Vehicle cloud collaborative offline detection method, device and equipment and storage medium

Abstract

The invention provides a vehicle cloud collaborative offline detection method, device and equipment and a storage medium. The method comprises the following steps: constructing a four-dimensional digital twinborn body; wherein the four-dimensional digital twin body is used for describing a battery mechanism from a geometric dimension, a physical dimension, a behavior dimension and a rule dimension, predicting a battery risk and executing rigid safety protection; and carrying out vehicle cloud collaborative offline detection based on the four-dimensional digital twinborn body. In the mode, cell-level battery health detection can be realized, a three-electricity system detection barrier is broken, and an electric control verification period is compressed.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing technology for electric vehicles, and in particular to a vehicle cloud-based collaborative offline inspection method, apparatus, equipment, and storage medium. Background Technology

[0002] Currently, existing electric vehicle battery testing methods have the following technical problems: 1. Insufficient detection depth: Current battery testing methods cannot reach the cell level (such as lithium plating and SEI film growth), resulting in a false negative rate of ≥15%.

[0003] 2. System fragmentation problem: The motor test ignores the harmonic distortion caused by inverter switching losses, and the estimated error of IGBT (Insulated Gate Bipolar Transistor) junction temperature is >20℃.

[0004] 3. Real-time defects: The verification time after the electronic control software is flashed is >8 minutes due to the lack of a digital mirror pre-verification mechanism. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a vehicle cloud-based collaborative offline testing method, device, equipment and storage medium to achieve cell-level battery health testing, break down the testing barriers of the three-electric system, and shorten the electronic control verification cycle.

[0006] In a first aspect, embodiments of the present invention provide a vehicle cloud-based collaborative offline detection method, the method comprising: constructing a four-dimensional digital twin; wherein the four-dimensional digital twin is used to describe battery mechanisms, predict battery risks and implement rigid safety protection from geometric, physical, behavioral and rule dimensions; and performing vehicle cloud-based collaborative offline detection based on the four-dimensional digital twin.

[0007] In an optional embodiment of this application, the geometric dimensions of the above-mentioned four-dimensional digital twin include: the four-dimensional digital twin is used to establish a point cloud model of the battery pack through computed tomography.

[0008] In optional embodiments of this application, the physical dimensions of the aforementioned four-dimensional digital twin include: the four-dimensional digital twin describes the circuit characteristics of the battery at a macroscopic scale; the four-dimensional digital twin describes the ion diffusion of the battery at a mesoscopic scale; and the four-dimensional digital twin describes the atomic interactions of the battery at a microscopic scale.

[0009] In an optional embodiment of this application, the behavioral dimension of the aforementioned four-dimensional digital twin includes: the four-dimensional digital twin performs data-driven prediction of the battery through a long short-term memory network artificial intelligence model.

[0010] In an optional embodiment of this application, the rule dimension of the above-mentioned four-dimensional digital twin includes: the four-dimensional digital twin constrains the functional safety of the battery through a preset functional safety standard.

[0011] In an optional embodiment of this application, the steps of offline detection based on a four-dimensional digital twin for vehicle cloud collaboration include: vehicle-side sensors uploading data to edge nodes in real time; edge nodes cleaning the data and transmitting the cleaned data stream to the cloud engine; the cloud engine requesting simulation prediction from the four-dimensional digital twin based on the cleaned data stream; the four-dimensional digital twin returning multiphysics simulation results to the cloud engine; the cloud engine performing dynamic time warping and virtual-real alignment on the fault diagnosis system based on the multiphysics simulation results; and the fault diagnosis system outputting a component-level positioning report to the maintenance system.

[0012] In optional embodiments of this application, after the step of the vehicle-side sensors uploading data to the edge node in real time, the method further includes: the edge node determining the priority of the data; the edge node processing the data in real time based on the priority and performing an alarm operation; or, the edge node uploading the data to the cloud based on the priority.

[0013] Secondly, embodiments of the present invention also provide a vehicle cloud-coordinated offline detection device, the device comprising: a four-dimensional digital twin construction module for constructing a four-dimensional digital twin; wherein the four-dimensional digital twin is used to describe battery mechanisms, predict battery risks and implement rigid safety protection from geometric, physical, behavioral and rule dimensions; and a vehicle cloud-coordinated offline detection module for performing vehicle cloud-coordinated offline detection based on the four-dimensional digital twin.

[0014] Thirdly, embodiments of the present invention also provide an electronic device, which includes a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement the above-mentioned vehicle cloud-based collaborative offline detection method.

[0015] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are invoked and executed by a processor, they cause the processor to implement the aforementioned vehicle cloud-based collaborative offline detection method.

[0016] The embodiments of the present invention bring the following beneficial effects: This invention provides a vehicle cloud-based collaborative offline testing method, apparatus, device, and storage medium, constructing a four-dimensional digital twin. The four-dimensional digital twin is used to describe battery mechanisms, predict battery risks, and implement rigid safety protection from geometric, physical, behavioral, and rule dimensions. Offline testing of the vehicle is performed based on the four-dimensional digital twin in a cloud-based collaborative manner. This approach enables cell-level battery health testing, breaks down barriers to testing the three-electric system (battery, motor, and electronic control system), and shortens the electronic control verification cycle.

[0017] Other features and advantages of this disclosure will be set forth in the following description, or some features and advantages may be inferred from the description or determined without doubt, or may be learned by practicing the techniques described above.

[0018] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0019] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0020] Figure 1 A flowchart of a vehicle cloud-based collaborative offline detection method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a four-dimensional digital twin provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of a cloud-based collaborative EOL detection method provided in an embodiment of the present invention; Figure 4 A schematic diagram of a motor system detection method provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of an edge intelligent traffic offloading scheme provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of a vehicle cloud-based collaborative offline detection device provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] Currently, existing electric vehicle battery testing methods suffer from problems such as insufficient testing depth, system fragmentation, and real-time deficiencies.

[0023] Based on this, embodiments of the present invention provide a vehicle cloud-based collaborative end-of-line testing method, apparatus, device, and storage medium. Specifically, it relates to a collaborative testing method for the battery-motor-electronic control system (hereinafter referred to as the "three-electric system") that integrates digital twin construction, multi-physics field coupling simulation, and cloud-based intelligent decision-making. This method is particularly suitable for end-of-line (EOL) testing scenarios that achieve latent fault prediction, performance boundary verification, and full lifecycle quality traceability of the three-electric system through virtual and real data interaction. The above method can achieve cell-level battery health testing, break down the testing barriers of the three-electric system, and shorten the electronic control system verification cycle.

[0024] To facilitate understanding of this embodiment, a detailed description of a vehicle cloud-based collaborative offline detection method disclosed in this embodiment of the invention will be provided first.

[0025] Example 1: This invention provides a vehicle cloud-based collaborative offline detection method, see [link to relevant documentation]. Figure 1 The flowchart shown illustrates a method for detecting the decommissioning of vehicle cloud-based collaborative systems. This method includes the following steps: Step S102: Construct a four-dimensional digital twin; wherein, the four-dimensional digital twin is used to describe the battery mechanism, predict battery risks and implement rigid safety protection from geometric, physical, behavioral and rule dimensions.

[0026] See Figure 2 The diagram shows a four-dimensional digital twin. In this embodiment, a four-dimensional digital twin with geometric, physical, behavioral, and rule dimensions can be constructed.

[0027] In some embodiments, the geometric dimensions of the four-dimensional digital twin include: the four-dimensional digital twin is used to establish a point cloud model of the battery pack through computed tomography.

[0028] In this embodiment, a point cloud model of the battery pack can be established using industrial CT (Computed Tomography), with a reconstruction error of <0.05mm.

[0029] In some embodiments, the physical dimensions of the aforementioned four-dimensional digital twin include: the four-dimensional digital twin describes the circuit characteristics of the battery at a macroscopic scale; the four-dimensional digital twin describes the ion diffusion of the battery at a mesoscopic scale; and the four-dimensional digital twin describes the atomic interactions of the battery at a microscopic scale.

[0030] In this embodiment, a multi-scale physicochemical model can be constructed, which describes the working mechanism of the battery from three different scales: (1) Macroscopic scale (circuit characteristics): Using an equivalent circuit model, the battery terminal voltage V term Expressed as open circuit voltage (OCV) (related to state of charge (SOC)) minus current I and internal resistance R int The product (related to temperature T). This level is used to describe the overall external characteristics of the battery.

[0031] (2) Mesoscale (ion diffusion): Partial differential equations are used to describe the diffusion process of lithium ions inside the electrode particles. This can represent the change of ion concentration over time and is determined by the ion diffusion coefficient and the electrochemical reaction flux that drives ion migration. This level is used to analyze the electrochemical kinetics inside the battery.

[0032] (3) Microscale (atomic interactions): Based on molecular dynamics, the Hamiltonian H is used to describe the interaction energy between atoms, including the kinetic and potential energy of atoms. This level is used to simulate the microstructural evolution of electrode materials.

[0033] In this embodiment, a multi-dimensional fusion analysis framework can also be constructed. Based on the above physical model, the model also integrates two key analysis dimensions: In some embodiments, the behavioral dimension of the four-dimensional digital twin includes: the four-dimensional digital twin performs data-driven prediction of the battery through a long short-term memory network artificial intelligence model.

[0034] (1) Behavioral dimension (data-driven prediction): A Long Short-Term Memory (LSTM) artificial intelligence model is introduced, and up to 128 dimensions of historical time-series sensor data are input to directly predict the probability of 14 different types of battery failures in the future. This method infers the failure evolution path based on data patterns.

[0035] In some embodiments, the rule dimension of the above-mentioned four-dimensional digital twin includes: the four-dimensional digital twin constrains the functional safety of the battery through a preset functional safety standard.

[0036] (2) Rule dimension (functional safety constraints): The specific requirements of the ISO 26262 functional safety standard are embedded into the system. For example, a hard rule is set: when the battery temperature is detected to exceed the safety threshold of 65°C, the system will immediately trigger the highest level (ASIL D) power reduction operation strategy to ensure system safety.

[0037] In summary, the aforementioned four-dimensional digital twin model can be used to build a comprehensive management platform that can not only deeply understand the internal mechanism of the battery, but also intelligently predict risks and implement rigid safety protection by deeply integrating first principles (multi-scale model), data-driven algorithms (LSTM prediction) and functional safety standards (ISO 26262 rules).

[0038] Step S104: Perform offline inspection of the vehicle in a cloud-based collaborative manner based on the four-dimensional digital twin.

[0039] In this embodiment, cloud-based collaborative EOL detection can be performed based on the aforementioned four-dimensional digital twin.

[0040] In some embodiments, the vehicle's on-board sensors upload data to the edge nodes in real time; the edge nodes clean the data and transmit the cleaned data stream to the cloud engine; the cloud engine requests simulation prediction from the four-dimensional digital twin based on the cleaned data stream; the four-dimensional digital twin returns multiphysics simulation results to the cloud engine; the cloud engine performs dynamic time warping and virtual-real alignment on the fault diagnosis system based on the multiphysics simulation results; and the fault diagnosis system outputs a component-level positioning report to the maintenance system.

[0041] See Figure 3 The diagram illustrates a cloud-based collaborative EOL detection method. Vehicle-side sensors can upload data to edge nodes in real time (latency <10ms). Edge nodes transmit cleaned data streams to the cloud engine. The cloud engine requests simulation predictions from a 4D digital twin. The 4D digital twin returns multiphysics simulation results to the cloud engine. The cloud engine performs DTW (Dynamic Time Warping) virtual-real alignment for fault diagnosis. The fault diagnosis module outputs a component-level location report to the maintenance system.

[0042] This invention provides a cloud-based collaborative offline testing method for vehicles, constructing a four-dimensional digital twin. This four-dimensional digital twin is used to describe battery mechanisms, predict battery risks, and implement rigid safety protection from geometric, physical, behavioral, and rule-based dimensions. Offline testing of the vehicle is then performed based on this four-dimensional digital twin. This method enables cell-level battery health testing, breaks down barriers to testing the three-electric system (battery, motor, and electronic control system), and shortens the electronic control verification cycle.

[0043] Example 2: This embodiment provides another vehicle cloud-based collaborative offline testing method, focusing on the specific implementation of battery system testing, motor system testing, and electronic control system testing.

[0044] I. Battery system testing can be performed as follows: Figure 3 As shown: Step 1, Twin Initialization: Load battery CT scan data and construct a geometric model of 3,072 cells. This process involves two core steps: (1) High-resolution mesh generation: Using a professional mesh generation algorithm, the CT scan data is converted into a fine three-dimensional mesh composed of hexahedrons. The mesh has extremely high precision, with a resolution of 0.5 mm. In the end, about 120 million mesh units were generated for the entire battery pack containing 3,072 cells, which is sufficient to accurately depict the complex geometry of each cell and its internal components.

[0045] (2) Model accuracy verification: After generating the mesh, the system will immediately perform a rigorous accuracy verification. By comparing the generated 3D mesh with the original CT scan point cloud data, the system ensures the digital model's accuracy in reproducing the physical battery. The verification standard is extremely stringent, requiring the maximum reconstruction error to not exceed 0.05 mm.

[0046] The significance of this step is that it provides a precise geometric foundation for the entire digital twin system, and all subsequent physics simulations (such as thermal, electrical, and stress analyses) will be performed on this high-precision 3D model.

[0047] Step 2: Lithium Plating Risk Warning: Calculate the risk index (where experimental verification coefficients k1=0.35, k2=0.42, k3=0.23). Risk Index Calculation: The system calculates the risk index (R0) in real time using a weighted formula. LI This formula integrates three key indicators: (1) Voltage sudden change (weight 0.35): Monitors the absolute value of the rate of change of voltage of a single cell. This indicator can quickly detect sudden faults such as internal short circuits.

[0048] (2) Low-frequency impedance (weight 0.42): The real part of the impedance at a frequency of 0.1 Hz is used to evaluate the internal health status of the cell (such as SEI film (Solid Electrolyte Interphase) growth and lithium deposition). This is the core indicator with the highest weight.

[0049] (3) Temperature non-uniformity (weight 0.23): By calculating the second derivative of the temperature field (temperature gradient), the presence of local hot spots inside the battery can be sensitively detected, so as to avoid the risk of local thermal runaway being masked by the overall average temperature.

[0050] Early warning triggering mechanism: The system sets a clear safety threshold (R) LI >0.75). Once the calculated comprehensive risk index exceeds this threshold, it means that the battery cell has entered a high-risk state. At this time, the cloud monitoring platform will automatically trigger the highest level red alert and accurately locate the specific coordinates of the abnormal battery cell, providing critical information for emergency intervention and maintenance.

[0051] II. Motor system testing, please refer to Figure 4 The diagram shown is a schematic diagram of a motor system testing method: Step 1: Electromagnetic-thermal coupling simulation: Establish a finite element model with 580,000 elements and solve the equations.

[0052] (1) High-precision finite element modeling.

[0053] First, a detailed finite element model containing 580,000 elements was established. This large mesh size ensured that the model could analyze the complex internal geometry of the battery in detail, laying the foundation for obtaining accurate simulation results.

[0054] (2) Solving the multiphysics equations by coupling.

[0055] The simulation process requires solving two core physical equations simultaneously to simulate the heat generated by the current and the resulting temperature change: Electromagnetic field simulation (based on Maxwell's equations): These equations are used to calculate the distribution of current (J) in the conductors inside the battery, which is the source of heat generation.

[0056] Thermal field simulation (based on the heat conduction equation): This equation describes the process of heat generation and transfer. One term in this equation is Joule heat obtained from electromagnetic simulation, which is input as a heat source into the temperature field calculation.

[0057] The core value of this step lies in its realization of physical field coupling analysis from "electricity" to "heat," which can dynamically simulate the heat generation, accumulation, and diffusion process inside the battery under different operating conditions. This allows for accurate prediction of potential local hot spots, providing crucial data for thermal runaway early warning and thermal management design.

[0058] Step 2: Virtual fault injection test: Simulate IGBT gate resistance drift in a digital mirror.

[0059] (1) Injecting a specific fault: When the specified fault type is "IGBT_R_drift" (IGBT gate resistance drift), the system will permanently increase the gate resistance parameter of the IGBT (Insulated Gate Bipolar Transistor) by 15% in the digital mirror of the controller. This parameter drift is a typical manifestation of component aging.

[0060] (2) Perform test verification: After the fault is injected, the system will immediately run the "faulty" digital image under the standard conditions of WLTC (Worldwide Harmonized Light Vehicles Test Cycle) to simulate the real driving state of the vehicle.

[0061] Core objective: This process aims to safely and risk-free assess how the performance of the entire control system (such as inverters and motor drives) would be affected when real-world hardware experiences such parameter drift failures, thereby enabling early prediction of potential failures and verification of fault-tolerant strategies.

[0062] Step 3: Boundary Response Verification: Judgment Criteria (ASIL Level C Requirements).

[0063] (1) Dynamic response performance indicators: Step response performance requirements: Rise time: Must be less than or equal to 80 milliseconds. This measures how quickly the system responds to sudden changes in the input signal.

[0064] Overshoot: must be less than 5%. This ensures that the system does not oscillate excessively or exceed the target value during rapid response.

[0065] (2) Harmonic response performance requirements: Phase lag: must be less than or equal to 10 degrees. This ensures that the system output signal closely tracks changes in the input signal without causing significant time delay.

[0066] Amplitude attenuation: must be less than 3%. This indicates that the system has good gain stability for signals of different frequencies, and the strength of the output signal will not be significantly lost.

[0067] In summary, these metrics collectively define the characteristics a high-performance system should possess: fast response, stable convergence, and accurate frequency tracking capability.

[0068] III. Electronic Control System Detection: Vehicle Information: 800V platform, battery capacity 120kWh; Fault Phenomenon: Charging protocol handshake failed after digital flashing.

[0069] 1. Diagnostic process: Load the electronic control image into the cloud and perform automated testing.

[0070] 2. Test result: Test case “CCS_Handshake_v2.1.5” failed to execute.

[0071] Problem Location: The fault was pinpointed to line 287 of the source file Protocol.c. A protocol handshake timeout issue exists there, with a measured timeout of 500 milliseconds, significantly exceeding the standard's 200 millisecond limit.

[0072] Solution: The diagnostic indicates that this timeout issue needs to be resolved by optimizing the configuration of the Socket communication buffer to ensure that the communication response speed meets the specification requirements.

[0073] The description clearly identifies the fault location, the violated standards, and the exact direction for repair.

[0074] In this embodiment, the vehicle-side sensor can be a quantum encoder, a magnetoresistive encoder, or an optical encoder. The magnetoresistive encoder can employ a TMR (Tunneling Magnetoresistance) sensor, which can reduce costs by 40% while maintaining accuracy at ±0.01°. The optical encoder can integrate an infrared compensation light source, improving its resistance to oil contamination.

[0075] In this embodiment, the model can be simplified. The reduced-order modeling technique uses a simplified mathematical expression to replace the complex electrochemical model for calculating the battery terminal voltage V. term V term [Open circuit voltage (OCV)] - Current (I) × [Internal resistance]; The open-circuit voltage component is obtained by fitting a quadratic polynomial (a0 + a1·SOC + a2·SOC²) with respect to SOC (state of charge), replacing the complex physicochemical relationships. Here, a0, a1, and a2 are the fitting coefficients.

[0076] The internal resistance voltage drop component consists of a constant term R0 and an exponential term (R1·e^(-t / τ1)) that decays over time, used to simulate the dynamic response characteristics of the battery. R0 and R1 are constants.

[0077] Reduced order effect: Through this simplification, the computation speed of the model is increased by 5 times compared to the high-precision microscopic model. This significant advantage in computational efficiency enables the model to be deployed on edge nodes with limited computing resources (such as vehicle controllers or local gateways) to achieve real-time state estimation and prediction.

[0078] In some embodiments, edge nodes determine the priority of data; edge nodes process data in real time and perform alarm operations based on the priority; or, edge nodes upload data to the cloud based on the priority.

[0079] See Figure 5The diagram shows an edge intelligent traffic offloading scheme. In this embodiment, data can be processed in real time based on data priority and alarm operations can be performed or data can be uploaded to the cloud, which can reduce network bandwidth usage by 60%.

[0080] The method provided in the embodiments of the present invention has the following main advantages: 1. Achieve cell-level battery health detection: Solve the problem of early warning of microscopic defects such as lithium plating and SEI film growth.

[0081] 2. Break down the barriers to testing the three-electric system: Establish a multi-physical field coupling fault tracing mechanism for battery-motor-electronic control.

[0082] 3. Reduce the electronic control verification cycle: The software verification time is reduced from 8.2 minutes to 1.5 minutes through digital writing technology.

[0083] The method provided in this embodiment of the invention can improve detection accuracy: regarding the lithium plating detection rate of batteries, the existing technology is 68%, while the method provided in this embodiment is 99.33%, an improvement of 46%; regarding fault location accuracy, the existing technology is at the system level, while the method provided in this embodiment is at the cell level, an improvement of 300%; regarding the IGBT junction temperature estimation error, the existing technology is ±20℃, while the method provided in this embodiment is ±0℃, an improvement of 90%. The method provided in this embodiment of the invention can improve efficiency, reducing the time for electronic control verification from 8.2 minutes to 1.5 minutes, an improvement of 447%; and by reducing the number of real vehicle test iterations through digital pre-writing, the development cost of a single model is reduced by 2.1 million.

[0084] This embodiment also included experimental verification: Test conditions: a pure electric sedan on an 800V platform, ambient temperature 25℃, SOC 50%. Result: The fault detected was a cooling system fault. The method provided in this embodiment demonstrates significant advantages in fault location accuracy and repair efficiency: Traditional fault location methods can only pinpoint the problem to the entire battery pack assembly, resulting in a large scope and vague diagnosis. The method provided in this embodiment can accurately locate the second cooling channel inside module 3, achieving a leap from "overall replacement" to "precise repair." This precise location brings a direct efficiency improvement: the average repair time per vehicle is reduced by approximately 3.2 hours.

[0085] Example 3: Corresponding to the above method embodiments, this invention provides a vehicle cloud-based collaborative offline detection device, see [link to relevant documentation]. Figure 6 The diagram shows a structural schematic of a vehicle cloud-based collaborative off-line inspection device, which includes: The four-dimensional digital twin construction module 61 is used to construct a four-dimensional digital twin; wherein, the four-dimensional digital twin is used to describe the battery mechanism, predict battery risks and implement rigid safety protection from the dimensions of geometry, physical dimension, behavior dimension and rule dimension. The vehicle cloud-based collaborative offline detection module 62 is used for vehicle cloud-based collaborative offline detection based on a four-dimensional digital twin.

[0086] This invention provides a vehicle cloud-based collaborative offline testing device that constructs a four-dimensional digital twin. This four-dimensional digital twin is used to describe battery mechanisms, predict battery risks, and implement rigid safety protection from geometric, physical, behavioral, and rule-based dimensions. Offline testing of the vehicle is then performed based on this four-dimensional digital twin in a cloud-based collaborative manner. This approach enables cell-level battery health testing, breaks down barriers to testing the three-electric system (battery, motor, and electronic control system), and shortens the electronic control verification cycle.

[0087] The aforementioned four-dimensional digital twin construction module is used to establish a point cloud model of the battery pack using computed tomography (CT) scans.

[0088] The aforementioned four-dimensional digital twin construction module is used to describe the circuit characteristics of the battery at a macroscopic scale; to describe the ion diffusion of the battery at a mesoscopic scale; and to describe the atomic interactions of the battery at a microscopic scale.

[0089] The aforementioned four-dimensional digital twin construction module is used for data-driven prediction of batteries by the four-dimensional digital twin through a long short-term memory network artificial intelligence model.

[0090] The aforementioned four-dimensional digital twin construction module is used to constrain the functional safety of the battery by the four-dimensional digital twin through preset functional safety standards.

[0091] The aforementioned vehicle cloud-based collaborative offline detection module is used for vehicle-side sensors to upload data to edge nodes in real time; edge nodes clean the data and transmit the cleaned data stream to the cloud engine; the cloud engine requests simulation prediction from the four-dimensional digital twin based on the cleaned data stream; the four-dimensional digital twin returns multiphysics simulation results to the cloud engine; the cloud engine performs dynamic time warping and virtual-real alignment for the fault diagnosis system based on the multiphysics simulation results; and the fault diagnosis system outputs a component-level location report to the maintenance system.

[0092] The aforementioned vehicle cloud-based collaborative offline detection module is also used by edge nodes to determine the priority of data; edge nodes process data in real time based on priority and execute alarm operations; or, edge nodes upload data to the cloud based on priority.

[0093] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the vehicle cloud-based collaborative offline detection device described above can be referred to the corresponding process in the aforementioned embodiments of the vehicle cloud-based collaborative offline detection method, and will not be repeated here.

[0094] Example 4: This invention also provides an electronic device for running the above-described vehicle cloud-based collaborative offline detection method; see also Figure 7 The diagram shows the structure of an electronic device, which includes a memory 100 and a processor 101. The memory 100 stores one or more computer instructions, which are executed by the processor 101 to implement the above-mentioned vehicle cloud-based collaborative offline detection method.

[0095] Furthermore, Figure 7 The electronic device shown also includes a bus 102 and a communication interface 103, with the processor 101, the communication interface 103 and the memory 100 connected via the bus 102.

[0096] The memory 100 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 103 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 102 may be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0097] Processor 101 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 101 or by instructions in software form. Processor 101 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 100, and processor 101 reads information from memory 100 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0098] This invention also provides a computer-readable storage medium storing computer-executable instructions. When these computer-executable instructions are called and executed by a processor, they cause the processor to implement the aforementioned vehicle cloud-based collaborative offline detection method. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0099] The computer program product of the vehicle cloud-based collaborative offline detection method, apparatus, device, and storage medium provided in the embodiments of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods in the preceding method embodiments. For specific implementation, please refer to the method embodiments, which will not be repeated here.

[0100] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and / or device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0101] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0102] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0103] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0104] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A vehicle cloud-based collaborative offline detection method, characterized in that, The method includes: Construct a four-dimensional digital twin; wherein the four-dimensional digital twin is used to describe battery mechanisms, predict battery risks, and implement rigid safety protection from geometric, physical, behavioral, and rule dimensions. Vehicle off-line inspection is performed in a cloud-based collaborative manner based on the aforementioned four-dimensional digital twin.

2. The method according to claim 1, characterized in that, The geometric dimensions of the four-dimensional digital twin include: The four-dimensional digital twin is used to establish a point cloud model of the battery pack through computed tomography.

3. The method according to claim 1, characterized in that, The physical dimensions of the four-dimensional digital twin include: The four-dimensional digital twin describes the circuit characteristics of the battery at a macroscopic scale; The four-dimensional digital twin describes the ion diffusion of the battery at the mesoscale. The four-dimensional digital twin describes the atomic interactions of the battery at the microscopic scale.

4. The method according to claim 1, characterized in that, The behavioral dimensions of the four-dimensional digital twin include: The four-dimensional digital twin uses a long short-term memory network artificial intelligence model to perform data-driven prediction of batteries.

5. The method according to claim 1, characterized in that, The rule dimensions of the four-dimensional digital twin include: The four-dimensional digital twin constrains the battery's functional safety through preset functional safety standards.

6. The method according to any one of claims 1-5, characterized in that, The steps for offline inspection of vehicles based on the aforementioned four-dimensional digital twin in a cloud-based collaborative manner include: The vehicle's onboard sensors upload data to the edge nodes in real time; The edge node cleans the data and transmits the cleaned data stream to the cloud engine; The cloud engine requests simulation predictions from the cleaned data flow to the four-dimensional digital twin. The four-dimensional digital twin returns multiphysics simulation results to the cloud engine; The cloud engine performs dynamic time warping and virtual-real alignment on the fault diagnosis system based on the multiphysics simulation results. The fault diagnosis system outputs a component-level location report to the maintenance system.

7. The method according to claim 6, characterized in that, After the step of the vehicle's on-board sensors uploading data to the edge nodes in real time, the method further includes: The edge nodes determine the priority of the data; The edge node processes the data in real time and performs an alarm operation based on the priority; or, the edge node uploads the data to the cloud based on the priority.

8. A vehicle cloud-based collaborative offline inspection device, characterized in that, The device includes: A four-dimensional digital twin construction module is used to construct a four-dimensional digital twin; wherein, the four-dimensional digital twin is used to describe battery mechanisms, predict battery risks, and implement rigid safety protection from geometric, physical, behavioral, and rule dimensions. The vehicle cloud-based collaborative offline detection module is used to perform vehicle cloud-based collaborative offline detection based on the four-dimensional digital twin.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing computer-executable instructions that can be executed by the processor, the processor executing the computer-executable instructions to implement the vehicle cloud-based collaborative offline detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the vehicle cloud-based collaborative offline detection method as described in any one of claims 1 to 7.

Images