used for carrying out defect detection on the mica sheet to obtain the mica sheet meeting the preset requirements, and the defect detection device comprises the following steps:
Acquiring a visual image of the mica sheet acquired by a camera;
extracting shallow layer features, middle layer features and deep layer features of the visual image of the mica sheet to obtain a mica sheet shallow layer feature map, a mica sheet middle layer feature map and a mica sheet deep layer feature map;
Performing feature interaction on the mica sheet shallow feature map, the mica sheet middle layer feature map and the mica sheet deep feature map to obtain a self-attention enhanced mica sheet multi-scale image feature map; and
And determining whether the mica sheet has defects or not based on the self-attention enhanced mica sheet multi-scale image feature map.
2. The intelligent production line of a liquid cooled energy storage battery of claim 1, wherein extracting the shallow, middle, and deep features of the visual image of the mica sheet to obtain a mica sheet shallow, middle, and deep feature map comprises:
And passing the visual image of the mica sheet through an image multi-scale feature extractor based on a pyramid network to obtain the shallow feature map of the mica sheet, the middle layer feature map of the mica sheet and the deep feature map of the mica sheet.
3. The intelligent production line of a liquid cooled energy storage battery of claim 2, wherein the feature interactions of the mica sheet shallow feature map, the mica sheet middle layer feature map, and the mica sheet deep feature map are performed to obtain a self-care enhanced mica sheet multi-scale image feature map, comprising:
The shallow layer feature map, the middle layer feature map and the deep layer feature map of the mica sheet are aggregated along the channel dimension to obtain a multi-scale image feature map of the mica sheet; and
And the self-attention strengthening mica sheet multi-scale image characteristic map is obtained by improving a self-attention module.
4. The intelligent production line for a liquid cooled energy storage battery of claim 3, wherein determining whether the mica sheet is defective based on the self-care enhanced mica sheet multi-scale image feature map comprises:
expanding the self-attention-strengthening mica sheet multi-scale image feature map to obtain a self-attention-strengthening mica sheet multi-scale image feature vector;
performing feature distribution optimization on the self-attention-strengthening mica sheet multi-scale image feature vector to obtain an optimized self-attention-strengthening mica sheet multi-scale image feature vector; and
And passing the optimized self-attention-strengthening mica sheet multi-scale image feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the mica sheet has defects or not.
5. The intelligent production line of a liquid cooled energy storage battery of claim 4, wherein performing feature distribution optimization on the self-attention enhanced mica sheet multiscale image feature vector to obtain an optimized self-attention enhanced mica sheet multiscale image feature vector comprises: performing feature distribution optimization on the self-attention-strengthening mica sheet multi-scale image feature vector by using the following optimization formula to obtain the optimized self-attention-strengthening mica sheet multi-scale image feature vector;
Wherein, the optimization formula is:
Wherein/> Is the self-attention enhanced mica sheet multiscale image feature vector,/>And/>Is the/>, of the self-attention enhanced mica sheet multiscale image feature vectorAnd/>Individual eigenvalues, and/>Is the global feature mean of the self-attention enhanced mica sheet multi-scale image feature vector,Is the/>, of the optimized self-care enhanced mica sheet multiscale image feature vectorAnd characteristic values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311388455.0A CN117438631B (en) | 2023-10-24 | 2023-10-24 | Intelligent production line of liquid cooling energy storage battery pack |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311388455.0A CN117438631B (en) | 2023-10-24 | 2023-10-24 | Intelligent production line of liquid cooling energy storage battery pack |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117438631A CN117438631A (en) | 2024-01-23 |
| CN117438631B true CN117438631B (en) | 2024-06-04 |
Family
ID=89552808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311388455.0A Active CN117438631B (en) | 2023-10-24 | 2023-10-24 | Intelligent production line of liquid cooling energy storage battery pack |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117438631B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1186900A (en) * | 1997-09-12 | 1999-03-30 | Ngk Insulators Ltd | Battery |
| CN109585935A (en) * | 2018-11-28 | 2019-04-05 | 江西安驰新能源科技有限公司 | A kind of packaging technology of lithium battery mould group |
| CN110459792A (en) * | 2018-05-07 | 2019-11-15 | 通用电气公司 | Quality Monitoring Control System and quality control method for fuel cell manufacturing line |
| CN114744271A (en) * | 2022-04-07 | 2022-07-12 | 江苏远信储能技术有限公司 | Energy storage module annular production line |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112242550B (en) * | 2020-10-30 | 2024-05-31 | 广东邦普循环科技有限公司 | Automatic production line for gradient utilization of power batteries |
| CN114663436A (en) * | 2022-05-25 | 2022-06-24 | 南京航空航天大学 | Cross-scale defect detection method based on deep learning |
-
2023
- 2023-10-24 CN CN202311388455.0A patent/CN117438631B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1186900A (en) * | 1997-09-12 | 1999-03-30 | Ngk Insulators Ltd | Battery |
| CN110459792A (en) * | 2018-05-07 | 2019-11-15 | 通用电气公司 | Quality Monitoring Control System and quality control method for fuel cell manufacturing line |
| CN109585935A (en) * | 2018-11-28 | 2019-04-05 | 江西安驰新能源科技有限公司 | A kind of packaging technology of lithium battery mould group |
| CN114744271A (en) * | 2022-04-07 | 2022-07-12 | 江苏远信储能技术有限公司 | Energy storage module annular production line |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117438631A (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110033453B (en) | Power transmission and transformation line insulator aerial image fault detection method based on improved YOLOv3 | |
| CN107886133A (en) | A kind of underground piping defect inspection method based on deep learning | |
| CN111444939B (en) | Small-scale equipment component detection method based on weak supervision cooperative learning in open scene of power field | |
| CN111784633A (en) | Insulator defect automatic detection algorithm for power inspection video | |
| CN114240891A (en) | Welding spot quality identification method fusing knowledge graph and graph convolution neural network | |
| Wang et al. | Research on image recognition of insulators based on YOLO algorithm | |
| US20210182615A1 (en) | Alexnet-based insulator self-explosion recognition method | |
| CN112258459A (en) | Lithium battery defect detection method based on integrated deep learning | |
| CN116026839A (en) | Detection device for surface defects of vehicle-mounted battery and intelligent detection method thereof | |
| CN113837994B (en) | Photovoltaic panel defect diagnosis method based on edge detection convolutional neural network | |
| CN115469184A (en) | New energy transmission line fault identification method based on convolutional network | |
| CN114693096A (en) | Power battery cascade utilization decision method and system based on scene matching | |
| CN117438631B (en) | Intelligent production line of liquid cooling energy storage battery pack | |
| CN113536944A (en) | Distribution line inspection data identification and analysis method based on image identification | |
| CN116503398B (en) | Insulator pollution flashover detection method and device, electronic equipment and storage medium | |
| CN111091533B (en) | Battery piece EL defect detection method based on improved SSD algorithm | |
| CN112967296A (en) | Point cloud dynamic region graph convolution method, classification method and segmentation method | |
| Cui et al. | Machine learning approach for solving inconsistency problems of Li‐ion batteries during the manufacturing stage | |
| CN116188374A (en) | Socket detection method, device, computer equipment and storage medium | |
| CN114549392B (en) | Color difference detection method, device and equipment for solar cell and computer medium | |
| CN113284103A (en) | Substation equipment defect online detection system based on space transformation fast R-CNN model | |
| CN112036472A (en) | Visual image classification method and system for power system | |
| CN111797925B (en) | Visual image classification method and device for power system | |
| Wang et al. | Photovoltaic Panel Intelligent Detection Method Based on Improved Faster-RCNN | |
| Shanbin et al. | Electrical cabinet wiring detection method based on improved yolov5 and pp-ocrv3 |
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 |