Industrial digital management method and system based on model construction

Abstract

The invention relates to the technical field of industrial equipment management, in particular to an industrial digital management method and system based on model construction. The method comprises the following steps: acquiring an industrial equipment operation log; performing motor thermal overload analysis according to the industrial equipment operation log to obtain motor thermal overload data; performing thermal isolation design based on the motor thermal overload data to obtain thermal isolation data; performing ventilation path blockage analysis according to the motor thermal overload data to obtain ventilation path blockage data; performing winding insulation aging detection based on the ventilation path blockage data to obtain winding insulation aging data; based on the winding insulation aging data, carrying out insulation paint film shedding detection to obtain insulation paint film shedding data; and performing protective coating upgrading according to the insulating paint film shedding data to obtain protective coating upgrading data. Based on the industrial equipment management technology, the intelligent rate of industrial equipment protection state recognition and operation and maintenance decision making is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment management, and in particular to an industrial digital management method and system based on model building. Background Art

[0002] Traditional industrial digital management employs a unified, integrated processing mechanism for multi-source, heterogeneous data from industrial equipment, often relying on a single type of sensor or log data for state analysis. This results in low accuracy in identifying complex equipment operating states. It lacks causal reasoning-driven parameter correlation modeling, making it impossible to organically link multi-dimensional influencing factors such as thermal overload, ventilation blockage, and insulation aging across both temporal and spatial dimensions. This limits the comprehensive tracing and prediction of equipment aging paths and fault evolution chains. In thermal isolation design and protective coating upgrades, static models or expert rule-of-thumbnail models often are used, lacking the ability to adaptively adjust to the actual operating environment and material physical properties. This results in significant deviations between design results and actual operating conditions. In processes such as ventilation blockage detection, insulation paint crack identification, and adhesion degradation analysis, manual intervention or reliance on static image analysis are often employed, lacking high-frequency sampling and dynamic simulation mechanisms, resulting in delayed detection responses and limited identification accuracy. In the coating aging simulation and digital management of protective capabilities, a numerical simulation platform based on the linkage of coating material parameters, motor power characteristics, and environmental variables is lacking, making it impossible to dynamically reflect coating performance changes, making it difficult to implement graded early warnings for protective capabilities and precise operational and maintenance decisions. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide an industrial digital management method and system based on model building to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a model-based industrial digital management method includes the following steps: Step S1: Obtaining an industrial equipment operation log; performing a motor thermal overload analysis based on the industrial equipment operation log to obtain motor thermal overload data; performing a thermal isolation design based on the motor thermal overload data to obtain thermal isolation data; Step S2: performing ventilation path blockage analysis based on the motor thermal overload data to obtain ventilation path blockage data; performing winding insulation aging detection based on the ventilation path blockage data to obtain winding insulation aging data; performing insulation paint film shedding detection based on the winding insulation aging data to obtain insulation paint film shedding data; Step S3: upgrading the protective coating according to the insulating paint film shedding data to obtain protective coating upgrade data; constructing a motor coating thermal insulation model according to the protective coating upgrade data and the thermal insulation data; performing a coating aging simulation according to the motor coating thermal insulation model to obtain coating aging data; Step S4: Perform coating delamination detection based on the coating aging data to obtain coating delamination data; perform coating adhesion degradation analysis based on the coating delamination data to obtain coating adhesion degradation data; perform digital management of the protection ability based on the coating adhesion degradation data to obtain digital management data of the protection ability.

[0005] The present invention realizes technological breakthroughs that are difficult to achieve in traditional technologies in multiple key links by constructing a full-link industrial digital processing process covering "operation log acquisition - status diagnosis - material analysis - structural modeling - dynamic simulation - hierarchical management". By fusing data from different dimensions such as motor thermal overload, ventilation path blockage, insulation paint film peeling, coating delamination, and adhesion degradation, the problem of low state recognition accuracy caused by single data in the prior art is solved; a causal correlation relationship is established between the equipment operation state and the material degradation behavior, and a time-continuous aging evolution chain is constructed, significantly improving the tracking and prediction ability of potential fault paths of the equipment; a thermal isolation design method based on thermal load and material thermal conductivity parameters is introduced to replace the static rule base, improving the adaptability of the thermal management module to the actual operating conditions; through high-frequency detection means such as dynamic simulation of ventilation resistance and infrared thermal imaging, dynamic identification of winding insulation aging and paint film peeling is realized, effectively improving the response speed and accuracy of detection; a dual-factor coupling method of thermal isolation data and coating material parameters is introduced during the upgrade of the protective coating, significantly enhancing the simulation accuracy of material behavior; coating aging behavior simulation is carried out based on a three-dimensional numerical thermal simulation platform, breaking the limitation of traditional reliance on manual experience to estimate the aging life; a multi-modal data fusion discrimination strategy is introduced in the coating delamination detection link to improve the delamination recognition accuracy and eliminate interference responses; a regional distribution differential evaluation method is adopted in the adhesion degradation analysis to refine the local protection performance differences; finally, a hierarchical index system is constructed in the digital management of the protection ability, and risk level division is realized based on core data such as adhesion, safety threshold, and thermal field distribution parameters, providing reliable data support for intelligent decision-making, thereby realizing intelligent evaluation and closed-loop control of the protection state of industrial equipment.

[0006] Preferably, this specification also provides an industrial digital management system based on model construction for executing the industrial digital management method based on model construction as described above. The industrial digital management system based on model construction includes: A thermal isolation design module for obtaining the operation log of industrial equipment; performing motor thermal overload analysis based on the operation log of industrial equipment to obtain motor thermal overload data; performing thermal isolation design based on the motor thermal overload data to obtain thermal isolation data; The insulation aging detection module is used to analyze the blockage of the ventilation path based on the motor thermal overload data to obtain ventilation path blockage data; perform winding insulation aging detection based on the ventilation path blockage data to obtain winding insulation aging data; perform insulation paint film peeling detection based on the winding insulation aging data to obtain insulation paint film peeling data; The motor coating heat insulation model construction module is used to upgrade the protective coating according to the insulation paint film peeling data to obtain protective coating upgrade data; construct a motor coating heat insulation model according to the protective coating upgrade data and the heat insulation data; perform coating aging simulation according to the motor coating heat insulation model to obtain coating aging data; The digital management module is used to detect coating hollowing according to the coating aging data to obtain coating hollowing data; perform coating adhesion deterioration analysis according to the coating hollowing data to obtain coating adhesion deterioration data; perform digital management of the protection ability according to the coating adhesion deterioration data to obtain digital management data of the protection ability.

[0007] The industrial digital management system based on model construction of the present invention can implement any industrial digital management method based on model construction of the present invention, and is used as a medium for coordinating the operations and signal transmissions between various modules to complete the industrial digital management method based on model construction. The internal modules of the system cooperate with each other, improving the intelligentization rate of the identification of the protection status of industrial equipment and the operation and maintenance decision-making. Description of the Drawings

[0008] By reading the detailed description of the non-restrictive embodiments with reference to the following drawings, other features, purposes, and advantages of the present invention will become more obvious: Figure 1 It is a schematic flow chart of the steps of an industrial digital management method based on model construction of the present invention; Figure 2 It is a detailed schematic flow chart of step S1 in the present invention; Figure 3 It is a detailed schematic flow chart of step S16 in the present invention; The realization, functional features, and advantages of the purpose of the present invention will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0009] The technical method of the present invention patent will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0010] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0011] It should be understood that although terms such as "first" and "second" may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0012] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides an industrial digital management method based on model construction, and the method includes the following steps: Step S1: Obtain the operation logs of industrial equipment; perform motor thermal overload analysis based on the operation logs of industrial equipment to obtain motor thermal overload data; perform thermal isolation design based on the motor thermal overload data to obtain thermal isolation data; In this embodiment, the operation log data of industrial equipment is collected by using an industrially deployed control system. The log content includes motor running current (unit: A), voltage (unit: V), winding temperature (unit: °C), running duration (unit: s), and load rate (percentage value). The OPC UA protocol is used for real-time data collection, and the data sampling frequency is set to 1 Hz. By setting the thermal overload judgment criterion, when the motor winding temperature continuously exceeds the set threshold of 135 °C and the duration exceeds 600 seconds, and at the same time the current exceeds 110% of the rated current (based on the rated current on the motor nameplate), it is recorded as a thermal overload event. All thermal overload events are numbered, classified, and archived, and the frequency and duration of thermal overload events of each motor per week are statistically analyzed.

[0013] When performing thermal isolation design based on thermal overload data, the thermal field finite element analysis tool ANSYS Icepak is used to establish a three-dimensional thermal simulation model in the motor housing structure. The heat source position (set in the stator winding area) is input, the ambient temperature is set to 40 °C, the air-cooled convective heat transfer coefficient is set to 18 W / m²·K, the thermal isolation material is set to a ceramic fiber layer, the thickness is set to 2 mm, and the thermal conductivity is 0.04 W / (m·K). By comparing the surface temperature rise differences with and without the thermal isolation layer through thermal simulation, thermal isolation data is formed, including the heat flux density map, the temperature gradient map, and the position of the highest temperature node.

[0014] Step S2: Perform a ventilation path blockage analysis based on the motor thermal overload data to obtain ventilation path blockage data; perform a winding insulation aging detection based on the ventilation path blockage data to obtain winding insulation aging data; perform an insulation paint film peeling detection based on the winding insulation aging data to obtain insulation paint film peeling data; In this embodiment, based on the thermal overload data obtained in step S1, the air duct pressure difference value (unit: Pa) during motor operation is extracted, which is collected by pressure difference sensors installed at the air inlet and outlet, and the sampling frequency is set to 0.5 Hz. The ventilation path blockage threshold is set such that when the pressure difference continuously is less than 30 Pa and is accompanied by a temperature rise higher than 120 °C, it is recorded as one blockage event. All blockage events are synchronously recorded with their corresponding timestamps. The blockage event data is input into the thermal aging analysis module of the stator winding. Using the IEC 60216 standard, the temperature data and the operation time data are input to calculate the thermal aging index TI (Temperature Index). When TI is lower than 105, it is considered that the insulation starts to age. The insulation resistance of the motor winding insulation layer is detected. The insulation resistance between phases is measured using a megohmmeter, a DC 1000 V voltage is applied, and the resistance value is read. If the resistance value is lower than 2 MΩ, it is determined as a severely aged insulation area. Continuing based on the aged insulation area, an infrared thermal imaging device (resolution 320x240, temperature measurement range: -20 °C to 250 °C) is used to scan the insulation surface to identify abnormal surface temperature difference areas. For the patch areas with a temperature difference greater than 8 °C, an image recognition algorithm of a high-definition industrial camera (5 million pixels) is further used. The Canny edge detection and gray threshold processing are used to identify the peeling position of the paint film, and the area and position coordinate data are recorded. The insulation paint film peeling data is stored in the form of two-dimensional image annotation, and the image coordinate system corresponds one-to-one with the motor winding position.

[0015] Step S3: Perform a protective coating upgrade based on the insulation paint film peeling data to obtain protective coating upgrade data; construct a motor coating heat insulation model based on the protective coating upgrade data and the thermal isolation data; perform coating aging simulation based on the motor coating heat insulation model to obtain coating aging data; In this embodiment, based on the paint film peeling data identified in step S2, a CAD three-dimensional modeling tool is called to perform surface reconstruction on the exposed parts of the motor. According to the protective coating layer thickness standard defined in the industrial standard JB / T 10918, the thickness of the first layer of primer is set to 25 μm, the thickness of the second layer of insulating paint is 40 μm, and the thickness of the third layer of anti-corrosion topcoat is 30 μm. The total coating thickness is 95 μm. The polyesterimide-based insulating paint is selected for the protective coating upgrade plan, and the thermal decomposition temperature is set to 220°C. According to the upgraded coating parameters and combined with the thermal insulation data obtained in step S1, a heat flux model of the coating-thermal insulation combined structure is constructed. The COMSOL Multiphysics thermal module is used for modeling, and the coating thermal conductivity (0.12 W / m·K), surface emissivity (0.92), and ambient wind speed (0.5 m / s) are input. The boundary condition is natural convection. The model solves the heat conduction equation to calculate the temperature field distribution at different positions under long-term operation, and the simulation time period is set to 3600 seconds. Based on the above thermal model, a coating aging life simulation module is constructed using the MATLAB programming language. The input variables include the operating temperature, operating cycle, UV irradiation intensity (set to 200 MJ / m² per year in total), and humidity environment (80% RH). The aging process simulation is carried out according to the Arrhenius aging acceleration equation, and the activation energy parameter is set to 90 kJ / mol. The aging rate constant k under different environments is calculated, and then the coating aging data is obtained, including the expected aging years, the coating peeling probability curve, and the distribution map.

[0016] Step S4: Perform coating hollowing detection based on the coating aging data to obtain coating hollowing data; perform coating adhesion degradation analysis based on the coating hollowing data to obtain coating adhesion degradation data; perform digital management of the protection ability based on the coating adhesion degradation data to obtain digital management data of the protection ability.

[0017] In this embodiment, based on the coating aging data obtained in step S3, a handheld laser vibration detector (frequency range 20Hz to 10kHz, measurement accuracy ±0.5Hz) is used to perform a tapping response test on the surface of the area predicted to be severely aged. The response frequency and attenuation rate are recorded, and the actual response is compared with the ideal solid-state coating frequency response. If the peak frequency drops by more than 30%, it is marked as a coating hollowing area. The hollowing detection results are coordinate-marked, and based on the distribution of the hollowing area, an adhesion detection device (pull-off adhesion tester, standard ASTM D4541) is further used to perform a fixed-point adhesion test on the same area. During the test, a test block is glued to the surface to be tested, and a hydraulic system is used to apply force, and the maximum peeling force is recorded. If it is less than 1.5MPa, it is considered to be an adhesion deterioration area. The test results are summarized to form adhesion degradation data, including position, pull-off strength value and test time. Based on the adhesion degradation data, a coating protection capability dataset is constructed. A database management module written in Python standardized the aging age, hollowing frequency, and adhesion indicators for different regions, using the Z-score method for data normalization. The normalized results were entered into the digital protection capability management platform and stored in a MySQL database. Fields included coating location number, adhesion level (level 1 to level 5), estimated peeling time (months), hollowing frequency, and recommended maintenance intervals, forming a complete digital protection capability management data structure.

[0018] Preferably, step S1 is specifically as follows: Step S11: Obtaining industrial equipment operation logs; In this embodiment, the operation log of the industrial motor equipment is exported from the embedded industrial control unit. The log record sources include the industrial site SCADA system and the PLC controller, and the sampling frequency is set to 1Hz. The operation log contains a timestamp, equipment number, operation status identification, real-time current, voltage, speed, operation time, and fault identification code. Use a structured data format (such as CSV) to import it into the log processing platform, for example, use Apache Kafka for streaming data access, and Apache Flink for parsing and filtering, and select the operation logs corresponding to all motor numbers. The filtering rule is to eliminate data with an operation status identification of "standby" or "fault shutdown", and only retain the data corresponding to the "running" status identification. The output result is a pure motor operation log data set, which serves as the basis for subsequent data calculation and parameter extraction.

[0019] Step S12: Recording current operating parameters based on the industrial equipment operation log; recording voltage operating parameters based on the industrial equipment operation log; and calculating motor power based on the current operating parameters and the voltage operating parameters; In this embodiment, by using the operation log data, a time series parsing tool (such as the pandas library in Python) is called to extract fields from the current operation parameters and voltage operation parameters. The current fields are named "Ia", "Ib", "Ic", and the voltage fields are named "Ua", "Ub", "Uc". The root mean square (RMS) values are calculated for the three-phase current and voltage respectively. The formula is: , . Calculate the motor power P using the active power calculation formula: , where the power factor is preset to 0.85 according to the motor nameplate parameters. All calculations are performed on a single data item through a data processing script, and the real-time power value is output once per second, with the unit of kilowatt (kW), forming power time series data.

[0020] Step S13: Estimate the winding temperature rise based on the motor power to obtain the motor winding temperature data; In this embodiment, using the power time series data, the winding temperature rise is estimated according to the principle of energy conservation of the motor thermal model. The formula for calculation is: , where P is the real-time power (kW), η is the motor heat conversion coefficient, set to 0.92, t is the unit time period (seconds), m is the motor winding mass, set to 7.5 kg, and c is the specific heat capacity of copper, a fixed value of 0.385 kJ / kg·K. The calculated output is the motor winding temperature rise value ΔT per second. ΔT is accumulated to the initial winding temperature (set to the ambient temperature of 𝑇_0 = 25 °C) to form a motor winding temperature data sequence. To prevent error accumulation, a temperature rise balance process is performed every 60 seconds, and an exponential moving average method is used to correct abnormal peaks.

[0021] Step S14: Perform a high-temperature determination on the motor winding temperature data according to the preset motor winding temperature threshold to obtain the motor winding high-temperature data; calculate the high-temperature duration based on the motor winding high-temperature data to obtain the high-temperature duration data; In this embodiment, the high-temperature determination threshold for the motor winding temperature is set to 125 °C, which is based on the maximum operating temperature standard supported by the motor winding insulation class F. The motor winding temperature data in S13 is judged second by second, and the time points with a temperature greater than or equal to 125 °C are marked as high-temperature states. Record the start and end times of the high-temperature state, and calculate the high-temperature duration, with the unit of seconds. For example, when the continuous high-temperature state occurs at the time points from 10:01:00 to 10:06:20, the high-temperature duration is 320 seconds. All the high-temperature state durations are continuously recorded to generate a high-temperature duration data list in the format: [start time, end time, duration]. And the temperature data in all high-temperature states are saved separately to form a motor winding high-temperature data set.

[0022] Step S15: Statistically analyze the high-temperature frequency based on the high-temperature data of the motor windings to obtain the data of high-frequency high-temperature periods; perform thermal overload identification based on the data of high-frequency high-temperature periods and the high-temperature duration data to obtain the motor thermal overload data. In this embodiment, in the high-temperature data set of the motor windings output in S14, the occurrence frequency of high-temperature events within each 24-hour time period is statistically analyzed. The high-temperature frequency identification threshold is set to 6 times / 24 hours, that is, if the high-temperature events occur more than 6 times within any consecutive 24 hours, it is marked as a high-frequency high-temperature period. Combining the high-temperature duration of each time in S14, calculate the total high-temperature duration within each high-frequency high-temperature period. The thermal overload identification threshold is set to that the single-segment continuous high temperature exceeds 180 seconds and this high-temperature segment is within the high-frequency high-temperature period, that is, it is determined as a thermal overload event. Mark each time period that meets this condition, and record the corresponding start and end times, high-temperature values, duration, etc., and output the motor thermal overload data table. The table structure includes: [start time, end time, maximum temperature, high-temperature duration, overload flag].

[0023] Step S16: Perform thermal isolation design based on the motor thermal overload data to obtain the thermal isolation data.

[0024] In this embodiment, based on the thermal overload data, the motor operation structure drawing is used for thermal isolation design. For the internal heat transfer path of the motor, evaluate the heat transfer path and material thermal conductivity of the corresponding part of the overload point. The thermal isolation target temperature is set to be within 95°C, and a ceramic insulation sheet with a thermal resistivity of not less than 0.4 m²·K / W is selected as the main thermal isolation material. According to the spatial structure of the overload point, use a 3D modeling tool (such as SolidWorks) to fit the dimensions of the installation area, and design a thermal isolation layer structure with a thickness of 10 mm and an area of 150×100 mm to cover the heat transfer surface between the motor winding housing and the stator. Conduct assembly simulation on the thermal isolation structure to verify the installation feasibility, and output the CAD layout drawing and material selection list to form the thermal isolation data, recording including material number, size, thickness, covering part, installation method, etc.

[0025] Preferably, step S16 is specifically: Step S161: Identify the thermal radiation path based on the motor thermal overload data to obtain the thermal radiation path data; In this embodiment, the time periods and heat accumulation regions corresponding to each overload event are extracted from the motor thermal overload data obtained in step S15. Combining the motor structure drawings and infrared thermal imaging detection images, thermal radiation path recognition is performed. An infrared thermal imager with a fixed wavelength band of 8μm to 14μm is used to perform long-term thermal imaging on the motor. The shooting frequency is set to once every 60 seconds, and continuous shooting is carried out for more than 8 hours. After the image is calibrated by pixel gray level, the continuous diffusion direction of the highest temperature area is extracted through the image temperature distribution histogram. The boundary of the high temperature area is recognized using the contour detection function findContours in OpenCV, and the thermal radiation path is constructed based on the shortest connection path between the boundary expansion direction and the heat source center. Each path records the starting point coordinates (heat source center), the ending point coordinates (high temperature point on the outer shell surface), and the path length (in mm), and is accompanied by temperature gradient information (in ℃ / mm). Finally, a thermal radiation path data table is formed, including fields: [heat source number, path number, starting point coordinates, ending point coordinates, path length, temperature gradient, direction angle].

[0026] Step S162: Determine the heat source range according to the thermal radiation path data to obtain heat source range data; In this embodiment, based on the thermal radiation path data, the area where all the starting points of the paths gather is analyzed, and the average temperature within a radius of 20 mm around each starting point is calculated. If there are 3 or more starting points of thermal radiation paths overlapping in a certain area and its average temperature is higher than the set heat source determination threshold of 150℃, then this area is marked as the heat source area. The determination threshold is set based on the motor insulation level, and temperatures higher than this will seriously affect the insulation performance. The heat density map of all starting point coordinate points is drawn through a two-dimensional plane thermal map, and Gaussian filtering is used for regional boundary smoothing processing to extract the closed hot area boundary to form the heat source range. Each heat source range is represented in the form of a polygon area, recording the heat source number, the size of the circumscribed rectangle, the center coordinates, the area size (in mm²), the highest temperature, and the average temperature. The heat source range data table is output for subsequent use in delimiting the heat insulation area.

[0027] Step S163: Determine the thermal insulation boundary based on the heat source range data to obtain thermal insulation boundary data; In this embodiment, using the heat source range data, a peripheral thermal isolation boundary is constructed for each heat source region. The boundary construction method adopts the isothermal expansion principle: starting from the center of the heat source, setting the isolation target temperature to 95°C, and inversely calculating the isolation radius through the thermal conductivity of copper or aluminum. For example, under the conditions of known copper thermal conductivity of 385 W / (m·K), initial heat source temperature of 155°C, and ambient temperature of 35°C, the distance is inversely solved through Fourier's law of heat conduction to make the temperature at the end of the heat transfer path ≤ 95°C, and the thermal isolation radius can be obtained as approximately 38 mm. On this basis, the heat isolation boundary is constructed by uniformly expanding 38 mm outward from the heat source boundary and performing polygon fitting. The thermal isolation boundary data structure is output, including fields: [heat source number, boundary coordinate point sequence, maximum boundary length, minimum boundary width, enclosed area], and is exported to a CAD format file for structural design use.

[0028] Step S164: Determine the structure size of the heat shield according to the thermal isolation boundary data; select the material type according to the structure size of the heat shield to obtain the material type data; perform sheet cutting according to the material type data to obtain the heat shield sheet data; perform air duct layout based on the heat shield sheet data to obtain the air duct structure data; reinforce the heat shield according to the air duct structure data to obtain the heat shield data; In this embodiment, according to the thermal isolation boundary data, the corresponding spatial structure size information within the boundary is extracted from the three-dimensional mechanical structure diagram. Using a CAD drawing tool (such as AutoCAD or SolidWorks), the boundary contour is projected onto the surface of the actual structure model, and its corresponding planar expansion size and three-dimensional curved surface adaptation size are measured to obtain the heat shield structure size data, with parameters including: expanded length and width, curved surface radius, installation screw hole spacing, fixed edge thickness, etc. According to the industrial heat insulation specification, setting the minimum plate thickness to 5 mm and the target temperature control temperature within 95°C, a fiberglass composite board with a thermal conductivity not greater than 0.15 W / (m·K) and a density not greater than 50 kg / m³ is selected from the standard industrial material database. Input the above size and material data into the control system of the sheet cutting equipment, such as using a laser cutting machine (laser power 2.5 kW, positioning accuracy ±0.1 mm), and complete the cutting operation after setting the cutting trajectory and feed speed to obtain the heat shield sheet data. According to the sheet data and the motor structure, the air flow path of the air duct layout is optimized through a CFD (Computational Fluid Dynamics) simulation tool (such as ANSYS Fluent), setting the inlet diameter to 50 mm and the outlet diameter to 80 mm to ensure that the flow rate is not less than 3.2 m / s, and finally output the air duct structure data table. Finally, assemble the sheets and set 12 fixed reinforcing ribs at the main structure boundaries, fix them with M6 stainless steel bolts, and the fixed point spacing is 60 mm. After reinforcement, the complete heat shield data is output.

[0029] Step S165: Evaluate the thermal isolation effect based on the heat shield data to obtain thermal isolation data.

[0030] In this embodiment, the installed heat shield is used to evaluate the thermal isolation effect at the industrial site. Temperature sensors (model: PT100, error ±0.3°C) are respectively arranged inside and outside the heat shield, and the sampling interval is set to 30 seconds. The inner surface temperature, outer surface temperature and external environment temperature of the heat shield are recorded during the 8-hour full-load operation of the motor. The temperature difference inside and outside the heat shield is statistically analyzed to determine whether the thermal isolation effect meets the standard. According to the industrial thermal safety specification, the thermal isolation effect standard is set as: the outer surface temperature of the heat shield shall not be higher than the ambient temperature + 20°C. By performing minimum, maximum and mean analysis on the data collected at 30s intervals on the time axis, the time periods that do not meet the temperature difference standard are marked. The final output of the evaluation is thermal isolation data, including: test time period, temperature difference distribution map, worst temperature zone number, location of thermal insulation failure risk zone, average temperature difference value. All data are uniformly summarized into a thermal performance evaluation report and archived.

[0031] Preferably, the ventilation path blockage analysis in step S2 is specifically as follows: Statistically calculate the motor heat according to the motor thermal overload data to obtain motor heat data; identify the heat source aggregation area according to the motor heat data; calculate the temperature difference between adjacent measurement points based on the heat source aggregation area to obtain the temperature difference data of the measurement points; In this embodiment, based on the motor thermal overload data formed in the previous steps, the average current (unit: A), voltage (unit: V) and overload duration (unit: s) of each overload cycle of the motor are extracted. The formula Q = P×t = U×I×t (where Q is the heat, unit: J) is used to calculate the heat input value corresponding to each overload stage. In a three-phase asynchronous motor, the motor power should be calculated according to where the power factor Set it to 0.85. After accumulating the heat, obtain the total heat value generated by each overload event, and form a motor heat data table with the event timestamp and heat value (J) as the recorded content. The fields include: [time, phase voltage U, phase current I, power P, overload time t, heat Q]. The data is exported in CSV format for the next heat source aggregation analysis. Through continuous 24-hour monitoring of the infrared thermal imaging camera (wavelength range 8 - 14μm, thermal sensitivity ≤ 0.05°C) installed on the surface of the motor housing, combined with the heat concentration period recorded in the motor heat data, extract the areas in the image where the temperature is higher than 140°C. Adopt the thermal imaging image gray inversion technology, set the area with a gray value above 220 as the high-temperature core, use the K-means clustering method for spatial clustering analysis, set the number of clusters to 5, and extract the high-frequency heat aggregation points. Each heat source aggregation area needs to meet the conditions that the area ≥ 30 cm², and the high-temperature value in the same coordinate area appears at least 7 times in 10 monitors, and use the time overlap degree ≥ 70% as the heat source determination condition. Finally, form the heat source aggregation area data in the format of: [heat zone number, center coordinates (x, y, z), maximum temperature, average temperature, area], which is used for subsequent temperature difference vector analysis. Symmetrically arrange multi-point temperature sensors around the heat source aggregation area, use K-type thermocouples with an accuracy of ±0.3°C, set the distance between measurement points to 10 cm, and form a dot matrix distribution. Collect the surface temperature data of 16 measurement points around each heat source, sample once per second, continuously collect for 300 seconds, and take the average value as the steady-state temperature value. Calculate the temperature difference ΔT = T_center - T_surrounding between the heat source center point and each surrounding measurement point, and count the coordinates, temperature and their corresponding temperature difference values of each measurement point to form a measurement point temperature difference data set. The structure of this data set is: [heat source number, measurement point number, measurement point coordinates, measurement point temperature, ΔT]. All data is archived through a Matlab script and a graphical heat distribution map is output.

[0032] Calculate the gradient vector direction based on the measurement point temperature difference data to obtain the temperature difference gradient direction data; obtain the motor heat dissipation path data; perform ventilation path mapping based on the motor heat dissipation path data and the temperature difference gradient direction data to obtain the ventilation path data; In this embodiment, a gradient calculation method in a two-dimensional coordinate system is adopted to solve the vector direction of the measurement point temperature difference data. Using the temperature difference distribution matrix T(x, y), calculate the horizontal and vertical temperature difference gradients respectively , . Adopt the central difference method for numerical gradient solution, and the gradient direction Configure a vector arrow for each measurement point, pointing in the direction of temperature decrease (i.e., the direction of heat flow). All data is uniformly generated into a vector field diagram, and the output data table includes: [measurement point number, coordinates (x, y), Gx, Gy, gradient direction θ (unit: °)]. This direction information is used for subsequent matching of the ventilation path and the heat flow vector. Perform a three-dimensional structure scan on the overall structure of the motor, and use a laser scanning device (accuracy ≤ 0.5 mm) to extract the three-dimensional structure model of its housing and fan ventilation system. By identifying the air inlet, air outlet, built-in air duct, and cooling ventilation holes on the housing, record the geometric parameters of each air flow path, including the starting point coordinates, ending point coordinates, cross-sectional diameter, ventilation path length, etc. Set a wind speed sensor (range 0 - 15 m / s, accuracy ±0.1 m / s) to monitor the air speed in the air duct and establish a real-time ventilation speed distribution diagram. All data is summarized to form a motor heat dissipation path data table, with the structure: [path number, starting point - ending point coordinates, path length, cross-sectional area, air flow speed]. The data output is used for subsequent air duct mapping and blockage analysis. By superimposing the temperature difference gradient vector field obtained in step 4 and the three-dimensional structure of the heat dissipation path obtained in step 5, perform spatial alignment and matching. Set the matching angle threshold to within 15°. If the angle between the temperature difference vector direction and the ventilation path direction is less than or equal to 15°, then it is considered that this path has an effective ventilation function. Use a Python script combined with a 3D modeling tool (such as ANSYS SpaceClaim) to compare each vector with the path direction, and mark the effective ventilation paths. Output the ventilation path data, including fields: [path number, number of matching vectors, average angle, ventilation effectiveness determination], and attach a diagram to show the overlapping area of the heat flow direction and the air flow direction.

[0033] Based on the ventilation path data, perform filter clogging detection to obtain filter clogging data; In this embodiment, a particulate matter collector is set at the air inlet of the air duct, and a PM filter structure and a differential pressure sensor (range 0 - 1000 Pa, accuracy ±1 Pa) are used to measure the differential pressure of the inlet and outlet air in real time. Set the initial reference value of the differential pressure to 80 Pa. If the actual differential pressure exceeds 150% of the initial value (i.e., 120 Pa) continuously for more than 5 minutes, it is determined that the filter is clogged. Record the detected clogging area number, differential pressure, sampling time, inlet air speed, etc. to form a filter clogging data table, with fields including: [filter number, inlet air flow rate, differential pressure value, clogging determination time, clogging degree level (divided into three levels: mild 80 - 120 Pa, moderate 120 - 180 Pa, severe > 180 Pa)], and generate an alarm record corresponding to each clogging event number.

[0034] Collect clogging sample according to the filter clogging data, and perform particle size analysis on the clogging sample to obtain clogging particle size data; perform surface roughness detection according to the clogging particle size data to obtain clogging roughness data; In this embodiment, a high-efficiency fine dust classifier (such as a laser particle size analyzer with a measurement range of 0.1 μm to 500 μm) is used to detect the particle diameter of the residual blockages on the filter screen. When sampling, sampling points are divided according to the filter screen area. 0.5 g of blocked dust is collected from each area, and the average particle size is measured three times. Particle size statistical parameters such as the peak value of the particle size distribution, D10, D50, and D90 are recorded. A particle size data table is output, including: [sample number, D50 value, maximum particle size, minimum particle size, distribution skewness coefficient], and the particles are analyzed to determine whether they are the sources of blockage such as fine particle suspensions, grease adhesives, or metal oxide chips. The blocked sample is placed under a white light interference surface profiler, the scanning area is set to 100 μm × 100 μm, and the scanning resolution is 0.5 μm to obtain a three-dimensional surface height map. According to the ISO4287 standard, roughness parameters such as the average roughness Ra, the maximum height Rz, and the number of peaks and valleys Rp are extracted. If the Ra value is greater than 4 μm, it is regarded as a high-adhesion surface particle. The structure of the roughness detection data table output is: [sample number, Ra, Rz, Rp, surface type (loose / smooth / sticky)], and the data is used for adhesion strength analysis.

[0035] Evaluate the adhesion strength of the ventilation duct based on the roughness data of the blockage; In this embodiment, combining the roughness parameters with the data of the adhesion tester (such as using the vertical pull-off method with the unit of N / cm²), the minimum pull-off force required for the particles to adhere to the metal surface of the ventilation duct is tested. The sample particles are artificially adhered to the metal specimen of the ventilation pipe (size 50 mm × 50 mm), and after drying, vertical loading is carried out until the particles fall off. If the adhesion force ≥ 2 N / cm², it is determined as a high-adhesion particle. The average adhesion strength of samples with different roughness grades is statistically analyzed, and a relationship table is established: [Ra range, average adhesion strength], which is used to infer whether the particles are likely to remain under the current wind speed and vibration intensity.

[0036] Based on the adhesion strength of the ventilation duct, analyze the blockage of the ventilation path to obtain the ventilation path blockage data.

[0037] In this embodiment, all high-adhesion strength particles are marked as high blockage risk sources, and combining the ventilation path wind speed data with the particle migration speed (calculated by the Stokes sedimentation formula), the deposition behavior of the particles in the ventilation duct is simulated. The critical settling velocity is set to 0.8 m / s. If the actual wind speed is lower than this value and the adhesion force is higher than 2.5 N / cm², then this path section is marked as a high blockage risk area. A ventilation path blockage data table is output, including fields: [path number, blockage risk level, adhesion force parameter, deposition simulation result, recommended cleaning period (unit: hour)].

[0038] Preferably, in step S2, the detection of the winding insulation aging is specifically: Based on the ventilation path blockage data, calculate the wind resistance to obtain the wind resistance data; In this embodiment, first, geometric parameter data of each ventilation pipe section in the motor ventilation system are obtained, including cross-sectional area, pipe length, number of elbows, bending angle, branch position, etc. At the same time, combined with the data of the position and degree of blockage area that have been collected, the effective ventilation area is calculated according to the proportion of the blocked volume to the cross-sectional area of the pipe, and the remaining ventilation channel width of the blocked section is accurately recorded. Then, combined with the real-time wind speed data (unit: m / s) in the channel and the air density value (the air density is 1.225 kg / m³ under standard conditions), the wind resistance values of each section are calculated according to the flow velocity and equivalent cross-sectional area of the ventilation section. The channel pressure loss calculation method in engineering thermodynamics is adopted to output the resistance value of each air duct section (unit: Pa), and compared with the normal wind resistance reference value to determine the wind resistance increment data, which is output as wind resistance data. The recording format includes the ventilation section number, blockage rate, wind speed, and pressure loss value.

[0039] Winding temperature rise analysis is carried out according to the wind resistance data to obtain winding temperature rise data; In this embodiment, after obtaining the wind resistance data, the temperature rise analysis of the motor winding in the area most severely affected by ventilation needs to be carried out. In the steps, first, the copper loss parameter of the winding is obtained, which can be obtained by multiplying the square of the current value by the winding resistance value. The winding resistance needs to be calculated according to the conductor length, cross-sectional area, and material resistivity; then, combined with the change of the heat transfer coefficient in the ventilation path, the heat generated by the winding per unit time and the heat dissipation capacity are calculated. The heat dissipation capacity is processed by the convective heat transfer formula, where the heat transfer coefficient h is estimated by the reduction ratio of the wind speed (when the wind speed is reduced by 30%, the heat transfer coefficient is reduced by about 25%). After comparing the heat generation amount with the heat dissipation capacity, the heat accumulation trend is obtained, and finally the winding temperature rise data (unit: °C) is calculated. This temperature rise data should be based on the standard operating winding temperature for temperature increment evaluation, and the thermal stress exposure time is calculated in combination with the operating duration.

[0040] Insulating material thermal stress detection is carried out according to the winding temperature rise data to obtain insulating material thermal stress data; In this embodiment, first, the material type of the insulating paint or insulating paper used in the winding is determined, and the elastic modulus (unit: GPa), thermal expansion coefficient (unit: 1 / K), glass transition temperature (Tg), and initial thermal decomposition temperature (Td) of the insulating material are extracted from the material database. The actual winding temperature is compared with the material Tg. If the temperature rise value exceeds the material Tg, it is judged to enter the plastic deformation zone; if the temperature rise value is close to Td, it is marked as the thermal decomposition risk zone. In this process, the maximum stress value (unit: MPa) generated inside the insulating layer due to thermal gradient and constrained deformation is calculated by the finite element thermal stress analysis method. This stress value is compared in proportion with the tensile strength of the material. If the thermal stress exceeds 50% of the yield strength, it is recorded as the high thermal stress state and output as the insulating material thermal stress data.

[0041] Calculating the material aging rate based on the thermal stress data of the insulating material; In this embodiment, the Arrhenius aging characteristic parameters of the insulating material are called, including the activation energy (unit: kJ / mol) and the frequency factor, and the temperature rise value is substituted into the aging rate formula to calculate the molecular degradation rate of the material per unit time. At the same time, considering the thermal stress action time and the thermal cycle frequency, the accelerated aging time of each time period is accumulated according to the equivalent aging life calculation rule, and finally the reduction ratio of the actual service life of the material under this thermal stress condition is obtained, and the material aging rate data is recorded in hours.

[0042] Conducting winding insulation aging assessment based on the material aging rate to obtain winding insulation aging data.

[0043] In this embodiment, the actual operating time and the cumulative aging time of the current winding are statistically analyzed, and hierarchical processing is carried out according to the winding life assessment rules in the IEC standard. For example, for the Class F insulation system in IEC60034, the maximum allowable operating temperature is 155 °C, and the insulation life at this temperature is 20,000 hours; if the measured temperature rises to 170 °C, the corresponding life is shortened to 10,000 hours, and so on. By comparing the actual aging time with the upper limit of the standard life, the life consumption ratio is calculated and the winding insulation aging grade is assigned. For example, it is defined that 0 - 30% is Grade I, 30% - 60% is Grade II, and above 60% is Grade III. Finally, the winding insulation aging data is composed of four items: winding number, cumulative aging time, remaining life percentage, and aging grade, providing a decision-making basis for subsequent maintenance.

[0044] Preferably, the detection of insulating paint film peeling in step S2 is specifically as follows: Extracting the insulating surface characteristics based on the winding insulation aging data to obtain insulating surface data; In this embodiment, according to the winding numbers marked as Grade II and above in the winding insulation aging data, the corresponding equipment is located and high-precision image acquisition operations are performed on the insulation layer. The image acquisition device needs to use an industrial imaging probe with a resolution of more than 600 dpi, and cooperate with an adjustable-intensity annular LED light source to ensure clear surface texture without reflection. The image processing system uses preprocessing techniques such as gray normalization, mean filtering, and edge enhancement to remove noise and background interference, and then extracts the insulating surface area through an image segmentation algorithm (such as the Otsu method based on the maximum inter-class variance) to obtain the image ROI coordinates and the corresponding gray texture data. During the extraction process, surface characteristic parameters need to be quantified, including the surface roughness factor (expressed as the gray change rate per unit area), the local brightness difference coefficient, the edge density, etc. All characteristics are indexed by the insulation number to form a structured insulating surface data table.

[0045] Conducting paint film crack detection based on the insulating surface data to obtain insulating paint film crack data; In this embodiment, crack image recognition processing is performed within the extracted insulating surface image region. This process uses an image recognition method that combines multi-scale edge detection and morphological algorithms. First, the potential crack boundary features are extracted by means of Sobel gradient enhancement, then the Canny edge detection with an adaptive threshold is used to accurately locate the continuous crack contour line, and the pixel skeleton structure of the crack path is restored through the morphological thinning algorithm. After the crack path is extracted, indicators such as the total crack length (unit: mm), maximum width (unit: μm), crack density (unit: cracks / mm²) need to be statistically analyzed, and the crack orientation analysis (extracting the main crack direction and the number of secondary crack branches) is carried out to construct complete insulating paint film crack data, including fields such as crack number, starting point coordinates, direction angle, length, and width.

[0046] Based on the crack propagation simulation of the insulating paint film crack data, crack propagation data is obtained; In this embodiment, the crack stress field is calculated by combining the mechanical parameters of the insulating material and the thermal stress history data. The crack propagation analysis adopts the calculation method of the stress intensity factor (SIF) at the crack tip. When calculating, the fracture toughness K_IC of the material (unit ) is introduced, the current crack length and the thermal stress distribution are mapped to the crack tip, and the SIF value at the crack tip is estimated by an analytical method. If the SIF exceeds the K_IC of the material, it is considered that the crack has a tendency to propagate, and the extension path and propagation rate of the crack are calculated in combination with the direction of the thermal stress change. Finally, information such as the predicted crack propagation length, predicted propagation direction angle, and predicted propagation rate (unit: mm / h) is output to form the crack propagation data.

[0047] Based on the crack propagation data, the adhesion force of the insulating paint film is evaluated to obtain the paint film adhesion force data; In this embodiment, the material of the adhesion surface (such as copper, aluminum, etc.) and the type of the paint film material are specified to obtain the corresponding reference value of the interfacial adhesion strength. The adhesion force evaluation adopts the method of pushing the cause of crack propagation. By analyzing information such as the stress distribution and crack morphology change (such as whether bifurcation occurs) during the crack tip propagation process, the interfacial fracture mode is analyzed. If it is inferred that the adhesion interface is separated, the energy required to be released per unit area of the interface is calculated, and it is compared with the critical energy standard value of this type of interface in the existing literature (unit: J / m²) to convert the actual adhesion strength estimate (unit: MPa), forming a paint film adhesion force data table, the content of which includes fields such as the measurement point number, the combination of interface materials, the ratio of the calculated adhesion force to the reference value, etc.

[0048] Based on the paint film adhesion force data, the detachment detection of the insulating paint film is carried out to obtain the insulating paint film detachment data.

[0049] In this embodiment, a lower limit threshold of the adhesion force is set, which is determined by the design standard of the insulation system. For example, if the designed adhesion strength of the insulation paint film is 8 MPa, then 70% of the critical adhesion force, which is 5.6 MPa, is set as the judgment basis. For all data points with adhesion force lower than this value, further compare whether the crack length exceeds 5 mm, whether the crack density is greater than 2 cracks / mm², and check whether its position is in the thermal concentration area. If any two of the three indicators are met, it is marked as a point with a risk of peeling, and the peeling detection result is output, including the detection number, crack characteristic indicators, adhesion force value, and judgment result, forming complete insulation paint film peeling data. This data can be used for subsequent evaluation of the structural protection level and insulation repair decision-making.

[0050] Preferably, step S3 is specifically as follows: Step S31: Calculate the peeling depth based on the insulation paint film peeling data to obtain peeling depth data; evaluate the damage degree of the insulation layer based on the peeling depth data to obtain insulation layer damage data; In this embodiment, based on the peeling area image data, a three-dimensional contour scanning device is used to perform micron-level high-precision topography measurement on the surface of the motor insulation. The contour scanning device uses white light interference method or laser confocal microscopy technology, and the scanning accuracy reaches within 0.1 μm. The scanning area needs to cover all the identified peeling number areas, and a relative height reference system is established with the non-peeling surrounding surface as the reference plane. Perform pixel-by-pixel subtraction operation on the scanned three-dimensional height matrix data, and statistically calculate the deepest point, average depth, and area-weighted depth of each peeling area, respectively forming the maximum peeling depth data, average peeling depth data, and comprehensive peeling volume data. All peeling depth data are stored in a structured database with the peeling number as the index. After completing the statistics of the peeling depth data, it is necessary to evaluate the damage degree of the insulation layer according to the insulation system structure level. The motor winding insulation layer generally includes three layers: primer, intermediate layer, and topcoat, with thicknesses of 10 μm, 30 μm, and 20 μm respectively. If the maximum peeling depth exceeds 60 μm, it is marked as full-layer penetration damage; if the peeling depth is between 30 - 60 μm, it is determined as middle layer and topcoat damage; if the peeling depth is less than 30 μm and above the topcoat, it is classified as mild surface layer damage. Combining the damage area and depth level, define the comprehensive damage level of each damage point as level I (mild), level II (moderate), or level III (severe), and construct an insulation layer damage data table, with fields including damage number, peeling depth, area, and level.

[0051] Step S32: Select a protective coating material based on the insulation layer damage data to obtain protective coating material data; In this embodiment, the data of industrial insulation repair materials registered in the enterprise technical standard library are called, including polyimide coating materials, modified silicone acrylic coating materials, two-component epoxy modified materials, etc. The materials are directly matched according to the damage level. For example, for the area with grade III damage, a two-component epoxy coating with a high temperature resistance of ≥180°C and a volume resistivity of ≥10^13 Ω·cm is selected; for the area with grade II damage, a polyimide material with a temperature resistance of ≥150°C and a flexibility of ≤1 mm is matched; for the area with grade I damage, a low-viscosity and fast-curing silicone acrylic emulsion coating material is matched. The physical property parameters of the selected materials, such as material number, thermal conductivity, electrical strength, dielectric constant, curing time, adhesion strength, etc., are imported to form a data table of the protective coating materials.

[0052] Step S33: Determine the coating thickness according to the data of the protective coating materials to obtain the coating thickness data; determine the topcoat coating method according to the data of the protective coating materials to obtain the topcoat coating method data; In this embodiment, the standard single-layer thickness is calculated based on the solid content in the data of the protective coating materials and the target coating layer thickness. Taking the polyimide material as an example, the target dry film thickness is 30 μm, and the solid content of the material is 60%, then the wet film thickness is 30 μm ÷ 60% ≈ 50 μm. The moving speed is set according to the spraying equipment parameters (such as paint output, spray width) to accurately control the coating thickness. If the brushing method is used, the number of brushing times and the time interval between each coating need to be controlled. If the material is of the two-component epoxy type, it needs to be pre-mixed in accordance with the specified ratio (for example, A:B = 4:1), left standing for 3 minutes to defoam, and then injected into the spray gun cavity. The spraying air pressure is controlled between 0.3 - 0.5 MPa. The coating process method (such as air spraying, high-pressure airless spraying, brushing) is recorded through the coating method data field, and combined with the coating thickness value, a complete topcoat coating method data is formed.

[0053] Step S34: Integrate the coating thickness data and the topcoat coating method data to obtain the protective coating upgrade data; In this embodiment, the coating thickness data and the topcoat coating method data are integrated into a unified data structure to form the protective coating upgrade data. This data includes fields such as coating material number, substrate treatment requirements (such as grinding grit P800), single-layer thickness value, total number of coating layers, coating method, curing conditions (such as temperature 80°C, time 2 hours), and the final surface roughness Ra value, etc. All parameters are used for the review and implementation record of the coating upgrade process.

[0054] Step S35: Construct a motor coating heat insulation model according to the protective coating upgrade data and the heat insulation data; In this embodiment, an insulation model of the motor coating is constructed based on the upgraded data of the protective coating and the existing thermal insulation data (including the heat shield structure data, thermal reflectivity, and thermal conductivity). In this model, the coating is defined as a multi-layer structure, with the bottom layer being the surface of the original winding, the middle layer being the insulation repair layer, and the upper layer being the surface protective coating; the heat shield data is projected onto the winding area through the heat flux density; taking the thermal conductivity, thermal diffusivity, layer thickness, etc. as input parameters, the finite volume method is used to calculate the steady-state heat transfer flux distribution between the layers; considering the air duct wind speed (2.5 m / s), ambient temperature (40 °C), and the temperature boundary of the outer surface of the coating (up to 120 °C), a steady-state heat balance solution is carried out; the heat flux density on the surface of the winding (unit: W / m²), the interface temperature distribution and other thermal field data are output for subsequent aging calculations.

[0055] Step S36: Perform coating aging simulation according to the insulation model of the motor coating to obtain coating aging data.

[0056] In this embodiment, the aging rate formula extracted from the measured data of the thermal aging of the insulation coating is adopted. The aging test period is set to 10,000 hours, and the thermal field parameters are loaded into the simulation system according to the surface temperature gradient calculated by the steady-state solution in step S35. The aging simulation process is iterated step by step with 500 hours as a unit step, updating the coating thickness change, the adhesion force decrease ratio, and the increase in thermal conductivity at each step. Finally, the aging rate (unit: μm / h), the adhesion force decrease rate (unit: %), and the change trend of thermal conductivity of each layer of coating material are output, forming complete coating aging data. All results are stored encoded according to the time series and structural stratification, providing data support for the coating maintenance and replacement cycle.

[0057] Preferably, step S36 is specifically: Step S361: Upload the insulation model of the motor coating to the thermal aging simulation platform; In this embodiment, when uploading the motor coating heat insulation model to the thermal aging simulation platform, a dedicated thermal aging simulation platform with a three-dimensional structure modeling input interface and a heat conduction simulation solver is required, such as a customized module platform based on the Ansys Workbench or COMSOL Multiphysics system. For the uploading operation, the motor coating heat insulation model needs to be exported as a supported standard geometric file format, such as STEP (.stp) or Parasolid (.x_t). The model should include clear distinctions of thermal properties between each structural layer, such as the inner winding area, insulation repair layer, protective surface layer, and external heat insulation cover structure. In the model uploading module, the "structural definition verification" function needs to be called to perform integrity checks on issues such as whether the thermal boundaries between structures are closed and whether material properties are missing, and the area discretization operation is completed with meshing parameters. The minimum side length of the mesh element should be controlled within 0.1 mm, and the maximum side length should not exceed 2 mm to ensure that the subsequent heat flux distribution accuracy meets the requirements of aging calculations.

[0058] Step S362: Set the environmental temperature range to 40°C - 120°C and the humidity range to 30% - 80%; In this embodiment, the environmental temperature range and humidity interval are set in the environmental parameter setting module of the thermal aging simulation platform. The environmental temperature range is set to 40°C to 120°C, and a stepped loading method with a step value of 10°C is adopted, with a total of 9 temperature levels. Each temperature level corresponds to an independent thermal aging simulation cycle, forming a grouped simulation scheme. The humidity range is set to 30% to 80%, and a fixed relative humidity level combination (30%, 50%, 65%, 80%) loading method is adopted, and a full permutation combination is carried out in combination with the temperature levels. Finally, a total of 36 groups of working condition combination parameter tables are generated. Each group of working conditions is organized by number, and the fields include temperature value, humidity value, simulation number, and working condition label. The system calls this table for sequential simulation loading.

[0059] Step S363: Set the motor operating power range to 50 kW - 150 kW and the working cycle to 8 hours - 24 hours; In this embodiment, the motor operating power range and working cycle are set. The operating power range is 50 kW to 150 kW, divided into 5 gears with a step of 25 kW: 50, 75, 100, 125, 150 kW; the working cycle is set to five gears of 8 hours, 12 hours, 16 hours, 20 hours, and 24 hours. The power and working cycle are cross-arranged to construct 25 kinds of motor operating load condition parameters. Each load condition needs to correspond to the definition of a heat source term. For example, in COMSOL, the heat source term is injected through the "Heat Source" node, with the unit of W / m³, and the calculation method is the total power value divided by the winding material volume. With a power of 100 kW and a winding volume of 0.01 m 3 , the injected heat source term is 1×107 W / m³. The simulation duration is set through the "Time Dependent Study" module for each operating cycle, with the unit being hours, and the thermal field evolution simulation is carried out according to the set cycle.

[0060] Step S364: Input the thermal conductivity of the coating material as 0.15 - 0.35 W / (m·K) and the thickness as 0.5 - 2.0 mm; In this embodiment, the thermal conductivity range is set to 0.15 - 0.35 W / (m·K), with a step of 0.05, totaling 5 values: 0.15, 0.20, 0.25, 0.30, 0.35 W / (m·K), which are input into the "Thermal Conductivity" field of the material library, and the unit remains W / (m·K). The coating thickness is used as a geometric parameter in the model structure. The thickness value range is set to 0.5 mm to 2.0 mm in the modeling module, and four structural versions of 0.5 mm, 1.0 mm, 1.5 mm, and 2.0 mm are generated with a step of 0.5 mm. The thickness variable is defined in the parametric simulation platform in the way of "Geometry Parameters" to achieve automatic batch simulation. All combined results arrange the thermal conductivity and thickness crosswise to generate 20 thermal parameter combinations, and each combination is executed as an independent simulation task.

[0061] Step S365: Run the thermal aging simulation program to obtain the coating aging data.

[0062] In this embodiment, the thermal aging simulation program is officially run. The platform calls all the combined input parameters, sequentially loads the working condition data (temperature, humidity), operating load data (power, cycle), and thermal parameter data (thermal conductivity, thickness), solves the thermal field distribution in the steady-state heat conduction module, and then loads the aging rate curve in the "Material Degradation" module. The time-temperature dependence relationship is controlled by the Arrhenius formula, and the iterative simulation cycle is set to update once every 100 hours, with a cumulative total duration of 10,000 hours. After each time step, the target indicators are extracted, including: the change in material thickness (μm), the residual percentage of adhesion force (%), the increase in thermal conductivity (%), the surface crack density (per mm²), etc. Finally, all simulation results are corresponding to the parameter combination table one by one with number identification and are stored in the "aging result data table" in the database. The fields include simulation number, working condition group number, time step sequence number, and thermal aging index value. Thus, the generation of the coating aging data is completed.

[0063] Preferably, step S4 is specifically as follows: Step S41: Conduct a heat conduction simulation based on the coating aging data to obtain the heat conduction data; In this embodiment, the execution of the heat conduction simulation requires the coating aging data as the input parameters, and a heat conduction simulation project is constructed using a platform with a finite element heat field solving function (such as COMSOL Multiphysics). During the simulation, the boundary conditions and material properties should be set. Among them, the thermal conductivity of the aged coating is input as the main variable, and this parameter should be derived from the result of the change in the thermal conductivity after aging in step S365. For example, it is reduced from the original thermal conductivity of 0.25 W / (m·K) to 0.18 W / (m·K). The heat source is set at the winding area, and the total heat power value is injected through the "Heat Source" module. For example, it is set to 100 kW, and the corresponding volume heat source intensity is 1×10 7 W / m³ (assuming the winding volume is 0.01 m³). The convective heat transfer condition is applied to the outer boundary, the ambient temperature is set to 80 °C, and the heat transfer coefficient is 25 W / (m²·K). The propagation path of the overall heat flow in the interlayer structure is simulated, the calculation period is for steady-state solution, and the output result is the temperature distribution data of each layer cross-section of the structure, with the unit of °C, and the spatial resolution requirement is less than 0.2 mm to meet the subsequent heat gradient calculation requirements.

[0064] Step S42: Draw a heat gradient distribution map based on the heat conduction data; identify the interface temperature difference offset based on the heat gradient distribution map to obtain the temperature difference offset data; identify the interface adhesion abnormal area according to the temperature difference offset. In this embodiment, the drawing of the heat gradient distribution map depends on the exported three-dimensional temperature field data. The temperature gradient between adjacent grids is calculated with each discrete grid node as the unit, and the central difference method is used to calculate the gradient vector distribution. MATLAB or the SciPy library in Python is used for calculation and processing. The magnitude of the temperature gradient (K / m) and the gradient direction (vector unit direction) are mapped to a three-dimensional graph, and a pseudo-color strip is used to represent the heat concentration distribution area. On this basis, by comparing the normal heat gradients of each interface point by point, the interface temperature difference offset phenomenon is identified. The offset is defined as the angle difference between the upper and lower temperature gradient directions of the interface exceeding 15°, or the absolute difference between the temperature at the center and the edge of the interface exceeding 5 °C. These areas are marked as offset abnormal areas. Finally, the coordinates of the offset abnormal areas are exported to form the "temperature difference offset data", and the format includes fields such as three-dimensional spatial position, interface normal angle offset, and absolute temperature difference value.

[0065] Step S43: Perform coating delamination detection according to the interface adhesion abnormal area to obtain the coating delamination data. In this embodiment, the abnormal adhesion interface area is located based on the temperature difference offset data, and then the coating delamination detection is carried out in combination with the thermoacoustic excitation detection device. This device consists of a thermal excitation module and an infrared detection module. The thermal excitation module rapidly heats the identified area to 90 °C by a directional laser pulse for 1 second. Subsequently, a high-resolution infrared thermal imager (such as FLIR X8501sc) is used to collect a sequence of thermal response images at a frequency of 100 frames per second for a total duration of 10 seconds. The delamination is determined by the time difference and amplitude difference between the surface temperature rise and the recovery curve in the image sequence. If the recovery time of a certain area lags behind the normal area by more than 1.5 seconds and the temperature rise amplitude exceeds 1.2 times the standard deviation, it is determined as a delamination area. The detection results are exported as a "delamination distribution map", recording field information such as the central point coordinates, area (mm²), and delamination thickness (mm) of the delamination area in JSON or CSV format. After sorting, it is the "coating delamination data".

[0066] Step S44: Analyze the degradation of the coating adhesion based on the coating delamination data to obtain the coating adhesion degradation data; In this embodiment, by extracting the area, thickness, and distribution density of the delamination area, the delamination proportion per unit area is calculated. For example, if a delamination area with a total area of 18 cm² is detected within a range of 100 cm², the delamination proportion is 18%. And the artificial indentation adhesion measurement method is used for verification. A constant load of 1 N is applied to the delamination area using a pressure needle, and the ratio of the coating rupture area to the original indentation area is recorded to evaluate the residual adhesion rate. For example, if the indentation area is 1 mm² and the peeling area is 0.6 mm², the residual adhesion rate is 40%. On this basis, the adhesion degradation level is comprehensively calculated by combining the delamination distribution density, area ratio, and residual rate. A situation where the adhesion drops by more than 50% and the delamination density exceeds 2 per cm² is defined as "severe degradation", and those below this standard are respectively classified into two levels of "mild degradation" and "moderate degradation". The final result forms the "adhesion degradation data", and the fields include the degradation level, delamination rate, residual rate, etc.

[0067] Particularly importantly, step S44 includes the following steps: Step S441: Perform a surface topography scan based on the coating delamination data to obtain an image of the coating microstructure; In this embodiment, a high-resolution scanning electron microscope (SEM) or a laser confocal microscope is used to perform point-by-point scanning on the coating surface and the delamination area to collect microscopic structure images. During the scanning process, the scanning range is set to the delamination area and at least 5 millimeters around it, and the resolution is set to 0.5 micrometers to ensure rich microscopic morphology information is obtained. The height information of each scanning point is recorded during the scanning process to form three-dimensional surface morphology image data of the coating micro-structure. After the image acquisition is completed, noise filtering is performed on the data to remove artifacts generated by instrument vibration and environmental influence, ensuring the accuracy of subsequent analysis. A dedicated image processing software is used to enhance and adjust the contrast of the acquired images to make the features of small pores and cracks more obvious. The output of this step is a high-resolution image containing the delamination area of the coating and its microscopic morphology features, providing a data basis for subsequent pore detection.

[0068] Step S442: Perform pore detection based on the microscopic structure image of the coating to obtain coating pore data; In this embodiment, image segmentation technology, such as threshold-based binary processing, is used to distinguish the pore area from the solid coating area in the image. The threshold parameter is determined by a pre-calibrated standard sample. Usually, the gray threshold is set between 80 and 120 to ensure that the pore boundaries are clearly distinguishable. An edge detection algorithm (such as Canny edge detection) is used to accurately locate the pore contour and exclude noise and small impurities. The pore morphology parameters include pore diameter, shape factor, and pore area, which are obtained by calculating using image processing software. The misjudged areas of non-pore structures, such as cracks or coating peeling edges, need to be excluded during the pore detection process to ensure the accuracy of the pore data. The pore detection results are output in the form of a digital pore coordinate and size list, serving as the input data for subsequent calculation of pore distribution density.

[0069] Step S443: Calculate the pore distribution density based on the coating pore data to obtain pore distribution density data; In this embodiment, the ratio of the total number of detected pores to the scanning area is used as the basic parameter of the pore distribution density. The scanning area is determined by the scanning range in step S441, and the unit is usually square millimeters. The distribution uniformity of pores in the entire scanning area is statistically analyzed, and a point pattern analysis method in spatial statistics (such as Ripley’s K function) is used to evaluate the aggregation or dispersion of pores. Calculate the pore volume fraction as a supplementary parameter, and combine it with the pore size distribution to obtain more detailed pore structure information. The pore distribution density data is output in the form of the number of pores per square millimeter and the pore volume fraction, along with the distribution uniformity index, providing a quantitative basis for mechanical strength testing.

[0070] Step S444: Perform mechanical strength testing on the coating based on the pore distribution density data to obtain coating mechanical strength data; In this embodiment, a coating tensile testing machine or a nanoindentation instrument is used to measure the mechanical properties of the coating sample. Sample preparation includes cutting a coating specimen of standard size (such as 10 mm × 10 mm) from the detection area, and the thickness is maintained within the standard range (0.5 mm to 2.0 mm). The test point layout is adjusted according to the pore distribution density data to ensure coverage of the pore-dense area and the pore-sparse area. The test parameters are set with a tensile speed of 1 mm / min and an indentation load of 100 mN, and mechanical property indexes such as the elastic modulus, fracture strength, and hardness of the coating are measured. Data recording includes the stress-strain curve and the indentation depth, and the influence of pores on the mechanical strength is evaluated by combining the pore distribution density analysis. The mechanical strength data is output in numerical form as the basic parameter for evaluating the deterioration of the coating adhesion.

[0071] Step S445: Evaluate the deterioration of the adhesion based on the coating mechanical strength data to obtain the coating adhesion deterioration data.

[0072] In this embodiment, a standard adhesion test method, such as the cross-cut method or the pull-off method, is adopted and comprehensively analyzed in combination with the mechanical strength test results. The cross-cut method is carried out according to the GB / T9286 standard, the cross-cut size is set to 1 mm × 1 mm, the line spacing is 0.2 mm, and a special tape is used for the pull-off test to record the percentage of the peeling area. For the pull-off method, a pull-off instrument is applied, the pull-off speed is set to 0.5 mm / min, and the maximum pull-off force is measured. The mechanical strength data and the adhesion test data are combined, and a multi-factor weighted calculation model is used to calculate the adhesion deterioration index. The threshold is set such that when it is less than 50% of the maximum strength, it is determined as significant deterioration. The coating adhesion deterioration data is output, and the numerical range is from 0 to 1, representing the degree from no deterioration to complete deterioration. This data provides a quantitative basis for subsequent coating maintenance and repair.

[0073] Step S45: Classify the risk level according to the coating adhesion deterioration data to obtain the protection ability classification data; In this embodiment, the risk level classification is based on the deterioration level as the basic reference item, where mild deterioration corresponds to protection level I, moderate deterioration corresponds to protection level II, and severe deterioration corresponds to protection level III. In addition, the thermal conductivity degradation coefficient Kₜ is introduced as an auxiliary reference parameter, and Kₜ is defined as the ratio of the thermal conductivity after aging to the original thermal conductivity. For example, if the original thermal conductivity is 0.25 W / (m·K) and after aging it is 0.18 W / (m·K), then Kₜ = 0.72. If Kₜ is lower than 0.7, the protection level is automatically upgraded by one level to compensate for the unstable adhesion boundary caused by the decrease in thermal performance. By inputting all the evaluation fields (hollow density, adhesion residual rate, thermal conductivity degradation coefficient) into the risk level evaluation rule table, the generation of the "protection ability classification data" is automatically completed, and each result includes information such as the protection level number, comprehensive score, and abnormal area coordinates.

[0074] It is particularly important that step S45 includes the following steps: Step S451: calculating a protection capability index based on coating adhesion degradation data; In this example, specific numerical parameters of coating adhesion degradation are obtained. These data are derived from coating adhesion strength curves previously obtained through nondestructive testing techniques (such as ultrasonic guided waves, thermal imaging, or mechanical peel testing). Based on the actual measured adhesion strength values, a weighted average method is used to calculate a comprehensive protective capability index, combining the coating area, thickness uniformity, and degradation distribution. The protective capability index is represented by a normalized value between 0 and 1, with 0 indicating complete failure and 1 indicating complete integrity. Weighting coefficients are pre-set based on the importance of different coating regions, such as assigning a weight of 0.6 to critical structural areas and 0.4 to non-critical areas. The overall protective capability index is calculated by multiplying the local adhesion degradation degree by the corresponding weight and summing the results. This step utilizes professional data processing software to process and statistically analyze the multi-point sampling data to ensure the accuracy and representativeness of the index.

[0075] Step S452: Comparing the preset adhesion safety threshold with the protection capability index to obtain a protection capability critical point; In this embodiment, a preset adhesion safety threshold is clearly defined, which is generally set between 0.3 and 0.5 MPa. The protection capability index calculated in step S451 is compared point by point with this threshold, and the specific value at which the index first falls below the threshold is identified as the protection capability critical point. During data processing, statistical analysis tools are used to screen out intervals with a clear downward trend in protection capability. Combined with time series data analysis, the stability and effectiveness of the critical point are confirmed, eliminating interference from transient abnormal data. This step emphasizes the precise application of the threshold to ensure that the critical point reflects the actual critical failure state of the coating.

[0076] Step S453: Divide the protection risk level according to the protection capability critical point; In this embodiment, the protection capability index range of 0-1 is divided into five risk level intervals: Level 1 (indicator 0.8-1.0), Level 2 (indicator 0.6-0.79), Level 3 (indicator 0.4-0.59), Level 4 (indicator 0.2-0.39), and Level 5 (indicator 0-0.19). Using the critical points determined in step S452, data samples are mapped to the interval standards one by one to clearly define the risk level assigned to each coating area. During the risk level classification process, a hierarchical clustering algorithm is used to statistically aggregate the risk intervals. This is combined with spatial distribution data to create a risk heat map to assist in identifying high-risk concentrated areas. This step also includes the removal of extreme values and outliers to ensure that the risk level classification is scientific and objective.

[0077] Step S454: Classify the protection capabilities according to the protection risk levels to obtain protection capability classification data.

[0078] In this embodiment, the protection risk level data is used as input. Combining the physical performance indicators of the coating material and the environmental exposure parameters, a systematic classification of the overall protection capability of the coating is carried out. The classification standard is set to five levels: Level A corresponds to the first-level risk, indicating that the coating is intact and has strong protection capabilities; Level B corresponds to the second-level risk, with a slight decrease in protection capabilities; Level C corresponds to the third-level risk, with an obvious weakening of protection; Level D corresponds to the fourth-level risk, with severely damaged protection functions; Level E corresponds to the fifth-level risk, with basically lost protection functions. The classification operation is implemented through the database association function, and cross-validation is carried out in combination with the coating life prediction model data to output the final protection capability classification data. This classification data is stored in a structured format, supporting subsequent calls by the automated management system and the formulation of maintenance decisions.

[0079] Step S46: Generate digital tags according to the protection capability classification data to obtain protection capability digital management data.

[0080] In this embodiment, the tag generation module calls the tag encoding function and defines the field order in a unified structure: equipment number, motor number, area number, protection level, risk score, update time, validity period, additional remarks information. The protection level field is represented by level numbers Ⅰ~Ⅲ, the risk score field is generated on a percentage basis, the update period is set to once every three months, and the tag validity period does not exceed six months. The tag generation format is a two-dimensional data matrix code (such as DataMatrix ECC200). The ZXing open-source library is used to generate a QR code image, with an image resolution of 300×300 pixels. Before encoding, the field content is encrypted by SHA-256 to ensure uniqueness and security. The generated digital tag is embedded in the equipment file database, and is bound one by one with the coating number and location coordinates to achieve the organized output of "protection capability digital management data".

[0081] Preferably, this specification also provides an industrial digital management system based on model construction for executing the industrial digital management method based on model construction as described above. This industrial digital management system based on model construction includes: A thermal isolation design module, configured to obtain the operation logs of industrial equipment; perform motor thermal overload analysis according to the operation logs of industrial equipment to obtain motor thermal overload data; perform thermal isolation design based on the motor thermal overload data to obtain thermal isolation data; An insulation aging detection module, configured to perform ventilation path blockage analysis according to the motor thermal overload data to obtain ventilation path blockage data; perform winding insulation aging detection based on the ventilation path blockage data to obtain winding insulation aging data; perform insulation paint film peeling detection based on the winding insulation aging data to obtain insulation paint film peeling data; The motor coating heat insulation model construction module is used to upgrade the protective coating according to the insulation paint film peeling data to obtain the protective coating upgrade data; construct the motor coating heat insulation model according to the protective coating upgrade data and the heat insulation data; perform coating aging simulation according to the motor coating heat insulation model to obtain the coating aging data; The digital management module is used to detect coating hollowing according to the coating aging data to obtain the coating hollowing data; analyze the deterioration of coating adhesion according to the coating hollowing data to obtain the coating adhesion deterioration data; perform digital management of the protection ability according to the coating adhesion deterioration data to obtain the digital management data of the protection ability.

[0082] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be included in the present invention.

[0083] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the widest scope consistent with the principles and novel features invented herein.

Claims

1. An industrial digital management method based on model construction, characterized in that It includes the following steps: Step S1: Obtain the operation log of industrial equipment; conduct motor thermal overload analysis based on the operation log of industrial equipment to obtain motor thermal overload data; perform thermal isolation design based on the motor thermal overload data to obtain thermal isolation data; Step S2: Conduct ventilation path blockage analysis based on the motor thermal overload data to obtain ventilation path blockage data; perform winding insulation aging detection based on the ventilation path blockage data to obtain winding insulation aging data; perform insulation paint film peeling detection based on the winding insulation aging data to obtain insulation paint film peeling data; Step S3: Upgrade the protective coating according to the insulation paint film peeling data to obtain protective coating upgrade data; Construct a motor coating heat insulation model according to the protective coating upgrade data and the thermal isolation data; perform coating aging simulation according to the motor coating heat insulation model to obtain coating aging data; Step S4: Conduct coating hollowing detection according to the coating aging data to obtain coating hollowing data; Conduct coating adhesion deterioration analysis according to the coating hollowing data to obtain coating adhesion deterioration data; perform digital management of the protection ability according to the coating adhesion deterioration data to obtain digital management data of the protection ability.

2. The industrial digital management method based on model construction according to claim 1, wherein Step S1 is specifically as follows: Step S11: Obtain the operation log of industrial equipment; Step S12: Record the current operation parameters based on the operation log of industrial equipment; record the voltage operation parameters based on the operation log of industrial equipment; Calculate the motor power according to the current operation parameters and the voltage operation parameters; Step S13: Estimate the winding temperature rise based on the motor power to obtain motor winding temperature data; Step S14: Determine the high temperature of the motor winding according to the preset motor winding temperature threshold for the motor winding temperature data to obtain motor winding high temperature data; calculate the high temperature duration based on the motor winding high temperature data to obtain high temperature duration data; Step S15: Count the high temperature frequency according to the motor winding high temperature data to obtain high-frequency high-temperature period data; Conduct thermal overload identification according to the high-frequency high-temperature period data and the high temperature duration data to obtain motor thermal overload data; Step S16: Perform thermal isolation design based on the motor thermal overload data to obtain thermal isolation data.

3. The industrial digital management method based on model construction according to claim 2, characterized in that Step S16 is specifically as follows: Step S161: Identify the heat radiation path based on the motor thermal overload data to obtain heat radiation path data; Step S162: Determine the heat source range according to the heat radiation path data to obtain heat source range data; Step S163: Determine the thermal isolation boundary based on the heat source range data to obtain thermal isolation boundary data; Step S164: Determine the structure size of the heat shield according to the thermal isolation boundary data; select the material type according to the structure size of the heat shield to obtain material type data; perform sheet cutting according to the material type data to obtain heat shield sheet data; conduct air duct layout based on the heat shield sheet data to obtain air duct structure data; reinforce the heat shield according to the air duct structure data to obtain heat shield data; Step S165: Evaluate the thermal isolation effect based on the heat shield data to obtain thermal isolation data.

4. The industrial digital management method based on model construction according to claim 1, wherein The ventilation path blockage analysis in Step S2 is specifically as follows: Statistical analysis of the heat of the motor based on the motor thermal overload data to obtain the motor heat data; identifying the heat source concentration area based on the motor heat data; calculating the temperature difference between adjacent measuring points based on the heat source concentration area to obtain the temperature difference data of the measuring points; Calculating the gradient vector direction based on the temperature difference data of the measuring points to obtain the temperature difference gradient direction data; obtaining the motor heat dissipation path data; performing ventilation path mapping based on the motor heat dissipation path data and the temperature difference gradient direction data to obtain the ventilation path data; Performing filter clogging detection based on the ventilation path data to obtain the filter clogging data; Collecting the clogging sample according to the filter clogging data and analyzing the particle size of the clogging sample to obtain the clogging particle size data; performing surface roughness detection based on the clogging particle size data to obtain the clogging roughness data; Evaluating the adhesion strength of the ventilation duct based on the clogging roughness data; Performing ventilation path clogging analysis based on the adhesion strength of the ventilation duct to obtain the ventilation path clogging data.

5. The industrial digital management method based on model construction according to claim 1, characterized in that, The winding insulation aging detection in step S2 is specifically as follows: Calculating the wind resistance based on the ventilation path clogging data to obtain the wind resistance data; Performing winding temperature rise analysis based on the wind resistance data to obtain the winding temperature rise data; Performing thermal stress detection of the insulating material based on the winding temperature rise data to obtain the thermal stress data of the insulating material; Calculating the material aging rate based on the thermal stress data of the insulating material; Performing winding insulation aging assessment based on the material aging rate to obtain the winding insulation aging data.

6. The industrial digital management method based on model construction according to claim 1, wherein The insulation paint film peeling detection in step S2 is specifically as follows: Extracting the insulation surface characteristics based on the winding insulation aging data to obtain the insulation surface data; Performing paint film crack detection based on the insulation surface data to obtain the insulation paint film crack data; Performing crack propagation simulation based on the insulation paint film crack data to obtain the crack propagation data; Evaluating the adhesion force of the insulation paint film based on the crack propagation data to obtain the paint film adhesion force data; Performing insulation paint film peeling detection based on the paint film adhesion force data to obtain the insulation paint film peeling data.

7. The industrial digital management method based on model construction according to claim 1, characterized in that Step S3 is specifically as follows: Step S31: Calculating the peeling depth based on the insulation paint film peeling data to obtain the peeling depth data; evaluating the damage degree of the insulation layer based on the peeling depth data to obtain the insulation layer damage data; Step S32: Selecting the protective coating material based on the insulation layer damage data to obtain the protective coating material data; Step S33: Determining the coating thickness based on the protective coating material data to obtain the coating thickness data; Determining the topcoat coating method based on the protective coating material data to obtain the topcoat coating method data; Step S34: Integrating the coating thickness data and the topcoat coating method data to obtain the protective coating upgrade data; Step S35: Constructing a motor coating heat insulation model based on the protective coating upgrade data and the heat insulation data; Step S36: Performing coating aging simulation based on the motor coating heat insulation model to obtain the coating aging data.

8. The industrial digital management method based on model construction according to claim 1, characterized in that Step S36 is specifically as follows: Step S361: Uploading the motor coating heat insulation model to the thermal aging simulation platform; Step S362: Setting the environmental temperature range to 40°C - 120°C and the humidity range to 30% - 80%; Step S363: Setting the motor operating power range to 50kW - 150kW and the working cycle to 8 hours - 24 hours; Step S364: Input the thermal conductivity of the coating material as 0.15 - 0.35 W / (m·K) and the thickness as 0.5 - 2.0 mm; Step S365: Run the thermal aging simulation program to obtain coating aging data.

9. The industrial digital management method based on model construction according to claim 1, wherein Step S4 specifically includes: Step S41: Conduct a heat conduction simulation based on the coating aging data to obtain heat conduction data; Step S42: Draw a heat gradient distribution map based on the heat conduction data; Identify the interface temperature difference offset based on the heat gradient distribution map to obtain temperature difference offset data; Identify the interface adhesion abnormal area according to the temperature difference offset; Step S43: Conduct a coating hollow detection based on the interface adhesion abnormal area to obtain coating hollow data; Step S44: Conduct an analysis of the deterioration of the coating adhesion based on the coating hollow data to obtain coating adhesion deterioration data; Step S45: Conduct a risk level classification based on the coating adhesion deterioration data to obtain protection ability classification data; Step S46: Generate a digital label based on the protection ability classification data to obtain digital management data for protection ability.

10. An industrial digital management system based on model construction, characterized in that, For implementing the model - based industrial digital management method as described in claim 1, the model - based industrial digital management system includes: A thermal isolation design module, which is used to obtain the operation log of industrial equipment; Conduct an analysis of motor thermal overload based on the operation log of industrial equipment to obtain motor thermal overload data; Conduct a thermal isolation design based on the motor thermal overload data to obtain thermal isolation data; An insulation aging detection module, which is used to conduct a ventilation path blockage analysis based on the motor thermal overload data to obtain ventilation path blockage data; Conduct a winding insulation aging detection based on the ventilation path blockage data to obtain winding insulation aging data; Conduct an insulation paint film peeling detection based on the winding insulation aging data to obtain insulation paint film peeling data; A motor coating heat insulation model construction module, which is used to upgrade the protective coating based on the insulation paint film peeling data to obtain protective coating upgrade data; Construct a motor coating heat insulation model according to the protective coating upgrade data and the thermal isolation data; Conduct a coating aging simulation according to the motor coating heat insulation model to obtain coating aging data; A digital management module, which is used to conduct a coating hollow detection based on the coating aging data to obtain coating hollow data; Conduct an analysis of the deterioration of the coating adhesion based on the coating hollow data to obtain coating adhesion deterioration data; Conduct digital management of the protection ability based on the coating adhesion deterioration data to obtain digital management data for protection ability.

Images