Vehicle charging fault processing method, device and equipment and storage medium

Abstract

The invention discloses a vehicle charging fault processing method and device, equipment and a storage medium, and the method comprises the steps: collecting communication data in a vehicle charging process, and carrying out the feature extraction of the communication data, and obtaining a feature sequence; matching the feature sequence on a pre-constructed fault propagation tree to obtain a dynamic causal chain set; screening from the dynamic causal chain set to obtain an effective fault chain; and determining a processing strategy corresponding to the effective fault chain, and processing the fault determined by the effective fault chain according to the processing strategy. According to communication data in the charging process, a feature sequence is obtained, so that interaction information among multiple equipment nodes is considered, matching is performed based on the feature sequence and a fault propagation tree to obtain a dynamic causal chain set, and an effective fault chain is screened out from the dynamic causal chain set, so that a charging fault reason is efficiently and accurately determined; and a processing strategy matched with the effective fault chain is determined, so that effective maintenance processing of fault diagnosis is realized.

Description

Technical Field

[0001] This invention relates to the field of fault diagnosis technology, and in particular to a method, apparatus, device, and storage medium for handling vehicle charging faults. Background Technology

[0002] With the development of fault diagnosis technology, more and more automatic diagnosis technologies are being applied to vehicle diagnosis. For example, vehicle charging faults are being diagnosed to promptly identify the cause of the charging failure and perform corresponding maintenance based on the cause. Currently, the most common approach is to rely on a defined rule base. When a fault code is detected, the system matches a preset rule and reports the error type.

[0003] However, current fault diagnosis methods are limited by static rules and can only identify abnormal situations of single device nodes, but cannot identify abnormal interactions of multiple device nodes. Furthermore, complex faults usually require manual recording of bus data and offline analysis. Therefore, existing fault diagnosis methods are not only inefficient, but also prone to inaccurate diagnosis. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for handling vehicle charging faults, so as to realize vehicle charging fault diagnosis and effective handling.

[0005] According to a first aspect of the present invention, a method for handling vehicle charging faults is provided, the method comprising: collecting communication data during the vehicle charging process, and extracting features from the communication data to obtain a feature sequence;

[0006] The feature sequences are matched on a pre-constructed fault propagation tree to obtain a dynamic causal chain set;

[0007] Valid fault chains are obtained by filtering from the set of dynamic causal chains, wherein each valid fault chain includes at least one fault node;

[0008] Determine the processing strategy corresponding to the effective fault chain, and process the faults determined by the effective fault chain according to the processing strategy.

[0009] According to another aspect of the present invention, a charging fault handling apparatus is provided, the apparatus comprising:

[0010] The feature sequence extraction module is used to collect communication data during the vehicle charging process and extract features from the communication data to obtain feature sequences.

[0011] The dynamic causal chain set acquisition module is used to match the feature sequence on a pre-constructed fault propagation tree to obtain a dynamic causal chain set;

[0012] The effective fault chain acquisition module is used to filter and acquire effective fault chains from the dynamic causal chain set, wherein the effective fault chain includes at least one fault node;

[0013] The fault handling module is used to determine the handling strategy corresponding to the effective fault chain, and to handle the faults determined by the effective fault chain according to the handling strategy.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: one or more processors;

[0015] Storage device for storing one or more programs.

[0016] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a storage medium for computer-executable instructions is provided, on which a computer program is stored, which, when executed by a processor, implements the method as described in any of the embodiments of the present invention.

[0018] The technical solution of this invention obtains feature sequences based on communication data during the charging process, thereby taking into account the interaction information between multiple device nodes. It then obtains a dynamic causal chain set by matching the feature sequences with the fault propagation tree, and filters out valid fault chains from them. This allows for efficient and accurate determination of the cause of the charging fault, as well as the determination of a processing strategy that matches the valid fault chain, thus achieving effective maintenance processing for fault diagnosis.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a vehicle charging fault handling method provided in Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart of another vehicle charging fault handling method provided in Embodiment 2 of the present invention;

[0023] Figure 3 This is a schematic diagram of a vehicle charging fault handling device according to Embodiment 3 of the present invention;

[0024] Figure 4 This is a structural block diagram of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, apparatus, product, or terminal device that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or terminal devices.

[0027] Example 1

[0028] Figure 1 This is a flowchart of a vehicle charging fault handling method provided in Embodiment 1 of the present invention. This embodiment is applicable to handling vehicle charging faults. The method can be executed by a vehicle charging fault handling device, which can be implemented in hardware and / or software, and can be integrated into an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0029] S101 collects communication data during the vehicle charging process and extracts features from the communication data to obtain feature sequences.

[0030] Optionally, the system collects communication data during the vehicle charging process and extracts features from the communication data to obtain feature sequences. This includes: collecting communication data between designated devices involved in the vehicle charging process, wherein the designated devices include the charging pile, the battery management system, and the vehicle controller; aligning the communication data with timestamps to obtain preprocessed data, and extracting valid values ​​from the preprocessed data to obtain valid data, wherein the valid data includes time, signal type, device, and numerical value; and extracting features from the valid data to obtain feature sequences.

[0031] Specifically, this embodiment collects communication data during the vehicle charging process. This communication data refers to the interaction data between designated devices involved in the charging process. For example, these designated devices could be the charging pile, battery management system, and vehicle controller. Therefore, the communication data can specifically be the interaction data between the charging pile and the battery management system, the interaction data between the charging pile and the vehicle controller, and the interaction data between the battery management system and the vehicle controller. Of course, this embodiment is merely illustrative and does not limit the specific types of designated devices involved in the charging process or the collected communication data. When collecting data, the sampling rate and timestamp synchronization accuracy can be preset, for example, a sampling rate of 2kHz and a timestamp synchronization accuracy of ±10μs. This embodiment is merely illustrative and does not limit the specific values.

[0032] In this embodiment, after collecting communication data during the charging process, the communication data is preprocessed. This preprocessing specifically includes data alignment and valid data extraction. For example, hardware-level timestamp alignment technology is used to align the communication data of the charging pile, battery management system, and vehicle controller according to the marked timestamps to obtain preprocessed data. Then, valid data such as time, signal type, device, and value are extracted from the preprocessed data, thereby avoiding the waste of computing resources caused by processing invalid data. The format of the obtained valid data can be a tensor (t, signal_ID, value, device_node), where t represents time, signal_ID represents signal type, such as voltage, temperature, current, duty cycle, or signal-to-noise ratio, value represents the value corresponding to the signal type, such as voltage value, and device_node represents device, such as charging pile, battery management system, or vehicle controller. After obtaining the valid data, feature extraction can be performed on the valid data to obtain feature sequences. Of course, this embodiment is only an example and does not limit the specific content of the feature sequences.

[0033] S102, matching the feature sequences on a pre-constructed fault propagation tree to obtain a dynamic causal chain set.

[0034] Optionally, the feature sequence is matched on a pre-constructed fault propagation tree to obtain a set of dynamic causal chains, including: obtaining each feature in the feature sequence; finding fault nodes that match each feature from the fault propagation tree, connecting the fault nodes with the relationship to obtain a first type of dynamic causal chain; extracting independent fault nodes as a second type of dynamic causal chain, and constructing a set of dynamic causal chains based on the first type of dynamic causal chain and the second type of dynamic causal chain.

[0035] Specifically, in this embodiment, a specified number of maintenance records are extracted from the local machine, and fault scenarios are extracted from the maintenance records. The extracted fault scenarios are then integrated to construct a fault propagation tree. The fault propagation tree includes associated fault nodes, and the fault nodes and the relationships between different fault nodes are determined from different fault scenarios. For example, the fault propagation tree includes CAN transceiver aging, signal distortion, or charging handshake failure. Of course, this embodiment is only an example and does not limit the number and type of fault nodes included in the fault propagation tree. It is specifically related to the maintenance records used. The more maintenance records used and the richer the fault scenarios, the more comprehensive the constructed fault propagation tree will be.

[0036] In this embodiment, each feature contained in the feature sequence is obtained, and a fault node matching each feature is searched on the fault propagation tree. For example, when the feature is that the signal-to-noise ratio exceeds a threshold, a query is performed on the fault propagation tree to obtain a fault node, such as signal distortion. Of course, this embodiment is only an example and does not limit the type of fault node found. After obtaining all fault nodes matching the feature sequence by searching the fault propagation tree, a dynamic causal chain is constructed based on the fault nodes. For example, after determining the fault node, the fault nodes with relationships found according to the feature sequence are connected based on the known correlations on the fault propagation tree to obtain a first type of dynamic causal chain. The number of first type dynamic causal chains can be multiple, and the number of nodes contained in each first type of dynamic causal chain can be different. For example, the first type of dynamic causal chain includes CAN transceiver aging. In this embodiment, the number of faulty nodes contained in each first type of dynamic causal chain is not limited.

[0037] In addition, in this embodiment, after connecting the fault nodes with related relationships, if there are still isolated fault nodes that are not related to other fault nodes, each isolated fault node is regarded as a second type of dynamic causal chain. For example, the second type of dynamic causal chain includes battery thermal runaway. Therefore, the number of the second type of dynamic causal chains is the same as the number of the remaining isolated fault nodes. In this embodiment, the specific number of the second type of dynamic causal chains is not limited.

[0038] In this embodiment, after obtaining all the first type of dynamic causal chains and the second type of dynamic causal chains, a dynamic causal chain set A = {battery thermal runaway, ...} is constructed based on the first type of dynamic causal chains and the second type of dynamic causal chains. In this embodiment, the number of dynamic causal chains contained in the dynamic causal chain set is not limited.

[0039] S103, select valid fault chains from the dynamic causal chain set.

[0040] Optionally, a valid fault chain can be obtained by filtering from the set of dynamic causal chains, including: obtaining a pre-configured list of valid fault node counts, wherein the list of valid fault node counts includes the number of valid nodes corresponding to each fault node in the fault propagation tree; when the number of valid nodes corresponding to each fault node in the dynamic causal chain is not greater than the actual number of nodes in the dynamic causal chain, the dynamic causal chain is determined to be a valid fault chain.

[0041] Specifically, in this embodiment, after obtaining the dynamic causal chain set, valid fault chains are filtered out from the set. The filtering is determined by referring to a pre-configured list of valid fault node counts, as shown in Table 1 below:

[0042]

[0043] The list of effective nodes for each fault node includes the number of effective nodes corresponding to each fault node in the fault propagation tree. The number of effective nodes refers to the minimum number of nodes required for a fault node to cause a charging fault. For example, in the case of battery thermal runaway, the node itself can determine that it has caused a charging fault, so the corresponding number of effective nodes is 1. In the case of signal distortion, it cannot cause a charging fault on its own, and it needs to be combined with at least one fault node to determine that it has caused a charging fault. Of course, this embodiment is only an example and does not limit the specific value of the number of effective nodes corresponding to each fault node. Users can set or adjust it according to the actual situation of the vehicle.

[0044] In a specific implementation, a dynamic causal chain is considered a valid fault chain when the number of valid nodes corresponding to each fault node in the dynamic causal chain is not greater than the actual number of nodes in the dynamic causal chain. For example, when the set of dynamic causal chains includes the dynamic causal chain "Battery thermal runaway," since the number of valid nodes for this fault node is determined to be 1 by looking up Table 1, and the actual number of nodes in the dynamic causal chain is also 1, this dynamic causal chain is determined to be a valid fault chain. That is, the charging fault is determined solely based on the battery thermal runaway fault node. Another example is when the set of dynamic causal chains includes the dynamic causal chain "CAN transceiver aging" (92% confidence level). Signal distortion When the charging handshake fails, since the effective number of nodes for CAN transceiver aging is 3, the effective number of nodes for signal distortion is 2, and the effective number of nodes for charging handshake failure is 1, and the actual number of nodes in the dynamic causal chain is 3, and since the effective number of nodes corresponding to each fault node is no greater than the actual number of nodes in the dynamic causal chain (3), it can be determined that the dynamic causal chain is also a valid fault chain. When the dynamic causal chain set includes the dynamic causal chain "voltage exceeding the limit", since the effective number of nodes for voltage exceeding the limit is 2, and the actual number of nodes in the dynamic causal chain is 1, and since the effective number of nodes for the fault node is greater than the actual number of nodes in the dynamic causal chain, it is determined that the dynamic causal chain is not a valid fault chain. That is, it is uncertain whether the charging failure will be caused solely by the fault node "voltage exceeding the limit". Thus, it can be seen that the valid fault chain in this embodiment includes at least one fault node. Of course, this embodiment is only an example and does not limit the specific method of determining the valid fault chain.

[0045] S104, determine the processing strategy corresponding to the effective fault chain, and process the faults determined by the effective fault chain according to the processing strategy.

[0046] Specifically, in this embodiment, after identifying a valid fault chain, the cause of the charging fault can be determined based on the valid fault chain, and a corresponding handling strategy can be determined for the cause of the fault, thereby performing fault handling according to the handling strategy. In addition, this embodiment saves the fault repair record, so that when the same fault cause is encountered again in the future, the corresponding handling strategy in the fault repair record can be referred to for automatic fault handling. Of course, this embodiment is only an example and does not limit the specific method of fault handling.

[0047] In this embodiment, no user involvement is required during the charging fault diagnosis process. Both the detection rate of composite faults and the accuracy of fault diagnosis are greatly improved, solving the problem that traditional solutions cannot identify multi-device coupled faults.

[0048] The technical solution of this invention obtains feature sequences based on communication data during the charging process, thereby taking into account the interaction information between multiple device nodes. It then obtains a dynamic causal chain set by matching the feature sequences with the fault propagation tree, and filters out valid fault chains from them. This allows for efficient and accurate determination of the cause of the charging fault, as well as the determination of a processing strategy that matches the valid fault chain, thus achieving effective maintenance processing for fault diagnosis.

[0049] Example 2

[0050] Figure 2 This is a flowchart of another vehicle charging fault handling method provided by an embodiment of the present invention. Based on the above embodiments, this embodiment specifically describes the handling strategy corresponding to the valid fault chain and the handling of the faults determined according to the handling strategy. Figure 2 As shown, the method includes:

[0051] S201 collects communication data during the vehicle charging process and extracts features from the communication data to obtain feature sequences.

[0052] Optionally, the system collects communication data during the vehicle charging process and extracts features from the communication data to obtain feature sequences. This includes: collecting communication data between designated devices involved in the vehicle charging process, wherein the designated devices include the charging pile, the battery management system, and the vehicle controller; aligning the communication data with timestamps to obtain preprocessed data, and extracting valid values ​​from the preprocessed data to obtain valid data, wherein the valid data includes time, signal type, device, and numerical value; and extracting features from the valid data to obtain feature sequences.

[0053] S202, matching the feature sequences on a pre-constructed fault propagation tree to obtain a dynamic causal chain set.

[0054] Optionally, the feature sequence is matched on a pre-constructed fault propagation tree to obtain a set of dynamic causal chains, including: obtaining each feature in the feature sequence; finding fault nodes that match each feature from the fault propagation tree, connecting the fault nodes with the relationship to obtain a first type of dynamic causal chain; extracting independent fault nodes as a second type of dynamic causal chain, and constructing a set of dynamic causal chains based on the first type of dynamic causal chain and the second type of dynamic causal chain.

[0055] S203, select valid fault chains from the dynamic causal chain set.

[0056] Optionally, a valid fault chain can be obtained by filtering from the set of dynamic causal chains, including: obtaining a pre-configured list of valid fault node counts, wherein the list of valid fault node counts includes the number of valid nodes corresponding to each fault node in the fault propagation tree; when the number of valid nodes corresponding to each fault node in the dynamic causal chain is not greater than the actual number of nodes in the dynamic causal chain, the dynamic causal chain is determined to be a valid fault chain.

[0057] S204, determine the score of each valid fault chain, and determine the level of the valid fault chain based on the score.

[0058] Optionally, the score for each valid fault chain is determined, including: obtaining the actual number of nodes in the valid fault chain and the number of valid nodes corresponding to each fault node in the valid fault chain; and calculating the score of the valid fault chain based on the actual number of nodes and the number of valid nodes.

[0059] Specifically, in this embodiment, after identifying the valid fault chains, the corresponding processing strategies will be further determined. Different valid fault chains will have different processing strategies. Before determining the processing strategies, this embodiment will first determine the score and level of the valid fault chains. In this embodiment, when determining the score of each valid fault chain, two dimensions of information need to be considered: one is the actual number of nodes in the valid fault chain itself, and the other is the number of valid nodes corresponding to each fault node in the valid fault chain. The fewer the number of valid nodes, the higher the score of the corresponding valid fault chain.

[0060] For example, for a valid fault chain: For a handshake failure, the actual number of nodes in the effective fault chain is 3. Referring to Table 1 above, the effective number of nodes for CAN transceiver aging is 3. The effective number of nodes for signal distortion is 2. The effective number of nodes for charging handshake failure is 2. Therefore, the score of the effective fault chain can be calculated using the following formula: X = 3 × 0.4 + 1 / (3 + 2 + 1) × 0.6 = 1.3. Here, 0.4 is the first weight corresponding to the actual number of nodes in the effective fault chain, and 0.6 is the second weight corresponding to the reciprocal of the sum of the effective node numbers. Of course, this embodiment is only an example and does not limit the specific calculation method for the score of the effective fault chain.

[0061] In addition, different levels are determined for different scores in this embodiment. The higher the level, the more severe the fault. For example, a score of 15 or above is classified as Level 1, a score between 10 and 15 is classified as Level 2, and a score below 10 is classified as Level 3. Of course, this embodiment is only an example and does not limit the specific values ​​of the level classification.

[0062] S205, determine the handling strategy based on the level and the fault nodes included in the effective fault chain.

[0063] Optionally, a handling strategy is determined based on the level and the fault nodes included in the effective fault chain, including: determining the handling type based on the level, wherein the handling type includes on-site handling, maintenance and repair and design optimization; determining the handling method based on the fault node, and determining the handling strategy based on the handling type and handling method.

[0064] Specifically, different levels correspond to different handling types. For example, since level three faults are the most severe, the corresponding handling type is on-site handling, which requires expert personnel to handle the actual fault on-site. Level two faults are of the next less severe severity, so the corresponding handling type is maintenance, which does not require going to the site and can be debugged and maintained remotely by logging into the system. Level three faults are of the least severe severity, so the corresponding handling type is design optimization, which only requires optimizing and adjusting the relevant charging parameters.

[0065] Furthermore, the processing types mentioned above only indicate the specific processing modes adopted for charging faults, but the specific processing methods need to be determined based on the fault nodes. For example, when the CAN transceiver of the fault node is aging, the processing method is to update the CAN transceiver. When there are multiple fault nodes among the effective fault nodes, a comprehensive analysis of the above fault nodes is needed to determine the processing method for the effective fault chain. When both the processing type and processing method are determined, the processing type and processing method are combined to determine the processing strategy for charging faults. Of course, this embodiment is only an example and does not limit the specific determination method of the processing strategy.

[0066] It is worth mentioning that this implementation determines the appropriate handling strategy for the faults identified in the effective fault chain. Simple faults can be resolved by direct debugging, avoiding unnecessary returns to the factory for repair. It can accurately provide the cause of the fault and the fault repair strategy. The fault handling strategy promotes design optimization and significantly shortens the design iteration cycle.

[0067] S206, Process the faults identified in the effective fault chain according to the processing strategy.

[0068] The technical solution of this invention obtains feature sequences based on communication data during the charging process, thereby taking into account the interaction information between multiple device nodes. It then obtains a dynamic causal chain set by matching the feature sequences with the fault propagation tree, and filters out valid fault chains from them. This allows for efficient and accurate determination of the cause of the charging fault, as well as the determination of a processing strategy that matches the valid fault chain, thus achieving effective maintenance processing for fault diagnosis.

[0069] Example 3

[0070] Figure 3This is a schematic diagram of a vehicle charging fault handling device provided in an embodiment of the present invention. Figure 3 As shown, the device includes: a feature sequence extraction module 310, a dynamic causal chain set acquisition module 320, an effective fault chain acquisition module 330, and a fault processing module 340.

[0071] The feature sequence extraction module 310 is used to collect communication data during the vehicle charging process and extract features from the communication data to obtain feature sequences.

[0072] The dynamic causal chain set acquisition module 320 is used to match feature sequences on a pre-built fault propagation tree to obtain a dynamic causal chain set;

[0073] The effective fault chain acquisition module 330 is used to filter and acquire effective fault chains from the dynamic causal chain set, wherein the effective fault chain includes at least one fault node;

[0074] The fault handling module 340 is used to determine the handling strategy corresponding to the valid fault chain, and to handle the faults determined by the valid fault chain according to the handling strategy.

[0075] Optionally, the feature sequence extraction module 310 is used to collect communication data between designated devices involved in the vehicle charging process, wherein the designated devices include charging piles, battery management systems and vehicle controllers.

[0076] The communication data is timestamped to obtain preprocessed data, and the preprocessed data is extracted to obtain valid data. The valid data includes time, signal type, device and value. The signal type includes voltage, temperature, current, duty cycle or signal-to-noise ratio.

[0077] Feature extraction is performed on valid data to obtain feature sequences.

[0078] Optionally, a dynamic causal chain set acquisition module 320 is used to acquire each feature in the feature sequence;

[0079] Find the fault nodes that match each feature on the fault propagation tree, and connect the fault nodes with the relationship to obtain the first type of dynamic causal chain;

[0080] Independent faulty nodes are extracted as the second type of dynamic causal chain, and a set of dynamic causal chains is constructed based on the first and second types of dynamic causal chains.

[0081] Optionally, the effective fault chain acquisition module 330 is used to acquire a pre-configured list of effective fault node counts, wherein the list of effective fault node counts includes the number of effective nodes corresponding to each fault node in the fault propagation tree.

[0082] When the number of valid nodes corresponding to each fault node in a dynamic causal chain is not greater than the actual number of nodes in the dynamic causal chain, the dynamic causal chain is determined to be a valid fault chain.

[0083] Optionally, the fault handling module 340 includes a handling strategy determination unit, used to determine the score of each valid fault chain and determine the level of the valid fault chain based on the score;

[0084] The handling strategy is determined based on the level and the fault nodes included in the effective fault chain.

[0085] Optionally, a processing strategy determination unit is used to obtain the actual number of nodes in the effective fault chain and the number of effective nodes corresponding to each fault node in the effective fault chain.

[0086] The score for a valid fault chain is calculated based on the actual number of nodes and the number of valid nodes.

[0087] Optionally, the treatment strategy determination unit is also used to determine the treatment type based on the level, wherein the treatment type includes on-site handling, maintenance and repair, and design optimization;

[0088] The handling method is determined based on the faulty node, and the handling strategy is determined based on the handling type and handling method.

[0089] The vehicle charging fault handling device provided in this embodiment of the invention can execute a vehicle charging fault handling method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0090] Example 4

[0091] Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0092] The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the invention described and / or claimed herein.

[0093] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0094] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other electronic devices through computer networks such as the Internet and / or various telecommunications networks.

[0095] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle charging fault handling methods.

[0096] That is, during the isothermal and isobaric ensemble simulation of molecular dynamics, if the long-range electrostatic force calculation conditions are met, then three-dimensional convolution calculations are performed on each grid point within the three-dimensional grid divided by the cuboid constraint space. Each grid point in the three-dimensional grid is used to simulate the spatial arrangement of atoms in the set molecular system. At the same time, in order to meet the isothermal and isobaric conditions, the size of the cuboid constraint space is dynamically adjusted during the simulation.

[0097] When performing a 3D convolution calculation on a target grid point, the 3D grid point coordinates of the target grid point are calculated based on the current size of the cuboid constrained space, and the target floating-point number required to calculate the 3D convolution factor is determined based on the 3D grid point coordinates. The convolution factor includes a target exponential function with the target floating-point number as input, and the target floating-point number is located in an infinite range.

[0098] Based on the first fixed-point scale value under the preset storage bit width, calculate the fixed-point grid factor corresponding to the target floating-point number, and convert the fixed-point grid factor into a mapped fixed-point grid factor according to the storage bit width and the first fixed-point scale value, wherein the floating-point number corresponding to the mapped fixed-point grid factor is located in a finite interval.

[0099] The fixed-point exponent calculation result corresponding to the mapped fixed-point grid factor is calculated with reference to a pre-set fitting table, and the target calculation result of the target exponent function is obtained by using the second fixed-point scale value corresponding to the fixed-point exponent calculation result; wherein, the fitting table includes fitting values ​​at each level obtained by Taylor fitting expansion of a specified floating-point number according to a specified number of segments.

[0100] Based on the three-dimensional convolution factor calculated from the target calculation result, the three-dimensional convolution calculation result of the target grid points is calculated for the calculation of long-range electrostatic force.

[0101] In some embodiments, the vehicle charging fault handling method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle charging fault handling method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle charging fault handling method by any other suitable means (e.g., by means of firmware).

[0102] Various embodiments of the apparatuses and techniques described above herein can be implemented in digital electronic circuit devices, integrated circuit devices, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), device-on-a-chip (SoC) devices, complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable device including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage device, at least one input device, and at least one output device, and transmitting data and instructions to the storage device, the at least one input device, and the at least one output device.

[0103] Computer programs used to implement the vehicle charging fault handling method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the processor of a general-purpose computer, a special-purpose computer, or other non-stop data migration device, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs can be executed entirely on the machine, partially on the machine, or as a standalone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0104] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution apparatus, device, or electronic device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage electronics, magnetic storage electronics, or any suitable combination thereof.

[0105] To provide interaction with a user, the devices and techniques described herein can be implemented on an electronic device having: a display device (e.g., a touchscreen) for displaying information to the user; and buttons through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0106] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0107] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for handling vehicle charging faults, characterized in that, The method includes: Collect communication data during the vehicle charging process, and extract features from the communication data to obtain feature sequences; The feature sequences are matched on a pre-constructed fault propagation tree to obtain a dynamic causal chain set; Valid fault chains are obtained by filtering from the set of dynamic causal chains, wherein each valid fault chain includes at least one fault node; Determine the processing strategy corresponding to the effective fault chain, and process the faults determined by the effective fault chain according to the processing strategy.

2. The method according to claim 1, characterized in that, The process of collecting communication data during vehicle charging and extracting feature sequences from the communication data includes: The system collects communication data between designated devices involved in the vehicle charging process, wherein the designated devices include a charging pile, a battery management system, and a vehicle controller. The communication data is timestamped to obtain preprocessed data, and the preprocessed data is extracted to obtain valid data. The valid data includes time, signal type, device, and value. The signal type includes voltage, temperature, current, duty cycle, or signal-to-noise ratio. The feature sequence is obtained by performing feature extraction on the valid data.

3. The method according to claim 1, characterized in that, The step of matching the feature sequence on a pre-constructed fault propagation tree to obtain a dynamic causal chain set includes: Obtain each feature from the feature sequence; Find the fault nodes that match each feature on the fault propagation tree, and connect the fault nodes with the relationship to obtain the first type of dynamic causal chain; Independent faulty nodes are extracted as a second type of dynamic causal chain, and the dynamic causal chain set is constructed based on the first type of dynamic causal chain and the second type of dynamic causal chain.

4. The method according to claim 1, characterized in that, The step of filtering and obtaining valid fault chains from the dynamic causal chain set includes: Obtain a pre-configured list of valid nodes for faulty nodes, wherein the list of valid nodes for faulty nodes includes the number of valid nodes corresponding to each faulty node in the fault propagation tree; When the number of valid nodes corresponding to each fault node in the dynamic causal chain is not greater than the actual number of nodes in the dynamic causal chain, the dynamic causal chain is determined to be the valid fault chain.

5. The method according to claim 1, characterized in that, The process for determining the handling strategy corresponding to the valid fault chain includes: Determine the score of each effective fault chain, and determine the level of the effective fault chain based on the score; The processing strategy is determined based on the level and the faulty nodes included in the effective fault chain.

6. The method according to claim 5, characterized in that, Determining the score for each of the effective fault chains includes: Obtain the actual number of nodes in the effective fault chain, and the number of effective nodes corresponding to each fault node in the effective fault chain; The score of the effective fault chain is calculated based on the actual number of nodes and the effective number of nodes.

7. The method according to claim 5, characterized in that, Determining the processing strategy based on the level and the fault nodes included in the effective fault chain includes: The treatment type is determined based on the level, wherein the treatment type includes on-site handling, maintenance and repair, and design optimization; The processing method is determined based on the faulty node, and the processing strategy is determined based on the processing type and the processing method.

8. A charging fault handling device, characterized in that, The device includes: The feature sequence extraction module is used to collect communication data during the vehicle charging process and extract features from the communication data to obtain feature sequences. The dynamic causal chain set acquisition module is used to match the feature sequence on a pre-constructed fault propagation tree to obtain a dynamic causal chain set; The effective fault chain acquisition module is used to filter and acquire effective fault chains from the dynamic causal chain set, wherein the effective fault chain includes at least one fault node; The fault handling module is used to determine the handling strategy corresponding to the effective fault chain, and to handle the faults determined by the effective fault chain according to the handling strategy.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-7.

10. A storage medium for computer-executable instructions, wherein a computer program is stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images