Analog machine maintenance method, system and equipment based on capability adaptation and data driving

Abstract

The invention belongs to the technical field of analog machine management, and particularly relates to an analog machine maintenance method, system and equipment based on capability adaptation and data driving. The method comprises the following steps: acquiring capability characteristic data of a plurality of maintainers and equipment parameters of a to-be-maintained analog machine; according to the capability characteristic data, determining a maintenance grade of each maintenance personnel corresponding to a preset capability grading system; determining a health degree score of the analog machine to be maintained according to the equipment parameters, and constructing a maintenance strategy according to the health degree score; and matching the plurality of maintenance tasks with a task permission range indicated by the maintenance level to determine maintenance personnel executing each maintenance task. The method can be combined with the artificial intelligence technology and used as artificial intelligence middleware or a function library, and by establishing a capability grading and task adaptation system, the maintenance quality problem and potential safety hazards caused by human errors are remarkably reduced.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of analog machine management, and particularly relates to an analog machine maintenance method, system and equipment based on capability adaptation and data driving. BACKGROUND

[0002] Flight simulators are core equipment for pilots to perform model modification, retraining and qualification maintenance, and the continuous airworthiness thereof is the basis for ensuring training quality and flight safety. At present, the maintenance of flight simulation training equipment mainly depends on preset fixed periods (such as monthly or quarterly inspection) and personal experience of maintenance personnel.

[0003] However, the above maintenance mode has many defects:

[0004] Firstly, there is a lack of scientific matching mechanism for the professional ability of maintenance personnel and the complexity of specific maintenance tasks. Different skill levels of personnel perform mismatched tasks, which is easy to cause hardware detection omission or software debugging deviation due to human operation errors, and to bury safety hazards. Secondly, the fixed maintenance period cannot dynamically adapt to the actual running load and component health status of the analog machine. For high-load running equipment, there may be problems of untimely maintenance, while for low-load equipment, it may cause excessive maintenance and resource waste.

[0005] In addition, the maintenance decision-making process lacks systematic analysis and support for full-dimensional running data of the equipment, and the fault early warning and root location ability is insufficient, and the troubleshooting efficiency is low.

[0006] Therefore, how to realize the precise matching of the ability of maintenance personnel and the task, and determine the dynamic maintenance decision based on the real-time running data of the equipment, is a problem to be solved in the field. SUMMARY

[0007] In order to solve the above problems in the prior art, i.e., the maintenance personnel ability and task are not matched in the existing flight simulator maintenance mode, the maintenance period is fixed and rigid, and there is a lack of data driving, the present application provides a flight simulator maintenance method based on capability adaptation and data driving, comprising:

[0008] obtaining capability feature data of a plurality of maintenance personnel and device parameters of an analog machine to be maintained;

[0009] determining a maintenance level corresponding to a preset capability classification system for each maintenance personnel according to the capability feature data, the maintenance level being used to indicate the task authority range of the corresponding maintenance personnel;

[0010] According to the equipment parameters, a health score of the analog machine to be maintained is determined, and a maintenance strategy is constructed according to the health score, the maintenance strategy including a plurality of maintenance tasks, the plurality of maintenance tasks corresponding to a task authority range indicated by at least one maintenance level in a preset ability grading system;

[0011] The plurality of maintenance tasks are matched with the task authority range indicated by the maintenance level to determine a maintenance personnel performing each maintenance task.

[0012] In some preferred embodiments, the preset ability grading system is graded based on professional background, working years and comprehensive examination results of the maintenance personnel;

[0013] The comprehensive examination results include scores of theoretical knowledge examination, practical skill examination and data interpretation ability examination, and the theoretical knowledge examination, practical skill examination and data interpretation ability examination correspond to different weight values respectively.

[0014] In some preferred embodiments, the equipment parameters include hardware operation parameters, software state parameters and equipment operation load parameters of the analog machine to be maintained, and the determination of the health score of the analog machine to be maintained according to the equipment parameters includes:

[0015] Respective sub-parameter scores corresponding to the hardware operation parameters, software state parameters and equipment operation load parameters are determined;

[0016] The health score is determined according to the sub-parameter scores, and the formula is:

[0017] ;

[0018] Wherein, is the health score, , and are corresponding weights of the hardware operation parameters, software state parameters and equipment operation load parameters respectively, , , are sub-class data scores corresponding to the hardware operation parameters, software state parameters and equipment operation load parameters respectively, , , are obtained by normalizing the hardware operation parameters, software state parameters and equipment operation load parameters respectively.

[0019] In some preferred embodiments, the construction of the maintenance strategy according to the health score includes:

[0020] The historical time series data of a plurality of sub-parameters of the health score are obtained.

[0021] According to the historical time-series data, a target degradation parameter is identified from the plurality of sub-parameters, which shows a persistent degradation trend;

[0022] The health score and the target degradation parameter are used as joint query conditions to match a target state node in a preset maintenance strategy graph, wherein the nodes in the maintenance strategy graph represent the states of the simulation machine defined by the health intervals and the sub-parameters, and the edges in the maintenance strategy graph represent the maintenance operations that cause the state of at least one node to change;

[0023] Starting from the matched target state node, an optimal maintenance operation sequence is determined in the maintenance strategy graph to reach a target health state node, which is a node in the maintenance strategy graph with a health interval higher than a preset threshold;

[0024] According to the optimal maintenance operation sequence, a plurality of maintenance tasks are constructed to form the maintenance strategy.

[0025] In some preferred embodiments, the maintenance strategy graph satisfies:

[0026] ;

[0027] wherein, is a set of nodes, is a set of directed edges, is an edge weight function;

[0028] The edge weight function is calculated as:

[0029] ;

[0030] wherein, is the weight value of the directed edge , is the directed edge from any node i to node j, is the maintenance operation sequence associated with the directed edge , is the estimated time consumption of executing the maintenance operation sequence , is a preset time normalization factor, is the resource consumption cost of executing the maintenance operation sequence , is a resource cost normalization factor, is the change amount of the health score after executing the maintenance operation sequence , is a health change normalization factor, is a preset constant function, whose value is 1 when the maintenance personnel is unavailable, and whose value is 0 when the maintenance personnel is available, is a non-negative adjustment coefficient, satisfying .

[0031] In some preferred embodiments, the optimal maintenance operation sequence is formulated as:

[0032] ;

[0033] wherein, is a candidate path in the maintenance strategy graph, is a set of all feasible paths from the starting node to any node in the target health state node set , and is a set of target health state nodes, consisting of all nodes whose health degree interval is higher than a preset threshold, is a weight value of the directed edge .

[0034] In some preferred embodiments, the matching of the plurality of maintenance tasks with the task authority range indicated by the maintenance level comprises:

[0035] constructing a personal ability vector of each maintenance personnel according to the ability feature data;

[0036] constructing a task demand vector corresponding to each maintenance task;

[0037] dividing each maintenance personnel into a corresponding maintenance level by determining a vector similarity between the personal ability vector and the task demand vector, and determining that the personal ability vector corresponding to the maintenance personnel is matched with the maintenance task corresponding to the task demand vector when the vector similarity is not less than a preset matching threshold;

[0038] wherein, the calculation formula of the vector similarity is:

[0039] ;

[0040] wherein, is the vector similarity, is a cosine form of the vector similarity, is the personal ability vector, is the task demand vector, is a vector dimension of the personal ability vector or the task demand vector, is a summation index of the vector dimension.

[0041] In some preferred embodiments, the method further comprises:

[0042] allocate a plurality of the maintenance tasks to corresponding maintenance personnel for execution;

[0043] verify short-term effectiveness within a preset first time period of executing the maintenance tasks, obtain a health degree evaluation result after maintenance, and determine whether the health degree evaluation result meets a preset short-term standard reaching condition;

[0044] continuously monitor a change trend of the health degree evaluation result after maintenance within a preset second time period after executing the maintenance tasks, and a length of the second time period is greater than that of the first time period.

[0045] The application provides a simulation machine maintenance system based on capability adaptation and data driving in a second aspect, which is used for implementing the method in the first aspect, and the system comprises:

[0046] a data acquisition module configured to acquire capability characteristic data of a plurality of maintenance personnel and equipment parameters of a simulation machine to be maintained;

[0047] a grade determination module configured to determine a maintenance grade corresponding to a preset capability grading system for each maintenance personnel according to the capability characteristic data, and the maintenance grade is used for indicating a task authority range of the corresponding maintenance personnel;

[0048] a strategy construction module configured to determine a health degree score of the simulation machine to be maintained according to the equipment parameters, and construct a maintenance strategy according to the health degree score, wherein the maintenance strategy comprises a plurality of maintenance tasks, and the plurality of maintenance tasks correspond to a task authority range indicated by at least one maintenance grade in the preset capability grading system;

[0049] a task allocation module configured to match the plurality of maintenance tasks with the task authority range indicated by the maintenance grade, so as to determine the maintenance personnel executing each maintenance task.

[0050] The application provides an electronic device in a third aspect, which comprises:

[0051] at least one processor;

[0052] and a memory in communication connection with the at least one processor;

[0053] wherein the memory stores instructions executable by the processor, and the instructions are used for being executed by the processor to implement the simulation machine maintenance method based on capability adaptation and data driving in the first aspect.

[0054] The application has the following beneficial effects:

[0055] The application establishes a capability grading and task adaptation system, ensures that the maintenance tasks are executed by personnel with corresponding skill levels, and significantly reduces maintenance quality problems and safety hazards caused by human errors.

[0056] Meanwhile, this invention determines the health score of the equipment based on the equipment parameters and further constructs a maintenance strategy, avoiding over-maintenance and under-maintenance, shortening the troubleshooting time, and improving maintenance efficiency.

[0057] Secondly, through dynamic maintenance strategies and closed-loop effect verification mechanisms, potential performance degradation and fault hazards can be identified and addressed in a timely manner, ensuring that the simulator's performance indicators continue to meet airworthiness standards during the interval between two regulatory certifications. Attached Figure Description

[0058] Other features, objects, and advantages of this application will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0059] Figure 1 This is a flowchart illustrating a simulator maintenance method based on capability adaptation and data-driven approaches provided in an embodiment of the present invention.

[0060] Figure 2 This is a schematic diagram of a health score change curve provided in an embodiment of the present invention;

[0061] Figure 3 This is a schematic diagram of the framework of a simulator maintenance system based on capability adaptation and data-driven operation, provided by an embodiment of the present invention.

[0062] Figure 4 This is a schematic diagram of the structure of a computer system that implements the methods, systems, and electronic devices of this application. Detailed Implementation

[0063] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0064] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0065] To more clearly explain the simulator maintenance method based on capability adaptation and data-driven principles of the present invention, the following will be combined with... Figure 1 The steps in the embodiments of the present invention will be described in detail below.

[0066] The first embodiment of the present invention provides a simulator maintenance method based on capability adaptation and data-driven approach, including steps S10-S50, each step of which is described in detail below:

[0067] Step S10: Obtain the capability characteristic data of multiple maintenance personnel, as well as the equipment parameters of the simulator to be maintained;

[0068] Step S20: Based on the capability characteristic data, determine the maintenance level of each maintenance personnel corresponding to the preset capability grading system. The maintenance level is used to indicate the task authority scope of the corresponding maintenance personnel.

[0069] Step S30: Determine the health score of the simulator to be maintained based on the equipment parameters, and construct a maintenance strategy based on the health score. The maintenance strategy includes multiple maintenance tasks, and the multiple maintenance tasks correspond to the task permission range indicated by at least one maintenance level in the preset capability grading system.

[0070] Step S40: Match the multiple maintenance tasks with the task permission scope indicated by the maintenance level to determine the maintenance personnel who will perform each maintenance task.

[0071] It should be noted that the simulator maintenance method proposed in this embodiment can be further used as an artificial intelligence middleware or function library. The control logic involved in this embodiment can be used to form the necessary computer program and assumed on the server side. On this basis, the server can be used in conjunction with various types of AI models. Taking the server integrating the output port of at least one large language model as an example, the user can use the large language model to integrate their needs into usable data as the necessary data for this method (such as the aforementioned capability feature data, etc.), effectively reducing the operation threshold. At the same time, the user can also use the large language model to parse the matching results of this embodiment, which is conducive to improving the convenience of this embodiment in real-world scenarios.

[0072] In this embodiment, the preset capability grading system is based on the maintenance personnel's professional background, years of service, and comprehensive assessment scores to classify them into levels; the comprehensive assessment scores include scores for theoretical knowledge assessment, practical skills assessment, and data interpretation ability assessment, with each of the three assessments corresponding to different weight values.

[0073] In this embodiment, the three core indicators of maintenance personnel (professional background, years of work experience, and comprehensive assessment scores) are graded. The comprehensive assessment scores cover three dimensions: theoretical knowledge (official standards, equipment principles, and maintenance specifications), practical skills (hardware testing, software debugging, and emergency response), and data interpretation ability (analysis of abnormal operating data and interpretation of health reports), with weightings of 30%, 50%, and 20%, respectively.

[0074] For example, the level classification and competency standards can be referenced in Table 1 below:

[0075] Table 1

[0076]

[0077] Please refer to Figure 2 ,like Figure 2 The curves showing the change in health score before and after maintenance are shown. The health trend before maintenance (71 points) and after maintenance (89 points) are compared, and the airworthiness stability line (80 points) and emergency maintenance line (60 points) are marked.

[0078] As a preferred implementation method, this embodiment applies a dynamic assessment mechanism, including:

[0079] Monthly specialized training: Practical training is organized to address high-frequency operational errors in the maintenance and management system (such as missed hardware wear and tear), and the assessment results are entered into the competency file;

[0080] Quarterly competency review: The review adopts a "theory + practical operation + case analysis" model. Those who fail will have their privileges suspended and will receive intensive training.

[0081] Annual Capability Upgrade: Based on the annual performance (maintenance qualification rate, fault handling efficiency) and review results, qualified individuals can apply for a level upgrade.

[0082] In this embodiment, a data analysis system is constructed that integrates multi-dimensional data acquisition, standardized preprocessing, intelligent modeling and evaluation, and precise early warning push to achieve the quantification of equipment status and early warning of anomalies.

[0083] In this embodiment, the data collection dimensions of the equipment parameters cover three major categories: hardware, software, and operating load. The equipment parameters include the hardware operating parameters, software status parameters, and equipment operating load parameters of the simulator to be maintained.

[0084] Determining the health score of the simulator to be maintained based on the equipment parameters includes:

[0085] Determine the scores of each sub-parameter corresponding to the hardware operating parameters, software status parameters, and equipment operating load parameters respectively;

[0086] The health score is determined based on the scores of the sub-parameters, and the formula is as follows:

[0087] ;

[0088] in, To score health, , and These are the corresponding weights for hardware operating parameters, software status parameters, and equipment operating load parameters. , , These are the scores for sub-categories of data corresponding to hardware operating parameters, software status parameters, and equipment operating load parameters. , , These parameters were obtained by normalizing the hardware operating parameters, software status parameters, and equipment operating load parameters, respectively.

[0089] For example, the specific parameters and data acquisition requirements in this embodiment are shown in Table 2 below:

[0090] Table 2

[0091]

[0092] For example, a multi-source data acquisition network can be built using embedded sensors and system log interfaces. After standardized preprocessing (removing outliers and synchronizing timestamps), the data is stored in an encrypted distributed database with a retention period of ≥3 years.

[0093] In this embodiment, a flexible maintenance plan is formulated based on personnel competency grading results and health assessment data to replace the traditional fixed-cycle model. At the same time, standardized operations are used to ensure maintenance quality. For example, see Table 3 below:

[0094] Table 3

[0095]

[0096] Standardized execution of maintenance procedures:

[0097] Standardized Operating Procedures (SOPs): Clearly define the steps, tools, and parameter standards for each maintenance item (e.g., motion system calibration requires a 0.01mm precision laser positioning instrument with a displacement deviation ≤0.1mm).

[0098] Full-process data recording: Real-time recording of operator, time, tool, measured data, and abnormal situations; key operations require double review and signature, generating electronic reports with timestamps;

[0099] Process quality control: The process is automatically paused when an operational deviation is detected, and can only continue after confirmation by the person in charge. The testing tools need to be calibrated every 6 months.

[0100] In this embodiment, a closed-loop mechanism is formed through short-term verification, long-term tracking, and annual evaluation to ensure that the maintenance effect meets the standards, while continuously optimizing the maintenance system based on the evaluation results.

[0101] Furthermore, in this embodiment, constructing a maintenance strategy based on the health score includes:

[0102] Historical time-series data of multiple sub-parameters of the health score are obtained; based on the historical time-series data, a target degradation parameter showing a continuous deterioration trend is identified among the multiple sub-parameters; the health score and the target degradation parameter are used as joint query conditions to match to a target state node in a preset maintenance strategy graph, wherein the nodes in the maintenance strategy graph are used to represent the simulator state defined by the health interval and sub-parameters, and the edges in the maintenance strategy graph are used to represent maintenance operations that cause the simulator state of at least one node to change; starting from the matched target state node, the optimal maintenance operation sequence to reach the target healthy state node is determined in the maintenance strategy graph, wherein the target healthy state node is a node in the maintenance strategy graph whose health interval is higher than a preset threshold; based on the optimal maintenance operation sequence, multiple maintenance tasks are constructed to form the maintenance strategy.

[0103] Specifically, this embodiment takes a full-motion flight simulator as an example. During operation, the simulator triggers a maintenance decision process. For example, in the most recent periodic health assessment, the simulator calculated a health score of 62 points (the preset health threshold is 80 points). Then, it calls the simulator's historical operation database for the past 30 days and extracts the time-series data of multiple sub-parameters that constitute the health score.

[0104] After analyzing the sub-parameters using trend analysis algorithms (e.g., linear fitting based on least squares), three parameters were identified as exhibiting a clear and continuous deterioration trend:

[0105] Visual system rendering frame rate: linearly decreased from a stable value of 60 FPS 30 days ago to the current 38 FPS; motion platform response latency: continuously increased from a baseline of 90 milliseconds to 150 milliseconds; avionics system software error frequency: climbed from an average of 2 times per day to 8 times per day recently.

[0106] The above three parameters are identified as the target deterioration parameters that caused the decrease in health score.

[0107] This embodiment has a pre-built maintenance strategy map specifically for this model. Each node of the map is a multi-dimensional vector that defines a combination of a health range and a set of sub-parameter states to characterize a specific simulator overall state.

[0108] The current health score (62 points) and the specific values ​​of the three target degradation parameters mentioned above are used as a joint query vector. This vector is then matched with nodes in the graph. By comparing the similarity between the query vector and the definition vectors of each node, the most matching node is finally identified as the current state node (e.g., node N_A). The attributes of node N_A are defined as follows: health range [55,65], visual frame rate [35,45] FPS, motion latency [140,160] ms, and avionics errors [6,10] times / day.

[0109] In the maintenance strategy graph, nodes are connected by directed edges. Each edge is associated with a maintenance operation sequence (e.g., "clean projector optical path - calibrate image geometry - update graphics driver") and is accompanied by attributes derived from historical execution data, including: estimated time consumption, expected resource consumption, historical execution success rate, and the health status of the target node after execution.

[0110] Starting with node N_A, and forming a target health state node set by including all nodes in the graph with a lower limit of health score above 80 (preset threshold) (such as nodes N_D and N_E), an optimization algorithm (e.g., an improved Dijkstra algorithm) is used to search for the optimal path from N_A to any target node in the graph based on the comprehensive cost function shown below:

[0111] Total cost = α × Time cost + β × Resource cost - γ × Health improvement benefit + δ × Feasibility penalty;

[0112] The feasibility penalty item checks in real time the required maintenance personnel skill levels, spare parts inventory, and other constraints of each edge. Calculations determine the path with the lowest overall cost: N_A → N_B → N_C. The corresponding maintenance operation sequence is: execute the operation sequence OP_AB associated with edge N_A→N_B (mainly for visual frame rate and motion latency), then execute the operation sequence OP_BC associated with edge N_B→N_C (mainly for avionics errors and depth calibration), which is the optimal maintenance operation sequence mentioned above.

[0113] The above optimal maintenance operation sequence is parsed and instantiated into an executable maintenance strategy, which contains several explicit maintenance tasks, such as:

[0114] Task 1 (corresponding to OP_AB section): Perform motion system servo valve testing and calibration, estimated to require 2 intermediate maintenance personnel, taking 2 hours;

[0115] Task 2 (corresponding to OP_AB): Perform consistency verification between the visual database and the graphics channel. It is estimated that one intermediate maintenance technician will be required, and the time required will be 1.5 hours.

[0116] Task 3 (corresponding to OP_BC section): Update the avionics core software to the specified patch version and verify it. It is estimated that one senior maintenance technician will be required, and the time required is 3 hours.

[0117] This embodiment transforms the health score of 62 into a maintenance plan targeting specific root causes of degradation (frame rate, latency, errors). Compared to traditional fixed-cycle maintenance or simple fault alarms, this embodiment effectively ensures the efficiency and accuracy of maintenance work.

[0118] Furthermore, the maintenance strategy graph satisfies:

[0119] ;

[0120] In the formula, For a set of nodes, Let be a set of directed edges. The edge weight function;

[0121] Edge weight function The calculation formula is:

[0122] ;

[0123] In the formula, For directed edges The weight value, Let be a directed edge pointing from any node i to node j. With directed edges Associated maintenance operation sequence, To execute the maintenance operation sequence The estimated time, The preset time normalization factor, To execute the maintenance operation sequence Resource consumption costs, As a normalization factor for resource costs, To execute the maintenance operation sequence The change in health score after the event. As a normalization factor for changes in health status, This is a preset constant function; its value is 1 when maintenance personnel are unavailable, and its value is 0 when maintenance personnel are available. It is a non-negative adjustment coefficient, satisfying .

[0124] Furthermore, the step of determining the optimal maintenance operation sequence to reach the target healthy state node in the maintenance strategy graph satisfies:

[0125] ;

[0126] In the formula, For the optimal maintenance operation sequence, To maintain a candidate path in the strategy graph. To start from the node Departure, Arrival The set of all feasible paths to any node in the set. This is the set of nodes representing the target health status, consisting of all nodes whose health level exceeds a preset threshold. For directed edges The weight value.

[0127] More specifically, in this embodiment, matching the multiple maintenance tasks with the task permission range indicated by the maintenance level includes:

[0128] Based on the aforementioned capability characteristic data, construct individual capability vectors for each maintenance personnel;

[0129] Construct task requirement vectors for each maintenance task;

[0130] By determining the vector similarity between the individual capability vector and the task requirement vector, each maintenance personnel is assigned to a corresponding maintenance level. When the vector similarity is not less than a preset matching threshold, it is determined that the maintenance personnel corresponding to the individual capability vector are matched with the maintenance tasks corresponding to the task requirement vector.

[0131] The formula for calculating the vector similarity is as follows:

[0132] ;

[0133] in, For vector similarity, This is the cosine form of vector similarity. For individual ability vectors, For the task requirement vector, The vector dimension is either the individual's ability vector or the task requirement vector. The summation index for the vector dimension.

[0134] Furthermore, the method in this embodiment also includes:

[0135] Within a preset first time period for performing the maintenance task, a short-term effect verification is performed to obtain the health assessment results after maintenance and to determine whether they meet the preset short-term achievement conditions.

[0136] During a preset second time period after the maintenance task is performed, the trend of the health assessment results after maintenance is continuously monitored, and the duration of the second time period is longer than that of the first time period.

[0137] For example, short-term effect verification can be performed within 24 hours after maintenance by comparing the health score (≥80 points) and the recovery of abnormal parameters before and after maintenance, and by performing ≥3 simulated flight tests. If the results are unsatisfactory, a second maintenance will be initiated.

[0138] Meanwhile, within one month after maintenance, continuously monitor the trend of changes in the health assessment results after maintenance, such as continuously monitoring the health trend and the number of training interruptions (≤3 times). If any abnormalities occur, investigate the cause (such as incomplete maintenance or component quality problems) and formulate improvement measures.

[0139] Furthermore, taking a Boeing 737-800 FFS Level D simulator of a certain airline as an example, the implementation process is as follows:

[0140] 1. Maintain team capabilities to adapt and implement.

[0141] Team configuration: 6 people (2 junior, 3 intermediate, and 1 senior), with permissions assigned through the maintenance and management system (junior level only enters basic data, while senior level has full permissions).

[0142] Dynamic training: Monthly "visual inspection omissions" were found among junior maintenance workers, who passed the assessment after specialized training; during the quarterly review, one intermediate maintenance worker failed the theoretical test, but passed the make-up test after intensive training.

[0143] 2. Data Collection and Health Assessment Implementation

[0144] Data acquisition module: Real-time acquisition of motion system response delay (1-second interval), visual frame rate (1-second interval), and timed acquisition of avionics error count (5-minute interval), etc.

[0145] Health assessment: On a certain day, there were 8 training sessions on average and 3 interruptions occurred (response delay of 120ms and avionics error 2 times). The calculated H score was 72 (hardware 32 points, software 21 points, load 19 points), triggering an airworthiness concern level warning.

[0146] 3. Dynamic maintenance, scheduling, and execution implementation

[0147] Maintenance decision: H=72 points and 3 monthly outages, P=50.2 points (triggering enhanced maintenance), quarterly inspection to be performed 15 days in advance;

[0148] Standardized execution: Intermediate maintenance personnel lead the replacement of hydraulic pipeline seals, senior maintenance personnel review the process, and after calibration, the response delay is reduced to 85ms and the health score is improved to 88 points;

[0149] Test and Acceptance: The three simulated flight tests were completed without interruption, meeting the acceptance criteria.

[0150] 4. Maintenance effect verification and optimization implementation

[0151] Short-term verification: Health score remained stable at 85-88 points within 24 hours, with no abnormal interruptions;

[0152] Long-term tracking: If there is one interruption within 1 month (temporary software error, repaired within 1 hour), the health score is maintained at 85-90 points;

[0153] Annual assessment: The bureau's assessment was passed on the first attempt, the maintenance qualification rate increased from 90% to 99%, and the weight of hydraulic pressure in the health model was optimized (from 2% to 3%).

[0154] Furthermore, please refer to Figure 3 The second embodiment of the present invention proposes a simulator maintenance system based on capability adaptation and data-driven approach, comprising:

[0155] The data acquisition module 210 is configured to acquire the capability characteristic data of multiple maintenance personnel, as well as the equipment parameters of the simulator to be maintained;

[0156] The level determination module 220 is configured to determine the maintenance level of each maintenance personnel corresponding to a preset capability grading system based on the capability characteristic data. The maintenance level is used to indicate the task authority scope of the corresponding maintenance personnel.

[0157] The strategy construction module 230 is configured to determine the health score of the simulator to be maintained based on the device parameters, and construct a maintenance strategy based on the health score. The maintenance strategy includes multiple maintenance tasks, and the multiple maintenance tasks correspond to the task permission range indicated by at least one maintenance level in a preset capability grading system.

[0158] The task allocation module 240 is configured to match multiple maintenance tasks with the task permission range indicated by the maintenance level in order to determine the maintenance personnel who will perform each maintenance task.

[0159] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the system described above can be found in the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0160] It should be noted that the simulator maintenance method and system based on capability adaptation and data-driven principles provided in the above embodiments are merely illustrative examples of the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiments can be merged into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are merely for distinguishing the various modules or steps and are not considered as an improper limitation of the present invention.

[0161] An electronic device according to a third embodiment of the present invention includes:

[0162] At least one processor;

[0163] and a memory communicatively connected to at least one of the processors;

[0164] The memory stores instructions that can be executed by the processor to implement the aforementioned simulator maintenance method based on capability adaptation and data-driven operation.

[0165] A computer-readable storage medium according to a fourth embodiment of the present invention stores computer instructions, which are executed by the computer to implement the above-described simulator maintenance method based on capability adaptation and data-driven operation.

[0166] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process and related descriptions of the storage device and processing device described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0167] The following is for reference. Figure 4 It shows a schematic diagram of the structure of a computer system for implementing embodiments of the systems, methods, and electronic devices of this application. Figure 4 The server shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0168] like Figure 4As shown, the computer system includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes based on programs stored in Read Only Memory (ROM) 302 or programs loaded from storage section 308 into Random Access Memory (RAM) 303. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An Input / Output (I / O) interface 305 is also connected to the bus 304.

[0169] The following components are connected to I / O interface 305: an input section 306 including a keyboard, mouse, etc.; an output section 307 including a cathode ray tube (CRT), liquid crystal display (LCD), and speakers, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card and a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0170] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0171] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0172] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0173] The terms “first”, “second”, etc., are used to distinguish similar objects, not to describe or indicate a specific order or sequence.

[0174] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent in such process, method, article, or apparatus / device.

[0175] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A simulator maintenance method based on capability adaptation and data-driven approach, characterized in that, include: Acquire the capability characteristics data of multiple maintenance personnel, as well as the equipment parameters of the simulator to be maintained; Based on the capability characteristic data, the maintenance level of each maintenance personnel is determined according to the preset capability grading system. The maintenance level is used to indicate the scope of task authority of the corresponding maintenance personnel. Based on the equipment parameters, the health score of the simulator to be maintained is determined, and a maintenance strategy is constructed based on the health score. The maintenance strategy includes multiple maintenance tasks, and the multiple maintenance tasks correspond to the task permission range indicated by at least one maintenance level in a preset capability grading system. Multiple maintenance tasks are matched with the task permission scope indicated by the maintenance level to determine the maintenance personnel who will perform each maintenance task.

2. The method as described in claim 1, characterized in that, The preset capability grading system is based on the maintenance personnel's professional background, years of service, and comprehensive assessment scores to classify them into different levels. The comprehensive assessment score includes scores for theoretical knowledge assessment, practical skills assessment, and data interpretation ability assessment, with each of these assessments having a different weight value.

3. The method as described in claim 1, characterized in that, The equipment parameters include the hardware operating parameters, software status parameters, and equipment operating load parameters of the simulator to be maintained. Determining the health score of the simulator to be maintained based on these equipment parameters includes: Determine the scores of each sub-parameter corresponding to the hardware operating parameters, software status parameters, and equipment operating load parameters respectively; The health score is determined based on the scores of the sub-parameters, and the formula is as follows: ； in, To score health, , and These are the corresponding weights for hardware operating parameters, software status parameters, and equipment operating load parameters. , , These are the scores for sub-categories of data corresponding to hardware operating parameters, software status parameters, and equipment operating load parameters. , , These parameters were obtained by normalizing the hardware operating parameters, software status parameters, and equipment operating load parameters, respectively.

4. The method according to claim 1, characterized in that, The step of constructing a maintenance strategy based on the health score includes: Obtain historical time-series data of multiple sub-parameters of the health score; Based on the historical time series data, identify the target degradation parameter that shows a continuous degradation trend among the various sub-parameters; The health score and the target degradation parameter are used as joint query conditions to match the target state node in the preset maintenance strategy graph. The node in the maintenance strategy graph is used to represent the simulator state defined by the health interval and sub-parameters, and the edge in the maintenance strategy graph is used to represent the maintenance operation that causes the simulator state of at least one node to change. Starting from the matched target state node, the optimal maintenance operation sequence to reach the target healthy state node is determined in the maintenance strategy graph. The target healthy state node is a node in the maintenance strategy graph whose health range is higher than a preset threshold. Based on the optimal maintenance operation sequence, multiple maintenance tasks are constructed to form the maintenance strategy.

5. The method according to claim 4, characterized in that, The maintenance strategy graph satisfies: ； In the formula, For a set of nodes, Let be a set of directed edges. The edge weight function; Edge weight function The calculation formula is: ； In the formula, For directed edges The weight value, Let be a directed edge pointing from any node i to node j. With directed edges Associated maintenance operation sequence, To execute the maintenance operation sequence The estimated time, The preset time normalization factor, To execute the maintenance operation sequence Resource consumption costs, As a normalization factor for resource costs, To execute the maintenance operation sequence The change in health score after the event. As a normalization factor for changes in health status, This is a preset constant function; its value is 1 when maintenance personnel are unavailable, and its value is 0 when maintenance personnel are available. It is a non-negative adjustment coefficient, satisfying .

6. The method according to claim 4, characterized in that, The optimal maintenance operation sequence for reaching the target healthy node is determined in the maintenance strategy graph, satisfying: ； In the formula, For the optimal maintenance operation sequence, To maintain a candidate path in the strategy graph. To start from the node Departure, Arrival The set of all feasible paths to any node in the set. This is the set of nodes representing the target health status, consisting of all nodes whose health level exceeds a preset threshold. For directed edges The weight value.

7. The method according to claim 1, characterized in that, The step of matching multiple maintenance tasks with the task permission scope indicated by the maintenance level includes: Based on the aforementioned capability characteristic data, construct individual capability vectors for each maintenance personnel; Construct task requirement vectors for each maintenance task; By determining the vector similarity between the individual capability vector and the task requirement vector, each maintenance personnel is assigned to a corresponding maintenance level. When the vector similarity is not less than a preset matching threshold, it is determined that the maintenance personnel corresponding to the individual capability vector are matched with the maintenance tasks corresponding to the task requirement vector. The formula for calculating the vector similarity is as follows: ； in, For vector similarity, This is the cosine form of vector similarity. For individual ability vectors, For the task requirement vector, The vector dimension is either the individual's ability vector or the task requirement vector. The summation index for the vector dimension.

8. The method according to claim 1, characterized in that, The method further includes: The maintenance tasks are assigned to the corresponding maintenance personnel for execution. Within a preset first time period for performing the maintenance task, a short-term effect verification is performed to obtain the health assessment results after maintenance and to determine whether they meet the preset short-term achievement conditions. During a preset second time period after the maintenance task is performed, the trend of the health assessment results after maintenance is continuously monitored, and the duration of the second time period is longer than that of the first time period.

9. A simulator maintenance system based on capability adaptation and data-driven approach, characterized in that, include: The data acquisition module is configured to acquire the capability characteristic data of multiple maintenance personnel, as well as the equipment parameters of the simulator to be maintained; The level determination module is configured to determine the maintenance level of each maintenance personnel corresponding to a preset capability grading system based on the capability characteristic data. The maintenance level is used to indicate the task authority scope of the corresponding maintenance personnel. The strategy construction module is configured to determine the health score of the simulator to be maintained based on the device parameters, and construct a maintenance strategy based on the health score. The maintenance strategy includes multiple maintenance tasks, and the multiple maintenance tasks correspond to the task permission range indicated by at least one maintenance level in a preset capability grading system. The task allocation module is configured to match multiple maintenance tasks with the task permission range indicated by the maintenance level in order to determine the maintenance personnel who will perform each maintenance task.

10. An electronic device, characterized in that, include: At least one processor; and a memory communicatively connected to at least one of the processors; The memory stores instructions that can be executed by the processor to implement the simulator maintenance method based on capability adaptation and data-driven methods as described in any one of claims 1-8.

Images