Speed reducer box sealing performance testing method and system based on intelligent sensor

Abstract

The invention provides a reducer box sealing performance test method and system based on an intelligent sensor, and relates to the technical field of sealing detection, and the method comprises the steps: collecting each sealing test point; generating a primary sealing test result; building a primary sealing test platform based on the intelligent sensor, generating a primary sealing test result, carrying out factory verification based on the primary sealing test result, and calling the box simulation model and the secondary leakage variable after leaving a factory to generate a secondary leakage model; secondary leakage fitness monitoring is performed, including instantaneous fitness monitoring and cumulative fitness monitoring. The technical problem that in the prior art, due to the fact that the sealing state change of the speed reducer under the actual working condition is difficult to reflect, sealing detection is inaccurate can be solved, and intelligent detection and evolution monitoring of the sealing performance of the speed reducer in the whole process from factory leaving to service are achieved through the intelligent sensor. The technical effects of improving the sealing reliability and preventing leakage faults are achieved.

Description

Technical Field

[0001] The present application relates to the field of sealing detection technology, and in particular to a method and system for testing the sealing performance of a reducer housing based on an intelligent sensor. Background Art

[0002] In current industrial equipment, reducers, as key components for power transmission and speed regulation, are widely used in wind power, rail transit, heavy metallurgy, automated production lines, and other fields. Due to their complex operating environments and frequently fluctuating operating loads, the sealing performance of reducer housings is directly related to the equipment's lubrication stability, operating efficiency, and system lifespan. Especially under harsh conditions such as high humidity, high temperature, and strong vibration, the housing sealing system is prone to leakage, oil seepage, and seal aging. These problems can lead to lubricant depletion, increased wear of transmission components, and even equipment failures and downtime, resulting in significant economic losses and safety hazards.

[0003] Currently, traditional sealing performance testing methods mainly rely on manual visual inspection, airtightness or liquidtightness testing, and fixed-point leak detection. These methods have obvious limitations: on the one hand, most of the testing methods are static offline testing, which cannot reflect the dynamic evolution of the reducer's sealing status under actual operating conditions; on the other hand, their ability to identify early-stage minor leaks is weak, making it difficult to achieve pre-emptive perception of potential failure risks.

[0004] In summary, the prior art has a technical problem in that it is difficult to reflect changes in the sealing state of the reducer under actual working conditions, resulting in inaccurate sealing detection. Summary of the Invention

[0005] The purpose of this application is to provide a reducer housing sealing performance testing method and system based on intelligent sensors to solve the technical problem in the prior art that it is difficult to reflect the changes in the sealing state of the reducer under actual working conditions, resulting in inaccurate sealing detection.

[0006] In view of the above problems, the present application provides a reducer housing sealing performance testing method and system based on intelligent sensors.

[0007] In the first aspect, the present application provides a reducer case sealing performance testing method based on smart sensors, and the reducer case sealing performance testing method based on smart sensors is implemented by a reducer case sealing performance testing system based on smart sensors, wherein the reducer case sealing performance testing method based on smart sensors includes: collecting various sealing test points of the reducer case; building a primary sealing test platform based on smart sensors, performing primary leakage variable control and sealing detection on the various sealing test points, and generating primary sealing test results; performing factory verification based on the primary sealing test results, calling the case simulation model and secondary leakage variables after leaving the factory, performing simulation of secondary leakage variables, and generating a secondary leakage model; connecting the secondary leakage model to the operating environment of the reducer case, and performing secondary leakage fitness monitoring, including instantaneous fitness monitoring and cumulative fitness monitoring.

[0008] In the second aspect, the present application also provides a reducer case sealing performance test system based on an intelligent sensor, which is used to execute the reducer case sealing performance test method based on an intelligent sensor as described in the first aspect, wherein the reducer case sealing performance test system based on an intelligent sensor includes: a test point acquisition unit, used to collect various sealing test points of the reducer case; a primary test unit, used to build a primary sealing test platform based on an intelligent sensor, perform primary leakage variable control and sealing detection on each sealing test point, and generate a primary sealing test result; a secondary simulation unit, used to perform factory verification based on the primary sealing test result, call the case simulation model and secondary leakage variables after leaving the factory, perform simulation of the secondary leakage variables, and generate a secondary leakage model; a secondary adaptation analysis unit, used to connect the secondary leakage model to the operating environment of the reducer case, and perform secondary leakage fitness monitoring, including instantaneous fitness monitoring and cumulative fitness monitoring.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: Collect data from various sealing test points of the reducer housing; build a primary sealing test platform based on intelligent sensors, perform primary leakage variable control and sealing detection on the various sealing test points, and generate primary sealing test results; perform factory verification based on the primary sealing test results, call the housing simulation model and secondary leakage variables after leaving the factory, perform simulation of secondary leakage variables, and generate a secondary leakage model; connect the secondary leakage model to the operating environment of the reducer housing, and perform secondary leakage fitness monitoring, including instantaneous fitness monitoring and cumulative fitness monitoring. By collecting the sealing test points of the reducer housing and combining intelligent sensors to build a primary sealing test platform, and using simulation modeling to build a secondary leakage model, dynamic prediction of sealing performance during operation is achieved, and finally, real-time evaluation of sealing status and grasp of degradation trends are achieved through fitness monitoring, thereby realizing intelligent detection and evolution monitoring of reducer sealing performance from factory to service, achieving the technical effect of improving sealing reliability and preventing leakage failures.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without creative work.

[0012] Figure 1 This is a flow chart of the reducer housing sealing performance testing method based on intelligent sensors in this application.

[0013] Figure 2 This is a structural diagram of the reducer housing sealing performance test system based on intelligent sensors in this application.

[0014] Description of reference numerals: Test point acquisition unit 11, primary test unit 12, secondary simulation unit 13, secondary adaptation analysis unit 14. DETAILED DESCRIPTION

[0015] This application solves the technical problem in the prior art of inaccurate sealing detection due to the difficulty in reflecting changes in the sealing state of the reducer under actual working conditions by providing a method and system for testing the sealing performance of the reducer housing based on intelligent sensors. By collecting the sealing test points of the reducer housing and combining them with intelligent sensors to build a primary sealing test platform, and using simulation modeling to build a secondary leakage model, dynamic prediction of the sealing performance during the operation phase is achieved. Finally, through fitness monitoring, real-time evaluation of the sealing state and grasp of the degradation trend are achieved. In this way, intelligent detection and evolution monitoring of the reducer sealing performance from factory to service are achieved, achieving the technical effect of improving sealing reliability and preventing leakage failures.

[0016] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0017] For example 1, please refer to the attached Figure 1 The present application provides a reducer case sealing performance testing method based on an intelligent sensor, wherein the reducer case sealing performance testing method based on an intelligent sensor is applied to a reducer case sealing performance testing system based on an intelligent sensor. The reducer case sealing performance testing method based on an intelligent sensor specifically includes the following steps: Step S100: collecting data on various sealing test points of the reducer housing.

[0018] Specifically, in actual industrial applications, the reducer housing is a key component of the power transmission system, and its sealing performance directly affects the reliability and service life of the equipment. In order to ensure that the sealing status meets the standards, it is necessary to comprehensively collect all potential sealing test points of the reducer housing. First, typical leakage areas are identified, including the end cover joint surface, bolt hole area, shaft seal area, and weld edge. The sealing test point refers to the location where the seal may fail during operation due to process errors, material fatigue, assembly errors, uneven thermal expansion or stress concentration. Specifically, all locations where leakage has occurred can be counted based on historical sealing failure records to obtain the various sealing test points, which provide key input data and reference basis for subsequent primary sealing tests and secondary tests.

[0019] Step S200: Building a primary sealing test platform based on the intelligent sensor, performing primary leakage variable control and sealing detection on each sealing test point, and generating a primary sealing test result.

[0020] Specifically, the primary seal test platform, built with intelligent sensors, is a core component of the reducer housing sealing performance testing process. It is designed to simulate standard pre-shipment operating conditions and perform high-precision, high-stability seal verification for all identified potential test points, i.e., individual sealing test points. Primary leakage variables refer to initial seal risk parameters arising solely from structural design, material defects, manufacturing tolerances, or assembly errors under standard operating conditions, without taking into account wear and aging. Controlling these variables is a prerequisite for the platform's operation and directly determines the reliability and accuracy of the test.

[0021] The platform mainly consists of two core modules: a test variable control module and an intelligent sensor module. The test variable control module is equipped with a hot air pressurization device, which can simulate the internal cavity pressurization of the box according to the set pressure-temperature curve. For example, in a typical test process, a step pressurization curve from normal temperature and pressure to 0.25MPa and 60°C is set according to the application constraints. The whole process lasts about 10 minutes to simulate the thermal-pressure coupling conditions experienced by the reducer during startup, preheating, and steady-state operation. Application constraints refer to the physical environmental restrictions imposed on the box in its target assembly system, such as spatial direction, fixing method, and the influence of surrounding heat sources. It determines the mode and range of hot air pressurization.

[0022] After pressurization stabilizes, the intelligent sensor module begins operation. The infrared imager captures the minute temperature differences caused by hot air escaping from the test point, achieving highly sensitive responses to temperature differences as small as 0.05°C. In conjunction with hot gas detection equipment, which typically employs infrared absorption spectroscopy or a mass flow meter, the module quantitatively analyzes characteristic components in the escaping gas, providing a result indicating whether a seal failure has occurred at the test point—the primary seal test result. In actual testing, a fully assembled reducer housing tested on this platform revealed a significant temperature hotspot in the upper left corner of the shaft seal joint. Hot gas testing confirmed a leak rate of 0.11 mL / s. This result was determined to be a minor leak, exceeding the standard upper limit (typically set at 0.1 mL / s). A corresponding primary seal test report was generated, marking the result as requiring repair. This system not only rapidly completes full-domain seal testing but also enables real-time correlation analysis of leak location, leak intensity, and environmental changes, enabling highly automated and intelligent seal quality assessment, significantly improving the accuracy and efficiency of pre-shipment quality control.

[0023] Step S300: Perform factory verification based on the primary sealing test result, call the box simulation model and secondary leakage variables after leaving the factory, perform simulation of the secondary leakage variables, and generate a secondary leakage model.

[0024] Specifically, after the primary sealing test is completed, factory verification is performed, which is a key quality checkpoint before the product leaves the factory. After leaving the factory, in order to predict the evolution trend of the sealing state of the box during long-term service, the box simulation model and secondary leakage variables are called for simulation and deduction. The box simulation model is a digital twin constructed based on three-dimensional structural mechanics modeling, material thermal-mechanical response model and historical operation data training. It can accurately simulate the deformation and stress response of the reducer box under different loads, temperature cycles, and frequency excitations. Secondary leakage variables represent non-initial factors that gradually appear in actual operation and affect the sealing performance, such as structural cracks caused by thermal fatigue, elastic attenuation caused by aging of sealing materials, and micro-displacement of the connection surface due to vibration.

[0025] During the simulation process, these secondary variables are gradually added to the simulation model, and multi-field coupling simulation is performed in combination with the primary test data recorded at the factory. For example, in an industrial gear reducer that mainly operates at high speed and heavy load, the secondary variables loaded into the simulation model include contact fatigue data after 300,000 operating cycles, the uneven thermal expansion field under the interference of surrounding heat sources, and the aging trend of the seal material hardness decreasing by 12%. The simulation results show that the shaft seal area where the boundary originally passed experienced the first decline in sealing performance at the 180,000th cycle, and the simulated leakage rate value exceeded 0.1mL / s at the 250,000th cycle. Based on these data, a secondary leakage model is generated. This model is no longer limited to a static state, but is a dynamic, iteratively updateable prediction model that can be used for sealing adaptability deduction under different operating conditions.

[0026] The construction of a secondary leakage model provides a data basis for formulating maintenance plans throughout the lifecycle of the housing. Manufacturers can use this data to optimize design redundancy, improve the durability of sealing structures, and even make health-based maintenance decisions during the after-sales service phase through model-driven maintenance. This integrated testing and simulation system, from primary detection to secondary prediction, represents a key shift in mechanical seal performance evaluation from static testing to dynamic intelligent prediction.

[0027] Step S400: connecting the secondary leakage model to the operating environment of the reducer housing, and performing secondary leakage fitness monitoring, including instantaneous fitness monitoring and cumulative fitness monitoring.

[0028] Specifically, once the reducer housing enters actual operating conditions, a previously constructed secondary leakage model is seamlessly integrated into its operating environment to ensure continuous risk management of sealing performance. This connection is achieved through edge computing nodes and an operation monitoring platform, enabling the model to simultaneously acquire reducer operating status data without compromising real-time performance, thereby continuously monitoring and evaluating sealing performance.

[0029] Secondary leakage fitness monitoring is a key link in the dynamic identification of the sealing status during operation, and is divided into two categories: instantaneous fitness monitoring and cumulative fitness monitoring. Instantaneous fitness monitoring is mainly aimed at high-speed response scenarios, and real-time analysis is performed on whether the current operating data induces leakage risks. Using the state parameters such as speed, load, temperature and vibration in the current sampling period as input, the changing trend of the sealing variables is immediately deduced through the secondary leakage model. If the box is subjected to abnormal impact loads or a sharp temperature rise (such as temperature changes exceeding 12°C / min, axial impact force peak exceeding 450N) within a certain period of time, it will be predicted that the sealing stress boundary at the corresponding structure may be breached, and then a low fitness warning will be output. For example, when the test platform simulates thermal shock conditions, the instantaneous fitness score drops to 0.41 (the score range is 0~1), and the event is immediately marked and the subsequent rebound evaluation mechanism is initiated.

[0030] Correspondingly, cumulative fitness monitoring focuses on the performance degradation trend during long-term operation. By continuously collecting operating data at multiple time points and inputting it into the leakage model in a time series, the gradual evolution of sealing variables under the effects of long-term fatigue, material aging, and load accumulation is simulated. The key technology lies in the fitness rebound analysis mechanism: it not only evaluates the change value of the sealing variable at each moment, but also compares whether there is a recovery trend after the previous monitoring cycle (for example, performance recovery caused by environmental improvement or load reduction). The analysis results are used as the initial conditions for the next round of predictions to achieve path-dependent modeling of the sealing status.

[0031] For example, in an analysis of six months of operating data for a wind turbine gearbox, it recorded an average daily operating time of 12 hours and a peak load of 180 Nm. The fitness curve showed that the score remained stable above 0.85 for the first 200 hours, then dropped to 0.63 at the 600th hour. After a decrease in ambient temperature and optimization of lubrication conditions, it briefly rebounded to 0.69 at the 720th hour. The final cumulative simulation predicted that the fitness warning threshold (0.45) would be reached around the 1600th hour. This information generated an early warning report and recommended maintenance windows.

[0032] Embedding the secondary leakage model into the operating environment enables instantaneous and cumulative dual-path fitness monitoring. This not only extends the sealing status of the reducer housing from static factory inspection to full-life intelligent monitoring, but also enables quantitative visualization of sealing risks, controllable trends, and predictable maintenance, providing a solid data foundation and intelligent algorithm support for equipment health management.

[0033] Furthermore, step S200 of this application includes: The primary sealing test platform includes a test variable control module and an intelligent sensor module; wherein, the test variable control module includes a hot air pressurizing device connected to the reducer housing, and the intelligent sensor module includes an infrared imager and a hot air detection device.

[0034] Specifically, the function of the test variable control module is to create internal cavity pressure and temperature conditions that are close to actual operating conditions, ensuring that leakage behavior can be fully stimulated and exposed, thereby providing an observable physical signal basis for subsequent sensor detection. Specifically, the test variable control module uses a hot air pressurization device, which is a device that can apply a preset temperature and pressure gradient to the inside of the box. It is seamlessly connected to the reducer box sealing interface through a flexible pressurization connection component. In a standard test process, the device uses 0.1MPa as the starting pressure and increases by 0.05MPa every 90 seconds until it reaches 0.3MPa, while maintaining the hot air temperature in the range of 60℃ to 80℃ to simulate the thermal-pressure changes faced by the reducer in the early stage of high-speed operation. This control process not only strictly implements the dynamic adjustment curve of temperature and pressure, but also has the functions of voltage stabilization self-calibration and over-temperature pressure relief protection to ensure safe and reliable testing.

[0035] The intelligent sensor module is responsible for collecting and analyzing leak data. Infrared imagers are used to detect thermal anomalies on the reducer housing surface. Their principle is based on the surface thermal gradient created by the heat energy released by leaking gas. This equipment typically has a thermal resolution of ±0.03°C, sufficient to detect subtle leaks. For example, a microcracked weld at the housing corner reveals a thin, high-temperature line approximately 2.5 mm wide, lasting for approximately 15 seconds. This corresponds to an infrared thermal gradient of 0.12°C, initially identifying it as a suspected leak. Thermal gas detection equipment further confirms whether gas is escaping from the area, typically using a portable laser gas analyzer or mass spectrometer-based gas detector. These devices can monitor real-time concentration changes of target gases (such as helium, SF6, or a marker gas added to pressurized air). For example, the thermal gas detection equipment recorded a sudden increase in marker gas concentration at the weld to 4.8 times the ambient baseline, with a leak rate of 0.087 mL / s, identifying the weld as a leak.

[0036] The advantage of this platform architecture is that it realizes a complete closed-loop process from variable excitation to signal capture, making the primary sealing test process controllable, repeatable and supported by high-resolution data. It not only improves the detection accuracy, but also provides a strong data foundation for subsequent repair decisions, quality tracking and model iteration.

[0037] Furthermore, step S200 of this application includes: Step S210: Collect the application constraints of the reducer housing; Step S220: Configure the hot air pressurization scheme based on the application constraints; Step S230: Send the hot air pressurization scheme to the test variable control module for hot air pressurization step control. When the control is stable, use the intelligent sensor module to perform thermal difference detection and hot air detection inside and outside the housing to generate detection results; Step S240: Use the detection results to perform sealing judgment and generate the primary sealing test results.

[0038] Specifically, during actual sealing performance testing, the diverse application scenarios of the reducer housing require the collection of application constraint information to achieve a more accurate test environment. Application constraints refer to factors such as the physical installation method, operating temperature range, pressure load conditions, orientation, spatial envelope, and thermal interference from adjacent components of the reducer housing within the target assembly system. These factors influence the stress and expansion state of the housing structure under real-world operating conditions, thereby having a practical impact on sealing performance.

[0039] Application constraints are usually collected with the help of simulation interfaces or on-site sensor records, including the use of 3D measuring instruments to obtain assembly postures, environmental sensors to record temperature and humidity parameters, and the combination of previous operating data to model and analyze structural responses. Based on these application constraints, a personalized hot air pressurization plan is automatically configured. For example, in the test of an industrial robot reducer box used in a high-temperature environment, its operating temperature is identified as 75°C, the maximum internal pressure is 0.28MPa, the posture is vertically installed, and the heat source is on the left side of the box. Therefore, the set hot air pressurization plan is: the temperature is gradually increased from room temperature to 80°C, and the pressure is increased by 0.05MPa to 0.3MPa, with a total of five steps. The heating and pressurization process lasts for 8 minutes, and the stable state is maintained for 90 seconds at each level to be as close to its actual service conditions as possible.

[0040] The hot air pressurization scheme is transmitted to the test variable control module via a control interface. During execution, the pressure and temperature changes within the chamber cavity are monitored in real time to ensure that their curves align with the set scheme. Fluctuations are dynamically corrected using a PID control algorithm until steady-state is achieved. At this point, the intelligent sensor module intervenes. An infrared imager first scans the chamber surface to capture the differential heat distribution inside and outside the chamber, identifying areas of potential abnormal heat conduction. Hot gas detection equipment then tests the gas composition and concentration in these areas to verify any gas leaks caused by seal failure.

[0041] For example, in one test, thermal differential detection identified an abnormally high temperature area of ​​approximately 1.8 cm² on the left side of the bottom of the box. Thermal imaging data showed a temperature difference of 0.14°C. Subsequent thermal gas detection results showed that the concentration of the marked gas at this location increased by 3.5 times, corresponding to a leakage rate of 0.094 mL / s. After comparing this test result with the set leakage threshold (typically 0.1 mL / s), the sealing judgment process is automatically executed, and the primary sealing test results are generated, including the presence of a sealing leak point, along with a complete test image, leak point map, environmental conditions, and leak intensity curve. This sealing assessment method, based on the fusion of application constraints and intelligent detection, is more adaptable and has greater engineering value than traditional static testing.

[0042] Furthermore, step S300 of this application includes: Step S310: Analyze the primary sealing test results to determine whether there is a primary leakage point; Step S320: If not, send the box simulation model and the secondary leakage variable to the application end of the reducer box, and perform a mapping simulation of the secondary leakage variable and the reducer box operating parameters on the application end to generate the secondary leakage model.

[0043] Specifically, in the sealing performance evaluation process, analyzing the primary sealing test results is a prerequisite for entering the subsequent simulation stage, which is used to determine whether there is a leak. If not, it means that the initial sealing state of the box is good, which can be used as the basic condition for constructing the subsequent secondary leakage model.

[0044] On this basis, the housing simulation model corresponding to the reducer housing and the preset secondary leakage variables are sent together to its actual application end, that is, the control system or embedded monitoring platform of the reducer in the target complete equipment. The key to the mapping simulation on the application end is to establish a functional relationship between the secondary leakage variables and the operating parameters of the reducer housing. Secondary leakage variables usually include the stress relaxation rate of the sealing surface caused by thermal cycling, the material hardness reduction coefficient, the microcrack development rate, etc., while the operating parameters of the reducer housing include torque load, input speed, operating temperature, starting frequency, vibration frequency, etc. The mapping simulation process uses multivariate regression, neural network fitting or time series prediction models, taking the operating parameters as independent variables to predict the evolution trend of the response of the induced secondary leakage variables. Among them, the housing simulation model is constructed by collecting the housing modeling parameters using the existing digital twin technology.

[0045] For example, the simulation was loaded with the following parameters: ambient temperature fluctuation of ±20°C, average daily operating time of 8 hours, average speed of 1600 rpm, and 150 starts per day. A leakage variable response curve was established based on historical training data. Simulation results showed that under these conditions, the sealing ring's clamping force decreased by 4.2% every 500 hours, and the microscopic displacement-induced gap expansion was 0.06 mm. The prediction was that after a cumulative operating time of 2400 hours, the leakage rate would exceed the warning value of 0.08 mL / s. This result formed a complete secondary leakage model, including key elements such as prediction intervals, failure trends, sensitive variable rankings, and risk point determination.

[0046] The key value of this step is that it not only extends the predictive capability of the test results in actual working conditions, but also transforms static experimental data into behavioral models with dynamic response capabilities, providing forward-looking data support for health monitoring, risk control, and product design optimization.

[0047] Furthermore, step S320 of this application includes: Step S321: Obtain the connection application structure and connection application mechanism of the reducer case; Step S322: Perform simulation modeling on the connection application structure to generate a connection application model; Step S323: Based on the application mechanism, perform collaborative connection between the case simulation model and the connection application model to generate an integrated architecture; Step S324: Use the integrated architecture to perform a mapping simulation of the secondary leakage variables and the reducer case operating parameters to generate the secondary leakage model.

[0048] Furthermore, the secondary leakage variable includes a structural failure variable of the reducer housing that causes sealing failure during operation, and the reducer housing operating parameters are operating state parameters of the reducer housing during operation. In the mapping simulation process, the reducer housing operating parameters are used as independent variables, and the secondary leakage variable is used as the dependent variable. The mapping simulation includes a single instantaneous simulation and multiple cumulative simulations.

[0049] Specifically, in the process of further improving the accuracy and adaptability of the reducer housing sealing performance prediction, obtaining its connection application structure and mechanism becomes the key starting point for building a high-fidelity secondary leakage model. The so-called connection application structure refers to the physical connection method between the reducer housing and other components (such as the motor, housing bracket, bearing seat, support base plate, etc.) in the target system, including bolt arrangement, flange contact surface, sealing gasket type and preload, etc.; while the connection application mechanism refers to how these structures work together to affect the housing sealing performance during operation, such as connection relaxation caused by thermal expansion and contraction, stress redistribution caused by torque transmission, interface deformation caused by vibration superposition, and other dynamic interactive behaviors. Once these connection structure and mechanism data are obtained, the corresponding simulation modeling process is constructed, and the finite element modeling software in the existing technology is used to perform parameter modeling of the connection application structure. The material of the connector, boundary constraints, contact type, load path and thermal coupling parameters are input to generate a multi-scale connection application model. In a typical application, a certain type of reducer uses a three-point rigid flange connection to the motor and the load-bearing base. In the modeling, a pre-tightening torque of 3.5 Nm and an interface friction coefficient of 0.15 are introduced, and the operating parameters of the contact surface temperature difference of ±15°C are set. Finally, a connection application model with time-varying contact stiffness is generated.

[0050] This model was then integrated with the existing enclosure simulation model through collaborative connection. This collaborative connection involves more than just geometric splicing; it also involves a linkage of physical and mechanical behaviors, achieving an integrated architecture through interface field variable coupling. For example, the path and magnitude of thermal stress propagation from the connection area to the main enclosure structure are precisely calculated, and the attenuation effect of micro-displacements on the internal sealing ring's compression force is also simultaneously reflected. The entire integrated architecture possesses complete dynamic response capabilities, capable of handling complex coupled loads and variable iterations.

[0051] Based on this, a mapping simulation is performed, using the reducer's operating parameters as input variables, including input shaft speed (e.g., 1700 rpm), peak cyclic load (e.g., 120 Nm), operating temperature rise (e.g., 28°C), and lateral vibration acceleration (e.g., 3.2 gRMS). These parameters are fed into the mapping engine, which generates a response curve to secondary leakage variables. Secondary leakage variables are defined as a series of structural failure variables, such as seal ring deformation, contact surface offset, and cavity internal pressure reverse leakage risk index.

[0052] Mapping simulations include both single-shot transient simulations—predictive analysis based on instantaneous sampling points during specific operating conditions, such as determining whether a high-temperature start-up moment will trigger a microleak—and multiple cumulative simulations, simulating the incremental evolution of variables over long-term operation. In a complete cumulative simulation, based on a 10-hour daily operation and a five-day workweek, the growth of sealing variables was calculated at the 1000th, 2000th, and 3000th hours. The results showed that the maximum deformation of the contact surface was 0.02mm, 0.05mm, and 0.09mm, respectively, predicting that the probability of seal failure would rise to 43% after 3300 hours.

[0053] This mapping simulation based on an integrated architecture not only realizes the behavior prediction under the real physical connection state, but also gives the secondary leakage model dynamic scalability, providing a feasible path for the full life cycle prediction of sealing performance in complex systems, and providing accurate model support for real-time risk control of intelligent operation and maintenance systems.

[0054] Furthermore, step S300 of the present application further includes step S330, which includes: Step S331: If it exists, perform repair decision analysis on the primary leakage point; Step S332: associate the repair decision with the reducer housing and mark it, then return it to the production line for repair control, and then perform primary sealing test.

[0055] Specifically, when the primary sealing test results show that there is a leak point in the reducer housing, the product will not be immediately judged as unqualified. Instead, a repair decision analysis process will be initiated. This process uses historical repair data based on an intelligent algorithm to classify the type, location, leakage intensity and potential impact range of the leak point, so as to determine whether it is repairable and the optimal repair strategy.

[0056] During the decision analysis process, an expert rule base is compared with a historical repair database, comprehensively considering repair cost, process complexity, and post-repair reliability. A repair plan is then output and assigned a repair level (e.g., "Repair Recommended," "Repair Required," or "Unrepairable"). A digital label is also generated, linking the repair decision to the unique serial number of the reducer housing. This label includes the leak point number, leak type, recommended repair measures, estimated repair time, and parameters requiring retesting.

[0057] This marking information is uploaded to the production line control system via the MES (Manufacturing Execution System), guiding process personnel or automated maintenance equipment to complete the repair control operation. Once the repair is complete, the box is automatically redirected to the primary seal test platform, where the hot air pressurization test and intelligent sensor detection process are repeated to verify that the repair meets factory standards.

[0058] Furthermore, step S400 of this application includes: Step S410: Monitor the operating environment in real time to generate real-time operating data; Step S420: Perform instantaneous fitness analysis of the sealing performance on the real-time operating data using the secondary leakage model through the first channel to generate a first performance monitoring result; Step S430: Continuously receive operating data at different times through the second channel, perform cumulative fitness analysis of the sealing performance using the secondary leakage model to generate a second performance monitoring result.

[0059] Specifically, to dynamically evaluate the reducer housing's sealing performance throughout its entire lifecycle, the operating environment requires high-frequency, real-time monitoring. This collected operating data is then fed into a secondary leakage model via two separate analysis channels. This architecture supports a multi-dimensional assessment of sealing status, ensuring the system can capture both transient anomalies and long-term trends of decline.

[0060] First, a real-time operating environment monitoring module is deployed at multiple key locations within the reducer housing. The sensor array covers multiple dimensions, including temperature, pressure, vibration, speed, and torque, with sampling periods accurate to the millisecond level. For example, a reducer on an industrial automation production line collects 120 data points per second when operating at full load, generating a real-time operating data stream that is processed at the edge and then transmitted to the backend model analysis module.

[0061] Through the first channel, this real-time data is immediately fed into the secondary leakage model, which performs an instantaneous fitness analysis of the sealing performance. This analysis, relying on a machine learning regression model and a stress-response coupling algorithm, maps the current operating state to the deformation and stress distribution of key sealing structures, thereby determining whether the sealing performance is still reliable at the current moment. For example, when the real-time vibration level suddenly rises to 5.8g and the internal temperature of the box rises by 11.4°C within one minute, the instantaneous fitness score quickly drops to 0.38. The system immediately determines it as "critically low," generates the first performance monitoring result, and triggers a rapid warning.

[0062] At the same time, through the second channel, the operating data at different times is continuously received in a time series manner and input into the same secondary leakage model to perform a cumulative fitness analysis of the sealing performance. This process uses a data sliding window and a stress history memory algorithm to merge the prediction results of each cycle with its previous state, dynamically simulating the evolution trajectory of the sealing failure variable under long-term operation. For example, a box experienced three overload conditions within 200 hours. The model recorded that the pre-tightening stress of its sealing ring decreased by 11%, the structural deformation accumulated to 0.07mm, and the cumulative fitness score dropped from the initial 0.92 to 0.56. Based on this, the system outputs the second performance monitoring result and determines that there is a downward trend in the medium and long-term sealing performance.

[0063] These two types of monitoring results—instantaneous and cumulative—not only provide a two-way view of the reducer housing's sealing status, both in the present and in the future, but also provide maintenance personnel with data to support preventive maintenance and intelligent scheduling. For example, the cumulative scoring curve can be used to predict the failure risk interval within the next 200 hours. This, combined with actual on-site plans, can intelligently schedule maintenance windows or adjust load strategies, ultimately achieving a data-driven seal reliability assurance mechanism.

[0064] Furthermore, step S430 of this application includes: Step S431: Using the secondary leakage model, perform sealing performance fitness and fitness rebound analysis on the operating data at different moments according to the time series relationship, use the rebound analysis results as the basis for the next moment analysis, perform sealing performance fitness and fitness rebound analysis again, and complete the cumulative fitness analysis.

[0065] Specifically, during the cumulative analysis of secondary leakage fitness, the operating data generated by the reducer housing at different time points is gradually analyzed based on the time series relationship to construct a dynamic model of the evolution of sealing performance over time. The core of this process lies in fitness rebound analysis, which not only analyzes the degradation trend of sealing performance at each moment, but also assesses whether there is a certain degree of performance recovery, thereby establishing a two-way evaluation framework that combines damage accumulation and state rebound.

[0066] First, the secondary leakage model receives a data stream from the operating environment. This data includes state parameters such as temperature, pressure, vibration, and speed at consecutive time points. At each time point, the model calculates the stress response, deformation amplitude, and changes in sealing material properties of the seal structure, outputting a seal performance fitness score. This score typically ranges from 0 (complete failure) to 1 (perfect health), reflecting the seal reliability at that time. A rebound analysis mechanism is introduced. After assigning a fitness score to the current operating data, the model further determines whether seal performance has temporarily or gradually recovered due to improved operating conditions (such as temperature drop, load reduction, or enhanced lubrication). For example, in one test, the fitness score dropped to 0.58 after sustained high load on the reducer housing at the 100th hour. Subsequently, operating conditions stabilized (load decreased by 17%, housing temperature dropped by 4.2°C), and the fitness score rebounded to 0.64 at the 120th hour. The rebound amplitude at this point was recorded as 0.06, indicating mild, reversible degradation.

[0067] This rebound amplitude and its rate of change serve as the initial input for the next moment's prediction, influencing the next round of fitness calculations and demonstrating a memory of the state history. A dynamic weighting strategy is also introduced to weight rebound effects over time: the influence of earlier rebounds gradually diminishes, ensuring the model's greater sensitivity to recent states. This creates a cumulative analysis mechanism with feedback and iteration capabilities. Each round of fitness and rebound analysis builds on the previous results, simulating the realistic evolution of the sealing state from "deterioration-relief-re-deterioration" in actual operation.

[0068] For example, a wind turbine gearbox was subjected to cumulative seal fitness monitoring over 1200 hours of continuous operation in a simulated sea breeze and high humidity environment. The initial score was 0.91, but after 400 hours, it dropped to 0.69 due to high-frequency vibration and condensation erosion. At 800 hours, the score rebounded to 0.76 due to load fluctuations and improved lubrication, but gradually declined to 0.52 by 1200 hours. Based on this, the model predicted that the seal fitness threshold might be approached at 1500 hours and recommended a maintenance inspection at 1300 hours.

[0069] By introducing fitness rebound analysis and constructing a time-dependent dynamic prediction chain, the system can not only characterize the downward trend of the sealing status, but also identify the stage of recoverability, enabling sealing performance management to move from single-point judgment to full life cycle modeling, significantly improving the ability to perceive sealing failure risks in advance and the decision-making support value.

[0070] In summary, the reducer housing sealing performance testing method based on the intelligent sensor provided in this application has the following technical effects: Collect data from various sealing test points of the reducer housing; build a primary sealing test platform based on intelligent sensors, perform primary leakage variable control and sealing detection on the various sealing test points, and generate primary sealing test results; perform factory verification based on the primary sealing test results, call the housing simulation model and secondary leakage variables after leaving the factory, perform simulation of secondary leakage variables, and generate a secondary leakage model; connect the secondary leakage model to the operating environment of the reducer housing, and perform secondary leakage fitness monitoring, including instantaneous fitness monitoring and cumulative fitness monitoring. By collecting the sealing test points of the reducer housing and combining intelligent sensors to build a primary sealing test platform, and using simulation modeling to build a secondary leakage model, dynamic prediction of sealing performance during operation is achieved, and finally, real-time evaluation of sealing status and grasp of degradation trends are achieved through fitness monitoring, thereby realizing intelligent detection and evolution monitoring of reducer sealing performance from factory to service, achieving the technical effect of improving sealing reliability and preventing leakage failures.

[0071] In the second embodiment, based on the same inventive concept as the reducer housing sealing performance test method based on the smart sensor in the above embodiment, the present application also provides a reducer housing sealing performance test system based on the smart sensor, please refer to the attached Figure 2 The reducer housing sealing performance test system based on the intelligent sensor includes: The test point collection unit 11 is used to collect the test points of the seals of the reducer housing.

[0072] The primary test unit 12 is used to build a primary sealing test platform based on the intelligent sensor, perform primary leakage variable control and sealing detection on each sealing test point, and generate a primary sealing test result.

[0073] The secondary simulation unit 13 is used to perform factory verification based on the primary sealing test results, call the box simulation model and secondary leakage variables after leaving the factory, perform simulation of the secondary leakage variables, and generate a secondary leakage model.

[0074] The secondary adaptation analysis unit 14 is used to connect the secondary leakage model to the operating environment of the reducer housing and perform secondary leakage fitness monitoring, including instantaneous fitness monitoring and cumulative fitness monitoring.

[0075] Furthermore, the primary test unit 12 in the reducer housing sealing performance test system based on intelligent sensors also includes: the primary sealing test platform includes a test variable control module and an intelligent sensor module; wherein, the test variable control module includes a hot air pressurization device connected to the reducer housing, and the intelligent sensor module includes an infrared imager and a hot air detection device.

[0076] Furthermore, the secondary simulation unit 13 in the reducer case sealing performance test system based on the intelligent sensor is also used to: analyze the primary sealing test results to determine whether there is a primary leakage point; if not, send the case simulation model and the secondary leakage variable to the application end of the reducer case, and perform a mapping simulation of the secondary leakage variables and the reducer case operating parameters on the application end to generate the secondary leakage model.

[0077] Furthermore, the secondary simulation unit 13 in the reducer case sealing performance test system based on the intelligent sensor is also used to: obtain the connection application structure and connection application mechanism of the reducer case; simulate and model the connection application structure to generate a connection application model; based on the application mechanism, perform collaborative connection between the case simulation model and the connection application model to generate an integrated architecture; use the integrated architecture to perform mapping simulation of the secondary leakage variables and the reducer case operating parameters to generate the secondary leakage model.

[0078] Furthermore, the secondary simulation unit 13 in the reducer case sealing performance test system based on intelligent sensors also includes: the secondary leakage variable includes the structural failure variable of the reducer case that causes sealing failure during operation, and the reducer case operating parameters are the operating state parameters of the reducer case during operation, wherein, in the mapping simulation process, the reducer case operating parameters are used as independent variables, and the secondary leakage variables are used as dependent variables, and the mapping simulation includes a single instantaneous simulation and multiple cumulative simulations.

[0079] Furthermore, the secondary simulation unit 13 in the reducer housing sealing performance test system based on the intelligent sensor is also used to: if any, perform a repair decision analysis of the primary leakage point; associate the repair decision with the reducer housing and mark it, then return it to the production line for repair control, and then perform a primary sealing test.

[0080] Furthermore, the primary test unit 12 in the reducer case sealing performance test system based on intelligent sensors is also used to: collect application constraints of the reducer case; configure a hot air pressurization scheme based on the application constraints; send the hot air pressurization scheme to the test variable control module for hot air pressurization step control, and when the control is stable, perform thermal difference detection and hot air detection inside and outside the case with the intelligent sensor module to generate a test result; perform sealing judgment based on the test result to generate the primary sealing test result.

[0081] Furthermore, the secondary adaptation analysis unit 14 in the reducer case sealing performance test system based on the intelligent sensor is also used to: monitor the operating environment in real time to generate real-time operating data; perform instantaneous fitness analysis of the sealing performance on the real-time operating data using the secondary leakage model through the first channel to generate a first performance monitoring result; continuously receive operating data at different times through the second channel, perform cumulative fitness analysis of the sealing performance using the secondary leakage model to generate a second performance monitoring result.

[0082] Furthermore, the secondary adaptation analysis unit 14 in the reducer housing sealing performance test system based on the intelligent sensor is also used to: perform sealing performance fitness and fitness rebound analysis on the operating data at different times according to the time series relationship using the secondary leakage model, use the rebound analysis results as the basis for analysis at the next moment, perform sealing performance fitness and fitness rebound analysis again, and complete the cumulative fitness analysis.

[0083] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1The reducer case sealing performance test method based on smart sensors and the specific examples in Example 1 are also applicable to the reducer case sealing performance test system based on smart sensors in this embodiment. Through the above detailed description of the reducer case sealing performance test method based on smart sensors, those skilled in the art can clearly understand the reducer case sealing performance test system based on smart sensors in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0084] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0085] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A method for testing the sealing performance of a reducer housing based on an intelligent sensor, characterized in that: include: Collect test data from various sealing points of the reducer housing; A primary sealing test platform is built based on intelligent sensors to perform primary leakage variable control and sealing detection on each sealing test point to generate primary sealing test results; Performing factory calibration based on the primary sealing test results, calling the box simulation model and secondary leakage variables after leaving the factory, performing simulation of the secondary leakage variables, and generating a secondary leakage model; The secondary leakage model is connected to the operating environment of the reducer housing, and secondary leakage fitness monitoring is performed, including instantaneous fitness monitoring and cumulative fitness monitoring.

2. The method for testing the sealing performance of a reducer housing based on an intelligent sensor according to claim 1, wherein: The primary sealing test platform includes a test variable control module and an intelligent sensor module; wherein, the test variable control module includes a hot air pressurizing device connected to the reducer housing, and the intelligent sensor module includes an infrared imager and a hot air detection device.

3. The method for testing the sealing performance of a reducer housing based on an intelligent sensor according to claim 1, wherein: Based on the primary sealing test results, a factory calibration is performed. After leaving the factory, the box simulation model is called to perform simulation of secondary leakage variables to generate a secondary leakage model, including: Analyze the primary sealing test results to determine whether there is a primary leak point; If it does not exist, the housing simulation model and the secondary leakage variables are sent to the application end of the reducer housing, and a mapping simulation of the secondary leakage variables and the reducer housing operating parameters is performed on the application end to generate the secondary leakage model.

4. The method for testing the sealing performance of a reducer housing based on an intelligent sensor according to claim 3, wherein: Performing a mapping simulation between the secondary leakage variables and the reducer housing operating parameters on the application side to generate the secondary leakage model includes: Obtaining the connection application structure and connection application mechanism of the reducer housing; Performing simulation modeling on the connection application structure to generate a connection application model; executing a collaborative connection between the cabinet simulation model and the connection application model based on the application mechanism to generate an integrated architecture; A mapping simulation between the secondary leakage variables and the speed reducer housing operating parameters is performed using the integrated architecture to generate the secondary leakage model.

5. The method for testing the sealing performance of a reducer housing based on an intelligent sensor according to claim 4, characterized in that: The secondary leakage variable includes the structural failure variable of the reducer housing that causes sealing failure during operation, and the reducer housing operating parameters are the operating state parameters of the reducer housing during operation. In the mapping simulation process, the reducer housing operating parameters are used as independent variables and the secondary leakage variable is used as the dependent variable. The mapping simulation includes a single instantaneous simulation and multiple cumulative simulations.

6. The method for testing the sealing performance of a reducer housing based on an intelligent sensor according to claim 2, wherein: Analyzing the primary sealing test results to determine whether a primary leak point exists also includes: If so, perform repair decision analysis on the primary leak point; The repair decision is associated with the reducer housing and marked, and then returned to the production line for repair control, and then a primary sealing test is performed.

7. The method for testing the sealing performance of a reducer housing based on an intelligent sensor according to claim 2, wherein: A primary sealing test platform is built based on intelligent sensors to perform primary leakage variable control and sealing detection on each sealing test point, and generate primary sealing test results, including: collecting application constraints of the reducer housing; configuring a hot air pressurization scheme based on the application constraints; The hot air pressurization scheme is sent to the test variable control module to perform hot air pressurization step control. When the control is stable, the intelligent sensor module is used to perform heat difference detection inside and outside the box and hot air detection to generate detection results; The sealing performance is judged based on the detection result to generate the primary sealing test result.

8. The method for testing the sealing performance of a reducer housing based on an intelligent sensor according to claim 1, wherein: Connecting the secondary leakage model to the operating environment of the reducer housing, performing secondary leakage fitness monitoring, including instantaneous fitness monitoring and cumulative fitness monitoring, including: Performing real-time monitoring on the operating environment to generate real-time operating data; performing an instantaneous fitness analysis of the sealing performance on the real-time operation data using the secondary leakage model through the first channel to generate a first performance monitoring result; The operation data at different times are continuously received through the second channel, and the cumulative fitness analysis of the sealing performance is performed using the secondary leakage model to generate a second performance monitoring result.

9. The method for testing the sealing performance of a reducer housing based on an intelligent sensor according to claim 8, wherein: Continuously receiving operating data at different times through the second channel, performing cumulative fitness analysis of the sealing performance using the secondary leakage model, and generating a second performance monitoring result, including: The secondary leakage model is used to perform sealing performance fitness and fitness rebound analysis on the operating data at different moments according to the time series relationship. The rebound analysis results are used as the basis for the next moment analysis, and the sealing performance fitness and fitness rebound analysis are performed again to complete the cumulative fitness analysis.

10. The reducer housing sealing performance test system based on intelligent sensor is characterized by: The method for testing the sealing performance of a reducer housing based on an intelligent sensor according to any one of claims 1 to 9 is configured to include: Test point collection unit, used to collect data from various sealing test points of the reducer housing; A primary test unit, configured to build a primary sealing test platform based on intelligent sensors, perform primary leakage variable control and sealing detection on each sealing test point, and generate primary sealing test results; A secondary simulation unit is used to perform factory verification based on the primary sealing test results, call the box simulation model and secondary leakage variables after leaving the factory, perform simulation of the secondary leakage variables, and generate a secondary leakage model; The secondary adaptation analysis unit is used to connect the secondary leakage model to the operating environment of the reducer housing and perform secondary leakage fitness monitoring, including instantaneous fitness monitoring and cumulative fitness monitoring.

Images