Auxiliary disassembly method, apparatus, system, device, and medium for power battery
The projected AR system for power battery disassembly addresses safety and efficiency issues by offering real-time, adaptive guidance and automated recipe generation, enhancing safety and efficiency in the disassembly of diverse battery types.
Patent Information
- Application Number
- PCT/CN2024/115217
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2026-03-05
AI Technical Summary
The disassembly of power batteries, particularly retired EV battery packs, is fraught with risks such as electric shock, physical injury, environmental pollution, and fire hazards due to the lack of effective technological assistance, unpredictable battery types, and the absence of real-time human intention estimation and adaptive learning in projected augmented reality (AR) systems.
A projected AR system for power battery disassembly that includes real-time component detection, human intention estimation, and adaptive learning to provide dynamic, user-friendly guidance, employing high-resolution projectors for color-coded instructions, real-time feedback, and automated recipe generation to ensure safe and efficient disassembly.
Enhances safety by preventing accidents and improving efficiency by providing real-time, adaptive guidance that adjusts to varying battery types, reduces cognitive load, and minimizes errors through proactive safety alerts and streamlined workflows.
Smart Images

Figure CN2024115217_05032026_PF_FP_ABST
Abstract
Description
Auxiliary disassembly method, apparatus, system, device, and medium for power batteryFIELD
[0001] The present disclosure relates to the technical field of batteries, in particular to an auxiliary disassembly method, apparatus, system, device, and medium for power battery.BACKGROUND
[0002] The recycling of power batteries is not only related to the development prospect of the new energy vehicle industry, but also an effective means to resolve the resource bottleneck.
[0003] There are high risks during the disassembly of power batteries mainly including electric shock risk, physical injury, environmental pollution, explosion and fire risk.SUMMARY
[0004] Embodiments of the present disclosure propose an auxiliary disassembly method, apparatus, system, device, and medium for power battery.
[0005] In a first aspect, an auxiliary disassembly method for power battery is provided. The method includes:
[0006] obtaining a first real-time image of a power battery;
[0007] determining a disassembly sequence of the power battery;
[0008] determining real-time remaining components of the power battery based on the first real-time image;
[0009] determining a component currently to be disassembled from the real-time remaining components based on the disassembly sequence; and
[0010] presenting first information indicating a worker to disassemble the component currently to be disassembled, in a projected manner on a surface of the component currently to be disassembled.
[0011] In a second aspect, an auxiliary disassembly system for power battery is provided. The system includes:
[0012] a first camera, configured to acquire first real-time image a power battery;
[0013] a controller, configured to determine a disassembly sequence of the power battery, determine real-time remaining components of the power battery based on the first real-time image, determine a component currently to be disassembled from the real-time remaining components based on the disassembly sequence, and generate first information indicating a worker to disassemble the component currently to be disassembled;
[0014] a projection device, configured to present the first information in a projected manner on a surface of the component currently to be disassembled.
[0015] In a third aspect, an auxiliary disassembly apparatus for power battery is provided. The apparatus includes:
[0016] an obtaining module, configured to obtain a first real-time image of a power battery;
[0017] a first determining module, configured to determine a disassembly sequence of the power battery;
[0018] a second determining module, configured to determine real-time remaining components of the power battery based on the first real-time image;
[0019] a third determining module, configured to determine a component currently to be disassembled from the real-time remaining components based on the disassembly sequence; and
[0020] a presenting module, configured to present first information indicating a worker to disassemble the component currently to be disassembled, in a projected manner on a surface of the component currently to be disassembled.
[0021] In a fourth aspect, an electronic device is provided. The electronic device comprising a processor and a memory, wherein an application program executable by the processor is stored in the memory for causing the processor to execute an auxiliary disassembly method for power battery as described in any of the above.
[0022] In a fifth aspect, a computer-readable medium comprising computer-readable instructions stored thereon is provided, wherein the computer-readable instructions for executing an auxiliary disassembly method for power battery as described in any of the above.
[0023] In a sixth aspect, a computer program product comprising a computer program, when the computer program is executed by a processor for executing an auxiliary disassembly method for power battery as described in any of the above.
[0024] According to the above technical solutions, obtaining a first real-time image of a power battery; determining a disassembly sequence of the power battery; determining real-time remaining components of the power battery based on the first real-time image; determining a component currently to be disassembled from the real-time remaining components based on the disassembly sequence; and presenting first information indicating a worker to disassemble the component currently to be disassembled, in a projected manner on a surface of the component currently to be disassembled. Dynamic, real-time and user-friendly guidance for disassembly is provided, which also improves the disassembly efficiency and safety.BRIEF DESCRIPTION OF THE DRAWINGS
[0025] To make technical solutions of examples of the present disclosure clearer, accompanying drawings to be used in description of the examples will be simply introduced hereinafter. Obviously, the accompanying drawings to be described hereinafter are only some examples of the present disclosure. Those skilled in the art may obtain other drawings according to these accompanying drawings without creative labor.
[0026] Fig. 1 is an exemplary flow chart of auxiliary disassembly method for power battery according to an embodiment of the present disclosure.
[0027] Fig. 2 is a schematic diagram of an exemplary scenario of disassembling a power battery based on projection assistance.
[0028] Fig. 3 is an exemplary flow chart of auxiliary disassembly process for power battery based on projection assistance according to an embodiment of the present disclosure.
[0029] Fig. 4 is an exemplary structure diagram of an auxiliary disassembly system for power battery according to an embodiment of the present disclosure.
[0030] Fig. 5 is an exemplary structure diagram of an auxiliary disassembly apparatus for power battery according to an embodiment of the present disclosure.
[0031] Fig. 6 is an exemplary structural diagram of an electronic device according to an embodiment of the present disclosure.
[0032] List of reference numbers: DETAILED DESCRIPTION
[0033] To make the purpose, technical scheme, and advantages of the disclosure clearer, the following examples are given to further explain the disclosure in detail. Nouns and pronouns related to people in this patent application are not limited to specific gender.
[0034] To be concise and intuitive in description, the scheme of the disclosure is described below by describing several representative embodiments. Many details in the embodiments are only used to help understand the scheme of the disclosure. However, it is obvious that the technical scheme of the disclosure can be realized without being limited to these details. To avoid unnecessarily blurring the scheme of the disclosure, some embodiments are not described in detail, but only the framework is given. Hereinafter, "including" refers to "including but not limited to" , "according to... " refers to "at least according to..., but not limited to... " . When the number of an element is not specifically indicated below, it means that the element can be one or more, or can be understood as at least one. The terms "a" or "an" in this disclosure should not be understood as one, but as at least one.
[0035] There are high risks during the disassembly of power batteries (such as power batteries) mainly including electric shock risk, physical injury, environmental pollution, explosion and fire risk. No existing solutions for the disassembly of power batteries (such as retired EV battery packs) using projected augmented reality. Taking power batteries as EV batteries as an example for explanation. The explanations are as follows:
[0036] Currently, the disassembly of retired EV batteries remains predominantly manual, with minimal technological assistance for technicians. While there are technological aids utilizing projected augmented reality (AR) , they primarily focus on battery assembly rather than disassembly. In the realm of disassembly, existing projects using projected AR are limited to e-waste, which is generally smaller in size and carries less risk associated with high / medium-voltage components. Furthermore, these projects primarily offer guidance without significant interaction between the operator and the AR system. Notably, there are no existing projects that incorporate real-time interior component detection and localization within the projected AR framework for EV battery disassembly.
[0037] Moreover, the complexity of the disassembly process for EV batteries is significantly higher than that of assembly processes for 3C products or even e-waste disassembly. Assembly tasks are typically more straightforward, as they involve objects of the same type and structure. In contrast, EV battery disassembly is highly complex due to the inability to control the type, year, and brand of retired EV battery packs received daily. The diversity of incoming EV battery packs is vast and constantly changing, making the disassembly process much more challenging than that of e-waste, where items like laptops belong to a single product line and are relatively easier to handle.
[0038] Additionally, the use of AR headsets for EV battery disassembly poses significant challenges. During the disassembly process, there is a risk of hazardous battery electrolyte leakage, necessitating the use of face masks, eye protection glasses, and insulation gloves for worker safety. These protective measures may hinder the effective use of AR headsets, making it difficult for technicians to utilize headset-based intelligent disassembly techniques.
[0039] In summary, here are the listed reasons why existing methods are inadequate: (1) Manual Disassembly Limitations: The disassembly process is heavily reliant on manual labor, leading to inefficiencies and a greater probability of error. The technological assistance provided now is minimal and does not address the complexities and variability of the tasks at hand. (2) Projected AR in Assembly vs. Disassembly: While projected AR has been utilized in battery assembly, its application in disassembly is non-existent. Assembly processes operate under controlled conditions with known battery types, whereas disassembly must deal with a wide variety of unknown and diverse battery types that enter the recycling stream. This unpredictability necessitates a system that can handle a broad range of scenarios, which current AR applications do not support. (3) Lack of Real-Time Human Intention Estimation: No current systems incorporate real-time estimation of human intentions, which is crucial for preventing accidents by anticipating unsafe movements or errors of labors in the disassembly process. (4) Absence of Adaptive Learning and Automated Documentation: There are no existing solutions that offer adaptive learning capabilities or the ability to automatically document and generate disassembly instructions for new and unknown battery types. As battery technology evolves rapidly, this capability is essential for ensuring that disassembly processes remain current and safe.
[0040] The gaps identified here highlight the need for a system that goes beyond static instructions and rudimentary projected AR applications. The proposed intelligent disassembly system using projected AR is uniquely designed to fill these gaps by providing real-time, adaptive guidance for disassembly that improves safety, efficiency, and knowledge management in the disassembly of EV batteries.
[0041] In contrast, the present disclosure utilizes projected AR for power battery disassembly, incorporating advanced features such as human intention estimation and real-time detection and localization of interior components. This approach not only enhances safety and efficiency but also addresses the limitations of existing AR applications in the context of power battery disassembly, particularly in managing the diversity and complexity of the task. The present disclosure addresses critical issues in the disassembly of power batteries (such as retired EV battery packs) , which are labor-intensive and prone to errors, posing significant safety risks due to medium voltage electric hazards inherent in such operations. The complexity of the task is exacerbated by the absence of a dynamic, real-time, user-friendly guidance system, leaving technicians to rely on static instructions that are neither efficient nor sufficiently safe. This leads to a heightened risk of accidents, particularly through:
[0042] (1) Safety Concerns: Real-time Human Action Estimation: The current lack of a system capable of real-time human intention estimation increases the danger of workers inadvertently entering hazardous zones or omitting critical disassembly steps. There is a clear need for an intelligent system that can predict and prevent potential safety breaches by recognizing human intentions and providing immediate corrective guidance.
[0043] (2) Efficiency and Knowledge Management: (a) Battery Pack Variability: With the rapid innovation in battery technology, new battery designs are introduced frequently, making it increasingly challenging to keep up with the specific disassembly workflows required for each type. The current approach does not support the efficient handling of this diversity, leading to inefficiencies and the risk of incorrect disassembly. (b) Complexity of Disassembly: The intricate nature of battery packs requires a nuanced understanding of their components and disassembly procedures. The existing methods do not account for this complexity, nor do they provide a means to manage and disseminate the intricate knowledge required. (c) High Labor Attrition Rate: The monotonous and strenuous nature of manual disassembly contributes to a high turnover rate among workers, compounding the inefficiencies and increasing training costs.
[0044] The present disclosure mitigates these issues by introducing a dynamic, user-friendly system that employs projected AR to offer adaptive, real-time visual guidance for power battery disassembly. The present disclosure will dramatically enhance safety by alerting workers of potential hazards and providing step-by-step instructions, thus ensuring accurate disassembly and material recovery. Furthermore, it will address efficiency by creating a flexible workflow capable of adjusting to various battery types and their specific disassembly requirements, streamlining the process, and reducing the cognitive load on workers.
[0045] The above disclosure provides a detailed explanation of the technical defects in the relevant technology, the reasons for these defects, and the process of thinking and analyzing how to overcome them. In fact, the understanding of the above-mentioned technical defects is not universal knowledge in this field, but rather a novel discovery made by inventors in their research. In addition, the tracing of the causes of the technical defect and the process of thinking and analyzing how to overcome it are also the gradual analysis results of the inventor in the actual research process, and are not universal knowledge in this field.
[0046] Fig. 1 is an exemplary flow chart of auxiliary disassembly method for power battery according to an embodiment of the present disclosure. As shown in Figure 1, the method includes:
[0047] Step 101: obtaining a first real-time image of a power battery.
[0048] Here, first real-time image of a power battery (preferably with the battery casing removed) can be obtained through devices such as 3D cameras / 2D cameras / point cloud scanners.
[0049] Step 102: determining a disassembly sequence of the power battery.
[0050] Disassembly sequence involves multiple key steps aimed at ensuring the safety and efficiency of power battery disassembly. Firstly, it is necessary to disconnect the connection between the power battery inlet pipe and the battery expansion pot to prevent liquid leakage or pressure issues during disassembly. Next, disconnect the two high-voltage harness connectors of the power battery to ensure that the power supply is cut off and avoid the risk of electric shock. Then, remove fixing bolts of the power battery collision beam to ensure stable removal of the collision beam and protect the safety of the operator. Finally, remove fixing bolts on each side of the battery assembly and slowly lower the platform vehicle to complete the entire disassembly process.
[0051] For example, the disassembly sequence of lithium-ion power battery packs usually includes: (1) scan the code, and remove the cover screws; (2) remove the upper cover; (3) dismantle copper bars and screws (4) remove mold assembly bolts (5) take out modules; (6) module testing / scanning code; (7) disassemble upper covers of modules; (8) dismantle mold flow guide and bracket; (9) dismantle side panels of modules: (10) remove battery cells, scan the code, and take the battery cells offline.
[0052] Here, scan QR code on the surface of the power battery to be disassembled to obtain the model and batch information of the battery, determine whether there is a disassembly sequence for the same model of power battery in a database; If it exists, directly output the disassembly sequence of the battery to be disassembled; If it does not exist, use human-computer interaction to obtain the characteristic information of the battery to be disassembled; and generate a disassembly sequence for the new energy power battery pack to be disassembled.
[0053] Step 103: determining real-time remaining components of the power battery based on the first real-time image.
[0054] At the beginning of disassembly, the remaining components are all components of the power battery. Then, as the disassembly work proceeds, the remaining components will change, usually less and less.
[0055] Step 104: determining a component currently to be disassembled from the real-time remaining components based on the disassembly sequence.
[0056] Here, according to component disassembly steps specified in the disassembly sequence, determine the component currently to be disassembled.
[0057] Step 105: presenting first information indicating a worker to disassemble the component currently to be disassembled, in a projected manner on a surface of the component currently to be disassembled.
[0058] Here, the projection device is controlled to project on surface of the component to be disassembled. For example, project on contour line or whole surface of the component. The projection content can include specific words: for example, “disassembly” . The projection content can also contain specific icons, such as icon of a screwdriver.
[0059] In one embodiment, the presenting first information comprises: projecting light with a first color, on a contour line of the surface of the component currently to be disassembled; the presenting second information comprises: projecting light with a second color different from the first color, on a contour line of the surface of the next component to be disassembled. In one embodiment, the method comprising: determining the next component to be disassembled follow the component currently to be disassembled based on the disassembly sequence; presenting second information indicating the worker to disassemble the next component to be disassembled after completing the disassembly of the component currently to be disassembled, in a projected manner on a surface of the next component to be disassembled.
[0060] Therefore, by projecting on the surface of battery components, workers can be visually alerted.
[0061] In one embodiment, the method comprises: obtaining a second real-time image of the worker; determining a real-time protection status of the worker based on the second real-time image; triggering a first alarm message when the real-time protection status does not comply with a first protection rule. Therefore, by analyzing real-time images of workers, it is possible to prevent safety errors (such as forgetting to wear goggles or insulated gloves) and improve safety.
[0062] In one embodiment, the method comprises: determining a current action of the worker based on the second real-time image; triggering a second alarm message when a target of the current action is the component currently to be disassembled and the current action does not comply with an action-specification associated with the component currently to be disassembled.
[0063] For example, the component currently to be removed is copper bar. The current action of the worker is to remove the copper bar with a screwdriver in hand. However, the workers did not use a support piece to support the copper bar, which violated the standard requirements for dismantling the copper bar, and therefore an alarm was issued.
[0064] In one embodiment, the method comprises: determining a current action of the worker based on the second real-time image; triggering a third alarm message when a target of the current action is not the component currently to be disassembled.
[0065] In one embodiment, the method comprises: predicting a future action of the worker based on the second real-time image and a historical action database of the worker; triggering a fourth alarm message when the future action does not comply with a second protection rule. The worker's historical action database stores the worker's historical actions and action habits determined based on the worker's historical actions. For example, action habits include: proceeding with module disassembly after removing the upper cover. Then, after removing the upper cover, a future action is predicated that the worker may proceed with module disassembly before the copper bars are fully disassembled. At this point, an alarm is required because the copper bars are used for connecting modules in series. If the copper busbar is not disassembled, there is a risk of high-voltage output points if a module of 24V is connected in series and 100V is directly disassembled. Before disassembling the module, it is necessary to ensure that the copper bars are disassembled, the series connection is disconnected, and the voltage is reduced.
[0066] In one embodiment, the power battery comprises an identity identifier, and the determining a disassembly sequence of the power battery comprises: extracting the identity identifier of the power battery based on the first real-time image; using the identity identifier as a search term to query a database for a disassembly sequence corresponding to the search term.
[0067] In one embodiment, the power battery does not comprise an identity identifier; and the determining a disassembly sequence of the power battery comprises: determining production information of the power battery; determining a similar power battery of the power battery based on the production information; referring to disassembly sequence of the similar power battery to perform a disassembly process of the power battery, wherein adjusting the disassembly sequence of the similar power battery as a reference based on the worker's experiential knowledge during the disassembly process; generating a disassembly sequence for the power battery based on a media file recording the disassembly process.
[0068] Fig. 2 is a schematic diagram of an exemplary scenario of disassembling a power battery based on projection assistance.
[0069] In Figure 2, worker 12 is performing battery disassembly. The projection device 11 projects a predetermined color, image, or text on the surface of the currently disassembled component 13 of power battery 10, thereby prompting the worker 12 to disassemble the component 13. Moreover, the projection device 11 projects a predetermined color, image, or text on the surface of the next component 13 to be removed, thereby prompting the worker 12 to subsequently remove the component 14. Moreover, in the surrounding environment of worker 12 (such as workbench surface or ground) , auxiliary disassembly information 15 (such as precautions or prompt information about which tool to be used) of the current disassembly assembly 13 is projected.
[0070] The present disclosure employs a suite of technical features that together form a comprehensive system designed to transform the battery disassembly process. Keywords explanation as followings:
[0071] (1) Battery disassembly recipe (that is, battery disassembly sequence) refers to a comprehensive set of detailed instructions and guidelines crafted for the systematic disassembly of a specific type of battery pack. Upon retrieval of the battery pack's information, the recipe outlines the necessary steps, tools, safety precautions, and handling procedures required to dismantle the battery pack efficiently and safely. It includes sequences for component separation, material sorting, and advises on the handling of hazardous elements (e.g., battery electrolyte) . These recipes are crucial for ensuring consistency, safety, and maximizing material recovery in the recycling process.
[0072] (2) Projected AR Assistance for Battery Pack Disassembly
[0073] Utilizing a high-resolution projector, the system casts detailed, dynamic visual instructions directly onto the operational space, i.e., surfaces of platform, battery packs, tool, etc. This eliminates the need for handheld devices or static paper manuals. Sub-features and systems including:
[0074] (a) Color-Coded Guidance: This feature employs intuitive color coding and symbols to guide technicians through the disassembly process, clearly indicating different actions, component types, and safety warnings, thereby reducing cognitive load and error potential.
[0075] (b) Real-Time Battery Component Recognition: Through sophisticated image processing and deep learning algorithms (e.g., Segment Anything with CLIP and et al) , the system identifies individual battery components (e.g., battery wires, BMS parts, battery modules and et al) in real time. Information from this sub-system indicates the Dynamic Instruction Adaptation to adjust the projected instructions to reflect the current step of the disassembly process.
[0076] (c) Human Intension Estimation: Human intention estimation here refers to the process of predicting a human's next action or movement based on their current behavior, body language, and context. In the context of this disclosure, this involves using sensors and algorithms (e.g., MediaPipe human hand and pose estimation to analyze the worker's movements and posture during the battery disassembly process) . The system then anticipates the worker's intended actions, such as which component they are likely to remove next or if they are about to make a potentially unsafe movement. The application of human intension estimation in this disclosure includes: (c1) Proactive Safety Alerts: By estimating the technician's intentions, the system can provide real-time warnings if the technician is about to perform a hazardous action, such as touching a high-voltage component or using the wrong tool. This preemptive guidance helps prevent accidents and ensures compliance with safety protocols. (c2) Efficiency Optimization: By understanding the technician's intended actions, the system can streamline the disassembly process, reducing unnecessary movements and ensuring that each step is performed optimally. This leads to faster and more efficient disassembly operations.
[0077] (d) Dynamic Instruction Adaptation: The system uses the estimated intentions to adapt the projected AR disassembly instructions in real-time. For example, if the technician is about to skip a critical step, the system can highlight the missed action or provide a reminder to ensure that the disassembly process follows the correct sequence. Meanwhile, the system's software responds to the real-time actions of the technician, updating the disassembly steps as the process unfolds. This ensures that instructions remain relevant to the task at hand and can adapt to any deviations or complications that arise.
[0078] (e) Real-time feedback / alert: During the projected AR-assisted battery disassembly workflow, real-time feedback is provided to operators in the form of sound, light, and vibration signals. This feedback is crucial for enhancing safety and efficiency in several ways: (1) Auditory feedback: Auditory cues alert technicians to potential hazards or confirm the completion of a step, ensuring that they remain aware of their surroundings and progress. (2) Visual feedback: Visual indicators, such as flashing colors or symbols projected onto the battery pack, guide the technician's actions, and highlight areas of focus or caution. (3) Haptic feedback: Haptic signals, such as a vibration in a tool or wearable devices, can provide immediate tactile feedback to the operator, signaling when to proceed or when caution is needed. Enhanced Safety and Efficiency: By providing clear, direct visual guidance, this system minimizes the need for extensive training, reduces the potential for mistakes, and ensures a safer work environment. It also streamlines the disassembly process, improving overall efficiency.
[0079] (f) Adaptive learning Cognitive Reasoning: (f1) Adaptive Learning and Recipe Generation: In cases where a new type of battery pack is encountered, the system records the manual disassembly steps executed by the technician. It then processes this data to generate a new disassembly guide, thereby continuously expanding its knowledge base for future reference. (f2) Cognitive Reasoning for Unknown Battery Types: Leveraging data capture and analysis, the system not only guides but also learns from each disassembly event. This is particularly crucial for processing unknown battery types, ensuring that each subsequent disassembly of similar packs becomes more efficient and informed.
[0080] The explanation for the workflow as follows:
[0081] Step 1: Battery Reception and Setup.
[0082] Receive retired EV battery packs. Position the battery packs under the high-resolution AR projector. Then, manually remove the top cover of the battery pack to expose the interior components to the projected AR assistance.
[0083] Step 2: Battery Information Retrieval
[0084] Scan the barcode or manually input data to retrieve battery information (e.g., brand, type, year made, disassembly recipe, etc. ) . If an existing disassembly recipe is available, proceed to Step 3 for initial disassembly planning. If no existing recipe is found (indicating a new type of EV battery pack) , proceed to Step 8 for manual disassembly recording, documentation, and automated recipe generation.
[0085] Step 3: Initial Planning
[0086] Based on the retrieved disassembly recipe, the system started the initial planning for the disassembly.
[0087] Step 4: Component Recognition
[0088] Use the overhead camera (2D camera and 3D camera) to scan the exposed EV battery components. Based on the retrieved disassembly recipe, the system recognizes and locates the existing or remaining interior battery components.
[0089] Step 5: Disassembly Workflow Planning &Projected AR Guidance
[0090] The system analyzes the battery components identified in Step 3. It then plans the disassembly workflow in real-time, considering safety and efficiency. The system projects step-by-step disassembly instructions onto the surfaces of battery pack and the surfaces of operation platform, highlighting key battery components by steps and providing color-coded guidance.
[0091] Step 6: Disassembly Execution
[0092] In this step, operators follow the AR-projected instructions to disassemble the EV battery pack. After completing each step, they wait for the next set of instructions. Repeat Steps 4 to 6 until the disassembly is complete.
[0093] Step 7: Disassembly Completion &documentation
[0094] The final output includes separated battery modules or cells and other battery components. The system records the disassembly process (e.g., videos or photos) for future reference and improvement, including time, duration, worker information, and disassembled components.
[0095] Step 8: Disassembly Instruction Recommendation
[0096] The system suggests initial disassembly steps based on similar EV battery pack types in the database. Operators can review and adjust these recommendations before proceeding, ensuring that the disassembly process starts with an informed approach.
[0097] Step 9: Manual Disassembly with Recording
[0098] Operators manually disassemble the new type of battery pack with limited technological assistance. The system records each step of the disassembly process in real-time, making sure that all the important details such as tool usage, component removal order, safety measures et al and captured within the video records.
[0099] Step 10: Scene and Operation Understanding
[0100] The system analyzes the recorded disassembly process (e.g., photos and videos) , using AI algorithms to understand the sequence of operations, identify critical components and their removal order, tool usage and recognize patterns in the disassembly technique. This step is crucial for generating an accurate and efficient EV battery pack disassembly recipe.
[0101] Step 11: Disassembly Recipe Generation
[0102] Based on the data collected in Step 9 and insights from step 10, the system generates a new disassembly recipe based on the initial disassembly instruction recommendation from step 8. This updated recipe includes detailed instructions, required tools, safety precautions, and component identification for future disassembly of the same battery type. The updated recipe is designed to optimize the EV battery pack disassembly process, ensuring safety and efficiency.
[0103] Step 12: Recipe Refinement Based on Human Feedback
[0104] After step 11, the disassembly recipe is updated, operators can provide further feedback on its effectiveness and suggest improvements. The system incorporates operators’ feedback to refine the recipe and adjusts it. This iterative process ensures that the disassembly recipe is continuously improved and adapted according to real-world conditions.
[0105] Fig. 3 is an exemplary flow chart of auxiliary disassembly process for power battery based on projection assistance according to an embodiment of the present disclosure. As shown in Figure 3, the auxiliary disassembly process for power battery comprises:
[0106] Step 301: Obtain a retired power battery.
[0107] Step 302: Determine whether disassembly sequence of the retired power battery can be obtained. If yes (Corresponding to the "Y" branch) , perform step 303 and its subsequent steps, otherwise (Corresponding to the "N" branch) , perform step 308 and its subsequent steps. Here, try to scan QR code of the power battery to obtain battery model information, and then retrieve a database based on the battery model information, so as to try to obtain disassembly sequence of the battery.
[0108] Step 303: Obtain the disassembly sequence of the power battery.
[0109] In the projection assisted disassembly process 400, the power battery is disassembled based on the disassembly sequence specified in the disassembly sequence. Process 400 includes:
[0110] Step 304: Identify components in the power battery.
[0111] Step 305: Determine component currently to be disassembled and next component to be disassembled based on the disassembly sequence, and project a red light on the surface of the current component to be disassembled, and a green light on the surface of the next component to be disassembled. Moreover, auxiliary disassembly information of the component currently to be disassembled is projected on the workbench, such as: precautions; and required tools.
[0112] Step 306: The user completes the disassembly of the component to be disassembled based on projection assistance. Then, return to step 304 to continue the process 400 until the disassembly sequence is completed.
[0113] Step 307: Recycle the disassembled components (such as battery module) and exit this process.
[0114] Step 308: determine production information of the power battery. For example, production information includes: manufacturer, production date, assembly line identification, etc.
[0115] Step 309: Determine a power battery similar to the power battery based on the production information. For example, a power battery with the same manufacturer and the same assembly line identification can be identified as similar power battery.
[0116] Step: 310: Obtain disassembly sequence of similar power battery.
[0117] Step 311: complete the disassembly of the power battery based on the reference of the disassembly sequence of power battery. In the process of disassembly, based on experience and knowledge of the worker, the disassembly sequence of similar power battery as a reference is adjusted accordingly. Record the disassembly process and generate media files of the disassembly process. Media files may include audio, video or images.
[0118] Step 312: determine disassembly sequence of the power battery based on media files of the disassembly process, and execute step 307.
[0119] These integrated features mentioned above solve the identified problem by creating a safer, more efficient, and adaptive disassembly process. The system's ability to learn and document new procedures ensures that it remains up-to-date with the latest battery technologies and disassembly techniques. Compared to existing solutions, the present disclosure provides direct, dynamic guidance that reduces the cognitive load on technicians and minimizes the risk of errors. The system's ability to adapt and learn improves efficiency and safety. Unlike static AR solutions, the direct projection is more engaging and less disruptive, leading to a streamlined disassembly process.
[0120] Fig. 4 is an exemplary structure diagram of an auxiliary disassembly system according to an embodiment of the present disclosure. The auxiliary disassembly system comprising: a first camera 30, configured to acquire first real-time image a power battery 33 located on workbench 34; a controller 31, configured to determine a disassembly sequence of the power battery 33, determine real-time remaining components of the power battery 33 based on the first real-time image, determine a component currently to be disassembled 36 from the real-time remaining components based on the disassembly sequence, and generate first information indicating a worker to disassemble the component currently to be disassembled; a projection device 32, configured to present the first information in a projected manner on a surface of the component currently to be disassembled 36. Components 38 have not yet been projected. However, as the dismantling work progresses, when components 38 begin to be dismantled, the projection device 32 will perform projection on the surface of component 38.
[0121] In one embodiment, controller 31 is configured to determine the next component to be disassembled 37 follow the component currently to be disassembled 36 based on the disassembly sequence, and generate second information indicating the worker to disassemble the next component to be disassembled 37 after completing the disassembly of the component currently to be disassembled 36. The projection device 32 is configured to present second information indicating the worker to disassemble the next component to be disassembled after completing the disassembly of the component currently to be disassembled, in a projected manner on a surface of the next component to be disassembled.
[0122] In one embodiment, the system comprises: a second camera 35, configured to acquire a second real-time image of the worker. The controller 31 is configured to determine a real-time protection status of the worker based on the second real-time image; and trigger a first alarm message when the real-time protection status does not comply with a first protection rule.
[0123] In one embodiment, the power battery does not comprise an identity identifier; the controller is configured to determine production information of the power battery; determine a similar power battery of the power battery based on the production information; refer to disassembly sequence of the similar power battery to perform a disassembly process of the power battery, wherein adjusting the disassembly sequence of the similar power battery as a reference based on the worker's experiential knowledge during the disassembly process; and generate a disassembly sequence for the power battery based on a media file recording the disassembly process.
[0124] Fig. 5 is an exemplary structure diagram of an auxiliary disassembly apparatus according to an embodiment of the present disclosure. The auxiliary disassembly apparatus 500, comprising: an obtaining module 501 , configured to obtain a first real-time image of a power battery; a first determining module 502, configured to determine a disassembly sequence of the power battery; a second determining module 503, configured to determine real-time remaining components of the power battery based on the first real-time image; a third determining module 504, configured to determine a component currently to be disassembled from the real-time remaining components based on the disassembly sequence; and a presenting module 505, configured to present first information indicating a worker to disassemble the component currently to be disassembled, in a projected manner on a surface of the component currently to be disassembled.
[0125] Embodiments of the present disclosure also propose an electronic device with a processor memory architecture.
[0126] Fig. 6 is an exemplary structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in Figure 6, electronic device 600 includes a processor 601, a memory 602, and a computer program stored on memory 602 that can run on processor 601. When the computer program is executed by processor 601, the auxiliary disassembly method for power battery as described above is implemented. Among them, memory 602 can be implemented as various storage media such as electrically erasable programmable read-only memory (EEPROM) , flash memory, programmable program read-only memory (PROM) , etc. Processor 601 can be implemented to include one or more central processors or one or more field programmable gate arrays, wherein the field programmable gate array integrates one or more central processor cores. Specifically, the central processing unit or core can be implemented as a CPU, MCU, DSP, and so on.
[0127] It should be noted that not all steps and modules in the above processes and structural diagrams are necessary, and some steps or modules can be ignored according to actual needs. The execution sequence of each step is not fixed and can be adjusted as needed. The division of each module is only for the convenience of describing the functional division used. In actual implementation, a module can be divided into multiple modules, and the functions of multiple modules can also be implemented by the same module. These modules can be in the same device or different devices.
[0128] The hardware modules in each implementation can be implemented mechanically or electronically. For example, a hardware module can include specially designed permanent circuits or logic devices (such as dedicated processors, such as FPGA or ASIC) to complete specific operations. Hardware modules can also include programmable logic devices or circuits temporarily configured by software (such as general-purpose processors or other programmable processors) for performing specific operations. As for the specific use of mechanical methods, either dedicated permanent circuits or temporarily configured circuits (such as software configuration) to implement hardware modules, it can be determined based on cost and time considerations.
[0129] The above is only a preferred embodiment of the present disclosure and is not intended to limit the scope of protection of the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.
[0130] Independent of the grammatical term usage, individuals with male, female or other gender identities are included within the term.
Claims
1.An auxiliary disassembly method for power battery, comprising:obtaining (101) a first real-time image of a power battery;determining (102) a disassembly sequence of the power battery;determining (103) real-time remaining components of the power battery based on the first real-time image;determining (104) a component currently to be disassembled from the real-time remaining components based on the disassembly sequence; andpresenting (105) first information indicating a worker to disassemble the component currently to be disassembled, in a projected manner on a surface of the component currently to be disassembled.2.The method of claim 1, comprises:determining the next component to be disassembled follow the component currently to be disassembled based on the disassembly sequence;presenting second information indicating the worker to disassemble the next component to be disassembled after completing the disassembly of the component currently to be disassembled, in a projected manner on a surface of the next component to be disassembled.3.The method of claim 2, wherein the presenting (105) first information comprises: projecting light with a first color, on a contour line of the surface of the component currently to be disassembled;wherein the presenting second information comprises: projecting light with a second color different from the first color, on a contour line of the surface of the next component to be disassembled.4.The method of claim 1, comprises:obtaining a second real-time image of the worker;determining a real-time protection status of the worker based on the second real-time image;triggering a first alarm message when the real-time protection status does not comply with a first protection rule.5.The method of claim 4, comprises:determining a current action of the worker based on the second real-time image;triggering a second alarm message when a target of the current action is the component currently to be disassembled and the current action does not comply with an action-specification associated with the component currently to be disassembled.6.The method of claim 4, comprises:determining a current action of the worker based on the second real-time image;triggering a third alarm message when a target of the current action is not the component currently to be disassembled.7.The method of claim 4, comprises:predicting a future action of the worker based on the second real-time image and a historical action database of the worker;triggering a fourth alarm message when the future action does not comply with a second protection rule.8.The method of any one of claims 1-7, wherein the power battery comprises an identity identifier, and the determining (102) a disassembly sequence of the power battery comprises:extracting the identity identifier of the power battery based on the first real-time image;using the identity identifier as a search term to query a database for a disassembly sequence corresponding to the search term.9.The method of any one of claims 1-7, wherein the power battery does not comprise an identity identifier; and the determining (102) a disassembly sequence of the power battery comprises:determining production information of the power battery;determining a similar power battery of the power battery based on the production information;referring to disassembly sequence of the similar power battery to perform a disassembly process of the power battery, wherein adjusting the disassembly sequence of the similar power battery as a reference based on the worker's experiential knowledge during the disassembly process;generating a disassembly sequence for the power battery based on a media file recording the disassembly process.10.An auxiliary disassembly system for power battery, comprising:a first camera (30) , configured to acquire first real-time image of a power battery;a controller (31) , configured to determine a disassembly sequence of the power battery, determine real-time remaining components of the power battery based on the first real-time image, determine a component currently to be disassembled from the real-time remaining components based on the disassembly sequence, and generate first information indicating a worker to disassemble the component currently to be disassembled;a projection device (32) , configured to present the first information in a projected manner on a surface of the component currently to be disassembled.11.The system of claim 10, comprises:a second camera (35) , configured to acquire a second real-time image of the worker;wherein the controller (31) is configured to determine a real-time protection status of the worker based on the second real-time image; and trigger a first alarm message when the real-time protection status does not comply with a first protection rule.12.The system of claim 10, wherein the power battery does not comprise an identity identifier; the controller (31) is configured to determine production information of the power battery; determine a similar power battery of the power battery based on the production information; refer to disassembly sequence of the similar power battery to perform a disassembly process of the power battery, wherein adjust the disassembly sequence of the similar power battery as a reference based on the worker's experiential knowledge during the disassembly process; and generate a disassembly sequence for the power battery based on a media file recording the disassembly process.13.An auxiliary disassembly apparatus for power battery, comprising:an obtaining module (501) , configured to obtain a first real-time image of a power battery;a first determining module (502) , configured to determine a disassembly sequence of the power battery;a second determining module (503) , configured to determine real-time remaining components of the power battery based on the first real-time image;a third determining module (504) , configured to determine a component currently to be disassembled from the real-time remaining components based on the disassembly sequence; anda presenting module (505) , configured to present first information indicating a worker to disassemble the component currently to be disassembled, in a projected manner on a surface of the component currently to be disassembled.14.An electronic device, comprising a processor (601) and a memory (602) , wherein an application program executable by the processor (601) is stored in the memory (602) for causing the processor (601) to execute an auxiliary disassembly method for power battery according to any one of claims 1-9.15.A computer-readable medium comprising computer-readable instructions stored thereon, wherein the computer-readable instructions for executing an auxiliary disassembly method for power battery according to any one of claims 1-9.16.Acomputer program product comprising a computer program, upon the computer program is executed by a processor for executing an auxiliary disassembly method for power battery according to any one of claims 1-9.
Citation Information
Patent Citations
Method and system for automatically disassembling scrapped and recycled power battery pack of new energy automobile
CN113212606A
Automobile power battery disassembly production line monitoring system and method
CN116774085A
Waste power battery disassembling equipment based on machine vision and control method thereof
CN117443896A
Method for guiding a worker during assembly
DE102014221753A1
Used battery pack disassembly and collection system
KR102684377B1