Equipment operation and maintenance fault troubleshooting method and device, equipment and medium

Abstract

The invention discloses an equipment operation and maintenance fault checking method and device, equipment and a medium. Through the pre-trained equipment fault diagnosis model, in combination with the real-time operation data, the historical fault case and the instruction template, the fault reason of the to-be-analyzed equipment can be quickly positioned, the maintenance suggestion is determined, the troubleshooting efficiency is improved, the time required by manual troubleshooting is reduced, and the overall operation and maintenance efficiency is improved. Through the reasoning layer in the equipment fault diagnosis model, the target troubleshooting thinking chain can be determined based on the input troubleshooting prompt, and the troubleshooting problem and the execution relation of each level are determined, so that the diagnosis process is organized and clear, and redundant and repeated troubleshooting work is reduced. The real-time operation data is checked in sequence according to the execution relation through the grading processing layer in the equipment fault diagnosis model, the fault problem can be quickly locked, and blindness and low efficiency of traditional manual checking are avoided. And the equipment fault removal knowledge base provides powerful knowledge support for fault diagnosis.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and urban traffic operation and maintenance management, and in particular to a method, device, equipment and medium for troubleshooting equipment operation and maintenance failures. Background Art

[0002] With the acceleration of urbanization and the rapid development of intelligent transportation systems, urban transportation operation and maintenance management is facing unprecedented challenges. Although the traditional operation and maintenance model has guaranteed the basic operation of the urban transportation system to a certain extent, its inherent limitations and inefficiency are becoming increasingly prominent, and it is difficult to meet the urgent needs of modern urban transportation for efficient and accurate operation and maintenance.

[0003] In the current operation and maintenance management system, the troubleshooting and handling of equipment failures are highly dependent on the personal experience and on-site operations of the operation and maintenance personnel. This approach is not only inefficient, but also has many disadvantages. First, the manual response speed is slow. From fault discovery to locating the root cause of the problem, and then taking measures to solve it, the entire process takes a long time, which often causes the traffic system to be in a non-optimal operating state for a long time, affecting the smoothness of urban traffic and the public's travel experience. Secondly, due to the lack of systematic fault diagnosis processes and standardized data support in the troubleshooting process, when faced with complex or new faults, operation and maintenance personnel often find it difficult to quickly and accurately locate the problem, which is prone to misjudgment or missed judgment, further exacerbating the difficulty and cost of fault handling.

[0004] In addition, traditional troubleshooting methods also face the problem of high false alarm rate. Although some fault detection systems based on fixed rules have improved the automation level of fault detection to a certain extent, the rule settings are often difficult to cover all possible fault scenarios and are easily affected by factors such as environmental changes and system upgrades, resulting in frequent false alarms, which not only wastes operation and maintenance resources, but may also cause unnecessary panic and confusion. Summary of the invention

[0005] The present application provides a method, device, equipment and medium for troubleshooting equipment operation and maintenance faults, which are used to solve the problems of low troubleshooting efficiency and poor troubleshooting quality in existing troubleshooting systems.

[0006] In a first aspect, the present application provides a method for troubleshooting equipment operation and maintenance failures, the method comprising:

[0007] Acquire real-time operating data of the target type of equipment to be analyzed, as well as historical failure cases of the equipment to be analyzed;

[0008] Determine the fault cause and maintenance suggestion of the equipment to be analyzed based on troubleshooting prompts by using a pre-trained equipment fault diagnosis model that supports the target type; wherein the troubleshooting prompts include the real-time operation data, the historical fault cases, and a pre-configured instruction template, and the instruction template is used to instruct to perform fault diagnosis on the real-time operation data;

[0009] The equipment fault diagnosis model determines the fault cause and maintenance suggestion of the equipment to be analyzed based on the troubleshooting prompt, including:

[0010] Through the inference layer of the equipment fault diagnosis model, based on the troubleshooting prompts, determine the target troubleshooting thinking chain corresponding to the equipment to be analyzed; wherein the target troubleshooting thinking chain includes the troubleshooting problems corresponding to each level and the execution relationship between the levels, and the execution relationship includes the execution conditions between the levels and the execution order between the levels;

[0011] Through the hierarchical processing layer of the equipment fault diagnosis model, according to the execution relationship, check in sequence whether the real-time operation data matches the troubleshooting problem corresponding to the current level until a matching troubleshooting problem is determined;

[0012] The fault cause and the maintenance suggestion are determined through the output layer of the equipment fault diagnosis model based on the matched troubleshooting questions and combined with the equipment troubleshooting knowledge base; wherein the fault cause and maintenance suggestion corresponding to each troubleshooting question are maintained in the equipment troubleshooting knowledge base.

[0013] In a second aspect, the present application also provides a device for troubleshooting equipment operation and maintenance failures, the device comprising:

[0014] An acquisition unit, used to acquire real-time operation data of a target type of equipment to be analyzed, and historical failure cases of the equipment to be analyzed;

[0015] a processing unit, configured to determine the fault cause and maintenance suggestion of the device to be analyzed based on a troubleshooting prompt by using a pre-trained device fault diagnosis model supporting the target type; wherein the troubleshooting prompt includes the real-time operation data, the historical fault case, and a pre-configured instruction template, and the instruction template is used to instruct to perform fault diagnosis on the real-time operation data;

[0016] The equipment fault diagnosis model determines the fault cause and maintenance suggestion of the equipment to be analyzed based on the troubleshooting prompt, including:

[0017] Through the inference layer of the equipment fault diagnosis model, based on the troubleshooting prompts, determine the target troubleshooting thinking chain corresponding to the equipment to be analyzed; wherein the target troubleshooting thinking chain includes the troubleshooting problems corresponding to each level and the execution relationship between the levels, and the execution relationship includes the execution conditions between the levels and the execution order between the levels;

[0018] Through the hierarchical processing layer of the equipment fault diagnosis model, according to the execution relationship, check in sequence whether the real-time operation data matches the troubleshooting problem corresponding to the current level until a matching troubleshooting problem is determined;

[0019] The fault cause and the maintenance suggestion are determined through the output layer of the equipment fault diagnosis model based on the matched troubleshooting questions and combined with the equipment troubleshooting knowledge base; wherein the fault cause and maintenance suggestion corresponding to each troubleshooting question are maintained in the equipment troubleshooting knowledge base.

[0020] In a third aspect, the present application provides a computer device, which includes a processor, and the processor is used to implement the steps of the device operation and maintenance fault troubleshooting method as described above when executing a computer program stored in a memory.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for troubleshooting equipment operation and maintenance failures as described above.

[0022] The beneficial effects of this application are as follows:

[0023] 1. Through the pre-trained equipment fault diagnosis model, combined with real-time operation data, historical fault cases and instruction templates, the fault cause of the equipment to be analyzed can be quickly located and maintenance suggestions can be determined, which improves the efficiency of troubleshooting and reduces the time required for manual troubleshooting, thereby improving the overall operation and maintenance efficiency.

[0024] 2. Through the reasoning layer in the equipment fault diagnosis model, the target troubleshooting thinking chain can be determined based on the input troubleshooting prompts, and the troubleshooting problems and execution relationships at each level can be clarified, making the diagnosis process clear and reducing redundant and repetitive troubleshooting work.

[0025] 3. Through the hierarchical processing layer in the equipment fault diagnosis model, the real-time operation data is checked in sequence according to the execution relationship, which can quickly identify the fault problem, avoid the blindness and inefficiency of traditional manual troubleshooting, reduce the chance of manual intervention, avoid misdiagnosis or missed diagnosis due to human judgment errors, and enhance the reliability and stability of troubleshooting.

[0026] 4. The equipment troubleshooting knowledge base provides powerful knowledge support for fault diagnosis. Each troubleshooting problem corresponds to a detailed fault cause and repair suggestion, which helps operation and maintenance personnel to quickly understand the problem and take effective measures. It also digitizes the operation and maintenance experience of professional experts and talents into assets and large-scale applications to guide the daily operation and maintenance work of front-line employees. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0028] Figure 1 A schematic diagram of a troubleshooting process for equipment operation and maintenance failures provided in an embodiment of the present application;

[0029] Figure 2 A schematic diagram of a specific equipment operation and maintenance fault troubleshooting process provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of the structure of a device for troubleshooting equipment operation and maintenance failures provided in an embodiment of the present application;

[0031] Figure 4 It is a structural schematic diagram of a computer device provided in an optional embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0033] In order to improve the efficiency and quality of troubleshooting, the present application provides a method, device, equipment and medium for troubleshooting equipment operation and maintenance faults.

[0034] Embodiment 1:

[0035] This application provides a method for troubleshooting equipment operation and maintenance failures. Figure 1 A schematic diagram of a troubleshooting process for equipment operation and maintenance failures provided in an embodiment of the present application, the process includes:

[0036] S101: Acquire real-time operation data of a target type of equipment to be analyzed, and historical failure cases of the equipment to be analyzed.

[0037] The device operation and maintenance fault troubleshooting method of the present application is applied to computer equipment, which can be an intelligent terminal, such as a computer, a robot, etc., or a server, such as an application server, a business server, etc.

[0038] In order to ensure the accuracy of troubleshooting of equipment operation and maintenance, in this application, for a specific type of equipment (referred to as the target type) that needs troubleshooting, based on the possible faults of these target type equipment in the application scenario, a customized method for troubleshooting the target type equipment is generated. These target type devices can be diverse, including but not limited to smart terminals (such as computers, robots, smart phones, tablets, etc.), servers (such as application servers, business servers, database servers, etc.), a key machine on an industrial production line, a server cluster in a data center, or a transformer in a smart grid, transportation equipment (such as high-speed rail, subway, train, etc.), etc.

[0039] In order to achieve accurate troubleshooting of a certain device of the target type (referred to as the device to be analyzed), in this application, it is first necessary to obtain the real-time operating data of the device to be analyzed. The real-time operating data is collected through the sensors, monitoring systems or data acquisition modules of the device to be analyzed, including but not limited to the temperature, humidity, current, voltage, speed, vibration frequency, network status, resource utilization (such as CPU, memory, disk usage) and other key parameters of the device to be analyzed.

[0040] In a possible implementation, various forms of real-time operating data can be captured from the device to be analyzed in real time, aiming to achieve comprehensive and uninterrupted monitoring of the entire life cycle of the device to be analyzed from installation to scrapping. The data in the real-time operating data is not limited to the traditional single form (such as numerical value), but covers multiple "modalities", that is, different types of information representation methods. Among them, the multiple modalities include but are not limited to at least two of the following: audio, video and numerical value.

[0041] For the collection of numerical values, different types of sensors can be installed at various key locations of the equipment to be analyzed, such as near heat sources, stress points, mechanical connections, etc. These sensors include but are not limited to temperature sensors, pressure sensors, vibration sensors, etc., which are used to monitor the physical parameters of the equipment in real time.

[0042] For audio collection, audio collection equipment can be installed around the device to be analyzed or at key locations to capture the sound signal of the device to be analyzed, thereby providing non-numerical information such as abnormal sounds of the device to be analyzed.

[0043] For video collection, video cameras can be installed around the device to be analyzed or at key locations to capture visual images of the device to be analyzed, thereby providing non-numerical information such as changes in the device's appearance.

[0044] It should be noted that the multimodal data acquisition module 11 acquires the operating data of the equipment to be analyzed in real time to ensure the timeliness and accuracy of the data.

[0045] Multimodal real-time operation data can complement each other. For example, video images can reveal damage to the appearance of equipment, while audio signals may capture abnormal sounds during mechanical operation. These can help to provide a more comprehensive understanding of the equipment status.

[0046] In addition to real-time operation data, historical failure cases are also an important basis for troubleshooting equipment to be analyzed. The historical failure cases can come from sources such as equipment maintenance records, fault reports, technical support documents, etc., and record information such as the failure phenomena, troubleshooting process, failure causes, and repair measures that occurred in the past. Among them, the collection of historical failure cases needs to cover the failure conditions of the equipment to be analyzed in various application scenarios. The collected historical failure cases need to be sorted, key information such as failure type, impact range, solution, etc. need to be extracted, and a standardized data structure needs to be constructed for subsequent analysis.

[0047] In a possible implementation, in order to improve the efficiency of troubleshooting, the historical fault cases of all devices can be classified and indexed. Classification can be based on fault type, device model, occurrence time, etc.; indexing can be achieved through keywords, tags, etc., so as to quickly retrieve relevant cases of the device to be analyzed.

[0048] S102: determining the fault cause and maintenance suggestion of the device to be analyzed based on troubleshooting prompts by using a pre-trained device fault diagnosis model that supports the target type; wherein the troubleshooting prompts include the real-time operation data, the historical fault cases, and a pre-configured instruction template, and the instruction template is used to instruct to perform fault diagnosis on the real-time operation data;

[0049] The equipment fault diagnosis model determines the fault cause and maintenance suggestion of the equipment to be analyzed based on the troubleshooting prompt, including:

[0050] Through the inference layer of the equipment fault diagnosis model, based on the troubleshooting prompts, determine the target troubleshooting thinking chain corresponding to the equipment to be analyzed; wherein the target troubleshooting thinking chain includes the troubleshooting problems corresponding to each level and the execution relationship between the levels, and the execution relationship includes the execution conditions between the levels and the execution order between the levels;

[0051] Through the hierarchical processing layer of the equipment fault diagnosis model, according to the execution relationship, check in sequence whether the real-time operation data matches the troubleshooting problem corresponding to the current level until a matching troubleshooting problem is determined;

[0052] The fault cause and the maintenance suggestion are determined through the output layer of the equipment fault diagnosis model based on the matched troubleshooting questions and combined with the equipment troubleshooting knowledge base; wherein the fault cause and maintenance suggestion corresponding to each troubleshooting question are maintained in the equipment troubleshooting knowledge base.

[0053] After obtaining the real-time operation data and the historical fault cases of the device to be analyzed based on the above embodiment, a troubleshooting prompt can be generated according to the real-time operation data, the historical fault cases and the pre-configured instruction template, wherein the instruction template is used to instruct to perform fault diagnosis on the real-time operation data.

[0054] In one possible implementation, before determining troubleshooting tips based on real-time operation data, the real-time operation data can be preprocessed to improve data quality and make the real-time operation data more suitable for subsequent analysis and model processing, thereby improving the accuracy and efficiency of fault diagnosis. The preprocessing includes but is not limited to one or more of the following: normalization, denoising, and structured processing. During the preprocessing process, one or more methods can be selected according to the characteristics of the data and the requirements of the model. For example, for numerical values ​​containing a lot of noise, denoising can be performed; for video and audio data, feature extraction and structured processing can be performed; for numerical data, normalization can be performed to ensure data consistency.

[0055] Next, the generated troubleshooting prompt is input into a pre-trained equipment fault diagnosis model that supports the target type. The troubleshooting prompt is processed by the fault diagnosis model to determine the fault cause and maintenance suggestions of the equipment to be analyzed. The fault diagnosis model includes an inference layer, a hierarchical processing layer, and an output layer. The output of the inference layer is connected to the input of the hierarchical processing layer, and the output of the hierarchical processing layer is connected to the input of the output layer.

[0056] Specifically, the troubleshooting tips input into the fault diagnosis model will first be processed by the reasoning layer. In the reasoning layer, a set of troubleshooting thinking chains involving various fault problems of target type equipment are pre-trained, that is, a set of carefully designed and trained troubleshooting solutions for various fault problems that may be encountered by target type equipment, which covers the complete process from preliminary judgment to in-depth investigation, and finally to the final determination of the cause of the fault and maintenance suggestions. Among them, the troubleshooting thinking chain includes the troubleshooting problems corresponding to each level and the execution relationship between each level. The execution relationship includes the execution conditions between each level and the execution order between each level. For example,

[0057] The initial condition of a troubleshooting chain: the platform door cannot be closed and no locking signal is received. This is the starting point of the entire troubleshooting, and all subsequent steps will be based on this initial condition. The various levels of the fault thinking chain include:

[0058] Level 1: Preliminary diagnosis:

[0059] ●Troubleshooting 1: Check whether the door is closed correctly.

[0060] ○Execution conditions: The initial conditions are met, that is, the platform door cannot be closed and there is no locking signal.

[0061] ○ Execution order: This check is done first.

[0062] ○ Subsequent reasoning:

[0063] ■If the door is closed and the door light indicates correct, proceed to Level 2.

[0064] ■If the door is not closed, proceed directly to the appropriate action (such as manually closing the door or checking the door operator) and re-evaluate the status.

[0065] Level 2: In-depth investigation

[0066] ●Troubleshooting problem 2: Check the output voltage of the lock signal.

[0067] ○Execution conditions: The door is closed and the door light indicates correctly, but the locking signal is still not received.

[0068] ○Execution order: Performed after preliminary diagnosis.

[0069] ○ Subsequent reasoning:

[0070] ■If the voltage is normal (24V), proceed to the next step to check the locking signal input terminal.

[0071] ■If the voltage is abnormal (0V or less than 20V), check the status of the power module or switch.

[0072] ●Troubleshooting problem 3: Check the lock signal input terminal and the safety circuit relay status.

[0073] ○Execution conditions: The locking signal output voltage is normal.

[0074] ○Execution order: After troubleshooting problem 2, proceed if the voltage is normal.

[0075] ○ Subsequent reasoning:

[0076] ■If the input voltage is normal and the relay contacts are normal, proceed to check the line connection, etc.

[0077] ■If the relay contacts are abnormal, replace the relay.

[0078] ●Troubleshooting issue 4: Check the working status of the power module, switch and K&G board.

[0079] ○Execution condition: The lock signal output voltage is abnormal.

[0080] ○Execution order: After troubleshooting problem 2, proceed if the voltage is abnormal.

[0081] ○ Subsequent reasoning:

[0082] ■If the power module and switch are normal, check the working status of the K&G board.

[0083] ■Based on the working status of the K&G board, decide whether to replace the K&G board or check for external interference / connection problems.

[0084] Level 3: Special Case Handling

[0085] ●Troubleshooting issue 5: Check whether individual doors are open and the door lights are always on.

[0086] ○ Execution conditions: At any level, if an abnormality is found in an individual door.

[0087] ○Execution order: Carry out at any time according to the specific situation.

[0088] ○ Subsequent reasoning:

[0089] ■If the locking signal is normal, check the door body or its control unit.

[0090] ■If the lock signal is abnormal, check the control unit or sensor failure.

[0091] The reasoning layer parses and compares the input troubleshooting tips to find the target troubleshooting chain that best matches the fault of the device to be analyzed. Once the reasoning layer determines the target troubleshooting chain, it can output the target troubleshooting chain to the hierarchical processing layer.

[0092] The hierarchical processing layer can conduct in-depth troubleshooting of the real-time operation data layer by layer and step by step according to the guidance of the target troubleshooting thinking chain. The hierarchical processing layer will check the troubleshooting problems corresponding to the level matching the real-time operation data one by one according to the execution order and execution conditions set in the target troubleshooting thinking chain, that is, determine each possible fault point in the device to be analyzed until the troubleshooting problem that best matches the fault in the real-time operation data of the device to be analyzed is found. The troubleshooting process is sequential, starting from the starting level of the target troubleshooting thinking chain and troubleshooting layer by layer. At each level, the hierarchical processing layer will verify whether the troubleshooting problem corresponding to the current level meets the execution conditions to decide whether to continue to the next level of troubleshooting. Once the hierarchical processing layer finds the troubleshooting problem that best matches the real-time operation data, the matching troubleshooting problem can be input into the output layer of the equipment fault diagnosis model.

[0093] The output layer can determine the specific fault cause and repair suggestion based on this matching troubleshooting question and the equipment troubleshooting knowledge base (which maintains the fault cause and repair suggestion corresponding to each troubleshooting question). In this way, the equipment fault diagnosis model can provide technicians with clear and specific guidance to help them quickly and accurately locate and solve equipment faults.

[0094] The equipment troubleshooting knowledge base includes resources such as the operating data of the target type of equipment, historical fault cases, fault diagnosis guides, and expert knowledge, so that comprehensive judgments can be made by combining practical experience and theoretical knowledge during the troubleshooting process.

[0095] In a possible implementation, after the computer device obtains the cause of the fault and the repair suggestion, it can present the cause of the fault and the repair suggestion to the operation and maintenance personnel or related systems in a clear and easy-to-understand manner. The presentation of the cause of the fault and the repair suggestion may include text descriptions, charts, flow charts and other forms, depending on the complexity of the cause of the fault and the repair suggestion and the needs of the recipient. For example, for a simple fault, only a short text description may be required; for a complex fault, a detailed description may be required in combination with a flow chart, a list of steps and key considerations.

[0096] In a possible implementation, in order to ensure the readability and operability of the fault causes and maintenance suggestions, the fault causes and maintenance suggestions can also be formatted and typeset. For example, select appropriate fonts, font sizes, colors, spacing, etc., and arrange the layout and structure of the content reasonably. Through good formatting and typesetting, the fault causes and maintenance suggestions can be made more intuitive and clear, which is convenient for operation and maintenance personnel to quickly understand and execute. Exemplarily, the computer device supports the automatic generation of troubleshooting reports based on a pre-configured report generation template. The report generation template can be customized according to the preferences and organizational specifications of different users, including but not limited to report structure, content layout, style design, etc. When generating a troubleshooting report, the fault causes and maintenance suggestions can be intelligently inserted into the report template.

[0097] In one possible implementation, the computer device can support multiple output channels to meet the needs of different scenarios. For example, it can directly display the cause of the fault and the maintenance suggestion on the monitoring screen for on-site operation and maintenance personnel to view; it can also print the solution into a paper document for off-site personnel to refer to; it can also send the solution to relevant personnel via email, text message, etc. This multi-channel output capability improves the flexibility and accessibility of the cause of the fault and the maintenance suggestion.

[0098] In some cases, customized output can also be supported to personalize the fault causes and maintenance suggestions according to the needs of different users or different devices. For example, solutions with different levels of detail can be provided for operators with different skill levels. Through customized output, it can ensure that the fault causes and maintenance suggestions are closer to actual needs, improving their practicality and effectiveness.

[0099] In a possible implementation, the computer device also has a feedback and recording function. After the operation and maintenance personnel obtain the output fault cause and maintenance suggestion, they can input modification opinions on the fault cause and maintenance suggestion through the feedback channel provided by the computer device. For example, the modification opinions are re-interpretation of the fault cause, adjustment or supplementation of the maintenance steps, change of required materials, etc. At the same time, after the computer device receives the modification opinions on the fault cause and maintenance suggestion, the real-time operation data, the modified fault cause and the modified maintenance suggestion can be saved accordingly, so as to use the real-time operation data, the modified fault cause and the modified maintenance suggestion as new training samples for optimizing the equipment fault diagnosis model to improve the accuracy and generalization ability of the model.

[0100] In a possible implementation, after receiving the fault cause and maintenance suggestion output by the computer device, the operation and maintenance personnel will verify and execute according to the actual situation. After confirming that there is no error or completing the maintenance, the operation and maintenance personnel confirm the fault cause and maintenance suggestion through the interface or tool provided by the computer device. After receiving the confirmation operation of the operation and maintenance personnel, the computer device can update the historical fault case according to the real-time operation data, the confirmed fault cause and maintenance suggestion, so as to facilitate the fault diagnosis of the next real-time operation data.

[0101] It should be noted that there are many ways to input confirmation operations. It can be input through the confirmation operation method provided by the graphical user interface, such as clicking the displayed confirmation button, etc., it can also be input through voice interaction, and it can also be input through action interaction, etc., which are not specifically limited here.

[0102] The beneficial effects of this application are as follows:

[0103] 1. Through the pre-trained equipment fault diagnosis model, combined with real-time operation data, historical fault cases and instruction templates, the fault cause of the equipment to be analyzed can be quickly located and maintenance suggestions can be determined, which improves the efficiency of troubleshooting and reduces the time required for manual troubleshooting, thereby improving the overall operation and maintenance efficiency.

[0104] 2. Through the reasoning layer in the equipment fault diagnosis model, the target troubleshooting thinking chain can be determined based on the input troubleshooting prompts, and the troubleshooting problems and execution relationships at each level can be clarified, making the diagnosis process clear and reducing redundant and repetitive troubleshooting work.

[0105] 3. Through the hierarchical processing layer in the equipment fault diagnosis model, the real-time operation data is checked in sequence according to the execution relationship, which can quickly identify the fault problem, avoid the blindness and inefficiency of traditional manual troubleshooting, reduce the chance of manual intervention, avoid misdiagnosis or missed diagnosis due to human judgment errors, and enhance the reliability and stability of troubleshooting.

[0106] 4. The equipment troubleshooting knowledge base provides powerful knowledge support for fault diagnosis. Each troubleshooting problem corresponds to a detailed fault cause and repair suggestion, which helps operation and maintenance personnel to quickly understand the problem and take effective measures. It also digitizes the operation and maintenance experience of professional experts and talents into assets and large-scale applications to guide the daily operation and maintenance work of front-line employees.

[0107] Embodiment 2:

[0108] In order to improve the accuracy of fault diagnosis, based on the above embodiments, in this application, the equipment fault diagnosis model is trained in the following manner:

[0109] Obtaining sample troubleshooting tips and their corresponding label data in the target type fault sample set; wherein the sample troubleshooting tips include sample fault operation data of the target type equipment, historical fault case samples of the target type equipment and the instruction template, and the label data includes the standard troubleshooting thinking chain, standard troubleshooting reasons and standard maintenance suggestions corresponding to the sample fault operation data;

[0110] By means of a pre-trained natural language processing model, based on the sample troubleshooting prompt, an expected troubleshooting thought chain, an expected troubleshooting reason and an expected maintenance suggestion corresponding to the sample troubleshooting prompt are obtained; wherein the natural language processing model has natural language understanding capability, the input of the output layer in the natural language processing model is respectively connected with the output of the inference layer and the output of the hierarchical processing layer in the natural language processing model, and the output of the inference layer is connected with the input of the hierarchical processing layer;

[0111] Based on the expected troubleshooting thinking chain and the standard troubleshooting thinking chain, the expected troubleshooting reasons and the standard troubleshooting reasons, the expected maintenance suggestions and the standard maintenance suggestions, the natural language processing model is fine-tuned to determine the equipment fault diagnosis model based on the fine-tuned natural language processing model.

[0112] In order to improve the accuracy of fault diagnosis, in this application, a target type fault sample set is collected in advance, so as to train a device fault diagnosis model that supports the troubleshooting of the target type equipment through the sample troubleshooting prompts in the target type fault sample set. Exemplarily, the real-time operation data of the target type equipment with faults (recorded as sample fault operation data) and the historical fault cases of the target type equipment (recorded as historical fault case samples) can be collected from the actual operation and maintenance environment, and the sample troubleshooting prompts are determined according to the sample fault operation data, the historical fault case samples and the pre-configured instruction templates. Among them, the source of the sample fault operation data includes but is not limited to equipment maintenance guidelines, operating specifications, commissioning procedures, technical standards, equipment manuals, maintenance manuals, fault cases, etc. These documents contain both structured equipment parameters, maintenance processes and other information, as well as unstructured fault descriptions, maintenance experience sharing and other content. For unstructured documents, they can be converted into structured data through natural language processing technology. For example, the fault description extracted from the equipment maintenance manual will be converted into a structured format containing elements such as fault phenomenon, occurrence conditions, and impact range, which is convenient for model understanding and processing.

[0113] After collecting the sample troubleshooting tips, the label data corresponding to each sample troubleshooting tip can be determined respectively. The label data includes the standard troubleshooting thinking chain, standard troubleshooting reasons, and standard maintenance suggestions. The standard troubleshooting thinking chain is a logical thinking chain developed by experts based on sample troubleshooting tips to guide troubleshooting. It clarifies the troubleshooting problems and execution relationships at each level. The standard troubleshooting reasons and standard maintenance suggestions are derived based on the standard troubleshooting thinking chain and are used to explain the cause of the fault and provide maintenance guidance.

[0114] For any sample troubleshooting prompt in the target type fault sample set, the sample troubleshooting prompt can be input into the pre-trained natural language processing model. The natural language processing model has powerful text understanding and generation capabilities, and can process complex language structures and semantic relationships, that is, it has natural language understanding capabilities. In the natural language processing model, the natural language processing model includes an inference layer, a hierarchical processing layer, and an output layer. The output of the inference layer is connected to the input of the hierarchical processing layer and the input of the output layer respectively, and the output of the hierarchical processing layer is connected to the input of the output layer so that the output layer can output the content output by the inference layer. The sample troubleshooting prompt input into the natural language processing model will first be input into the inference layer of the natural language processing model. Through the inference layer, the input sample troubleshooting prompt is processed to determine the expected troubleshooting thinking chain. The expected troubleshooting thinking chain is respectively input into the hierarchical processing layer and the output layer of the natural language processing model. Through the hierarchical processing layer, according to the execution relationship of the expected troubleshooting thinking chain, the sample fault operation data is sequentially checked to see if it matches the troubleshooting problem corresponding to the current level until the matching troubleshooting problem is determined. The hierarchical processing layer inputs the determined matching troubleshooting questions to the output layer. The output layer determines the expected fault cause and expected maintenance suggestion based on the input matching troubleshooting questions and the pre-built equipment troubleshooting knowledge base. The output layer outputs the expected troubleshooting thinking chain, the expected fault cause, and the expected maintenance suggestion. Based on the first loss value between the expected troubleshooting thinking chain and the standard troubleshooting thinking chain, the second loss value between the expected troubleshooting cause and the standard troubleshooting cause, and the loss value between the expected maintenance suggestion and the standard maintenance suggestion, a comprehensive loss value is determined. Based on the comprehensive loss value, the parameters in the natural language processing model are fine-tuned so that the fine-tuned natural language processing model has the ability to troubleshoot the target type of equipment. Then, the direct connection between the inference layer and the output layer in the fine-tuned natural language processing model is disconnected, that is, the output layer no longer outputs the troubleshooting thinking chain to obtain the equipment fault diagnosis model.

[0115] Since the target type fault sample set contains a large number of sample troubleshooting prompts, the above operations can be performed for each sample troubleshooting prompt. When the preset convergence conditions are met, the equipment fault diagnosis model training is completed.

[0116] Among them, satisfying the preset convergence condition may be that the number of iterations for training the natural language processing model reaches the set maximum number of iterations, or the change in the determined comprehensive loss value remains within a very small range in multiple consecutive iterations, etc. In specific implementations, the setting can be flexibly performed and is not specifically limited here.

[0117] As a possible implementation method, when performing model training, the sample troubleshooting prompts in the target type fault sample set can be divided into training samples and test samples. The natural language processing model is first trained based on the training samples, and then the reliability of the above-mentioned trained fault warning model is verified based on the test samples.

[0118] Embodiment 3:

[0119] Figure 2 A schematic diagram of a specific equipment operation and maintenance fault troubleshooting process provided in an embodiment of the present application, the process includes:

[0120] S201: Based on a target type fault sample set, a pre-trained device fault diagnosis model supporting the target type is obtained.

[0121] In a possible implementation, the equipment fault diagnosis model is trained in the following manner:

[0122] Obtain sample troubleshooting tips and their corresponding label data in the target type fault sample set; wherein the sample troubleshooting tips include sample fault operation data of the target type equipment, historical fault case samples of the target type equipment, and instruction templates; the label data includes the standard troubleshooting thinking chain, standard troubleshooting reasons, and standard maintenance suggestions corresponding to the sample fault operation data;

[0123] Through the pre-trained natural language processing model, based on the sample troubleshooting prompts, the expected troubleshooting thought chain, expected troubleshooting cause and expected maintenance suggestion corresponding to the sample troubleshooting prompts are obtained; wherein the natural language processing model has the ability to understand natural language, and the input of the output layer in the natural language processing model is respectively connected with the output of the reasoning layer and the output of the hierarchical processing layer in the natural language processing model, and the output of the reasoning layer is connected with the input of the hierarchical processing layer;

[0124] Based on the expected troubleshooting thinking chain and the standard troubleshooting thinking chain, the expected troubleshooting reasons and the standard troubleshooting reasons, the expected maintenance suggestions and the standard maintenance suggestions, the natural language processing model is fine-tuned to determine the equipment fault diagnosis model based on the fine-tuned natural language processing model.

[0125] S202: Acquire real-time operation data of the target type of equipment to be analyzed, and historical failure cases of the equipment to be analyzed.

[0126] S203: Determine the target troubleshooting thinking chain corresponding to the device to be analyzed based on troubleshooting prompts through the inference layer of the device fault diagnosis model that is pre-trained to support the target type.

[0127] Among them, the target troubleshooting thinking chain includes the troubleshooting problems corresponding to each level and the execution relationship between each level. The execution relationship includes the execution conditions between each level and the execution order between each level.

[0128] S204: Through the hierarchical processing layers of the equipment fault diagnosis model, according to the execution relationship, check in sequence whether the real-time operation data matches the troubleshooting problem corresponding to the current level, until a matching troubleshooting problem is determined.

[0129] S205: Through the output layer of the equipment fault diagnosis model, based on the matching troubleshooting problems and combined with the equipment troubleshooting knowledge base, the cause of the fault and maintenance suggestions are determined.

[0130] Among them, the equipment troubleshooting knowledge base maintains the fault causes and maintenance suggestions corresponding to each troubleshooting problem.

[0131] S206: Generate a troubleshooting report according to a preset report generation template, based on the cause of the fault and maintenance suggestions.

[0132] Embodiment 3:

[0133] Based on the same inventive concept, the present application also provides a device for troubleshooting equipment operation and maintenance failures. Figure 3 A schematic diagram of the structure of a device for troubleshooting equipment operation and maintenance failures provided in an embodiment of the present application, the device comprising:

[0134] An acquisition unit 31 is used to acquire real-time operation data of a target type of equipment to be analyzed, and historical failure cases of the equipment to be analyzed;

[0135] The processing unit 32 is used to determine the fault cause and maintenance suggestion of the device to be analyzed based on the troubleshooting prompt by using the pre-trained device fault diagnosis model supporting the target type; wherein the troubleshooting prompt includes the real-time operation data, the historical fault case and a pre-configured instruction template, and the instruction template is used to instruct to perform fault diagnosis on the real-time operation data;

[0136] The equipment fault diagnosis model determines the fault cause and maintenance suggestion of the equipment to be analyzed based on the troubleshooting prompt, including:

[0137] Through the inference layer of the equipment fault diagnosis model, based on the troubleshooting prompts, determine the target troubleshooting thinking chain corresponding to the equipment to be analyzed; wherein the target troubleshooting thinking chain includes the troubleshooting problems corresponding to each level and the execution relationship between the levels, and the execution relationship includes the execution conditions between the levels and the execution order between the levels;

[0138] Through the hierarchical processing layer of the equipment fault diagnosis model, according to the execution relationship, check in sequence whether the real-time operation data matches the troubleshooting problem corresponding to the current level until a matching troubleshooting problem is determined;

[0139] The fault cause and the maintenance suggestion are determined through the output layer of the equipment fault diagnosis model based on the matched troubleshooting questions and combined with the equipment troubleshooting knowledge base; wherein the fault cause and maintenance suggestion corresponding to each troubleshooting question are maintained in the equipment troubleshooting knowledge base.

[0140] In some possible implementations, the equipment fault diagnosis model is trained in the following manner:

[0141] Obtaining sample troubleshooting tips and their corresponding label data in the target type fault sample set; wherein the sample troubleshooting tips include sample fault operation data of the target type equipment, historical fault case samples of the target type equipment and the instruction template, and the label data includes the standard troubleshooting thinking chain, standard troubleshooting reasons and standard maintenance suggestions corresponding to the sample fault operation data;

[0142] By means of a pre-trained natural language processing model, based on the sample troubleshooting prompt, an expected troubleshooting thought chain, an expected troubleshooting reason and an expected maintenance suggestion corresponding to the sample troubleshooting prompt are obtained; wherein the natural language processing model has natural language understanding capability, the input of the output layer in the natural language processing model is respectively connected with the output of the inference layer and the output of the hierarchical processing layer in the natural language processing model, and the output of the inference layer is connected with the input of the hierarchical processing layer;

[0143] Based on the expected troubleshooting thinking chain and the standard troubleshooting thinking chain, the expected troubleshooting reasons and the standard troubleshooting reasons, the expected maintenance suggestions and the standard maintenance suggestions, the natural language processing model is fine-tuned to determine the equipment fault diagnosis model based on the fine-tuned natural language processing model.

[0144] In some possible implementations, the acquisition unit 31 is further used to preprocess the real-time operation data; wherein the preprocessing includes one or more of the following: structured processing, normalization, and denoising.

[0145] In some possible implementations, the real-time operating data is collected from multiple modalities on the device to be analyzed, and the multiple modalities include at least two of the following: audio, video, and numerical value.

[0146] In some possible implementations, the device further includes: an output module;

[0147] The output module is used to generate a troubleshooting report based on the fault cause and the maintenance suggestion according to a preset report generation template.

[0148] In some possible implementations, the device further includes: a storage module;

[0149] The storage module is used to receive modification opinions on the fault cause and the maintenance suggestion; and save the real-time operation data, the modified fault cause and the modified maintenance suggestion accordingly, so as to optimize the training of the equipment fault diagnosis model based on the real-time operation data, the modified fault cause and the modified maintenance suggestion.

[0150] In some possible implementations, the device further includes: a storage module;

[0151] The storage module is used to receive a confirmation operation on the fault cause and the maintenance suggestion; and update the historical fault case according to the real-time operation data, the fault cause and the maintenance suggestion.

[0152] The device for troubleshooting equipment operation and maintenance faults in this embodiment is presented in the form of a functional module, where the module refers to an application specific integrated circuit (ASIC), a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0153] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0154] Embodiment 5:

[0155] See also Figure 4 , Figure 4 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present application, such as Figure 4As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 A processor 10 is taken as an example.

[0156] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0157] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0158] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of a computer device based on the presentation of a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0159] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0160] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0161] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0162] Embodiment 6:

[0163] On the basis of the above embodiments, an embodiment of the present application further provides a computer-readable storage medium, in which a computer program executable by a processor is stored. When the program runs on the processor, the processor implements the following steps when executing:

[0164] Acquire real-time operating data of the target type of equipment to be analyzed, as well as historical failure cases of the equipment to be analyzed;

[0165] Determine the fault cause and maintenance suggestion of the equipment to be analyzed based on troubleshooting prompts by using a pre-trained equipment fault diagnosis model that supports the target type; wherein the troubleshooting prompts include the real-time operation data, the historical fault cases, and a pre-configured instruction template, and the instruction template is used to instruct to perform fault diagnosis on the real-time operation data;

[0166] The equipment fault diagnosis model determines the fault cause and maintenance suggestion of the equipment to be analyzed based on the troubleshooting prompt, including:

[0167] Through the inference layer of the equipment fault diagnosis model, based on the troubleshooting prompts, determine the target troubleshooting thinking chain corresponding to the equipment to be analyzed; wherein the target troubleshooting thinking chain includes the troubleshooting problems corresponding to each level and the execution relationship between the levels, and the execution relationship includes the execution conditions between the levels and the execution order between the levels;

[0168] Through the hierarchical processing layer of the equipment fault diagnosis model, according to the execution relationship, check in sequence whether the real-time operation data matches the troubleshooting problem corresponding to the current level until a matching troubleshooting problem is determined;

[0169] The fault cause and the maintenance suggestion are determined through the output layer of the equipment fault diagnosis model based on the matched troubleshooting questions and combined with the equipment troubleshooting knowledge base; wherein the fault cause and maintenance suggestion corresponding to each troubleshooting question are maintained in the equipment troubleshooting knowledge base.

[0170] Since the principle of solving the problem by the above-mentioned computer-readable storage medium is similar to the method for troubleshooting equipment operation and maintenance failures, the implementation of the above-mentioned computer-readable storage medium can refer to the embodiment of the method, and the repeated parts will not be repeated.

[0171] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for troubleshooting equipment operation and maintenance failures, characterized in that: The method comprises: Acquire real-time operating data of the target type of equipment to be analyzed, as well as historical failure cases of the equipment to be analyzed; Determine the fault cause and maintenance suggestion of the equipment to be analyzed based on troubleshooting prompts by using a pre-trained equipment fault diagnosis model that supports the target type; wherein the troubleshooting prompts include the real-time operation data, the historical fault cases, and a pre-configured instruction template, and the instruction template is used to instruct to perform fault diagnosis on the real-time operation data; The equipment fault diagnosis model determines the fault cause and maintenance suggestion of the equipment to be analyzed based on the troubleshooting prompt, including: Through the inference layer of the equipment fault diagnosis model, based on the troubleshooting prompts, determine the target troubleshooting thinking chain corresponding to the equipment to be analyzed; wherein the target troubleshooting thinking chain includes the troubleshooting problems corresponding to each level and the execution relationship between the levels, and the execution relationship includes the execution conditions between the levels and the execution order between the levels; Through the hierarchical processing layer of the equipment fault diagnosis model, according to the execution relationship, check in sequence whether the real-time operation data matches the troubleshooting problem corresponding to the current level until a matching troubleshooting problem is determined; The fault cause and the maintenance suggestion are determined through the output layer of the equipment fault diagnosis model based on the matched troubleshooting questions and combined with the equipment troubleshooting knowledge base; wherein the fault cause and maintenance suggestion corresponding to each troubleshooting question are maintained in the equipment troubleshooting knowledge base.

2. The method according to claim 1, characterized in that The equipment fault diagnosis model is trained in the following way: Obtaining sample troubleshooting tips and their corresponding label data in the target type fault sample set; wherein the sample troubleshooting tips include sample fault operation data of the target type equipment, historical fault case samples of the target type equipment and the instruction template, and the label data includes the standard troubleshooting thinking chain, standard troubleshooting reasons and standard maintenance suggestions corresponding to the sample fault operation data; By means of a pre-trained natural language processing model, based on the sample troubleshooting prompt, an expected troubleshooting thought chain, an expected troubleshooting reason and an expected maintenance suggestion corresponding to the sample troubleshooting prompt are obtained; wherein the natural language processing model has natural language understanding capability, the input of the output layer in the natural language processing model is respectively connected with the output of the inference layer and the output of the hierarchical processing layer in the natural language processing model, and the output of the inference layer is connected with the input of the hierarchical processing layer; Based on the expected troubleshooting thinking chain and the standard troubleshooting thinking chain, the expected troubleshooting reasons and the standard troubleshooting reasons, the expected maintenance suggestions and the standard maintenance suggestions, the natural language processing model is fine-tuned to determine the equipment fault diagnosis model based on the fine-tuned natural language processing model.

3. The method according to claim 1, characterized in that After acquiring the real-time operation data of the target type of equipment to be analyzed and the historical failure cases of the equipment to be analyzed, and before determining the failure cause and maintenance suggestion of the equipment to be analyzed based on the troubleshooting prompts by using the pre-trained equipment fault diagnosis model supporting the target type, the method further includes: The real-time operation data is preprocessed; wherein the preprocessing includes one or more of the following: structured processing, normalization, and denoising.

4. The method according to claim 1, characterized in that The real-time operation data is collected from multiple modalities on the device to be analyzed, and the multiple modalities include at least two of the following: audio, video, and numerical value.

5. The method according to claim 1, characterized in that The method further comprises: Generate a troubleshooting report based on the cause of the fault and the maintenance suggestions according to the preset report generation template.

6. The method according to claim 1 or 5, characterized in that The method further comprises: Receive modification suggestions for the cause of the fault and the repair suggestion; The real-time operation data, the modified fault cause and the modified maintenance suggestion are correspondingly saved, so as to optimize and train the equipment fault diagnosis model based on the real-time operation data, the modified fault cause and the modified maintenance suggestion.

7. The method according to claim 1, characterized in that The method further comprises: Receiving a confirmation operation of the fault cause and the maintenance suggestion; The historical fault cases are updated according to the real-time operation data, the fault causes and the maintenance suggestions.

8. A device for troubleshooting equipment operation and maintenance failures, characterized in that: The device comprises: An acquisition unit, used to acquire real-time operation data of a target type of equipment to be analyzed, and historical failure cases of the equipment to be analyzed; a processing unit, configured to determine the fault cause and maintenance suggestion of the device to be analyzed based on a troubleshooting prompt by using a pre-trained device fault diagnosis model supporting the target type; wherein the troubleshooting prompt includes the real-time operation data, the historical fault case, and a pre-configured instruction template, and the instruction template is used to instruct to perform fault diagnosis on the real-time operation data; The equipment fault diagnosis model determines the fault cause and maintenance suggestion of the equipment to be analyzed based on the troubleshooting prompt, including: Through the inference layer of the equipment fault diagnosis model, based on the troubleshooting prompts, determine the target troubleshooting thinking chain corresponding to the equipment to be analyzed; wherein the target troubleshooting thinking chain includes the troubleshooting problems corresponding to each level and the execution relationship between the levels, and the execution relationship includes the execution conditions between the levels and the execution order between the levels; Through the hierarchical processing layer of the equipment fault diagnosis model, according to the execution relationship, check in sequence whether the real-time operation data matches the troubleshooting problem corresponding to the current level until a matching troubleshooting problem is determined; The fault cause and the maintenance suggestion are determined through the output layer of the equipment fault diagnosis model based on the matched troubleshooting questions and combined with the equipment troubleshooting knowledge base; wherein the fault cause and maintenance suggestion corresponding to each troubleshooting question are maintained in the equipment troubleshooting knowledge base.

9. A computer device, characterized in that: The computer device includes a processor, and the processor is used to implement the steps of the device operation and maintenance fault troubleshooting method as described in any one of claims 1 to 7 when executing a computer program stored in a memory.

10. A computer-readable storage medium, characterized in that: It stores a computer program executable by a computer device. When the program is run on the computer device, the computer device executes the steps of the device operation and maintenance fault troubleshooting method as described in any one of claims 1 to 7 above.

Images