Fault diagnosis method and device, electronic equipment and storage medium

Abstract

The invention discloses a fault diagnosis method and device, electronic equipment and a storage medium, and relates to the technical field of vehicle diagnosis. The fault diagnosis method comprises the following steps: acquiring equipment operation state information of the unmanned vehicle, determining abnormal information in the equipment operation state information, and determining a first type of fault corresponding to the abnormal information and a first fault level of the first type of fault according to a preset rule base; when the first type of fault does not exist, determining a second type of fault of the unmanned vehicle and the fault probability of the second type of fault through the preset fault recognition model and the abnormal data; and determining a second fault level of a second type of fault according to the fault probability, and determining a fault diagnosis result according to the first type of fault, the first fault level, the second type of fault and the second fault level. According to the embodiment of the invention, the accuracy and efficiency of determining the fault diagnosis result are improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle diagnostic technology, and in particular to a fault diagnosis method, device, electronic device, and storage medium. Background Technology

[0002] With the advancement of smart city construction, unmanned low-speed sanitation vehicles are gradually becoming more common in urban cleaning operations. These vehicles can effectively address the pain points of traditional sanitation operations, such as high labor costs, low efficiency, and significant safety risks, and are particularly suitable for low-speed scenarios such as urban roads, parks, and residential areas.

[0003] However, current fault diagnosis for unmanned low-speed sanitation vehicles relies on manual on-site operation with diagnostic equipment. After a fault occurs, manual dispatch is required, and diagnosing a single vehicle is time-consuming, failing to meet the needs of handling multiple vehicles simultaneously. Furthermore, faulty vehicles left on roads can easily cause traffic congestion and even accidents, especially on main roads or during peak hours. The diagnostic data lacks systematic analysis, making it difficult to support preventative maintenance decisions. Therefore, how to achieve automated diagnosis of unmanned low-speed sanitation vehicles while ensuring fault accuracy has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a fault diagnosis method, device, electronic device, and storage medium to solve the problem that existing technologies cannot automatically diagnose faults in unmanned low-speed sanitation vehicles.

[0005] According to one aspect of the present invention, a fault diagnosis method is provided, wherein the method includes:

[0006] Acquire the equipment operation status information of the unmanned vehicle, determine the abnormal information in the equipment operation status information, and determine the first type of fault and the first fault level of the first type of fault according to the preset rule base;

[0007] In the absence of a first type of fault, the second type of fault and the probability of the second type of fault of the unmanned vehicle are determined by the preset fault identification model and the abnormal data;

[0008] The second fault level of the second type of fault is determined based on the fault probability, and the fault diagnosis result is determined according to the first type of fault, the first fault level, the second type of fault, and the second fault level.

[0009] According to another aspect of the present invention, a fault diagnosis apparatus is provided, wherein the apparatus comprises:

[0010] An anomaly determination module is used to acquire the equipment operation status information of the unmanned vehicle, determine the anomaly information in the equipment operation status information, and determine the first type of fault and the first fault level of the first type of fault according to a preset rule base.

[0011] The data identification module is used to determine the second type of fault and the probability of the second type of fault of the unmanned vehicle by means of the preset fault identification model and the abnormal data when the first type of fault does not exist.

[0012] The fault determination module is used to determine the second fault level of the second type of fault based on the fault probability, and to determine the fault diagnosis result according to the first type of fault, the first fault level, the second type of fault, and the second fault level.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform a fault diagnosis method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement a fault diagnosis method according to any embodiment of the present invention.

[0018] The technical solution of this invention obtains the equipment operation status information of an unmanned vehicle, identifies abnormal information in the equipment operation status information, and determines the first type of fault and the first fault level of the first type of fault according to a preset rule base, thereby achieving rapid judgment of simple faults. When there is no first type of fault, the probability of the second type of fault and the second type of fault of the unmanned vehicle is determined by a preset fault identification model and abnormal data. The second fault level of the second type of fault is determined according to the fault probability. The fault diagnosis result is determined according to the first type of fault, the first fault level, the second type of fault, and the second fault level. This achieves accurate identification of complex faults through in-depth analysis and improves the accuracy of determining the fault diagnosis result. At the same time, by first determining whether there is a first type of fault and then judging the fault by the preset fault identification model, resource waste is avoided.

[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 fault diagnosis method provided in Embodiment 1 of the present invention;

[0022] Figure 2 This is a flowchart of a fault diagnosis method provided according to Embodiment 2 of the present invention;

[0023] Figure 3 This is a structural architecture diagram of a fault diagnosis system provided according to Embodiment 3 of the present invention;

[0024] Figure 4 This is a flowchart of a fault diagnosis method provided in Embodiment 3 of the present invention;

[0025] Figure 5 This is a schematic diagram of the structure of a fault diagnosis device according to Embodiment 4 of the present invention;

[0026] Figure 6 This is a schematic diagram of the structure of an electronic device that implements a fault diagnosis method according to an embodiment of the present invention. Detailed Implementation

[0027] 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.

[0028] 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, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises 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 apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a fault diagnosis method according to Embodiment 1 of the present invention. This embodiment is applicable to fault diagnosis of unmanned low-speed sanitation vehicles. The method can be executed by a fault diagnosis device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] S110. Obtain the equipment operation status information of the unmanned vehicle, determine the abnormal information in the equipment operation status information, and determine the first type of fault and the first fault level of the first type of fault according to the preset rule base.

[0032] Among them, an unmanned vehicle is an intelligent vehicle that achieves unmanned driving through a computer system and various sensors. For example, an unmanned vehicle may include, but is not limited to, an unmanned low-speed sanitation vehicle. Equipment operating status information can be understood as the operating parameter information of the unmanned vehicle during operation. For example, equipment operating parameters may include, but are not limited to, information such as battery state of charge (SOC), battery voltage, motor temperature, and vehicle speed. In actual operation, sensors can be installed on the unmanned vehicle to collect its equipment operating status information. Abnormal information refers to data in the equipment operating status information that deviates from the normal range and may cause malfunctions. For example, abnormal information can be any type of data in the equipment operating status information. A preset rule base can be understood as a pre-set database for storing preset threshold rules; a corresponding preset threshold rule exists for each type of abnormal data. A first type of fault refers to the fault type obtained by fault diagnosis according to the preset rule base. In one embodiment, a first type of fault may include, but is not limited to, sensor disconnection, motor overheating, or abnormal tire pressure. A first fault level can be understood as the level corresponding to the first type of fault; different fault repair methods may exist for different first fault levels. Generally, the first fault level for each first type of fault can be pre-set.

[0033] In this embodiment, information such as battery SOC, battery voltage, motor temperature, and vehicle speed of the autonomous vehicle can be collected by pre-set sensors as equipment operating status information. Generally, different collection frequencies can be set for each type of equipment operating status information. For example, the collection frequency for battery voltage can be 10Hz, the collection frequency for motor temperature can be 5Hz, and the collection frequency for vehicle speed can be 20Hz. These are not limited and can be changed according to business needs. Then, abnormal information in the equipment operating status information is identified. In actual operation, abnormal judgment rules can be pre-set, such as battery SOC fluctuation > 3% / minute, motor temperature change range > 8°C within 1 minute, and sudden acceleration or deceleration of the vehicle. When the abnormal judgment rules are met, the information is confirmed as abnormal. The abnormal information is then matched against a pre-set threshold rule in a pre-set rule base to determine whether the abnormal information meets the pre-set threshold rule. If it does, the fault information corresponding to the pre-set threshold rule is determined as the first type of fault of the autonomous vehicle, and the fault level corresponding to the target threshold rule is taken as the first fault level of the first type of fault. If the conditions are met, no first type of fault is generated.

[0034] S120. When there is no first type of fault, determine the second type of fault and the fault probability of the unmanned vehicle by using a preset fault identification model and abnormal data.

[0035] The preset fault identification model can be understood as a pre-set model used to identify the second type of fault of the drone and the probability of the second type of fault. Generally, the preset fault identification model can be installed on a cloud server. The preset fault identification model consists of a Long Short-Term Memory (LSTM) network model and a random forest model. The fault probability can be understood as the likelihood of a second type of fault occurring.

[0036] In this embodiment, time-domain and frequency-domain features of the anomaly information can be extracted. These features are then input into a preset fault identification model. The model assigns the anomaly information to each fault type based on the probability of each feature being classified according to the time-domain and frequency-domain characteristics. The type corresponding to the maximum probability is designated as the second type of fault, and the probability of the second type of fault is taken as the fault probability. In actual operation, the average value, variance, and peak value of parameters in the anomaly information can be determined as time-domain features. The anomaly information is then subjected to Fourier transform to extract the frequency distribution of motor temperature and vehicle speed, and the proportion of abnormal frequencies, which are used as frequency-domain features. The time-domain and frequency-domain features are input into the Long Short-Term Memory (LSTM) network model and the Random Forest model of the preset fault identification model, respectively, to calculate the probability of each fault type. The results from the LSM network model and the Random Forest model are then weighted and summed to determine the fault type corresponding to the final maximum value, which is taken as the second type of fault. The weighted summation probability is taken as the fault probability of the second type of fault. In one embodiment, since there can be multiple abnormal data, there may be data quality issues due to misalignment of data time. Preprocessing operations can be performed on the abnormal information, such as removing extreme values ​​of sensor false alarms, aligning different abnormal information in time, and standardizing the data.

[0037] S130. Determine the second fault level of the second type of fault based on the fault probability, and determine the fault diagnosis result according to the first type of fault, the first fault level, the second type of fault, and the second fault level.

[0038] The second fault level can be understood as the level corresponding to the second type of fault. Different fault repair methods can exist for different second fault levels. Generally, the second fault level for each type of fault can be determined by the fault probability. A fault probability range for each fault level can be preset, and the fault level corresponding to the fault probability range to which the fault probability belongs is determined as the second fault level. The fault diagnosis result can be understood as the final diagnosis result.

[0039] In this embodiment, a pre-set fault probability interval can be extracted to determine the fault probability interval to which the fault probability belongs, and the fault level corresponding to the fault probability interval can be determined as the second fault level of the second type of fault. Then, it is determined whether a first type of fault exists. If a first type of fault exists, the first type of fault and the first fault level can be used as the fault diagnosis result; if a first type of fault does not exist, the second type of fault and the second fault level can be used as the fault diagnosis result.

[0040] In this embodiment of the invention, by acquiring the equipment operating status information of an unmanned vehicle, abnormal information in the equipment operating status information is identified, and a first type of fault and a first fault level of the first type of fault are determined according to a preset rule base, thus achieving rapid judgment of simple faults. When there is no first type of fault, the probability of a second type of fault and a second type of fault of the unmanned vehicle is determined by a preset fault identification model and abnormal data. The second fault level of the second type of fault is determined according to the fault probability, and the fault diagnosis result is determined according to the first type of fault, the first fault level, the second type of fault, and the second fault level. This achieves accurate identification of complex faults through in-depth analysis and improves the accuracy of determining the fault diagnosis result. At the same time, by first determining whether there is a first type of fault and then judging the fault by the preset fault identification model, resource waste is avoided.

[0041] In one embodiment, after determining the fault diagnosis result according to the first type of fault, the first fault level, the second type of fault, and the second fault level, the method further includes:

[0042] When the second type of fault is the target level, determine the type of the current location of the unmanned vehicle, determine the scope of the fault impact according to the type, and determine the repair urgency of the second type of fault.

[0043] The priority of the second type of fault and the second fault shall be determined according to the fault probability, the scope of the fault impact and the urgency of maintenance.

[0044] Extract the first fault priority of the first type of fault from the pre-set list, determine the fault repair order according to the first fault priority and the second fault priority, and match the target repair team according to the fault repair order.

[0045] The target level can be understood as the fault level requiring maintenance. Generally, multiple levels can be set for the second fault level, with higher levels indicating greater urgency. Some lower-level faults may not require maintenance. The "type" refers to the environmental type corresponding to the current location; for example, the type could include main roads, secondary roads, and the interior of a residential area. The impact range of a fault differs for different types, and generally, the impact range for each type can be pre-set. Maintenance urgency refers to the urgency at which the unmanned vehicle needs maintenance. Generally, maintenance urgency can be determined by the direct hazard of the fault, its impact on operations, and the safety risk level. In actual operation, the hazards of different types of faults to the unmanned vehicle vary. For example, the direct hazard of a fault can include severely degraded component functionality, scrapped core components, or no impact on core functions; the impact on operations can include, but is not limited to, complete inability to operate, severe impact on operations, slight impact on operations, and no impact; the safety risk level can include high risk, medium risk, and low risk. Fault scores can be pre-set for the direct hazard of the fault, its impact on operations, and the safety risk level, and maintenance urgency can be determined based on these scores. The second fault priority refers to the order in which the second type of fault is repaired. The target maintenance team refers to the team that performs maintenance work on the autonomous vehicle; different maintenance teams can repair different types of faults.

[0046] In this embodiment, when the second type of fault is at the target level, the current location of the unmanned vehicle can be determined, and then the type of the current location can be determined, matching the fault impact range of that type. In actual operation, the type can include at least main roads, secondary roads, and the area within a residential community, and the fault impact range corresponding to each type can be pre-set. In one embodiment, each fault impact range can be quantified into a numerical value. The direct hazard level, the impact on the operation, and the safety risk level of the fault are determined according to the second type of fault, and the maintenance urgency is calculated based on these factors. In actual operation, the direct hazard level, the impact on the operation, and the safety risk level can be quantitatively scored separately, and the sum of these scores is used as the maintenance urgency. Corresponding thresholds can be set for fault probability, fault impact range, and maintenance urgency. These thresholds can be different, and each can be multiplied by its corresponding threshold to determine the sum of the products. The second fault priority is determined based on the sum of these products. For example, with a fault severity threshold of 0.5, a fault impact range threshold of 0.3, and a repair urgency threshold of 0.2, the sum = (fault severity × 0.5) + (fault impact range × 0.3) + (repair urgency × 0.2). For different fault priorities, corresponding score ranges can also be set, and the score range corresponding to the sum can be determined as the second fault priority.

[0047] In one embodiment, the direct hazard level of a fault can be categorized as follows: 30 points for causing the scrapping of core components, 20 points for causing severe functional degradation, and 10 points for not affecting core functions. Regarding the impact of a fault on operations, 40 points can be assigned for complete inability to operate, 30 points for severely affecting operations, 20 points for slightly affecting operations, and 10 points for no impact. Similarly, the safety risk level can be categorized as follows: high risk 30 points, medium risk 20 points, and low risk 10 points. The sum of the direct hazard level, the impact on operations, and the safety risk level is used as the maintenance urgency. The fault's impact range can also be quantified into a score; for example, the impact range of a fault on a main road can be set to 30 points, the impact range of a fault on a secondary road to 20 points, and the impact range of a fault within a residential area to 10 points.

[0048] The first fault priority for the first type of fault can be preset. Generally, the first fault priority corresponding to the first type of fault can be directly extracted. All unmanned vehicles can be sorted according to the first fault priority and the second fault priority as the fault repair order. The corresponding target repair teams are then matched sequentially according to the fault repair order to achieve dynamic allocation of repair resources according to the fault priority of the unmanned vehicles, thereby improving the overall processing efficiency.

[0049] In one embodiment, matching a target maintenance team according to the fault repair sequence includes:

[0050] Collect the current location and skill tags of the preset maintenance team to determine the current location of the unmanned vehicle as the vehicle position;

[0051] Based on the fault repair sequence, pre-set repair teams corresponding to the skill tags that match the first type of fault / second type of fault of each unmanned vehicle are selected as candidate repair teams.

[0052] Determine the distance between the current location of the candidate repair team and the vehicle's location, and select the candidate repair team with the minimum distance as the target repair team.

[0053] Among them, skill tags are tags used to indicate the repair capabilities of the preset repair teams. There can be multiple preset repair teams, and each preset repair team can correspond to one or more skill tags.

[0054] In this embodiment, the current location and skill tag of each preset maintenance team can be determined, and the current location of the unmanned vehicle can be collected as the vehicle location. A first type of fault / second type of fault is determined for each unmanned vehicle. Based on the fault repair order, the skill tags matching the first type of fault or the second type of fault are determined sequentially, and the preset maintenance teams corresponding to the successfully matched skill tags are selected as candidate maintenance teams. To reduce the time it takes for candidate maintenance teams to reach the fault location, the distance between the current location of each candidate maintenance team and the vehicle location can be determined, and the candidate maintenance team with the closest distance is selected as the target maintenance team. In one embodiment, after determining the target maintenance team, dynamic path planning can also be performed based on the target maintenance team's current location and the vehicle location.

[0055] In one embodiment, after acquiring the device operating status information of the unmanned vehicle and determining the abnormal information in the device operating status information, the method further includes:

[0056] Determine the target data type of the abnormal data and determine the level of abnormality.

[0057] Adjust the preset frequency of collecting device operating status information of the target data type according to the anomaly level.

[0058] Here, the target data type can refer to the type of abnormal data. For example, the target data type library includes, but is not limited to, battery SOC, battery voltage, motor temperature, and vehicle speed. The anomaly level can be understood as the degree of abnormality of the abnormal data, and the preset frequency for adjusting different anomaly levels can be based on different preset frequencies.

[0059] In this embodiment, the target data type corresponding to the abnormal data can be identified, and the rules for determining the anomaly level corresponding to the target data type can be determined. For example, a threshold range for abnormal data changes can be set. When abnormal data meets the corresponding threshold range, the anomaly level corresponding to the threshold range is determined as the anomaly level of the abnormal data. The adjustment frequency corresponding to the anomaly level is extracted, and the preset frequency for collecting device operating status information of the target data type is adjusted according to the adjustment frequency corresponding to the anomaly level. For example, when the battery SOC fluctuation is >3% / minute, the preset frequency can be automatically increased to 50Hz; when the motor temperature changes by >8°C within 1 minute, the preset frequency can be automatically increased to 30Hz, facilitating the collection of more data to determine the fault status of the autonomous vehicle.

[0060] Example 2

[0061] Figure 2 This is a flowchart of a fault diagnosis method according to Embodiment 2 of the present invention. This embodiment is a further optimization and extension based on the above embodiments, and can be combined with various optional technical solutions in the above embodiments. Figure 2 As shown, the method includes:

[0062] S201. Collect the equipment operation status information of the unmanned vehicle at a preset frequency, determine the abnormal information in the equipment operation status information according to preset conditions, and match the preset threshold rule associated with the abnormal information in the preset rule base as the target threshold rule.

[0063] The preset frequency can be understood as the pre-set frequency for collecting device operating status information. The preset frequency can be different for different data types of device operating status information. For example, the preset frequency for battery voltage can be 10Hz, the preset frequency for motor temperature can be 5Hz, and the preset frequency for vehicle speed can be 20Hz. The preset conditions can be understood as preset rules for determining abnormal information. Different preset conditions can be set for different data types, such as battery SOC fluctuation > 3% / minute, or motor temperature change range > 8℃ within 1 minute. The preset threshold rules refer to pre-set rules for determining the first type of fault. For example, a battery fault is determined when battery SOC fluctuation > 3% / minute, or a motor fault is determined when the temperature change range within 1 minute is > 8℃.

[0064] In this embodiment, the device operation status information of the unmanned vehicle can be collected at a preset frequency corresponding to each data type. The data type is then matched against preset conditions to determine whether the device operation status information meets these conditions. If the device operation status information meets the preset conditions, it is identified as abnormal information. The abnormal information is then matched against a preset threshold rule in a preset rule base as the target threshold rule.

[0065] S202. When it is determined that the abnormal information meets the target threshold rule, the fault information corresponding to the target threshold rule is determined as the first type of fault of the unmanned vehicle, and the fault level corresponding to the target threshold rule is determined as the first fault level of the first type of fault.

[0066] In the embodiment, it can be determined whether the abnormal information meets the target threshold rule. If it does not meet the rule, the first type of fault is not generated. If it does meet the rule, the fault information corresponding to the target threshold rule can be extracted, and the fault information can be used as the first type of fault of the unmanned vehicle. The fault level corresponding to the target threshold rule can be used as the first fault level of the first type of fault.

[0067] S203. Perform preprocessing operations on the abnormal information, extract the time-domain and frequency-domain features of the abnormal information after the preprocessing operations, and use the time-domain and frequency-domain features as target data.

[0068] Among them, time-domain features are features extracted directly from time-series data, reflecting the magnitude, fluctuation trend, and rate of change of the signal at different time points; frequency-domain features are features extracted after the time-domain signal has been transformed to the frequency domain using mathematical methods such as Fourier transform, reflecting the energy proportion and dominant frequency of different frequency components in the signal. For example, time-domain features may include, but are not limited to, information such as the average value, variance, and peak value of anomaly information, while frequency-domain features may include, but are not limited to, information such as the frequency distribution of motor temperature and vehicle speed, and the proportion of abnormal frequencies extracted from anomaly information through Fourier transform.

[0069] In this embodiment, abnormal data can undergo preprocessing operations such as data cleaning, time alignment, and standardization to extract time-domain features such as average value, variance, and peak value of the abnormal information, as well as frequency-domain features such as frequency distribution of motor temperature and vehicle speed, and percentage of abnormal frequencies. These time-domain and frequency-domain features are then used as target data. In actual operation, extreme values ​​of sensor false alarms (such as a sudden jump in motor temperature to 150°C for a very short period) can be eliminated, different abnormal data can be time-aligned, and the abnormal data can be standardized.

[0070] S204. Input the target data into the preset fault identification model.

[0071] The preset fault identification model consists of a long short-term memory network model and a random forest model.

[0072] S205. Determine the first probability of the target data belonging to each fault type using a long short-term memory network model, and determine the second probability of the target data belonging to each fault type using a random forest model.

[0073] In this embodiment, the target data can be input into a long short-term memory network model to determine the first probability that the target data belongs to each fault type, and the target data can be input into a random forest model to determine the second probability that the target data belongs to each fault type.

[0074] S206. Determine the first weight of the Long Short-Term Memory Network model and the second weight of the Random Forest model, and determine the target probability of each fault type according to the first probability, second probability, first weight and second weight of each fault type.

[0075] In this embodiment, the first weight of the long short-term memory network model and the second weight of the random forest model can be extracted. The product of the first probability and the first weight and the product of the second probability and the second weight corresponding to each fault type can be determined respectively. The sum of the product of the first probability and the first weight and the product of the second probability and the second weight is used as the target probability of each fault type.

[0076] S207. The fault type corresponding to the maximum value of the target probability is taken as the second type of fault, and the target probability of the second type of fault is taken as the fault probability.

[0077] In an embodiment, the maximum value among each target probability can be determined, the fault type corresponding to the maximum value can be taken as the second type of fault, and the target probability corresponding to the second type of fault can be determined as the fault probability.

[0078] S208. Determine the preset fault probability range corresponding to the fault probability as the second fault level of the second type of fault.

[0079] The preset fault probability interval refers to the interval used to determine the second fault level of the second type of fault. The number of preset fault probability intervals can be set according to business needs. For example, taking the preset fault probability interval as an example, the first probability interval can be set as a fault greater than 60% and less than or equal to 80%; the second probability interval can be set as a fault greater than 80% and less than or equal to 100%; and the third probability interval can be set as a fault of 100%.

[0080] In the embodiment, a preset fault probability range to which the fault probability belongs can be determined, and the preset fault probability range corresponding to the fault probability can be used as the second fault level of the second type of fault.

[0081] S209. When a first type of fault exists, the first type of fault and the first fault level shall be used as the fault diagnosis result.

[0082] In an embodiment, when a first type of fault exists, the first type of fault and the first fault level can be used as the fault diagnosis result.

[0083] S210. When there is no first type of fault, the second type of fault and the second fault level shall be used as the fault diagnosis result.

[0084] In the embodiment, if there is no first type of fault, the second type of fault and the second fault level can be used as the fault diagnosis result.

[0085] In this embodiment of the invention, the device operation status information of an unmanned vehicle is collected at a preset frequency, and abnormal information in the device operation status information is determined according to preset conditions. A preset threshold rule associated with the abnormal information is matched in a preset rule base as a target threshold rule. When the abnormal information satisfies the target threshold rule, the fault information corresponding to the target threshold rule is determined as the first type of fault of the unmanned vehicle, and the fault level corresponding to the target threshold rule is taken as the first fault level of the first type of fault. Preprocessing is performed on the abnormal information, and the time-domain and frequency-domain features of the abnormal information after preprocessing are extracted. These time-domain and frequency-domain features are used as target data, which is input into a preset fault identification model. A first probability of the target data belonging to each fault type is determined using a Long Short-Term Memory (LSTM) network model, and a second probability of the target data belonging to each fault type is determined using a Random Forest (RFS) model. The first weight of the short-term memory network model and the second weight of the random forest model are used to determine the target probability of each fault type according to the first probability, second probability, first weight, and second weight of each fault type. The fault type corresponding to the maximum value of the target probability is taken as the second type of fault, and the target probability of the second type of fault is taken as the fault probability. The preset fault probability interval corresponding to the fault probability is determined as the second fault level of the second type of fault. When the first type of fault exists, the first type of fault and the first fault level are taken as the fault diagnosis result. When the first type of fault does not exist, the second type of fault and the second fault level are taken as the fault diagnosis result. This allows for the determination of the second type of fault by combining the long short-term memory network model and the random forest model when the first type of fault cannot be quickly determined. This improves the accuracy of determining the fault type of the autonomous vehicle and the reliability of the fault diagnosis result.

[0086] Example 3

[0087] Figure 3This is a structural architecture diagram of a fault diagnosis system according to Embodiment 3 of the present invention. This embodiment, based on the above embodiments, uses an unmanned low-speed sanitation vehicle as an example and the fault diagnosis system executing a fault diagnosis method as an example to further illustrate a fault diagnosis method. Figure 3 As shown, the fault diagnosis system includes a sanitation vehicle cluster, a cloud diagnostic server, and an operation and maintenance terminal.

[0088] The sanitation vehicle cluster comprises multiple unmanned low-speed sanitation vehicles, each equipped with an onboard terminal. The cluster is responsible for data collection, local preprocessing, and 4G transmission, serving as the core of the front-end sensing system. The cluster integrates a 4G communication module (supporting Cat1 / Cat4) and uses a long-lived TCP connection to maintain communication with the cloud, with a heartbeat interval of ≤30 seconds. The edge processing unit leverages GPU hardware resources, utilizing redundant computing power on the domain controller for local data preprocessing (sampling rate ≥100Hz), reducing cloud computing pressure. Sensors collect equipment operating status information. Automatic fault code parsing is supported, with an abnormal data compression rate ≥80%.

[0089] The cloud diagnostic server is the core processing layer, integrating a fault diagnosis engine to achieve functions such as data reception, intelligent diagnosis, resource scheduling, and data storage, and supports elastic scaling. Specifically, data reception is built on the Netty framework, supporting 1000+ concurrent connections with a message processing latency of ≤50ms.

[0090] The diagnostic engine integrates multiple diagnostic models: a time-series anomaly detection model (LSTM, prediction accuracy ≥92%) is used for early fault warnings of components such as batteries and motors. A random forest classification model (feature importance ranking: braking system 0.32 > battery system 0.28 > steering system 0.25) is used for fault type identification. Knowledge graph reasoning is performed, integrating maintenance manuals, historical cases, and expert experience to form a fault handling knowledge base. A resource scheduling priority algorithm is used to determine the secondary fault priority of the secondary fault type, and time-series data is stored in Influx DB. The fault feature library is stored in MongoDB, supporting fast fuzzy matching.

[0091] The maintenance terminal provides web and mobile interaction interfaces to enable real-time monitoring, work order management, and augmented reality (AR) assisted maintenance. Specifically, it includes a responsive web interface supporting large-screen visualization (fault heatmaps, maintenance progress dashboards); and a mobile app integrating AR assisted maintenance functionality, with maintenance guidance steps displayed with an accuracy rate of ≥98%.

[0092] In one embodiment, Figure 4 This is a flowchart of a fault diagnosis method according to Embodiment 3 of the present invention. In this embodiment, the warning level is used as the second fault level, such as... Figure 4 As shown, the method includes:

[0093] After the vehicle terminal starts, it collects real-time equipment operating status information such as battery / SOC and motor temperature. The edge computing unit preprocesses this information (e.g., compressing / filtering abnormal data) and transmits the abnormal data to the cloud server data receiving layer via the 4G network (supporting 1000+ concurrent connections). Specifically, the 4G network transmission uses the Message Queuing Telemetry Transport Protocol (MQTT) with a Quality of Service (QoS) level of 2.

[0094] In one embodiment, the sampling frequency (preset frequency) for collecting device operating status information may include 10Hz for battery voltage, 5Hz for motor temperature, and 20Hz for vehicle speed. Simultaneously, abnormal data is reported trigger-based. For example, if battery SOC fluctuation > 3% / minute, the sampling rate automatically increases to 50Hz; if motor temperature changes > 8°C within 1 minute, the sampling rate automatically increases to 30Hz. Edge-end (autonomous vehicle) initial filtering: Common faults, i.e., first-type faults (such as sensor disconnection), are quickly identified based on preset threshold rules. If no corresponding fault can be matched through the preset threshold rules, the fault information is sent to the cloud diagnostic server. The cloud diagnostic server uses a machine learning model (preset fault identification model) to perform multi-dimensional feature extraction (such as time-domain and frequency-domain features) and deep analysis to determine the second-type fault and its probability. When multiple parameters are abnormal at the same time, it may indicate a more serious system-level fault. For example, if the battery voltage and motor temperature are abnormal at the same time, it may be due to power system overload. If the motor temperature and vehicle speed are abnormal at the same time, it may mean that the vehicle is at risk of losing control. In the case of multiple abnormal parameters, the system will use a machine learning model (preset fault identification model) to extract multi-dimensional features (such as time domain and frequency domain features).

[0095] In one embodiment, the cloud diagnostic server can employ a three-level early warning mechanism to achieve tiered response and avoid resource waste, as detailed below:

[0096] Level 1 Warning (Yellow): The predicted probability of failure is >60%, and it is recommended to check within 24 hours.

[0097] Level 2 warning (orange): Fault probability > 80%, triggering automatic order dispatch.

[0098] Level 3 Warning (Red): Real-time fault confirmation, and immediate push of emergency dispatch instructions.

[0099] The priority of the second type of fault is determined by the fault probability, the scope of fault impact, and the urgency of maintenance. For example, the result of the second type of fault priority is calculated as (fault probability × 0.5 + fault impact × 0.3 + maintenance urgency × 0.2). The corresponding priority of the second type of fault is determined according to the result of the second type of fault priority. Then, maintenance resources are matched.

[0100] Specifically, the system can determine the target maintenance team based on the skill tags (e.g., battery repair, mechanical failure) and location information (radius ≤ 5km preferred) of the pre-set maintenance teams, and optimize the maintenance route by combining real-time traffic data to achieve dynamic path planning. The target maintenance team can synchronize the maintenance results to the database, forming a full lifecycle data chain to support model iterative optimization. The cloud diagnostic server updates the vehicle health status of the autonomous vehicle and generates diagnostic reports for storage.

[0101] In this embodiment, stable vehicle data transmission is achieved through a wide-area 4G network, ensuring timely diagnostics. Machine learning algorithms are used to improve fault prediction accuracy and reduce false alarm rates. Simultaneously, priority ranking of multi-vehicle faults and dynamic allocation of maintenance resources are implemented to improve overall processing efficiency.

[0102] Example 4

[0103] Figure 5 This is a schematic diagram of the structure of a fault diagnosis device according to Embodiment 4 of the present invention, as shown below. Figure 5 As shown, the device includes: an anomaly determination module 51, a data identification module 52, and a fault determination module 53.

[0104] Among them, the anomaly determination module 51 is used to obtain the equipment operation status information of the unmanned vehicle, determine the abnormal information in the equipment operation status information, and determine the first type of fault and the first fault level of the first type of fault corresponding to the abnormal information according to the preset rule base.

[0105] The data identification module 52 is used to determine the probability of the second type of fault and the second type of fault of the unmanned vehicle by means of a preset fault identification model and abnormal data when the first type of fault does not exist.

[0106] The fault determination module 53 is used to determine the second fault level of the second type of fault based on the fault probability, and to determine the fault diagnosis result according to the first type of fault, the first fault level, the second type of fault and the second fault level.

[0107] The technical solution of this invention involves an anomaly determination module acquiring the equipment operating status information of an unmanned vehicle, identifying anomaly information within this information, and determining the first type of fault and its first fault level according to a preset rule base, thus enabling rapid determination of simple faults. When the first type of fault does not exist, the data identification module determines the probability of a second type of fault and its second type of fault using a preset fault identification model and anomaly data. The fault determination module then determines the second fault level of the second type of fault based on the fault probability, and finally determines the fault diagnosis result based on the sum of the first type of fault, its first fault level, the second type of fault, and its second fault level. This achieves accurate identification of complex faults through in-depth analysis, improving the accuracy of fault diagnosis results. Furthermore, by first determining whether a first type of fault exists and then using the preset fault identification model to determine the fault, resource waste is avoided.

[0108] In one embodiment, the fault diagnosis device further includes:

[0109] The urgency determination module is used to determine the type of the unmanned vehicle's current location when the second type of fault is the target level, determine the scope of the fault's impact according to the type, and determine the maintenance urgency of the second type of fault.

[0110] The priority determination module is used to determine the priority of the second type of fault and the second fault according to the fault probability, the fault impact range and the maintenance urgency.

[0111] The team matching module is used to extract the first fault priority of the first type of fault in the pre-set system, determine the fault repair order according to the first fault priority and the second fault priority, and match the target repair team according to the fault repair order.

[0112] In one embodiment, the team matching module is specifically used for:

[0113] Collect the current location and skill tags of the preset maintenance team to determine the current location of the unmanned vehicle as the vehicle position;

[0114] Based on the fault repair sequence, pre-set repair teams corresponding to the skill tags that match the first type of fault / second type of fault of each unmanned vehicle are selected as candidate repair teams.

[0115] Determine the distance between the current location of the candidate repair team and the vehicle's location, and select the candidate repair team with the minimum distance as the target repair team.

[0116] In one embodiment, the anomaly determination module 51 includes:

[0117] The rule determination unit is used to collect the equipment operation status information of the unmanned vehicle at a preset frequency, determine the abnormal information in the equipment operation status information according to preset conditions, and match the preset threshold rule associated with the abnormal information in the preset rule base as the target threshold rule.

[0118] The anomaly determination unit is used to determine the fault information corresponding to the target threshold rule as the first type of fault of the unmanned vehicle when the anomaly information is determined to meet the target threshold rule, and to take the fault level corresponding to the target threshold rule as the first fault level of the first type of fault.

[0119] In one embodiment, the data identification module 52 includes:

[0120] The data determination unit is used to perform preprocessing operations on the abnormal information, extract the time-domain and frequency-domain features of the abnormal information after the preprocessing operations, and use the time-domain and frequency-domain features as target data.

[0121] The model input unit is used to input target data into a preset fault identification model; wherein, the preset fault identification model consists of a long short-term memory network model and a random forest model;

[0122] The probability determination unit is used to determine the first probability of the target data belonging to each fault type through a long short-term memory network model, and to determine the second probability of the target data belonging to each fault type through a random forest model.

[0123] The weight determination unit is used to determine the first weight of the long short-term memory network model and the second weight of the random forest model, and to determine the target probability of each fault type according to the first probability, the second probability, the first weight and the second weight of each fault type.

[0124] The fault determination unit is used to take the fault type corresponding to the maximum value of the target probability as the second type of fault, and take the target probability of the second type of fault as the fault probability.

[0125] In one embodiment, the fault determination module 53 includes:

[0126] The level determination unit is used to determine the preset fault probability range corresponding to the fault probability as the second fault level of the second type of fault.

[0127] The first result determination unit is used to determine the first type of fault and the first fault level as the fault diagnosis result when a first type of fault exists.

[0128] The second result determination unit is used to take the second type of fault and the second fault level as the fault diagnosis result when there is no first type of fault.

[0129] In one embodiment, the fault diagnosis device further includes:

[0130] The anomaly level determination module is used to determine the target data type of the abnormal data and to determine the anomaly level of the abnormal data.

[0131] The frequency update module is used to adjust the preset frequency of collecting device operating status information of the target data type according to the anomaly level.

[0132] The fault diagnosis device provided in the embodiments of the present invention can execute the fault diagnosis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0133] Example 5

[0134] Figure 6 This is a schematic diagram of an electronic device implementing a fault diagnosis method according to an embodiment of the present invention. 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, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing 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.

[0135] like Figure 6 As 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.

[0136] 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 devices through computer networks such as the Internet and / or various telecommunications networks.

[0137] 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 a fault diagnosis method.

[0138] In some embodiments, a fault diagnosis 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 a fault diagnosis method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a fault diagnosis method by any other suitable means (e.g., by means of firmware).

[0139] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-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 system 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 system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0140] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0141] 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 system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or 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 fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0142] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides 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).

[0143] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0144] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0145] 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.

[0146] 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 fault diagnosis method, characterized in that, include: Acquire the equipment operation status information of the unmanned vehicle, determine the abnormal information in the equipment operation status information, and determine the first type of fault and the first fault level of the first type of fault according to the preset rule base; In the absence of a first type of fault, the second type of fault and the probability of the second type of fault of the unmanned vehicle are determined by the preset fault identification model and the abnormal data; The second fault level of the second type of fault is determined based on the fault probability, and the fault diagnosis result is determined according to the first type of fault, the first fault level, the second type of fault, and the second fault level.

2. The method according to claim 1, characterized in that, After determining the fault diagnosis result according to the first type of fault, the first fault level, the second type of fault, and the second fault level, the method further includes: When the second type of fault is of the target level, determine the type of the current location of the unmanned vehicle, determine the scope of the fault impact according to the type, and determine the repair urgency of the second type of fault; The priority of the second type of fault and the second fault is determined according to the fault probability, the fault impact range, and the maintenance urgency. Extract the first fault priority of the first type of fault that is preset, determine the fault repair order according to the first fault priority and the second fault priority, and match the target repair team according to the fault repair order.

3. The method according to claim 2, characterized in that, The matching of target repair teams according to the fault repair sequence includes: Collect the current location and skill tags of the preset maintenance team to determine the current location of the unmanned vehicle as the vehicle position; According to the fault repair sequence, the preset repair teams corresponding to the skill tags that match the first type of fault / second type of fault of each unmanned vehicle are determined as candidate repair teams in sequence; Determine the distance between the current location of the candidate repair team and the location of the vehicle, and select the candidate repair team corresponding to the minimum distance as the target repair team.

4. The method according to claim 1, characterized in that, The process of acquiring the unmanned vehicle's equipment operating status information, determining abnormal information within that information, and identifying a first type of fault and a first fault level corresponding to the abnormal information according to a preset rule base includes: The unmanned vehicle's equipment operation status information is collected at a preset frequency, and abnormal information in the equipment operation status information is determined according to preset conditions. The preset threshold rule associated with the abnormal information is matched in the preset rule base as the target threshold rule. When it is determined that the abnormal information meets the target threshold rule, the fault information corresponding to the target threshold rule is determined as the first type of fault of the unmanned vehicle, and the fault level corresponding to the target threshold rule is determined as the first fault level of the first type of fault.

5. The method according to claim 1, characterized in that, The step of determining the second type of fault and the probability of the second type of fault of the unmanned vehicle through the preset fault identification model and the abnormal data includes: Perform preprocessing operations on the abnormal information, extract the time-domain and frequency-domain features of the abnormal information after the preprocessing operations, and use the time-domain and frequency-domain features as target data; The target data is input into a preset fault identification model; wherein, the preset fault identification model consists of a long short-term memory network model and a random forest model; The first probability of the target data belonging to each fault type is determined by the Long Short-Term Memory Network model, and the second probability of the target data belonging to each fault type is determined by the Random Forest model. Determine the first weight of the long short-term memory network model and the second weight of the random forest model, and determine the target probability of each fault type according to the first probability, the second probability, the first weight, and the second weight of each fault type; The fault type corresponding to the maximum value of the target probability is taken as the second type of fault, and the target probability of the second type of fault is taken as the fault probability.

6. The method according to claim 1, characterized in that, The step of determining the second fault level of the second type of fault based on the fault probability, and determining the fault diagnosis result according to the first type of fault, the first fault level, the second type of fault, and the second fault level, includes: The preset fault probability range corresponding to the fault probability is determined as the second fault level of the second type of fault. When a first type of fault exists, the first type of fault and the first fault level are used as the fault diagnosis result; When the first type of fault does not exist, the second type of fault and the second fault level are taken as the fault diagnosis result.

7. The method according to claim 1, characterized in that, After acquiring the device operating status information of the unmanned vehicle and determining the abnormal information in the device operating status information, the process further includes: Determine the target data type of the abnormal data and determine the abnormality level of the abnormal data; Adjust the preset frequency of collecting device operating status information of the target data type according to the anomaly level.

8. A fault diagnosis device, characterized in that, include: An anomaly determination module is used to acquire the equipment operation status information of the unmanned vehicle, determine the anomaly information in the equipment operation status information, and determine the first type of fault and the first fault level of the first type of fault according to a preset rule base. The data identification module is used to determine the second type of fault and the probability of the second type of fault of the unmanned vehicle by means of the preset fault identification model and the abnormal data when the first type of fault does not exist. The fault determination module is used to determine the second fault level of the second type of fault based on the fault probability, and to determine the fault diagnosis result according to the first type of fault, the first fault level, the second type of fault, and the second fault level.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the fault diagnosis method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the fault diagnosis method according to any one of claims 1-7.

Images