Gearbox operation and maintenance detection method and device

Abstract

The present invention provides a method and device for operation and maintenance detection of a gearbox, which relates to the technical field of gearbox testing. The present invention constructs a digital twin model to perform operation and maintenance detection and analysis on the sensor data of the gearbox in the current period, determines the gearbox's stress data and fault detection results and other performance data, and then generates multiple feasible maintenance plans. The performance data, maintenance plan and digital twin model of the gearbox are visually displayed to the user, making it convenient for the user to intuitively observe the gearbox's fault conditions and other performance data, and select the corresponding maintenance plan. The maintenance plan can be determined without the user having to disassemble the machine and perform extensive analysis, thereby shortening the time for gearbox fault analysis and determination of maintenance plans, as well as the gearbox downtime, and improving the maintenance efficiency of gearbox fault handling.

Description

Technical Field

[0001] The present invention relates to the technical field of gearbox testing, and in particular to a gearbox operation and maintenance detection method and device. Background Art

[0002] In the field of intelligent coal mine tunneling equipment, form-fitting gearboxes play a vital role. As a key transmission component, their operating status directly impacts the overall performance and efficiency of the tunneling equipment. To ensure the safe, stable, and reliable operation of tunneling equipment, real-time, accurate fault detection and timely maintenance of form-fitting gearboxes are crucial. However, in practical applications, fault detection and maintenance processes face numerous technical challenges.

[0003] Traditional gearbox fault detection, repair, and maintenance rely primarily on manual experience and simple vibration and temperature monitoring. While these methods can determine whether a gearbox fault exists to a certain extent, they often cannot accurately determine the specific fault type, location, or cause. When traditional monitoring systems issue a fault warning or detect an abnormal signal, technicians often need to shut down the machine and disassemble the gearbox for a detailed internal inspection. This process is not only time-consuming and labor-intensive, but also requires a specialized repair team and expensive disassembly tools, significantly increasing maintenance costs.

[0004] More seriously, the disassembly process itself can cause unnecessary damage to other intact parts of the gearbox, further extending downtime and repair cycles. Furthermore, the post-disassembly analysis process relies heavily on the technician's experience and intuition, lacking objective and accurate diagnostic evidence. This often makes it difficult to accurately locate faults and ensure the effectiveness of repair plans. This can not only lead to recurring faults, affecting the continuous operation of tunneling equipment, but can also lead to additional maintenance costs due to excessive or improper repairs.

[0005] In summary, the current gearbox fault detection and maintenance process has technical problems such as long maintenance time and low efficiency. Summary of the Invention

[0006] The present invention provides a gearbox operation and maintenance detection method and device, which can timely detect and maintain gearbox faults, shorten the downtime of gearbox faults, and improve the maintenance efficiency of gearbox fault handling.

[0007] In a first aspect, the present invention provides an operation and maintenance detection method for a gearbox, the method comprising: obtaining sensor data of the gearbox in a current period; the sensor data comprises vibration signals, infrared data, rotational speed, pressure and load; based on the sensor data, feature extraction and conversion are performed to obtain operating condition data of the current period; based on the operating condition data and a preset digital twin model, operation and maintenance detection analysis is performed to determine the performance data of the gearbox in the current period; the performance data comprises stress data and fault detection results of each node in the gearbox; the fault detection results comprise fault type, faulty component and fault location; based on the performance data of the gearbox in the current period, a plurality of feasible maintenance plans are generated; based on the performance data, the plurality of feasible maintenance plans, and the digital twin model, a visual interface of the gearbox is generated and displayed.

[0008] In one possible implementation, before determining the performance data of the gearbox, operation and maintenance inspection and analysis are performed based on the operating condition data and a preset digital twin model, the process also includes: obtaining the geometric data of each component of the gearbox, the sensor data and stress data during the gearbox test, and the fault characteristics of each time period during the gearbox test, the fault characteristics include: fault type, fault component and fault location; constructing a three-dimensional structure module of the gearbox based on the geometric data of each component of the gearbox; determining the operating condition data of multiple time periods based on the sensor data during the gearbox test; the operating condition data includes operating condition characteristics and temperature change characteristics; performing Gaussian regression fitting based on the operating condition characteristics and stress data of multiple time periods to obtain a Gaussian process regression module; performing neural network training based on the temperature change characteristics of multiple time periods and the fault characteristics of multiple time periods to obtain an artificial intelligence module; and constructing a digital twin model based on the gearbox three-dimensional structure module, the Gaussian process regression module, and the artificial intelligence module.

[0009] In one possible implementation, operation and maintenance inspection and analysis are performed based on operating condition data and a preset digital twin model to determine the performance data of the gearbox, including: determining the stress data of each node in the gearbox based on the operating condition characteristics in the operating condition data and the Gaussian process regression module in the digital twin model; and determining the fault detection results of the gearbox based on the temperature change characteristics in the operating condition data and the artificial intelligence model in the digital twin model.

[0010] In one possible implementation, multiple feasible maintenance plans are generated based on the performance data of the gearbox in the current period, including: based on the performance data of the current period and the performance data of multiple time periods in the pre-stored historical period, the gearbox is evaluated to determine the performance evaluation level of the gearbox; the performance evaluation level includes normal, minor fault and serious fault; based on the performance evaluation level of the gearbox and the fault detection result, the fault information to be maintained is determined, and the fault information includes the components to be maintained and the fault type; based on the fault information to be maintained and the maintenance strategy library, multiple pending maintenance plans are determined, and the pending maintenance plans include the required maintenance time, maintenance personnel, maintenance tools and spare parts; based on the work plan of the gearbox and the required maintenance time, multiple maintenance times are determined; based on the multiple maintenance times and the pending maintenance plans, multiple feasible maintenance plans are generated; the feasible maintenance plans include maintenance time, maintenance personnel, maintenance tools and spare parts.

[0011] In one possible implementation, a visualization interface of a gearbox is generated and displayed based on performance data, multiple feasible maintenance plans, and a digital twin model, including: updating and annotating a three-dimensional structure module of the gearbox in the digital twin model based on stress data in the performance data to obtain an updated three-dimensional structure module of the gearbox; rendering the updated three-dimensional structure module of the gearbox based on fault detection results and a performance evaluation level in the performance data to obtain a rendered three-dimensional structure module; generating a first window based on the rendered three-dimensional structure module; determining the health status of each component of the gearbox based on the fault detection results and the performance evaluation level; generating a second window based on the health status of each component of the gearbox; generating a third window in the form of a two-dimensional chart based on multiple feasible maintenance plans; and generating a visualization interface of the gearbox based on the first window, the second window, and the third window.

[0012] In one possible implementation, based on the fault detection result in the performance data and the performance evaluation level, the updated gearbox three-dimensional structure module is rendered to obtain a rendered three-dimensional structure module, including: if the fault detection result is a minor fault and the performance evaluation level is a minor fault, the faulty component is rendered in a first color and other components other than the faulty component are rendered in a second color; if the fault detection result is a serious fault, or the performance evaluation level is a serious fault, the faulty component is rendered in the first color and the second color respectively, and the faulty component is displayed alternately in the first window; and other components other than the faulty component are rendered in the second color.

[0013] In one possible implementation, feature extraction and conversion are performed based on sensor data to obtain operating condition data for the current time period, including: performing wavelet transform processing on the vibration signal for the current time period to obtain a two-dimensional time-frequency image; the two-dimensional time-frequency image is used to reflect the time domain information and frequency domain information of the vibration signal; calculating statistical information of each sensor data based on the speed, pressure and load for the current time period; the statistical information includes the mean, variance, median, maximum and minimum values; performing feature fusion based on each sensor data, the statistical information of each sensor data, and the two-dimensional time-frequency image to obtain operating condition characteristics; performing finite element analysis based on the infrared data for the current time period to determine the temperature distribution data for the current time period in the gearbox; determining the temperature change characteristics for the current time period based on the temperature distribution data for the current time period in the gearbox; and determining the operating condition data for the current time period based on the operating condition characteristics and the temperature change characteristics.

[0014] In one possible implementation, the method also includes: recording sensor data of the gearbox in multiple time periods after maintenance; determining operating condition data in multiple time periods based on the sensor data in multiple time periods; determining performance data of the gearbox in multiple time periods based on the operating condition data in multiple time periods and a digital twin model; and evaluating the health status of the gearbox after maintenance based on the performance data of the gearbox in multiple time periods to determine the maintenance effect.

[0015] In one possible implementation, the performance data also includes the failure probability corresponding to the fault type; accordingly, based on the operating condition data and the preset digital twin model, operation and maintenance detection and analysis are performed to determine the performance data of the gearbox in the current period, and further include: based on the performance data of the current period and the performance data of multiple time periods in the pre-stored historical period, the health status of the gearbox is evaluated to determine the health parameters of the gearbox; based on the health parameters of the gearbox, the maintenance cycle of each component of the gearbox is determined; based on the maintenance cycle of each component of the gearbox and the work plan of the gearbox, a maintenance plan of the gearbox is determined.

[0016] In the second aspect, an embodiment of the present invention provides an operation and maintenance detection device for a gearbox, which includes a communication module and a processing module. The communication module is used to obtain sensor data of the gearbox in the current period; the sensor data includes vibration signals, infrared data, speed, pressure and load; the processing module is used to perform feature extraction and conversion based on the sensor data to obtain the working condition data of the current period; based on the working condition data and a preset digital twin model, operation and maintenance detection analysis is performed to determine the performance data of the gearbox in the current period; the performance data includes stress data and fault detection results of each node in the gearbox; the fault detection results include fault type, fault component and fault location; based on the performance data of the gearbox in the current period, multiple feasible maintenance plans are generated; based on the performance data, multiple feasible maintenance plans, and the digital twin model, a visual interface of the gearbox is generated and displayed.

[0017] In a third aspect, an embodiment of the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to call and run the computer program stored in the memory to execute the steps of the method described in the first aspect and any possible implementation of the first aspect.

[0018] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and is characterized in that when the computer program is executed by a processor, it implements the steps of the method described in the first aspect and any possible implementation method of the first aspect.

[0019] The present invention provides a method and device for gearbox operation and maintenance inspection. By constructing a digital twin model, the method analyzes the gearbox's sensor data for the current period, determines performance data such as the gearbox's stress data and fault detection results, and generates multiple feasible maintenance plans. The gearbox's performance data, maintenance plans, and digital twin model are then visually displayed to the user, allowing them to intuitively observe performance data such as gearbox fault conditions and select appropriate maintenance plans. This eliminates the need for the user to disassemble the gearbox and perform extensive analysis to determine a maintenance plan. This reduces the time required to analyze and determine a gearbox fault and repair plan, as well as gearbox downtime, and improves the efficiency of gearbox fault handling and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 1 is a flow chart of a gearbox operation and maintenance detection method provided by an embodiment of the present invention;

[0022] Figure 2 1 is a schematic structural diagram of a gearbox operation and maintenance detection device provided by an embodiment of the present invention;

[0023] Figure 3 It is a structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0025] In the description of the present invention, unless otherwise specified, “ / ” means “or”. For example, A / B can mean A or B. “And / or” in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, “at least one” and “a plurality of” refer to two or more. Words such as “first” and “second” do not limit the quantity and execution order, and words such as “first” and “second” do not necessarily limit them to be different.

[0026] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner to facilitate understanding.

[0027] Furthermore, the terms "including," "having," and any variations thereof, as used in the description of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or modules is not limited to the listed steps or modules, but may optionally include other steps or modules not listed, or may optionally include other steps or modules inherent to the process, method, product, or apparatus.

[0028] In order to make the purpose, technical solutions and advantages of the present invention more clear, the following will be described through specific embodiments in conjunction with the accompanying drawings of the present invention.

[0029] like Figure 1 As shown, an embodiment of the present invention provides a method for operation and maintenance detection of a gearbox, which includes steps S101-S105.

[0030] S101. Obtain sensor data of the gearbox in the current period.

[0031] In the embodiment of the present application, the sensor data includes vibration signals, infrared data, rotation speed, pressure and load.

[0032] For example, embodiments of the present invention can install sensors at key locations on the gearbox, including vibration sensors, infrared sensors, speed sensors, pressure sensors, and load sensors. Data from these sensors is collected in real time through a data acquisition system to ensure data accuracy and real-time availability. The collected data is then preprocessed, including denoising, filtering, and outlier processing, to improve data quality.

[0033] S102: Based on the sensor data, perform feature extraction and conversion to obtain the working condition data of the current period.

[0034] For example, embodiments of the present invention can use signal processing techniques and machine learning algorithms to extract features reflecting gearbox operating conditions from sensor data, such as vibration frequency, amplitude, temperature distribution, pressure changes, and load conditions. The extracted features are then converted into a standardized operating condition data format for subsequent analysis and processing.

[0035] As a possible implementation manner, step S102 may be specifically implemented as steps S1021 - S1022 .

[0036] S1021 . Perform wavelet transform processing based on the vibration signal of the current period to obtain a two-dimensional time-frequency image.

[0037] In some embodiments, a two-dimensional time-frequency image is used to reflect the time domain information and frequency domain information of the vibration signal.

[0038] For example, embodiments of the present invention can collect vibration signals from a sensor for the current time period. Wavelet transform is performed on the collected vibration signals, converting them from the time domain to the time-frequency domain. Appropriate wavelet basis functions and decomposition levels are selected to obtain a clear two-dimensional time-frequency image. Based on the wavelet transform results, a two-dimensional time-frequency image is generated that reflects both the time and frequency domain information of the vibration signal.

[0039] S1022. Calculate statistical information of each sensor data based on the speed, pressure, and load of the current period.

[0040] In some embodiments, the statistical information includes mean, variance, median, maximum, and minimum values.

[0041] For example, embodiments of the present invention can collect speed, pressure, and load data for the current period from corresponding sensors, and perform statistical calculations on the collected data, including calculating statistical information such as mean, variance, median, maximum, and minimum values.

[0042] S1023. Based on the data of each sensor, the statistical information of each sensor data, and the two-dimensional time-frequency image, feature fusion is performed to obtain the working condition feature.

[0043] For example, embodiments of the present invention can integrate collected sensor data, calculated statistical information, and generated two-dimensional time-frequency images. Features relevant to the gearbox operating condition are extracted from the integrated data. These features may include specific frequency components of the vibration signal, speed stability, and the range of pressure and load variations. The extracted features are then fused to produce operating condition characteristics that comprehensively reflect the current gearbox operating condition.

[0044] S1024. Perform finite element analysis based on the infrared data of the current period to determine the temperature distribution data in the gearbox during the current period.

[0045] For example, embodiments of the present invention can collect infrared data from an infrared sensor for the current period. Finite element analysis is performed on the collected infrared data to simulate the temperature distribution within the gearbox. The analysis considers factors such as the gearbox's geometry, material properties, and heat conduction. Based on the results of the finite element analysis, temperature distribution data within the gearbox for the current period is generated.

[0046] S1025. Determine the temperature change characteristics of the current period based on the temperature distribution data of the gearbox in the current period.

[0047] S1026. Determine the operating condition data for the current period based on the operating condition characteristics and the temperature change characteristics.

[0048] For example, embodiments of the present invention can extract features related to gearbox temperature variations from temperature distribution data, such as maximum temperature, minimum temperature, and temperature gradient. These extracted operating characteristics are then integrated with temperature variation characteristics to generate operating condition data for the current period. This operating condition data should comprehensively reflect the operating status and performance of the gearbox during the current period.

[0049] S103. Based on the operating condition data and the preset digital twin model, perform operation and maintenance inspection and analysis to determine the performance data of the gearbox in the current period.

[0050] In the embodiment of the present application, the performance data includes stress data of each node in the gearbox and fault detection results; the fault detection results include the fault type, fault component and fault location.

[0051] For example, embodiments of the present invention can pre-build a digital twin model of the gearbox that simulates its actual operation, including component interactions and stress distribution. Operating condition data is input into the digital twin model, and simulations are performed to obtain performance data for the gearbox during the current period, including stress data for each node and fault detection results. The simulation results from the digital twin model, combined with a fault detection algorithm, can be used to identify the fault type, faulty component, and location.

[0052] As a possible implementation manner, step S103 may be specifically implemented as steps S1031 - S1032 .

[0053] S1031. Based on the operating condition characteristics in the operating condition data and the Gaussian process regression module in the digital twin model, determine the stress data of each node in the gearbox.

[0054] Exemplarily, an embodiment of the present invention can extract features related to the stress state of the gearbox from the operating condition data, such as load size, speed, operating time, etc. These features should be able to fully reflect the operating condition changes of the gearbox during operation. The Gaussian process regression module integrated in the digital twin model is used to predict the stress data of each node in the gearbox based on the extracted operating condition features. Gaussian process regression is a non-parametric Bayesian regression method that is suitable for modeling small sample data and nonlinear relationships. When applying Gaussian process regression, it is necessary to set the kernel function (such as RBF kernel, Matern kernel, etc.) and hyperparameters (such as length scale, noise variance, etc.), which can be obtained by optimizing the training data. The extracted operating condition features are input into the Gaussian process regression module to obtain the stress prediction value of each node in the gearbox. Output stress data, including information such as the stress size and direction of each node.

[0055] S1032. Determine the gearbox fault detection result based on the temperature change characteristics in the operating condition data and the artificial intelligence model in the digital twin model.

[0056] For example, embodiments of the present invention can extract features related to gearbox temperature changes from operating condition data, such as temperature change trends and temperature fluctuation ranges. These features should be able to reflect the changes in the thermal state of the gearbox during operation. The artificial intelligence model (such as a deep learning model, support vector machine, etc.) integrated in the digital twin model is used to detect faults based on the extracted temperature change features. When applying the artificial intelligence model, the model must first be trained so that it can recognize the difference between normal and faulty states. The training data should include temperature change features under normal conditions and temperature change features under known fault conditions. The extracted temperature change features are input into the artificial intelligence model to obtain the gearbox fault detection results. The output results should include information such as the fault type, fault location, and fault severity. Based on the fault detection results, a maintenance plan can be further formulated or other measures can be taken to eliminate the fault.

[0057] S104: Generate multiple feasible maintenance plans based on the performance data of the gearbox in the current period.

[0058] For example, the embodiment of the present invention can formulate multiple feasible maintenance plans based on the performance data and fault detection results of the gearbox, including preventive maintenance, corrective maintenance, and improvement maintenance.

[0059] As a possible implementation manner, step S104 can be specifically implemented as steps S1041 - S1045 .

[0060] S1041. Based on the performance data of the current period and the performance data of multiple time periods in the pre-stored historical period, the gearbox is subjected to a performance evaluation, and a performance evaluation level of the gearbox is determined.

[0061] In some embodiments, the performance evaluation levels include normal, minor failure, and major failure.

[0062] For example, embodiments of the present invention can compare and analyze performance data (such as vibration, temperature, and pressure) from the current period with historical performance data to identify changing trends and anomalies in the performance data. Gearbox performance can be evaluated using a pre-built performance evaluation model (such as a machine learning-based classification model). This model outputs a gearbox performance evaluation grade based on the input performance data. Based on the model's output, the gearbox performance evaluation grade is categorized as normal, minor fault, or major fault. This grading facilitates the development of subsequent maintenance plans.

[0063] S1042. Determine the fault information to be maintained based on the performance evaluation level of the gearbox and the fault detection result.

[0064] In some embodiments, the fault information includes the component to be maintained and the fault type.

[0065] For example, embodiments of the present invention can utilize a fault detection algorithm (e.g., a vibration signal-based fault diagnosis algorithm) to detect gearbox faults and identify the specific fault type and location. The fault detection results are then combined with the performance evaluation level to determine the fault information requiring maintenance. This information includes the component to be maintained (e.g., bearings, gears, etc.) and the fault type (e.g., wear, fracture, etc.).

[0066] S1043: Determine multiple pending maintenance plans based on the fault information to be maintained and the maintenance strategy library.

[0067] In some embodiments, the pending maintenance plan includes required maintenance time, maintenance personnel, maintenance tools, and spare parts.

[0068] For example, embodiments of the present invention can pre-build a maintenance strategy library containing various fault types and their corresponding maintenance strategies. These strategies can include information such as maintenance methods, maintenance tools, and spare parts. Based on the fault information to be maintained, an appropriate maintenance strategy is selected from the maintenance strategy library. Based on actual conditions (such as the maintenance personnel's skill level and the availability of maintenance tools), multiple maintenance plans are developed. Each plan should include key information such as the required maintenance time, maintenance personnel, maintenance tools, and spare parts.

[0069] S1044. Determine multiple maintenance times based on the gearbox's work plan and required maintenance duration.

[0070] For example, embodiments of the present invention can analyze the gearbox's operating schedule, including operating hours, downtime, and load conditions. This helps determine an appropriate maintenance window. Based on the required maintenance duration and the operating schedule, multiple possible maintenance windows are determined. These windows should ensure that the gearbox can be shut down for maintenance operations while minimizing the impact on production.

[0071] S1045. Generate multiple feasible maintenance plans based on multiple maintenance times and pending maintenance plans.

[0072] In some embodiments, the feasible maintenance plan includes maintenance time, maintenance personnel, maintenance tools, and spare parts.

[0073] For example, embodiments of the present invention can combine multiple maintenance schedules with pending maintenance plans to generate multiple feasible maintenance plans. These plans should include information such as specific maintenance schedules, maintenance personnel, maintenance tools, and spare parts. The generated multiple feasible maintenance plans are evaluated, taking into account factors such as maintenance cost, maintenance effectiveness, and impact on production. Ultimately, the optimal maintenance plan is selected for implementation.

[0074] S105. Generate and display a visual interface of the gearbox based on performance data, multiple feasible maintenance plans, and the digital twin model.

[0075] For example, a visual interface for a gearbox is designed, including a 3D model of the gearbox, operating data display, performance data charts, fault detection result prompts, and maintenance plan presentations. Data visualization: Gearbox performance data, fault detection results, and maintenance plan information are displayed on the visual interface in the form of graphics, charts, and animations, facilitating intuitive understanding and analysis. Interactive functionality: Interactive functions such as data query, solution selection, and parameter adjustment are implemented in the visual interface to enable users to make decisions based on their actual needs.

[0076] As a possible implementation manner, step S105 may be specifically implemented as steps S1051 - S1055 .

[0077] S1051. Based on the stress data in the performance data, the gearbox three-dimensional structure module in the digital twin model is updated and labeled to obtain an updated gearbox three-dimensional structure module.

[0078] For example, an embodiment of the present invention can map stress data in the performance data to the gearbox three-dimensional structure module of the digital twin model. This generally involves associating stress values ​​with corresponding nodes or components in the model. Based on the mapped stress data, the gearbox three-dimensional structure module in the digital twin model is updated. The update may include changing the color, transparency, or adding annotations to intuitively display the stress distribution. Annotations are added to the updated three-dimensional structure module to indicate the magnitude and direction of the stress. The annotations can be numbers, arrows, or other visual elements to help users understand the stress state.

[0079] S1052. Based on the fault detection results in the performance data and the performance evaluation level, the updated gearbox three-dimensional structure module is rendered to obtain a rendered three-dimensional structure module.

[0080] Embodiments of the present invention can map fault detection results and performance evaluation levels onto an updated three-dimensional structural model. This may involve associating different types of faults and evaluation levels with corresponding components in the model. Based on the mapping results, rendering parameters such as color, texture, and lighting are set to highlight the faulty components and evaluation levels. The rendering parameters should be selected to clearly convey the fault information and evaluation level. Rendering is then performed to obtain a rendered three-dimensional structural model. The rendered model should intuitively display the gearbox's fault status and performance evaluation level.

[0081] Exemplarily, if the fault detection result is a minor fault and the performance evaluation level is a minor fault, the faulty component is rendered in a first color, and other components except the faulty component are rendered in a second color.

[0082] For example, determine the primary and secondary colors. The primary color is typically a softer color (such as light yellow or green) to indicate minor faults or minor performance degradation. The secondary color is a more neutral or basic color (such as gray or light blue) to indicate other components in a normal state. In the 3D structure module, find the component corresponding to the minor fault detection result and render it in the primary color. Render all other components except the faulty component in the secondary color.

[0083] As another example, if the fault detection result is a serious fault, or the performance evaluation level is a serious fault, the faulty component is rendered in the first color and the second color respectively, and the faulty component is displayed alternately in the first window; other components except the faulty component are rendered in the second color.

[0084] For example, determine the primary and secondary colors. In this case, the primary color might be a more striking color (such as red or orange) to emphasize severe faults; the secondary color is still used to indicate other components in normal conditions. Set a flashing effect, including parameters such as flashing frequency, duration, and brightness variation. In the 3D structure module, find components corresponding to severe fault detection results or severe performance evaluation levels and render them in the primary color. In the first window, display these faulty components in an alternating flashing pattern according to preset flashing parameters to attract the user's attention. Render all components except the faulty component in the secondary color.

[0085] For example, if a gear in a gearbox fails, the present invention can render that gear in red and gray, respectively. All other components within the gearbox (such as bearings and other gears) are rendered in gray. The gearbox is then displayed in the first window, with all other healthy components in gray and the failed gear alternating between red and gray. This provides a warning of gearbox failure.

[0086] S1053: Generate a first window based on the rendered three-dimensional structure module.

[0087] For example, embodiments of the present invention can create a new window in the visualization interface to display the rendered 3D structure module. The window size, position, and layout should be adjusted based on user needs and interface design. The rendered 3D structure module is embedded in the first window. The display quality of the module in the window is ensured, including clarity, color, and dynamic effects.

[0088] S1054. Based on the fault detection results and the performance evaluation level, determine the health status of each component of the gearbox.

[0089] For example, embodiments of the present invention can comprehensively assess the health status of various gearbox components based on fault detection results and performance evaluation levels. This assessment may involve comprehensive consideration of the fault type, severity, and evaluation level. The assessment results are recorded as health status data for each gearbox component. This data should include information such as component name, health status level, and evaluation time.

[0090] S1055: Generate a second window based on the health status of each component of the gearbox.

[0091] For example, embodiments of the present invention can visualize the health status data of various gearbox components, allowing users to intuitively understand the health status of each component. This visualization may involve using color coding, charts, or text to represent health status levels. A new window is created within the visualization interface to display the health status of each gearbox component. The window layout and display method should be adjusted based on user needs and interface design.

[0092] S1056. Based on multiple feasible maintenance plans, generate a third window in the form of a two-dimensional chart.

[0093] For example, embodiments of the present invention can visualize multiple feasible maintenance plans in a two-dimensional chart format, allowing users to compare and select the optimal plan. Charts may include bar charts, line charts, pie charts, and other graphic elements to illustrate various aspects of the maintenance plan (e.g., cost, time, and effectiveness). A new window is created in the visualization interface to display the two-dimensional charts of the multiple feasible maintenance plans. Ensure the clarity and readability of the charts within the window.

[0094] S1057: Generate a visualization interface of the gearbox based on the first window, the second window, and the third window.

[0095] Exemplarily, an embodiment of the present invention may integrate the first window, the second window, and the third window into a single visualization interface. The integration process should ensure that the layout of each window is reasonable and coordinated, and that it is convenient for users to switch and view. Interactive functions such as zooming, rotating, and clicking and selecting are added to the visualization interface so that users can more flexibly view and analyze the status and maintenance plan of the gearbox. The interactive design should be simple and intuitive, easy for users to understand and operate. After the integration and interactive design are completed, the final gearbox visualization interface is displayed. The interface should be able to clearly convey the status, fault information, health status, and maintenance plan of the gearbox, providing users with comprehensive decision support.

[0096] The present invention provides a gearbox operation and maintenance inspection method. By constructing a digital twin model, it analyzes the gearbox's sensor data during the current period, determines gearbox performance data such as stress data and fault detection results, and then generates multiple feasible maintenance plans. The gearbox's performance data, maintenance plans, and digital twin model are then visually displayed to the user, allowing them to intuitively observe performance data such as gearbox fault conditions and select appropriate maintenance plans. This method eliminates the need for the user to disassemble the gearbox and perform extensive analysis to determine a maintenance plan. This reduces the time required to identify gearbox faults and determine maintenance plans, as well as gearbox downtime, and improves the efficiency of gearbox fault handling and maintenance.

[0097] Optionally, the gearbox operation and maintenance detection method provided by the embodiment of the present invention further includes steps S201-S206 before step S103.

[0098] S201. Acquire geometric data of various components of the gearbox, sensor data and stress data during the gearbox test, and fault characteristics of various time periods during the gearbox test.

[0099] In some embodiments, the fault characteristics include: fault type, fault component, and fault location.

[0100] For example, geometric data typically comes from a CAD (Computer-Aided Design) model or 3D scanning technology. CAD models provide precise dimensions and shape information for gearbox components, while 3D scanning technology captures the geometry of the physical gearbox. Data format: Ensure that the acquired geometric data format is compatible with subsequent modeling software. Common formats include STL, OBJ, and IGES. Data verification: Verify the geometric data to ensure its integrity and accuracy, preventing errors in subsequent modeling.

[0101] For example, design a gearbox test plan, clearly defining the test objectives, test conditions, and sensor layout. During the test, use sensors to collect real-time parameters such as gearbox vibration, temperature, pressure, and load, and record stress data. Ensure that all sensor data is synchronized in time to facilitate subsequent analysis of the gearbox's performance under different operating conditions.

[0102] For example, during the test, the time, type, component, and location of the gearbox failure are recorded. Fault classification: Faults are classified to identify the characteristics and possible causes of each failure. Fault data organization: Fault data is organized into a structured format to facilitate subsequent analysis and modeling.

[0103] S202: Construct a three-dimensional structure module of the gearbox based on the geometric data of each component of the gearbox.

[0104] For example, select appropriate 3D modeling software, such as SolidWorks or Autodesk Inventor. Based on the geometric data, construct a 3D structural model of the gearbox in the modeling software, including the assembly relationships and relative positions of the components. Verify the constructed 3D structural model to ensure the accuracy and reliability of the model.

[0105] S203: Determine operating condition data for multiple time periods based on sensor data during the gearbox test.

[0106] In some embodiments, the operating condition data includes operating condition characteristics and temperature change characteristics.

[0107] For example, the collected sensor data is preprocessed, including denoising, filtering, and outlier processing. Operating condition characteristics, such as vibration frequency, amplitude, and temperature change rate, are extracted from the preprocessed data. Based on the timeline of the test process, the sensor data is divided into multiple time periods, each corresponding to a specific operating condition.

[0108] S204: Based on the working condition characteristics and stress data of multiple time periods, Gaussian regression fitting is performed to obtain a Gaussian process regression module.

[0109] For example, the operating condition characteristics and stress data are organized into a training set and a test set. The training set is trained using a Gaussian process regression algorithm to obtain a Gaussian process regression model. The trained model is validated using the test set to evaluate the model's predictive performance.

[0110] S205: Based on the temperature change characteristics of multiple time periods and the fault characteristics of multiple time periods, neural network training is performed to obtain an artificial intelligence module.

[0111] For example, features useful for fault prediction are selected from temperature change features and fault features. Neural network design: Design a suitable neural network structure, such as a convolutional neural network (CNN) or recurrent neural network (RNN). Model training: Use temperature change features and fault features to train the neural network and develop an artificial intelligence module capable of predicting faults.

[0112] S206. Build a digital twin model based on the gearbox three-dimensional structure module, Gaussian process regression module, and artificial intelligence module.

[0113] For example, the gearbox 3D structure module, Gaussian process regression module, and artificial intelligence module are integrated to form a complete digital twin model. Model validation and optimization: The constructed digital twin model is validated and optimized to ensure that it accurately simulates the actual operation of the gearbox. Interface design: Design interfaces for the digital twin model to interact with the external environment, such as data input / output interfaces and visualization interfaces.

[0114] In this way, the embodiment of the present invention can construct a digital twin model before performing performance testing on the gearbox, which facilitates the visualization of gearbox faults and improves the maintenance efficiency of gearbox fault handling.

[0115] Optionally, the gearbox operation and maintenance detection method provided by the embodiment of the present invention further includes steps S301-S304.

[0116] S301. Record sensor data of the gearbox at multiple time periods after maintenance.

[0117] For example, after gearbox maintenance, multiple monitoring periods are planned based on actual needs. The period lengths can be flexibly set based on the gearbox's operating characteristics and the maintenance content. Ensure that sensors installed on the gearbox (such as vibration sensors, temperature sensors, and pressure sensors) are in normal working order and can accurately collect the required data. During each monitoring period, gearbox sensor data is collected periodically or continuously to ensure data integrity and continuity. The collected sensor data is properly stored for subsequent analysis and processing.

[0118] S302 : Determine operating condition data for multiple time periods based on sensor data for multiple time periods.

[0119] For example, the collected sensor data is preprocessed, including data cleaning (removing outliers and filling missing values) and data conversion (such as unit conversion and data standardization). Features that reflect the gearbox operating conditions, such as vibration frequency, amplitude, temperature trends, and pressure fluctuations, are extracted from the preprocessed sensor data. Based on the extracted features, an operating condition dataset for each time period is constructed, including various operating condition features and corresponding time period identifiers.

[0120] S303. Determine the performance data of the gearbox in multiple time periods based on the operating condition data in multiple time periods and the digital twin model.

[0121] For example, operating condition data for each time period is fed into a pre-built digital twin model. The digital twin model simulates the gearbox's operation at each time period, including component interactions, stress distribution, and energy transfer. Performance data for the gearbox at each time period, such as stress, temperature, wear, and failure risk, is then extracted from the digital twin model.

[0122] S304. Based on the performance data of the gearbox in multiple time periods, evaluate the health status of the gearbox after maintenance and determine the maintenance effect.

[0123] For example, embodiments of the present invention can compare the performance data of the gearbox after maintenance in each time period with the performance data before maintenance to analyze the changing trends of the performance data. Based on the changing trends of the performance data, the health status of the gearbox after maintenance is evaluated, including the degree of overall performance recovery and the reduction in failure risk. The comprehensive evaluation results are used to determine the effectiveness of the gearbox maintenance, such as whether the expected goals were achieved and whether further maintenance is required. Based on the evaluation results, feedback and optimization of the digital twin model are performed to improve the accuracy and reliability of the model. At the same time, based on the maintenance effect, subsequent maintenance plans and strategies are adjusted.

[0124] In this way, the embodiment of the present invention can analyze the sensor data of the gearbox at multiple time periods after maintenance and evaluate the maintenance effect.

[0125] In some embodiments, the performance data also includes a failure probability corresponding to the failure type;

[0126] Optionally, the gearbox operation and maintenance detection method provided by the embodiment of the present invention further includes steps S401-S406 after step S103.

[0127] S401 : Based on the performance data of the current period and the pre-stored performance data of multiple time periods in the historical period, the health status of the gearbox is evaluated to determine the health parameters of the gearbox.

[0128] For example, embodiments of the present invention can integrate performance data for the current period (including failure probabilities corresponding to fault types) with pre-stored performance data from multiple time periods in the past to form a complete dataset. This dataset comprehensively reflects the performance of the gearbox over different time periods. A health assessment model is constructed using machine learning or statistical methods, such as support vector machines, random forests, and neural networks. This model outputs a health assessment of the gearbox's health based on the input performance data. The integrated dataset is input into the health assessment model, which then outputs health parameters for the gearbox. These health parameters can be one or more numerical values ​​that quantify the health of the gearbox. For example, a health parameter can be a value between 0 and 1, where 1 indicates a completely healthy gearbox and 0 indicates a severe fault. In addition to calculating the health parameters for the current period, trends in health parameters over time can also be analyzed to understand the evolution of the gearbox's health.

[0129] S402: Determine the maintenance period of each component of the gearbox based on the health parameters of the gearbox.

[0130] For example, an embodiment of the present invention can decompose the health parameters of the gearbox into the health of each component. This can be achieved by analyzing the performance data of each component inside the gearbox, such as the vibration data of the bearings, the wear data of the gears, etc. According to the health of each component, combined with the life curve of the component, the failure probability and other information, the maintenance cycle of each component is calculated. The maintenance cycle can be a time range, indicating that maintenance operations need to be performed on the component within this time range. According to the health of each component and the maintenance cycle, the maintenance tasks of the gearbox are prioritized. Components with higher priority should be maintained first to ensure the overall health and safe operation of the gearbox.

[0131] S403: Determine a maintenance plan for the gearbox based on the maintenance cycles of the various components of the gearbox and the working plan of the gearbox.

[0132] For example, an embodiment of the present invention can analyze the working plan of the gearbox, including information such as the operating time, downtime, load conditions, etc. of the gearbox. This information will be used to determine the feasibility of the gearbox maintenance plan. A maintenance plan for the gearbox is formulated based on the maintenance cycle and work plan of each component. The maintenance plan should include key information such as maintenance time, maintenance content, and maintenance personnel. When formulating a maintenance plan, consider the availability of maintenance resources (such as personnel, equipment, spare parts, etc.) and the impact of maintenance on the operation of the gearbox. By optimizing the maintenance plan, it is ensured that maintenance tasks can be completed efficiently and orderly while minimizing the impact on the operation of the gearbox. When executing the maintenance plan, the maintenance process is monitored and recorded. This helps to detect potential problems in a timely manner and adjust and optimize the maintenance plan. At the same time, maintenance records also provide valuable data support for subsequent health assessments and maintenance cycle calculations.

[0133] In this way, the embodiment of the present invention can analyze the health status of the gearbox before the gearbox fails and coordinate the maintenance plan of the gearbox, thereby facilitating the overall planning of gearbox maintenance and extending the service life of the gearbox.

[0134] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0135] The following are device embodiments of the present invention. For details not fully described therein, reference may be made to the corresponding method embodiments described above.

[0136] Figure 2 The schematic diagram of the structure of a gearbox operation and maintenance detection device provided by an embodiment of the present invention is shown. The operation and maintenance detection device 500 includes a communication module 501 and a processing module 502.

[0137] The communication module 501 is used to obtain the sensor data of the gearbox in the current period; the sensor data includes vibration signals, infrared data, speed, pressure and load.

[0138] Processing module 502 is used to extract and convert features based on sensor data to obtain operating condition data for the current period; based on the operating condition data and a preset digital twin model, perform operation and maintenance detection analysis to determine the performance data of the gearbox for the current period; the performance data includes stress data and fault detection results of each node in the gearbox; the fault detection results include the fault type, faulty component, and fault location; based on the performance data of the gearbox for the current period, generate multiple feasible maintenance plans; based on the performance data, multiple feasible maintenance plans, and the digital twin model, generate and display a visual interface of the gearbox.

[0139] Figure 3 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the electronic device 600 of this embodiment includes: a processor 601, a memory 602, and a computer program 603 stored in the memory 602 and executable on the processor 601. When the processor 601 executes the computer program 603, the steps in the above-mentioned method embodiments are implemented, for example Figure 1 Alternatively, when the processor 601 executes the computer program 603, the functions of the modules / units in the above-mentioned device embodiments are realized, for example, Figure 2 The functions of the communication module 501 and the processing module 502 are shown.

[0140] Exemplarily, the computer program 603 may be divided into one or more modules / units, which are stored in the memory 602 and executed by the processor 601 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 603 in the electronic device 600. For example, the computer program 603 may be divided into Figure 2 Shown are a communication module 501 and a processing module 502 .

[0141] The processor 601 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0142] The memory 602 can be an internal storage unit of the electronic device 600, such as a hard drive or memory of the electronic device 600. The memory 602 can also be an external storage device of the electronic device 600, such as a plug-in hard drive, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped with the electronic device 600. Furthermore, the memory 602 can include both an internal storage unit of the electronic device 600 and an external storage device. The memory 602 is used to store the computer program and other programs and data required by the terminal. The memory 602 can also be used to temporarily store data that has been output or is about to be output.

[0143] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A gearbox operation and maintenance detection method, characterized in that: include: Acquire sensor data of the gearbox during the current period; the sensor data includes vibration signals, infrared data, speed, pressure, and load; Based on the sensor data, feature extraction and conversion are performed to obtain operating condition data for the current period; Based on the operating condition data and the preset digital twin model, operation and maintenance detection analysis is performed to determine the performance data of the gearbox in the current period; the performance data includes stress data and fault detection results of each node in the gearbox; The fault detection result includes the fault type, fault component and fault location; Generate multiple feasible maintenance plans based on the performance data of the gearbox during the current period; generating and displaying a visual interface of the gearbox based on the performance data, the multiple feasible maintenance solutions, and the digital twin model; The method comprises the following steps: performing feature extraction and conversion based on the sensor data to obtain the working condition data of the current time period, including: performing wavelet transform processing based on the vibration signal of the current time period to obtain a two-dimensional time-frequency image; the two-dimensional time-frequency image is used to reflect the time domain information and frequency domain information of the vibration signal; calculating the statistical information of each sensor data based on the speed, pressure and load of the current time period; the statistical information includes the average value, variance, median value, maximum value and minimum value; performing feature fusion based on each sensor data, the statistical information of each sensor data, and the two-dimensional time-frequency image to obtain the working condition characteristics; performing finite element analysis based on the infrared data of the current time period to determine the temperature distribution data of the current time period in the gearbox; determining the temperature change characteristics of the current time period based on the temperature distribution data of the current time period in the gearbox; and determining the working condition data of the current time period based on the working condition characteristics and the temperature change characteristics.

2. The gearbox operation and maintenance detection method according to claim 1, characterized in that: Before performing operation and maintenance inspection and analysis based on the operating condition data and the preset digital twin model to determine the performance data of the gearbox, the method further includes: Acquire geometric data of various components of the gearbox, sensor data and stress data during the gearbox test, and fault characteristics at various time periods during the gearbox test, the fault characteristics including: fault type, fault component, and fault location; Constructing a three-dimensional structure module of the gearbox based on the geometric data of each component of the gearbox; Determining operating condition data for multiple time periods based on sensor data during the gearbox test; the operating condition data includes operating condition characteristics and temperature change characteristics; Based on the working condition characteristics and stress data of the multiple time periods, Gaussian regression fitting is performed to obtain a Gaussian process regression module; Based on the temperature change characteristics of multiple time periods and the fault characteristics of multiple time periods, neural network training is performed to obtain an artificial intelligence module; The digital twin model is constructed based on the gearbox three-dimensional structure module, Gaussian process regression module, and artificial intelligence module.

3. The gearbox operation and maintenance detection method according to claim 1, characterized in that: The operation and maintenance detection analysis is performed based on the operating condition data and the preset digital twin model to determine the performance data of the gearbox, including: Determining stress data of each node in the gearbox based on the operating condition characteristics in the operating condition data and the Gaussian process regression module in the digital twin model; Based on the temperature change characteristics in the operating condition data and the artificial intelligence model in the digital twin model, the fault detection results of the gearbox are determined.

4. The gearbox operation and maintenance detection method according to claim 1, characterized in that: The method generates multiple feasible maintenance plans based on the performance data of the gearbox in the current period, including: Based on the performance data of the current period and the performance data of multiple time periods in the pre-stored historical period, the gearbox is evaluated for performance, and a performance evaluation level of the gearbox is determined; the performance evaluation level includes normal, minor fault and major fault; Determining fault information to be maintained based on the performance evaluation level of the gearbox and the fault detection result, the fault information including the component to be maintained and the fault type; Based on the fault information to be maintained and the maintenance strategy library, multiple pending maintenance plans are determined, wherein the pending maintenance plans include the required maintenance time, maintenance personnel, maintenance tools and spare parts; Determining multiple maintenance times based on the gearbox work plan and the required maintenance duration; Based on the multiple maintenance times and the pending maintenance plans, multiple feasible maintenance plans are generated; the feasible maintenance plans include maintenance time, maintenance personnel, maintenance tools and spare parts.

5. The gearbox operation and maintenance detection method according to claim 1, characterized in that: The generating and displaying of a visual interface of the gearbox based on the performance data, the multiple feasible maintenance solutions, and the digital twin model includes: Based on the stress data in the performance data, updating and annotating the gearbox three-dimensional structure module in the digital twin model to obtain an updated gearbox three-dimensional structure module; Rendering the updated gearbox three-dimensional structure module based on the fault detection result and the performance evaluation level in the performance data to obtain a rendered three-dimensional structure module; generating a first window based on the rendered three-dimensional structure module; Determining the health status of each component of the gearbox based on the fault detection result and the performance evaluation level; generating a second window based on the health status of each gearbox component; Based on the multiple feasible maintenance plans, generating a third window in the form of a two-dimensional chart; A visualization interface of the gearbox is generated based on the first window, the second window, and the third window.

6. The gearbox operation and maintenance detection method according to claim 5, characterized in that: The updated gearbox three-dimensional structure module is rendered based on the fault detection result and the performance evaluation level in the performance data to obtain the rendered three-dimensional structure module, including: If the fault detection result is a minor fault and the performance evaluation level is a minor fault, the faulty component is rendered in a first color and other components except the faulty component are rendered in a second color; If the fault detection result is a serious fault, or the performance evaluation level is a serious fault, the faulty component is rendered in a first color and a second color respectively, and the faulty component is displayed alternately in a first window with a flashing display; and other components except the faulty component are rendered in the second color.

7. The gearbox operation and maintenance detection method according to claim 1, characterized in that: The method further comprises: Record sensor data of the gearbox at multiple time periods after maintenance; Determining operating condition data for multiple time periods based on sensor data for multiple time periods; Determining performance data of the gearbox in the multiple time periods based on the operating condition data in the multiple time periods and the digital twin model; Based on the performance data of the gearbox in multiple time periods, the health status of the gearbox after maintenance is evaluated to determine the maintenance effect.

8. The gearbox operation and maintenance detection method according to claim 1, characterized in that: The performance data also includes a failure probability corresponding to the failure type; Accordingly, after performing operation and maintenance inspection and analysis based on the operating condition data and the preset digital twin model to determine the performance data of the gearbox in the current period, the method further includes: Evaluate the health of the gearbox based on the performance data of the current period and pre-stored performance data of multiple time periods in the historical period to determine the health parameters of the gearbox; Determining maintenance cycles for various components of the gearbox based on the health parameters of the gearbox; A maintenance plan for the gearbox is determined based on the maintenance cycles of the various components of the gearbox and the working plan of the gearbox.

9. A gearbox operation and maintenance detection device, characterized in that: include: A communication module is used to obtain sensor data of the gearbox during the current period; the sensor data includes vibration signals, infrared data, speed, pressure and load; A processing module, configured to extract and convert features based on the sensor data to obtain operating condition data for the current period; Based on the operating condition data and the preset digital twin model, operation and maintenance detection analysis is performed to determine the performance data of the gearbox in the current period; the performance data includes stress data and fault detection results of each node in the gearbox; The fault detection result includes the fault type, fault component and fault location; Generate multiple feasible maintenance plans based on the performance data of the gearbox during the current period; generating and displaying a visual interface of the gearbox based on the performance data, the multiple feasible maintenance solutions, and the digital twin model; The processing module is specifically configured to perform wavelet transform processing on the vibration signal of the current period to obtain a two-dimensional time-frequency image; the two-dimensional time-frequency image is configured to reflect the time domain information and frequency domain information of the vibration signal; and calculate statistical information of each sensor data based on the speed, pressure, and load of the current period; the statistical information includes the mean, variance, median, maximum, and minimum values; Based on the sensor data, the statistical information of the sensor data, and the two-dimensional time-frequency image, feature fusion is performed to obtain the working condition feature; Based on the infrared data of the current period, finite element analysis is performed to determine the temperature distribution data of the gearbox during the current period; Determine the temperature variation characteristics of the current period based on the temperature distribution data of the gearbox during the current period; Based on the operating condition characteristics and the temperature change characteristics, the operating condition data of the current time period is determined.

Images