Equipment fault prediction method and device based on digital twinborn model

Abstract

The invention relates to an equipment fault prediction method and device based on a digital twin model. The method comprises the following steps: when an equipment monitoring twin model fails to detect an equipment fault, firstly obtaining the running state, temperature and load cycle data of equipment; and substituting the operation state data into the fixed fault and use fault calculation model to obtain corresponding fixed fault data and use fault data. Then, the fixed fault data are corrected according to the temperature data, and the fixed fault data after temperature correction are obtained; and correcting the use fault data according to the load cycle data to obtain the use fault data after load correction. And then, in combination with the fixed fault data of temperature correction and the use fault data of load correction, calculating failure data of the equipment on a use time axis, and further obtaining a failure curve of the equipment. And finally, extracting data points meeting a preset failure condition from the failure curve as equipment failure prediction information, so that the real-time performance and the accuracy in equipment failure prediction can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and device for predicting equipment failure based on a digital twin model. Background Art

[0002] In traditional technology, equipment failure prediction usually establishes the normal operation mode of the equipment by monitoring the operating parameters of the equipment (such as temperature, pressure, vibration, etc.) and comparing them with historical data. Once the parameters are detected to be deviated, the early warning mechanism is triggered. In addition, traditional methods also include experience-based failure mode analysis (such as fault tree analysis FMEA), periodic inspections and manual expert systems. Through regular inspections, data statistics and empirical rules, combined with the service life of the equipment and historical failure data, potential failure points are predicted, thereby achieving maintenance and preventive maintenance of the equipment. However, traditional technology often relies on empirical rules and manual inspections in equipment failure prediction, and it is difficult to handle complex and changing system environments, resulting in a lack of real-time and accuracy in the prediction of equipment failures. Summary of the invention

[0003] Based on this, it is necessary to provide a device failure prediction method, device, computer equipment, computer-readable storage medium and computer program product based on a digital twin model that can effectively improve the real-time and accuracy of device failure prediction in response to the above-mentioned technical problems.

[0004] In a first aspect, the present application provides a method for predicting equipment failures based on a digital twin model, comprising: When the equipment monitoring twin model fails to detect fault information of the target equipment, the equipment operation status data, equipment operation temperature data and equipment load cycle data of the target equipment are obtained; Substituting the equipment operation status data into the fixed fault calculation model and the usage fault calculation model of the target equipment respectively to obtain the target fixed fault data and the target usage fault data; Correcting the object fixed fault data according to the equipment operating temperature data to obtain temperature corrected fixed fault data; Correcting the object usage fault data according to the equipment load cycle data to obtain load corrected usage fault data; Calculating the failure data of the target device on the usage time axis according to the temperature-corrected fixed failure data and the load-corrected usage failure data to obtain a device failure curve; Data points that meet preset failure conditions are extracted from the equipment failure curve as equipment failure prediction information of the target equipment.

[0005] In a second aspect, the present application also provides a device for predicting equipment failures based on a digital twin model, comprising: The equipment data acquisition module is used to obtain the equipment operation status data, equipment operation temperature data and equipment load cycle data of the target equipment when the equipment monitoring twin model fails to detect the existence of fault information of the target equipment; A fault data calculation module, used to substitute the equipment operation status data into the fixed fault calculation model and the usage fault calculation model of the target equipment respectively, to obtain the target fixed fault data and the target usage fault data; A fault data correction module, used for correcting the object fixed fault data according to the equipment operation temperature data to obtain temperature corrected fixed fault data; The fault data correction module is further used to correct the object usage fault data according to the equipment load cycle data to obtain load corrected usage fault data; A failure curve generating module, used to calculate the failure data of the target device on the usage time axis according to the temperature-corrected fixed failure data and the load-corrected usage failure data, and obtain a device failure curve; The equipment failure prediction module is used to extract data points that meet preset failure conditions from the equipment failure curve as equipment failure prediction information of the target equipment.

[0006] In a third aspect, the present application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements any step of a device fault prediction method based on a digital twin model.

[0007] The above-mentioned equipment fault prediction method, device and computer equipment based on the digital twin model, by inputting the equipment operation status data into the fixed fault calculation model and the use fault calculation model respectively, generates the object fixed fault data and the object use fault data of the object equipment, and then uses the temperature data of the equipment to perform temperature correction on the fixed fault data, and uses the load cycle data to perform load correction on the use fault data, so as to more accurately reflect the failure trend of the equipment under different working environments; further use the two corrected fault data to calculate the failure curve of the equipment, and extract the fault prediction information that meets the preset failure conditions from it, so as to realize the early warning of equipment failure. Through the above-mentioned fault prediction mechanism, the real-time and accuracy of the prediction of equipment faults can be effectively improved, the reliability of equipment operation can be further significantly improved, the maintenance and overhaul cycle can be optimized, the downtime caused by sudden faults can be reduced, the maintenance cost can be reduced, and the operation and maintenance efficiency of the overall equipment can be improved, thereby providing a strong guarantee for the long-term stable operation of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0009] Figure 1 is an application environment diagram of a device fault prediction method based on a digital twin model in an embodiment; Figure 2 Schematic diagram of a process of predicting equipment failure based on a digital twin model in one embodiment; Figure 3 A schematic flow chart of a method for obtaining temperature-corrected fixed fault data in one embodiment; Figure 4 A flow chart of a method for obtaining fault data using load correction in one embodiment; Figure 5 A schematic flow chart of a method for obtaining a first device failure curve in an embodiment; Figure 6 It is a schematic flow chart of a method for obtaining a second device failure curve in one embodiment; Figure 7 A schematic flow chart of a method for obtaining a third device failure curve in one embodiment; Figure 8 is a structural block diagram of a device for predicting equipment failure based on a digital twin model in one embodiment; Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0010] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0011] The device fault prediction method based on the digital twin model provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 101 communicates with the server 102 through the network. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or it can be placed on the cloud or other network servers. Among them, the server 102 can be implemented with an independent server or a server cluster composed of multiple servers.

[0012] In an exemplary embodiment, Figure 2 As shown in the figure, a device fault prediction method based on digital twin model is provided. Figure 1 The server in the example is used to illustrate, including the following steps 201 to 206. Among them: Step 201, when the equipment monitoring twin model fails to detect the existence of fault information of the target equipment, the equipment operation status data, equipment operation temperature data and equipment load cycle data of the target equipment are obtained.

[0013] Among them, the equipment monitoring twin model can be a virtual simulation model of the object equipment. By acquiring the data of the physical equipment in real time, it generates a corresponding digital model to simulate the operating status and behavior of the equipment.

[0014] The target device may be a specific device or mechanical system that is studied, analyzed or repaired during the monitoring and prediction process.

[0015] Among them, fault information can be indicative data of any abnormal state or performance degradation that may occur in the equipment during operation, usually including the type of equipment fault, the time of occurrence, the scope of impact and its impact on production or operation.

[0016] Among them, the equipment operation status data can be various real-time data describing the current working conditions of the equipment, including parameters such as the equipment's operating speed, torque, power, vibration, and pressure.

[0017] The equipment operating temperature data may be temperature data recorded in real time by various components of the equipment during operation.

[0018] The equipment load cycle data may be a record of load changes over time during the operation of the equipment, including the load intensity, frequency and change pattern borne by the equipment in different time periods.

[0019] Specifically, when the equipment monitoring twin model fails to find fault information of the target equipment, the real-time operation status data, equipment operation temperature data and load cycle data of the target equipment are obtained through the data acquisition system. The real-time operation status data reflects the current working condition of the equipment, the equipment operation temperature data provides the thermal state of the equipment in the working environment or the working environment for a period of time before, and the equipment load cycle data reflects the operation cycle characteristics of the equipment under different load conditions.

[0020] Step 202 , the equipment operation status data is substituted into the fixed fault calculation model and the usage fault calculation model of the target equipment respectively, to obtain the target fixed fault data and the target usage fault data.

[0021] Among them, the fixed fault calculation model can be used to predict the failure of equipment in long-term operation due to factors such as material aging, fatigue, corrosion, etc.

[0022] The fault calculation model used may be a model for predicting the occurrence of faults in a device under actual workload and operating conditions.

[0023] Among them, the object fixed fault data can be the fault data obtained after substituting the operating status data of the equipment into the fixed fault calculation model. It represents the potential failure risk of the equipment within a specific time period, which is caused only by fixed factors such as material aging and fatigue.

[0024] Among them, the object usage fault data can be the fault data obtained after substituting the operating status data of the equipment into the usage fault calculation model. It reflects the impact of the equipment's actual operating conditions on the occurrence of faults, including the risk of faults caused by overload, long-term high-load operation, frequent start and stop and other factors.

[0025] Specifically, the equipment operation status data based on the equipment (such as operation time, load conditions, vibration, speed, etc.) is substituted into the fixed fault calculation model. The fixed fault calculation model assumes that the equipment components will gradually be damaged due to factors such as material aging, fatigue, corrosion, etc. during long-term operation, and the fixed fault data of the equipment is generated. This part of the fault is usually not affected by the use environment, but is more related to time and the degree of equipment aging. At the same time, the equipment operation status data of the equipment (such as operation time, load conditions, vibration, speed, etc.) is also substituted into the use fault calculation model. The use fault calculation model takes into account the working conditions of the equipment under different loads and environments, and can estimate the use fault data caused by the operating conditions (such as overload, frequent start and stop, etc.) of the equipment. These faults are usually closely related to the working intensity, use frequency and operation mode of the equipment. Through the calculation of these two models, the object fixed fault data and object use fault data can be obtained respectively.

[0026] Step 203, correcting the object fixed fault data according to the equipment operating temperature data to obtain temperature corrected fixed fault data.

[0027] Among them, temperature correction of fixed fault data can be to consider the operating characteristics of the equipment at different temperatures and correct the fault data of the equipment. Especially in high temperature environments, the aging and fatigue processes of the equipment are usually accelerated. Therefore, temperature correction can more accurately reflect the failure risk of the equipment in the actual temperature environment.

[0028] Specifically, in the process of equipment failure prediction, the equipment operating temperature is an important factor, because high temperature environment will accelerate the aging and damage of equipment components, especially thermal fatigue, material expansion, chemical reaction and other phenomena. Therefore, the Arrhenius model is used to quantify the impact of equipment operating temperature on the failure rate. The Arrhenius model is based on the relationship between temperature and chemical reaction rate. It is assumed that the rate of equipment failure will increase exponentially with each increase in temperature. In the specific implementation, the actual operating temperature data of the equipment will be used as input and passed to the temperature factor in the Arrhenius model. By calculating the impact of temperature on the failure rate, the fixed failure data of the equipment is adjusted. That is, the operating state of the equipment at different temperatures may cause changes in the physical and chemical properties of the material. For example, metal materials may accelerate lattice fatigue in high temperature environments, plastic materials may soften or age, and lubricants may also degrade at high temperatures, thereby affecting the life and reliability of equipment components. Therefore, the Arrhenius model will be corrected according to the impact of temperature on the failure rate based on the current operating temperature of the equipment. When the equipment is in a higher temperature environment, the model will increase the probability of failure, reflecting the accelerated damage caused by high temperature; conversely, when the temperature is lower, the failure rate will be reduced accordingly. The Arrhenius model is used to correct the fixed fault data so that it can accurately reflect the actual occurrence of equipment failures under different temperature conditions and obtain temperature-corrected fixed fault data.

[0029] Step 204, correcting the object usage fault data according to the equipment load cycle data to obtain load corrected usage fault data.

[0030] Among them, load correction using fault data can be to substitute the working data of the equipment under different load cycle conditions into the load correction model, adjust the original fault data, and reflect the actual fault risk of the equipment under high load, frequent load change and other working environments. This correction helps to accurately predict the occurrence of equipment failures under complex use conditions.

[0031] Specifically, equipment load cycle data is an important factor in equipment use failure, because equipment often experiences different degrees of load changes in actual operation, which will affect its fatigue life and failure mode. When using equipment load cycle data to correct use failure data, the Coffin–Manson model is used to consider the influence of load on equipment fatigue behavior. The Coffin–Manson model is mainly used to describe the process of fatigue damage and crack propagation of materials under alternating load conditions. Specifically, the Coffin–Manson model calculates the acceleration of fatigue life and crack propagation by considering factors such as the amplitude and frequency of load-corrected use failure data. The core of the model is to establish the failure law of equipment under load conditions based on the relationship between load-corrected use failure data and the plastic deformation of the material. When the load cycle of the equipment increases, the fatigue accumulation of the material and the development speed of microcracks will accelerate, causing the equipment to fail earlier. Therefore, by inputting the load cycle data of the equipment into the Coffin–Manson model, the use failure data can be accurately corrected to reflect the possibility of equipment failure under working conditions such as high load, frequent start-up and shutdown or vibration. The corrected data more realistically reflects the fatigue damage process of the equipment under different loads, helps to improve the accuracy of fault prediction, and provides a scientific basis for equipment maintenance and management.

[0032] During the actual operation, the equipment will experience different load cycles and generate equipment load cycle data. The amplitude and frequency of the equipment load cycle data directly affect the fatigue damage of the equipment components. In order to accurately evaluate the failure risk of the equipment under different load conditions, the Coffin–Manson model is used to correct the use failure data. Starting from the fatigue mechanism of the material, this model believes that when the equipment is subjected to alternating loads, plastic deformation and cumulative extension of microcracks will occur, especially under high loads or frequent load changes, the fatigue damage of equipment components will accelerate. Therefore, the Coffin–Manson model considers not only the amplitude of the load (the intensity of the load change), but also the frequency of the load (the rate of load change), because the larger the load amplitude, the more severe the plastic deformation and crack extension of the components, and the faster the accumulation of fatigue damage; the higher the load frequency, the more load cycles the equipment experiences per unit time, thereby aggravating the fatigue process and causing crack extension and failure to occur in advance. Specifically in the implementation process, by collecting the equipment load cycle data of the equipment, analyzing its load amplitude, frequency and number of cycles, and then substituting these data into the Coffin–Manson model, the model will calculate the fatigue life of the equipment components and the acceleration of crack propagation based on these load characteristics, reflecting the specific development of equipment fatigue damage under different working load conditions, and then correcting the original object usage failure data to obtain temperature-corrected fixed failure data, so that the prediction of the impact of load on equipment failure is more accurate, especially in scenarios with large load fluctuations or long-term high-load operation, it can identify the potential fatigue failure risk of the equipment in advance, and optimize the equipment maintenance cycle and fault warning mechanism.

[0033] In a specific embodiment, assume that a device is running in a factory, and the load cycle data of the device shows that when the device is working under high load, the load amplitude reaches the maximum value, and the load changes 20 times per hour (that is, the load frequency is high). Based on these data, the actual load conditions of the equipment are first recorded, such as the fluctuation range and change frequency of each load. Then, these load data are input into the Coffin–Manson model, and the model calculates the effect of each load cycle on the plastic deformation and fatigue accumulation of the equipment components based on different combinations of load amplitude and frequency. For example, if the equipment is running under high load for a long time, the model may show that the crack propagation rate caused by the high load amplitude is accelerated, and the higher load frequency further aggravates the accumulation of fatigue damage. The final model corrects the object use failure data based on these calculation results, so that the predicted equipment failure time is more consistent with the actual load condition.

[0034] Step 205 , calculate the failure data of the target equipment on the usage time axis according to the temperature-corrected fixed failure data and the load-corrected usage failure data, and obtain the equipment failure curve.

[0035] The usage timeline may be the accumulated time data of all time periods from when the equipment is put into use to when it is set to be used.

[0036] The failure data may be the probability of a possible equipment failure predicted by a calculation model, and each probability data may be matched with a corresponding time, frequency and type.

[0037] Among them, the equipment failure curve can be a graphical representation of the probability of equipment failure at different time points or under different usage conditions. It usually takes time or usage cycle as the horizontal axis and the equipment failure probability or failure rate as the vertical axis, depicting the trend and possibility of equipment failure during the entire use process, with the passage of time or the change of usage load, and marking the corresponding time, frequency and type on each data point on the vertical axis.

[0038] Specifically, based on the temperature-corrected fixed fault data, the temperature-corrected fixed fault data is integrated by taking each usage time data point on the usage time axis of the equipment as the integral upper limit, and the integral results of all usage time data points are used to establish the failure probability curve of fixed faults; this curve reflects the probability of failure of the equipment under different temperature environments as the usage time increases. Similarly, using the load-corrected usage fault data, the temperature-corrected fixed fault data is integrated by taking each usage time data point on the usage time axis of the equipment as the integral upper limit, and the failure probability curve of usage fault is calculated, which represents the failure probability of the equipment under different load conditions. These two curves represent the failure behavior of the equipment under the influence of two different factors, temperature and load, respectively, but they are calculated separately based on different correction data. In order to obtain a more comprehensive failure prediction, the two failure probability curves are synthesized by the curve superposition method. Specifically, the superposition method synthesizes the failure probabilities of the two curves on the time axis, comprehensively considering the joint influence of temperature and load on equipment failure, and thus obtaining a comprehensive failure probability curve.

[0039] Step 206: extracting data points that meet preset failure conditions from the equipment failure curve as equipment failure prediction information for the target equipment.

[0040] The preset failure condition may be a specific standard set based on equipment operating characteristics, historical failure data, or factory preset conditions to determine whether the equipment is close to failure.

[0041] Among them, the equipment failure prediction information can be the prediction result generated by analyzing the equipment's operating data, environmental impact, and corrected failure data, including the time point when the equipment may fail in the future, the failure type, and the probability of the failure occurring.

[0042] Specifically, preset failure conditions are set according to the target equipment, such as the critical probability of equipment failure (for example, when the equipment failure probability reaches a certain threshold), when the remaining life of the equipment is lower than a certain value, or the acceleration interval of the failure, and data points that meet the preset failure conditions are extracted from the equipment failure curve. In the extraction process, the absolute value of the failure probability, the speed and trend of the failure occurrence, such as the sharp rise interval of the failure probability, are considered to obtain initial fault prediction information. In addition, all the initial fault prediction information extracted in the previous step is further combined with the actual use environment and historical maintenance data of the equipment for further refined screening to ensure that only data points closely related to the current working conditions and historical performance of the equipment are extracted as equipment fault prediction information.

[0043] In the above-mentioned equipment fault prediction method based on the digital twin model, the equipment operation status data is input into the fixed fault calculation model and the usage fault calculation model respectively to generate the object fixed fault data and the object usage fault data of the object equipment, and then the temperature data of the equipment is used to perform temperature correction on the fixed fault data, and the load cycle data is used to perform load correction on the usage fault data, so as to more accurately reflect the failure trend of the equipment under different working environments; the two corrected fault data are further used to calculate the failure curve of the equipment, and the fault prediction information that meets the preset failure conditions is extracted from it, so as to realize early warning of equipment failure. The above-mentioned fault prediction mechanism can effectively improve the real-time and accuracy of equipment fault prediction, further significantly improve the reliability of equipment operation, optimize maintenance and overhaul cycles, reduce downtime caused by sudden failures, reduce maintenance costs, and improve the overall equipment operation and maintenance efficiency, thereby providing a strong guarantee for the long-term stable operation of the equipment.

[0044] In an exemplary embodiment, Figure 3 As shown, the object fixed fault data is corrected according to the equipment operating temperature data to obtain the temperature corrected fixed fault data, including steps 301 to 302. Among them: Step 301, determining life simulation environment parameters and life simulation duration parameters corresponding to the accelerated life simulation according to the equipment operating temperature data and the object fixed fault data.

[0045] Among them, life simulation environmental parameters can be various variables used to simulate the actual working environment conditions of the equipment during accelerated life testing. These parameters include external factors such as temperature, humidity, vibration, load, etc., which directly affect the aging speed and failure mode of the equipment. Especially in terms of temperature, the working conditions of the equipment at high temperatures usually lead to accelerated material aging, so temperature is a key environmental parameter in life simulation.

[0046] Among them, the life simulation duration parameter can be used in the accelerated life test to simulate the length of time the device runs under specific environmental conditions. Unlike the actual use time, the life simulation time is usually calculated based on the acceleration factor, with the purpose of quickly obtaining the trend of device aging and failure by shortening the test time. For example, in a high temperature environment, the aging process of the device will be accelerated, and the simulation time will be set according to this acceleration ratio.

[0047] Specifically, since the life simulation environment parameters usually involve the temperature stress to which the equipment is subjected, the influence of high temperature on the equipment material is taken into account (for example, the accelerated effect of temperature on metal fatigue, plastic aging, etc.), and these temperature data are mapped to an acceleration factor to simulate the working conditions in a high temperature environment. Specifically, when the temperature is high, the failure rate of the equipment will accelerate. Therefore, the model will be adjusted according to the temperature difference and an acceleration factor will be set. This factor is usually calculated by a temperature-related model such as the Arrhenius equation to reflect the influence of temperature on the aging process of the equipment. Therefore, according to the equipment operating temperature data and the object fixed fault data, the specific range of the life simulation environment parameters corresponding to the accelerated life simulation is determined. At the same time, based on the expected aging of the equipment at a specific temperature, an accelerated use time is usually set to simulate the "accelerated use cycle" that the equipment has gone through in this high temperature environment as the life simulation duration parameter to ensure that the simulation duration can reflect the failure trend of the equipment under actual high temperature conditions.

[0048] Step 302 , performing accelerated life simulation on the target device according to the life simulation environment parameters and the life simulation duration parameters, and obtaining temperature-corrected fixed fault data.

[0049] Among them, accelerated life simulation can be a test method that predicts the long-term service life of equipment by artificially accelerating the aging process of the equipment. By artificially increasing environmental factors such as temperature and load in a laboratory environment, the use of the equipment under extreme conditions is simulated, thereby accelerating the aging process of the equipment and revealing the possible failure modes and failure times of the equipment in advance.

[0050] Specifically, in the process of accelerated life simulation, the aging process experienced by the device in a short period of time is simulated by placing the device in a high temperature environment or simulating high temperature conditions (for example, by heating the device or controlling the ambient temperature). At this time, the working state, temperature, load and other factors of the device will be dynamically monitored, and the operating conditions will be set to be more stringent than the conventional working environment to accelerate the aging process of the device. By performing accelerated testing on the device, the device can complete the failure mode that may occur during long-term use in a short period of time, and then calculate the failure probability, failure rate and other indicators of the device under these temperature conditions. All data will generate a temperature-corrected fixed fault data set, which represents the impact of temperature changes on the occurrence of faults in the actual work of the device. It usually includes continuous monitoring of various key indicators in the operation of the device, such as temperature, pressure, vibration, etc., recording and analyzing the occurrence time and frequency of equipment failures. Finally, the temperature-corrected fixed fault data obtained through simulation can provide a more accurate basis for the future fault prediction of the device, truly reflect the accelerating effect of temperature on the life of the device, and provide more detailed and accurate input for the subsequent fault prediction model.

[0051] The calculation expression for temperature-corrected fixed fault data in accelerated life simulation or actual production work is: in, Fixed fault data for the object, is the initial inherent fault data, which is obtained through the user manual of the equipment. The data in the user manual is obtained by the equipment manufacturer through testing the equipment. T(t) is the time at which the object equipment t Equipment operating temperature data, The coefficient of influence of temperature on inherent failure data is determined by studying the influence of temperature on equipment through accelerated aging test in the laboratory. The time-dependent degradation coefficient of the target device is determined by simulating extreme working conditions (such as high temperature, high load, etc.) of the device through accelerated life testing. is the activation energy, is the Boltzmann constant, T is the temperature, is the load or stress, H is the humidity, It is the sensitivity coefficient of load to inherent failure data, which is determined by laboratory material fatigue tests (such as uniaxial tension tests and cyclic loading tests) to determine the changes in failure rates of different materials under different loads. The sensitivity coefficient of humidity to inherent fault data is determined by studying the effect of humidity on equipment through laboratory humidity accelerated aging tests. is the load effect, is the humidity effect, is the temperature effect, is the Arrhenius model fault data, Fixed glitched data for temperature correction.

[0052] In this embodiment, by determining the environmental parameters and duration parameters of the accelerated life simulation based on the equipment operating temperature data and fixed fault data, the failure process of the equipment under extreme conditions such as high temperature can be simulated in a relatively short time. The accelerated life simulation effectively reduces the time and cost required in actual testing, and can more quickly evaluate the impact of temperature on fixed faults of the equipment. Further, by obtaining temperature-corrected fixed fault data, it helps predict the long-term stability and reliability of the equipment in the actual operating environment, thereby discovering potential failure risks in advance, optimizing maintenance plans, extending the service life of the equipment, and improving the operating safety and economy of the equipment.

[0053] In an exemplary embodiment, Figure 4 As shown, the object usage fault data is corrected according to the equipment load cycle data to obtain the load corrected usage fault data, including steps 401 to 402. Among them: Step 401, determining usage simulation environment parameters and usage simulation mechanical parameters corresponding to usage fatigue simulation according to equipment load cycle data and object usage failure data.

[0054] Among them, fatigue simulation can be a computer simulation method based on actual working loads and environmental conditions to predict fatigue damage caused by repeated loads during long-term use of equipment. This simulation simulates the stress and strain response of the equipment material and the accumulation process of fatigue cracks by exposing the equipment to load cycles. Through repeated loading, the damage evolution of the equipment under various load conditions is simulated, and its fatigue life is finally predicted.

[0055] The use simulation environment parameters can be the working environment conditions of the equipment set during the use fatigue simulation, including factors such as load amplitude, load frequency, working temperature, humidity, etc. These environmental parameters reflect the working state and external conditions experienced by the equipment in actual use, and they have an important impact on the fatigue life and failure mode of the equipment.

[0056] Among them, the simulated mechanical parameters can be parameters related to the mechanical properties of materials involved in fatigue simulation, such as the yield strength, fatigue limit, elastic modulus, stress-strain relationship, etc. of the material. These parameters reflect the mechanical behavior of the equipment material under different stress conditions and determine the accumulation rate and failure mode of its fatigue damage. By inputting these mechanical parameters into the fatigue simulation, the stress distribution of the equipment under load, the fatigue crack propagation of the material and the final failure point can be accurately predicted.

[0057] Specifically, according to the equipment load cycle data of the target equipment and the object usage failure data, the load amplitude, load cycle frequency and duration experienced by the equipment in actual work are analyzed to determine the load fluctuation pattern and its impact on equipment fatigue damage. Large load amplitude and high frequency usually accelerate equipment fatigue damage, so these factors will directly determine the loading conditions in the simulation. At the same time, by combining the object usage failure data, the actual failure prediction of the equipment under different load conditions without correction is understood, so as to calculate the initial simulation parameters and make the simulation more in line with the use status of the equipment in real working conditions. In addition, it is necessary to consider the impact of external environmental factors such as temperature and humidity on equipment fatigue characteristics, and fine-tune the initial simulation parameters to obtain the usage simulation environment parameters.

[0058] At the same time, key working condition information is extracted from the load cycle data of the equipment, such as the load amplitude, load cycle frequency, load change mode (such as sine wave, impact loading, etc.) experienced by the equipment, and the distribution of these loads in the operating cycle. These working condition information reflects the load fluctuation characteristics of the equipment in actual use and is the core input for evaluating fatigue damage. Further based on the working environment and material properties of the equipment, the use of simulated mechanical parameters is determined, including the yield strength, fatigue limit, elastic modulus, stress-strain curve, etc. of the material. These mechanical parameters are crucial for predicting the fatigue behavior of the material under repeated loading. For example, the fatigue life of the material usually shortens with the increase of the frequency and amplitude of the load. By integrating the load cycle data, using the simulated environment parameters and using the simulated mechanical parameters, a fatigue simulation environment is constructed, which will reflect the behavior of the equipment under the actual working load. In the process of using fatigue simulation, fatigue analysis methods such as rain flow counting method, SN curve or FEM (finite element analysis) model are usually used.

[0059] Step 402, performing usage fatigue simulation on the target equipment according to the usage simulation environment parameters and the usage simulation mechanical parameters, and obtaining load-corrected usage failure data.

[0060] Specifically, according to the use simulation environment parameters and the use simulation mechanical parameters, the actual use fatigue simulation phase is entered. At this time, the equipment load cycle data of the equipment is combined with the material mechanical parameters through computer simulation software or based on the rain flow counting method, SN curve or FEM (finite element analysis) and other methods to simulate the fatigue damage of the equipment under repeated loads. The simulation process simulates multiple cycles of load, calculates the stress and strain effects of each load on the internal materials of the equipment, and gradually accumulates damage. For example, under high loads, microcracks may appear in equipment components, and with more load cycles, these cracks will gradually expand and cause equipment failure. Through simulation, the degree of fatigue damage experienced by the equipment in long-term use can be quantified, and the fatigue life of each component and the time when the failure occurs can be obtained. The simulation results will generate load-corrected use failure data, which accurately reflects the potential failure risk caused by fatigue damage to the material due to load cycles under actual working conditions. The load-corrected use failure data is more in line with the actual use environment of the equipment than the uncorrected data.

[0061] The calculation expression for load correction using failure data in fatigue simulation or actual production work is: in, Use fault data for objects, is the initial use failure data, which is obtained by statistically analyzing the usage of other devices with the same usage environment and usage methods. T(t) is the failure rate of the target device at time t Equipment operating temperature data, The coefficient of influence of temperature on the failure data is determined by studying the influence of temperature on the equipment through the temperature accelerated aging test in the laboratory. It is the time-dependent degradation coefficient of the target device, which is determined by simulating extreme working conditions (such as high temperature, high load, etc.) of the device through accelerated life testing. T is the temperature. is the load or stress, H is the humidity, The sensitivity coefficient of humidity to the use failure data is determined by conducting humidity accelerated aging tests in the laboratory to study the effect of humidity on the equipment. is the equipment load cycle data, The failure data of the target equipment degrades over time. is the time degradation rate, obtained by fitting the usage of other devices with the same usage environment and usage method, is the correction factor related to the equipment load cycle data, is a material constant, obtained by performing fatigue strain tests (such as tension-compression cycle tests) on the material in the laboratory. is the influence coefficient of temperature on the strain of equipment material, which is determined by fatigue test under temperature change in the laboratory. The coefficient of influence of load on the strain of equipment material is determined by the influence of load amplitude on strain in fatigue tests under different loads. is the coefficient of influence of humidity on the strain of the equipment material, which is determined by the influence on the equipment in the humidity accelerated test. c is the Coffin–Manson constant, which is obtained through experimental testing. The experiment usually includes a low-cycle fatigue test on the material and records the fatigue life of the material at different strain amplitudes. is the total strain amplitude, Use fault data for load correction.

[0062] In this embodiment, by determining the environmental parameters and mechanical parameters for fatigue simulation based on the equipment load cycle data and the use failure data, the fatigue behavior of the equipment under long-term load can be accurately simulated under conditions closer to the actual working conditions. This simulation can reveal the specific impact of load fluctuations, frequent fluctuations and the physical response of the equipment on the occurrence of failures, so as to better understand the accumulation of fatigue damage during the actual use of the equipment. The load-corrected use failure data obtained through this process can effectively supplement the deficiencies of traditional fault prediction models, provide more accurate fault prediction results, help identify potential faults caused by load cycles in advance, optimize equipment maintenance cycles, reduce sudden failures and downtime, and improve equipment reliability and service life.

[0063] In an exemplary embodiment, Figure 5 As shown, according to the temperature-corrected fixed fault data and the load-corrected usage fault data, the failure data of the target device on the usage time axis is calculated to obtain the device failure curve, including steps 501 to 503. Among them: Step 501 , using each usage duration data point on the usage time axis as each integral upper limit value, respectively integrates the temperature-corrected fixed fault data and the load-corrected usage fault data to obtain each integral fixed fault data and each integral usage fault data.

[0064] Among them, the usage time data point can be each time node in the entire process from the equipment being put into use to the occurrence of a failure or the end of operation. It is located on the usage timeline, and each data point represents the operating status of the equipment at a specific time, such as hours, days or months.

[0065] Among them, the integrated fixed fault data can be the result of cumulative calculation of the temperature-corrected fixed fault data based on the equipment's usage time data points. At each time data point, the integration is used to reflect the cumulative risk of fixed faults of the equipment during that time period. The integration process reflects the accumulation of the probability of fixed faults of the equipment over time.

[0066] Among them, the integrated usage failure data can be the result of accumulating the load-corrected usage failure data based on the equipment usage time data points. Unlike the fixed failure data, the usage failure is usually related to the load cycle that the equipment is subjected to during operation. The process of integrating the usage failure data reflects the fatigue damage and failure risk probability gradually accumulated by the equipment under different load cycles.

[0067] Specifically, the service timeline of the equipment is defined with the life simulation duration parameter as the reference duration, where the service timeline covers the entire time period from the start of operation to the occurrence of the fault. Since the adequacy of the service timeline is guaranteed, the time length of the service timeline is greater than the service simulation duration. Each data point on the service timeline represents the operation time of the equipment at a certain moment, such as hours, days, months, etc. These duration data points will be used as the upper limit of the integral to calculate the cumulative faults of the equipment at different time points. The specific operation is to associate the temperature-corrected fixed fault data and the load-corrected usage fault data with each duration point on the timeline respectively. The integration process is to sum the temperature-corrected fixed fault data and the load-corrected usage fault data of the equipment in each time period respectively, indicating the cumulative fault impact on the equipment during this period. Through integration, the failure risk probability and cumulative damage value of the equipment under different usage durations can be obtained, and each integral fixed fault data and each integral usage fault data can be obtained.

[0068] Step 502 , fitting each integrated fixed fault data and each integrated usage fault data respectively to obtain a fixed fault fitting curve and a usage fault fitting curve.

[0069] The fixed fault fitting curve may be a curve obtained by mathematically fitting the integrated fixed fault data, and is used to describe the damage accumulation trend caused by the fixed fault of the equipment under specific operating conditions.

[0070] The usage fault fitting curve may be a curve obtained by mathematically fitting the integrated usage fault data, which indicates the fault accumulation trend caused by fatigue damage during the load cycle of the equipment.

[0071] Specifically, since the temperature-corrected fixed fault data and the load-corrected used fault data need to be fitted respectively, an appropriate mathematical fitting model (such as an exponential model, a power law model or a polynomial fitting) is selected to represent the relationship between the data and time. These models will use the least squares method or other optimization algorithms to find the best fitting curve so that the fitting curve can fit the actual fault data as closely as possible. The obtained fixed fault fitting curve and used fault fitting curve respectively describe the fault evolution process of the equipment under the influence of temperature and load.

[0072] Step 503: superimpose the fixed fault fitting curve and the working fault fitting curve to obtain the equipment failure curve.

[0073] Specifically, the key to superimposing the fixed fault fitting curve and the use fault fitting curve is to calculate how the temperature and load effects of the equipment fault work together and accumulate at each time node. In order to more accurately reflect the joint effects of the temperature and load correction factors, a nonlinear superposition mechanism is required, which takes into account the complex interaction between different types of faults (such as fixed faults and use faults). In this process, the fault data of each fitting curve needs to be normalized first to eliminate the dimensional differences and impact strength differences between different fault types. Then, by establishing a weight coefficient or correction factor, the addition method at each time point is dynamically adjusted according to the working state, load conditions and temperature changes of the equipment; especially in the case of interaction between load and temperature, this addition is not just a simple mathematical summation, but also requires the introduction of multiplication factors or exponential superposition. These factors can be adjusted according to the historical fault data of the equipment and the actual working conditions, so that under extreme load or temperature conditions, the increase in fault risk shows a more significant nonlinear growth trend, and the equipment failure curve is obtained.

[0074] In this embodiment, by taking each time data point on the usage time axis as the upper limit of integration, integrating the temperature-corrected fixed fault data and the load-corrected usage fault data, the accumulated faults under different usage times can be obtained, which can more accurately reflect the fault development trend of the equipment during long-term use. Further, by fitting the integrated data, the fitting curves of fixed faults and usage faults can be obtained, which can provide a more accurate prediction model for equipment failure. By superimposing these two fitting curves, the final equipment failure curve can comprehensively consider the impact of temperature and load cycle on equipment life, thereby providing a comprehensive reference for fault prediction. It can identify possible faults that may occur in the future use cycle of the equipment in advance, optimize maintenance and replacement plans, reduce the risk of equipment downtime, and improve the operational reliability and safety of the equipment.

[0075] In an exemplary embodiment, Figure 6As shown, the fixed fault fitting curve and the use fault fitting curve are superimposed to obtain the equipment failure curve, including steps 601 to 602. Among them: Step 601 , performing correlation analysis on the fixed fault fitting curve and the used fault fitting curve to determine curve correlation data.

[0076] Among them, correlation analysis can be a statistical method to explore the relationship and mutual influence between two or more variables. In equipment failure prediction, correlation analysis is used to study the relationship between temperature-corrected fixed failure data and load-corrected operating failure data, with the aim of identifying their joint role in the equipment failure process.

[0077] The curve correlation data may be the result of correlation analysis, which reflects the relationship and influence degree between the fixed fault fitting curve and the use fault fitting curve. These data include the correlation coefficient of the two curves at different time points, the interaction strength, and the influence degree of one curve on the other curve in a specific time period.

[0078] Specifically, it is necessary to analyze the relationship between the fixed fault fitting curve and the usage fault fitting curve. The purpose of the relationship analysis is to clarify how the two curves work together in the equipment failure process. The specific analysis method is, for example, time synchronization of the curves, that is, aligning the corresponding time points on the two curves to ensure their performance in the same time dimension; then, statistical methods such as correlation analysis or covariance analysis are used to quantify the strength of the correlation between the two curves. If the change trends of the two curves in certain periods are highly consistent, it may mean that in these periods, the contribution of fixed faults and usage faults to equipment failures is mutually reinforcing. In addition, methods such as multivariate regression analysis or principal component analysis can be used to explore the key factors affecting the correlation between the two curves, such as external conditions such as equipment load changes and ambient temperature. Through correlation analysis, curve correlation data can be obtained, including the intersection of the two curves at different stages, the correlation coefficient, and their joint impact on equipment failure.

[0079] Step 602 : performing nonlinear superposition on the fixed fault fitting curve and the used fault fitting curve according to the curve correlation data to obtain the equipment failure curve.

[0080] Among them, nonlinear superposition can be the addition or fusion of two or more influencing factors in a nonlinear way to reflect the complex interactive relationship between them.

[0081] Specifically, based on the curve correlation data obtained by correlation analysis, the fixed fault fitting curve and the use fault fitting curve are nonlinearly superimposed, wherein the key to nonlinear superposition is that the influence of the two curves on the equipment failure is not a simple additive relationship, but there is a certain complex interaction. In the specific implementation process, it is necessary to use a nonlinear superposition algorithm to dynamically adjust the weights of the two curves according to the curve correlation data. For example, the curve correlation data shows that in certain specific time periods, the temperature has a greater impact on the fixed fault, while the load has a stronger impact on the use fault. Then, in these time periods, the formula of nonlinear superposition should give more weight to the fixed fault fitting curve, and adjust the superposition ratio in other time periods. In the process of the nonlinear superposition algorithm, product superposition, exponential superposition or logarithmic superposition can be used. For example, by constructing a product model, the total failure probability of the equipment is jointly determined by the influence of the fixed fault and the use fault, wherein the contribution of each curve changes dynamically according to the actual working conditions. The nonlinear characteristics between the fixed fault fitting curve and the use fault fitting curve are mutually enhanced or mutually suppressed by the nonlinear superposition algorithm to obtain the equipment failure curve.

[0082] In this embodiment, by performing correlation analysis on the fixed fault fitting curve and the used fault fitting curve, the mutual influence of temperature correction and load correction on the development of equipment faults can be revealed. The determination of curve correlation data can help judge the relationship strength and interaction between the two, and provide a basis for subsequent nonlinear superposition. Based on these correlation data, the two curves are nonlinearly superimposed, and the resulting equipment failure curve can more accurately reflect the fault evolution process of the equipment under complex working conditions. Not only does it improve the accuracy of fault prediction, but it can also comprehensively consider the superposition effect of multiple influencing factors, providing more reliable data support for equipment maintenance decisions, thereby optimizing maintenance strategies, reducing equipment failure rates, extending the service life of equipment, and ensuring the stability and safety of the production process.

[0083] In an exemplary embodiment, Figure 7 As shown, according to the curve correlation data, the fixed fault fitting curve and the use fault fitting curve are nonlinearly superimposed to obtain the equipment failure curve, including steps 701 to 706. Wherein: Step 701 : determining an exponential superposition parameter, a logarithmic superposition parameter and a power-law superposition parameter according to a fixed fault fitting curve and a used fault fitting curve.

[0084] Among them, the exponential superposition parameters can be coefficients used to adjust the curve shape when performing exponential model superposition. These parameters control the fault growth rate and acceleration, usually including the baseline fault value and the growth factor (i.e., the exponential value of the exponent), which determine how factors such as temperature and load affect the acceleration trend of faults during equipment operation.

[0085] The logarithmic superposition parameter may be a coefficient for adjusting the shape of the curve when performing logarithmic model superposition, and usually includes a baseline fault value and a logarithmic growth coefficient, which define the cumulative characteristics of equipment faults under changes in time or working conditions.

[0086] The power law superposition parameters may be parameters used to adjust the curve shape when performing power law model superposition, and these parameters include power exponents and constant terms, which control the degree of nonlinear change in the process of equipment failure growth.

[0087] Specifically, the curve features of the fixed fault fitting curve and the fault fitting curve obtained by fitting are extracted to analyze their growth rate, change form and potential interaction. For example, the growth of equipment failures shows exponential acceleration, logarithmic accumulation or power-law nonlinear growth. The system will automatically determine the exponential superposition parameters, logarithmic superposition parameters and power-law superposition parameters corresponding to the superposition algorithm suitable for each curve through optimization algorithms (such as least squares method, maximum likelihood estimation, etc.).

[0088] Step 702 , using exponential superposition parameters, logarithmic superposition parameters and power-law superposition parameters respectively, nonlinearly superimpose the fixed fault fitting curve and the fault fitting curve to obtain an exponential superposition curve, a logarithmic superposition curve and a power-law superposition curve.

[0089] Among them, the exponential superposition curve can be a curve generated by combining different fault data (such as fixed fault data and usage fault data) through an exponential model. It is mainly used to describe the acceleration process of equipment failure, and is usually applicable to rapid fault growth caused by factors such as high temperature and high load.

[0090] The logarithmic superposition curve may be a curve generated by combining the fixed fault data and the usage fault data of the equipment through a logarithmic model. The curve is used to describe the faults gradually accumulated during the long-term operation of the equipment.

[0091] Among them, the power-law superposition curve can be a curve obtained by combining the power-law model with fixed fault data and use fault data. It is mainly used to describe the growth pattern of equipment failure under specific nonlinear working conditions. The power-law superposition curve can capture the complex failure modes caused by load fluctuations and extreme environmental changes.

[0092] Specifically, the exponential superposition parameters, logarithmic superposition parameters and power-law superposition parameters are applied to the exponential superposition algorithm, logarithmic superposition algorithm and power-law superposition algorithm respectively, and the fixed fault fitting curve and the use fault fitting curve are nonlinearly superimposed respectively. In the process of nonlinear superposition, the exponential superposition algorithm will enhance the accelerated growth trend of the fault, which is suitable for rapid failure caused by temperature change; the logarithmic superposition algorithm is suitable for simulating the gradually accumulated faults in long-term stable operation; the power-law superposition algorithm can handle complex nonlinear fault growth, which is usually suitable for the non-uniform impact of load fluctuations on equipment. In actual calculation, the system combines the values ​​of the two curves according to the formula of each superposition model to obtain three different superposition curves, namely the exponential superposition curve, the logarithmic superposition curve and the power-law superposition curve.

[0093] Step 703 , respectively performing error calculations on the exponential superposition curve, the logarithmic superposition curve, and the power law superposition curve to obtain error data of each curve.

[0094] The curve error data can be the data obtained by comparing the difference between the superposition curve and the actual fault data. The error calculation usually adopts statistical methods, such as mean square error (MSE) or mean absolute error (MAE). The error data reflects the accuracy of different superposition models (such as exponential, logarithmic, power law superposition curves) in fitting the actual fault data.

[0095] Specifically, the errors between the exponential superposition curve, the logarithmic superposition curve, and the power law superposition curve are respectively measured using error measurement standard algorithms, such as mean square error (MSE), mean absolute error (MAE), or relative error (RE) to quantify the difference between each superposition curve and the actual fault data, where the actual fault data comes from equipment under the same environmental conditions and the same usage conditions, and the usage time of the equipment is much longer than that of the target equipment. The system compares each superposition curve with the actual fault data, calculates the curve error data of each superposition curve, and then understands the accuracy of fault prediction by different superposition methods; the smaller the error, the more consistent the superposition model is with the law of actual equipment failure.

[0096] Step 704, when the difference between the error data of each curve is less than the preset error standard, complexity analysis or generalization ability analysis is performed on the exponential superposition curve, the logarithmic superposition curve and the power law superposition curve to obtain complexity analysis data or generalization analysis data.

[0097] The preset error standard can be a tolerance range used to measure the fitting effect of each superposition curve when selecting a model. Usually, during the model fitting process, an error range is set, requiring that the error difference between the superposition curve and the actual fault data does not exceed the standard. If the error difference exceeds the preset error standard, it means that the fitting effect of the model is poor.

[0098] Complexity analysis can be a process of evaluating the complexity of a model in predicting faults. In this process, the main focus is on the number of parameters, the amount of computation, and the adaptability of the model to the data. Models with higher complexity may be too complex and prone to overfitting, while models with too low complexity may not be able to capture the key features in the data.

[0099] Among them, generalization analysis can be used to evaluate the prediction performance of the model under unknown data or new working conditions. It examines whether the model can adapt to different equipment operating environments and working conditions, so as to effectively predict future failures. Through cross-validation and other techniques, generalization analysis helps to determine the stability and robustness of the model.

[0100] The complexity analysis data may be data obtained by evaluating the complexity of the model, and generally includes the number of parameters of the model, the computational complexity, and the computational efficiency of the model.

[0101] The generalization analysis data may be data obtained through generalization capability analysis, which usually includes the prediction accuracy, stability, and adaptability of the model to different working conditions on unseen data.

[0102] Specifically, after the error calculations are performed on the exponential superposition curve, the logarithmic superposition curve, and the power-law superposition curve, if the error differences of the exponential superposition curve, the logarithmic superposition curve, and the power-law superposition curve are all less than the preset error standard (for example, the error difference is within the tolerance range), it means that the three curves can fit the actual data well, and further complexity analysis or generalization analysis is required. The complexity analysis mainly examines the complexity of each model, such as the number of parameters and the amount of calculation of the model, to avoid overfitting of the model and ensure that its structure is highly adaptable and concise. The generalization analysis tests the performance of the model on unseen data, that is, whether the model can effectively predict the failure of the equipment under different working conditions. The system will perform generalization analysis through cross-validation, leave-one-out method and other techniques to evaluate the adaptability and robustness of each superposition curve under different working conditions, and obtain complexity analysis data or generalization analysis data for each superposition curve.

[0103] Step 705 , selecting a superposition curve with the minimum complexity analysis data from the exponential superposition curve, the logarithmic superposition curve, and the power law superposition curve as the equipment failure curve.

[0104] Specifically, the complexity analysis data of the exponential superposition curve, the logarithmic superposition curve, and the power law superposition curve are compared, and the curve with the least complexity among the complexity analysis data is selected as the final equipment failure curve. For example, in large-scale equipment monitoring, selecting the model with the lowest computational complexity can reduce the system's computing resource usage and improve response speed while ensuring prediction accuracy.

[0105] Step 706 , selecting a superposition curve with a maximum value of generalized analysis data from the exponential superposition curve, the logarithmic superposition curve, and the power law superposition curve as the equipment failure curve.

[0106] Specifically, the generalization ability scores of the exponential superposition curve, logarithmic superposition curve and power-law superposition curve are compared, and the superposition curve with the highest score, that is, the curve with the maximum generalization ability data, is selected as the final equipment failure curve to ensure that the selected curve can maintain high prediction accuracy and adaptability under different operating environments or working conditions, especially when facing different types of equipment or external changes.

[0107] In this embodiment, by determining the exponential, logarithmic and power law superposition parameters for the fixed fault fitting curve and the fault fitting curve, and performing nonlinear superposition, three different types of failure curves can be obtained, which can reflect the failure trend of the equipment under complex working conditions from different angles. By performing error calculation and complexity analysis on these curves, the fitting accuracy of each curve and its computational complexity can be effectively evaluated to ensure that the selected failure curve achieves the best balance between accuracy and computing resource usage. In addition, the generalization ability analysis ensures that the selected curve has good adaptability and stability under different use conditions. Finally, by selecting the superposition curve with the minimum complexity or the maximum generalization ability, it can be ensured that the obtained equipment failure curve is not only accurate in theory, but also has strong robustness and prediction accuracy in practical applications. This method greatly improves the reliability of equipment failure prediction, helps to identify potential risks in advance, optimize the maintenance strategy of the equipment, and reduce the probability of failure, thereby improving the use efficiency and operation safety of the equipment.

[0108] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0109] Based on the same inventive concept, the embodiment of the present application also provides a device for predicting device failures based on a digital twin model for implementing the device failure prediction method based on a digital twin model mentioned above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the device failure prediction device based on a digital twin model provided below can be referred to the limitations of the device failure prediction method based on a digital twin model above, and will not be repeated here.

[0110] In an exemplary embodiment, Figure 8 As shown, a device for predicting equipment failure based on a digital twin model is provided, comprising: an equipment data acquisition module 801, a fault data calculation module 802, a fault data correction module 803, a failure curve generation module 804 and an equipment failure prediction module 805. Each module in the above-mentioned device for predicting equipment failure based on a digital twin model can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules to implement any step of a method for predicting equipment failure based on a digital twin model.

[0111] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. When the computer program is executed by the processor, a device fault prediction method based on a digital twin model is implemented.

[0112] Those skilled in the art will understand that Fig. 9The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0113] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0114] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0115] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0116] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0117] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0118] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0119] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for predicting equipment failure based on a digital twin model, characterized in that: The method comprises: When the equipment monitoring twin model fails to detect fault information of the target equipment, the equipment operation status data, equipment operation temperature data and equipment load cycle data of the target equipment are obtained; Substituting the equipment operation status data into the fixed fault calculation model and the usage fault calculation model of the target equipment respectively to obtain the target fixed fault data and the target usage fault data; Correcting the object fixed fault data according to the equipment operating temperature data to obtain temperature corrected fixed fault data; Correcting the object usage fault data according to the equipment load cycle data to obtain load corrected usage fault data; Calculating the failure data of the target device on the usage time axis according to the temperature-corrected fixed failure data and the load-corrected usage failure data to obtain a device failure curve; Data points that meet preset failure conditions are extracted from the equipment failure curve as equipment failure prediction information of the target equipment.

2. The method according to claim 1, characterized in that The step of correcting the object fixed fault data according to the equipment operating temperature data to obtain temperature corrected fixed fault data includes: Determining life simulation environment parameters and life simulation duration parameters corresponding to the accelerated life simulation according to the equipment operating temperature data and the object fixed fault data; The accelerated life simulation is performed on the target device according to the life simulation environment parameter and the life simulation duration parameter to obtain the temperature corrected fixed fault data.

3. The method according to claim 2, characterized in that The calculation expression of the temperature correction fixed fault data is: in, Fixed fault data for the object, is the initial inherent fault data, T(t) is the fault of the target device at time t Equipment operating temperature data, is the influence coefficient of temperature on inherent fault data, is the time-dependent degradation coefficient of the target device, is the activation energy, is the Boltzmann constant, T is the temperature, is the load or stress, H is the humidity, is the sensitivity coefficient of the load to the inherent fault data, is the sensitivity coefficient of humidity to inherent fault data, is the load effect, is the humidity effect, is the temperature effect, is the Arrhenius model fault data, Fixed glitched data for temperature correction.

4. The method according to claim 1, characterized in that The step of correcting the object usage fault data according to the equipment load cycle data to obtain load corrected usage fault data includes: Determine usage simulation environment parameters and usage simulation mechanical parameters corresponding to usage fatigue simulation according to the equipment load cycle data and the object usage failure data; The usage fatigue simulation is performed on the target device according to the usage simulation environment parameters and the usage simulation mechanical parameters to obtain the load-corrected usage failure data.

5. The method according to claim 4, characterized in that The load correction calculation expression using fault data is: in, Use fault data for objects, is the initial use fault data, T(t) is the fault of the target device at time t Equipment operating temperature data, is the influence coefficient of temperature on the use failure data, is the time-dependent degradation coefficient of the target device, T is the temperature, is the load or stress, H is the humidity, is the sensitivity coefficient of humidity to the use failure data, is the equipment load cycle data, The failure data of the target equipment degrades over time. is the time degradation rate, is the correction factor related to the equipment load cycle data, is the material constant, is the influence coefficient of temperature on the strain of equipment material, is the influence coefficient of load on equipment material strain, is the coefficient of influence of humidity on the strain of equipment material, c is the Coffin–Manson constant, is the total strain amplitude, Use fault data for load correction.

6. The method according to claim 1, characterized in that The step of calculating the failure data of the target device on the usage time axis according to the temperature-corrected fixed failure data and the load-corrected usage failure data to obtain a device failure curve includes: Taking each usage duration data point of the usage time axis as each integral upper limit value, the temperature-corrected fixed fault data and the load-corrected usage fault data are respectively integrated to obtain each integral fixed fault data and each integral usage fault data; Fitting each of the integrated fixed fault data and each of the integrated usage fault data respectively to obtain a fixed fault fitting curve and a usage fault fitting curve; The fixed fault fitting curve and the usage fault fitting curve are superimposed to obtain the equipment failure curve.

7. The method according to claim 6, characterized in that The step of superimposing the fixed fault fitting curve and the use fault fitting curve to obtain the equipment failure curve includes: Performing correlation analysis on the fixed fault fitting curve and the usage fault fitting curve to determine curve correlation data; According to the curve correlation data, the fixed fault fitting curve and the usage fault fitting curve are nonlinearly superimposed to obtain the equipment failure curve.

8. The method according to claim 7, characterized in that The step of performing nonlinear superposition on the fixed fault fitting curve and the usage fault fitting curve according to the curve correlation data to obtain the equipment failure curve includes: Determining an exponential superposition parameter, a logarithmic superposition parameter, and a power-law superposition parameter according to the fixed fault fitting curve and the usage fault fitting curve; Using the exponential superposition parameter, the logarithmic superposition parameter and the power-law superposition parameter respectively, the fixed fault fitting curve and the use fault fitting curve are nonlinearly superimposed to obtain an exponential superposition curve, a logarithmic superposition curve and a power-law superposition curve; Performing error calculations on the exponential superposition curve, the logarithmic superposition curve, and the power-law superposition curve respectively to obtain error data of each curve; When the difference between the error data of each curve is less than the preset error standard, complexity analysis and generalization ability analysis are performed on the exponential superposition curve, the logarithmic superposition curve and the power law superposition curve to obtain complexity analysis data and generalization analysis data; Selecting a superposition curve having a minimum value of the complexity analysis data from the exponential superposition curve, the logarithmic superposition curve and the power law superposition curve as the equipment failure curve; Alternatively, a superposition curve in which the generalized analysis data is a maximum value is selected from the exponential superposition curve, the logarithmic superposition curve and the power-law superposition curve as the device failure curve.

9. A device for predicting equipment failure based on a digital twin model, characterized in that: The device comprises: The equipment data acquisition module is used to obtain the equipment operation status data, equipment operation temperature data and equipment load cycle data of the target equipment when the equipment monitoring twin model fails to detect the existence of fault information of the target equipment; A fault data calculation module, used to substitute the equipment operation status data into the fixed fault calculation model and the usage fault calculation model of the target equipment respectively, to obtain the target fixed fault data and the target usage fault data; A fault data correction module, used for correcting the object fixed fault data according to the equipment operation temperature data to obtain temperature corrected fixed fault data; The fault data correction module is further used to correct the object usage fault data according to the equipment load cycle data to obtain load corrected usage fault data; A failure curve generating module, used to calculate the failure data of the target device on the usage time axis according to the temperature-corrected fixed failure data and the load-corrected usage failure data, and obtain a device failure curve; The equipment failure prediction module is used to extract data points that meet preset failure conditions from the equipment failure curve as equipment failure prediction information of the target equipment.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images