Digital-twin-based device asset whole life cycle management method and system

Abstract

The present application relates to the technical field of equipment asset management, and more particularly to a method and system for equipment asset life cycle management based on digital twinning, which provides a measurable, calculable and quantified index with clear physical meaning for the complex interaction between mechanical stress field and chemical corrosion field by introducing nonlinear coupling strength; the mechanical-chemical coupling fatigue damage factor and the corrosion intensity index of lubricating medium are constructed, and are further integrated into the electromechanical-chemical coupling mode vector to uniformly represent the comprehensive health state of the equipment from the system level. This not only can detect abnormalities earlier and more sensitively, but also can accurately locate the degradation source, thereby providing a solid data foundation for subsequent differentiated maintenance decisions; a complete closed loop from sensing, diagnosis, decision-making to optimization is formed, which greatly improves the automation and intelligence level of asset management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of equipment asset management, and in particular to a method and system for equipment asset lifecycle management based on digital twinning. BACKGROUND

[0002] In large offshore wind farms, the core asset "gearbox" is subjected to predictive maintenance. The gearbox is long-term exposed to a comprehensive harsh environment of high salt mist corrosion, complex alternating stress caused by turbulent wind load, and frequent start-stop and variable operating conditions caused by grid dispatching instructions. Pitting induced by salt mist environment (chemical field) will become the initiation point of fatigue cracks (mechanical field), significantly reducing the material fatigue limit; while the instantaneous high thermal load (thermal field) caused by frequent emergency stop and start (operation control) will accelerate the oxidative degradation of lubricating oil (chemical field), change its viscosity-temperature characteristics, and then affect the oil film thickness (mechanical field) in the gear meshing area, aggravating the wear. The existing model cannot effectively capture, quantify and predict the complex nonlinear interaction between multiple physical fields and its coupled influence on the overall remaining life of the equipment.

[0003] Disadvantages of the prior art: the method based on physical model establishes the mechanical / thermodynamic differential equations of gears and bearings, estimates the state through a state observer (such as Kalman filter), and linearizes or ignores the coupling terms; the data-driven method uses SCADA and vibration historical data to train machine learning models (such as LSTM, random forest) for fault warning or RUL prediction, and cannot explicitly represent the "corrosion-fatigue coupling strength" as a physical and chemical coupling hidden variable. SUMMARY

[0004] The main purpose of the present application is to provide a method for equipment asset lifecycle management based on digital twinning, and further to provide a system for equipment asset lifecycle management based on digital twinning capable of running and implementing the above method, effectively solving the above problems mentioned in the background art.

[0005] The technical solution of the present application is as follows:

[0006] In a first aspect, a method for equipment asset lifecycle management based on digital twinning is provided, which comprises the following steps:

[0007] S1, collecting and preprocessing original sensor data, the original sensor data including real-time salt mist concentration, real-time electrochemical noise, real-time lubricating oil temperature, real-time generator torque, real-time generator speed and real-time lubricating oil acid value, and outputting a real-time data set after preprocessing;

[0008] S2, based on the pre-processed real-time generator torque and real-time generator speed, calculate the real-time gearbox equivalent load; input the real-time gearbox equivalent load into the built gear contact stress finite element model, output the real-time gear surface equivalent stress; based on the pre-processed real-time electrochemical noise and real-time lubricating oil acid value, obtain the real-time instantaneous corrosion rate; based on the real-time gear surface equivalent stress and the real-time instantaneous corrosion rate, calculate the nonlinear coupling strength;

[0009] S3, based on the real-time gear surface equivalent stress and the nonlinear coupling strength, calculate the real-time mechanical-chemical coupling fatigue damage factor, and based on the pre-processed real-time lubricating oil acid value and the real-time instantaneous corrosion rate, calculate the real-time lubricating medium corrosion intensity index;

[0010] S4, combine the real-time mechanical-chemical coupling fatigue damage factor and the real-time lubricating medium corrosion intensity index to generate a real-time electromechanical-chemical coupling modal vector, simultaneously extract all historical electromechanical-chemical coupling modal vectors of the gearbox during the historical health operation period, obtain a health boundary by using a support vector data description algorithm, calculate the marginal distance of the real-time electromechanical-chemical coupling modal vector to the health boundary and generate a decision.

[0011] Further improvement of the application is that the S2 comprises the following specific steps:

[0012] S21, based on the pre-processed real-time generator torque data and real-time generator speed data, calculate the real-time gearbox equivalent load, and the calculation formula of the real-time gearbox equivalent load is:

[0013] ;

[0014] Wherein, represents the gearbox equivalent load at t time, represents the rated power, represents the generator torque at t time, represents the generator speed at t time;

[0015] S22, input the real-time gearbox equivalent load into the built gear contact stress finite element model, output the real-time gear surface equivalent stress . ;

[0016] S23, based on the pre-processed real-time electrochemical noise data and real-time lubricating oil acid value data, obtain the real-time instantaneous corrosion rate through the pre-marked electrochemical noise intensity-corrosion rate mapping table .

[0017] Further improvement of the application is that the S2 further comprises:

[0018] S24, calculating the real-time gear surface equivalent stress based on the real-time gear surface equivalent stress and the real-time instantaneous corrosion rate , calculating a nonlinear coupling strength representing the coupling effect of gear mechanical stress and chemical corrosion intensity, the calculation formula of the nonlinear coupling strength being:

[0019] ;

[0020] wherein, represents the nonlinear coupling strength at time t, is a fitting coefficient, is a fatigue limit of the gear material, is a standard corrosion rate of the gear material, is the gear surface equivalent stress at time t, is the instantaneous corrosion rate at time t.

[0021] The further improvement of the present application is that the calculation formula of the real-time mechanical-chemical coupling fatigue damage factor in S3 is:

[0022] ;

[0023] wherein, represents the mechanical-chemical coupling fatigue damage factor at time t, represents the mechanical-chemical coupling fatigue damage factor at time t-1, is a coupling sensitivity coefficient, and m is a material S-N curve index, is a load cycle number increment.

[0024] The further improvement of the present application is that the calculation formula of the real-time lubricating medium corrosion intensity index in S3 is:

[0025] ;

[0026] wherein, represents the real-time lubricating medium corrosion intensity index at time t, represents the real-time lubricating oil acid value at time t, represents a new oil acid value, represents a standard corrosion rate reference value, is a temperature influence coefficient, represents the difference between the real-time lubricating oil temperature at time t and the new oil temperature.

[0027] The further improvement of the present application is that S4 comprises the following specific steps:

[0028] S41, multiplying the real-time mechanical-chemical coupling fatigue damage factor by the real-time lubricating medium corrosion intensity index Combination construction generates real-time electromechanical-chemical coupling modal vector , ;

[0029] S42, extract all historical electromechanical-chemical coupling modal vectors of the gear box historical health operation period as health sample data, based on the health sample data, obtain the health boundary by using a support vector data description algorithm , the support vector data description algorithm takes a radial basis function as a kernel;

[0030] S43, extract the real-time electromechanical-chemical coupling modal vector to the sign distance of the health boundary as the marginal distance , judge whether the marginal distance is greater than 0, when the marginal distance is greater than 0, it is judged that the current state is within the health boundary, and a health signal is output, when the marginal distance is not greater than 0, it is judged that the current state reaches or exceeds the health boundary, and an early warning signal is output.

[0031] The further improvement of the application is that the S43 further comprises: when the marginal distance is not greater than 0, it is judged that the current state reaches or exceeds the health boundary, further analyzing the components of the real-time electromechanical-chemical coupling modal vector , calculating the change amount of the real-time mechanical-chemical coupling fatigue damage factor relative to the average value of the historical mechanical-chemical coupling fatigue damage factor , and calculating the change amount of the real-time lubricating medium corrosive strength index relative to the average value of the historical lubricating medium corrosive strength index , when , a mechanical overload or corrosion fatigue acceleration early warning signal is output, when , a lubricating oil degradation early warning signal is output, wherein k is a proportional coefficient.

[0032] Secondly, a device asset whole life cycle management system based on digital twinning is provided, which comprises: the system comprises: a data acquisition module, a nonlinear coupling module, a feature calculation module, a judgment and early warning module;

[0033] The data acquisition module is used for acquiring and preprocessing original sensor data, and the original sensor data includes real-time salt mist concentration, real-time electrochemical noise, real-time lubricating oil temperature, real-time generator torque, real-time generator speed and real-time lubricating oil acid value, and outputs a preprocessed real-time data set;

[0034] The nonlinear coupling module is configured to calculate real-time gearbox equivalent load based on the preprocessed real-time generator torque and real-time generator speed, input the real-time gearbox equivalent load into a built gear contact stress finite element model, and output real-time gear face equivalent stress; obtain real-time instantaneous corrosion rate based on the preprocessed real-time electrochemical noise and real-time lubricating oil acid value; and calculate nonlinear coupling strength based on the real-time gear face equivalent stress and the real-time instantaneous corrosion rate.

[0035] The feature calculation module is configured to calculate real-time mechanical-chemical coupling fatigue damage factor based on the real-time gear face equivalent stress and the nonlinear coupling strength, and calculate real-time lubricating medium corrosive strength index based on the preprocessed real-time lubricating oil acid value and real-time instantaneous corrosion rate.

[0036] The judgment and early warning module is configured to combine the real-time mechanical-chemical coupling fatigue damage factor and the real-time lubricating medium corrosive strength index to generate a real-time mechatronic chemical coupling mode vector, extract all historical mechatronic chemical coupling mode vectors of the gearbox during a historical healthy operation period, obtain a health boundary by using a support vector data description algorithm, calculate a marginal distance from the real-time mechatronic chemical coupling mode vector to the health boundary, and generate a decision.

[0037] The technical effects of the present application are as follows:

[0038] A device asset full life cycle management method based on digital twinning is constructed, which introduces nonlinear coupling strength for the first time, provides a measurable, calculable and quantifiable index with clear physical meaning for the complex interaction between mechanical stress field and chemical corrosion field, which makes the originally neglected or simplified coupling effect (such as accelerated initiation of fatigue cracks at corrosion pits) become a core variable that can be directly adjusted in the digital twinning model, thereby improving the model prediction accuracy from "qualitative speculation" to "quantitative analysis" level; by constructing mechanical-chemical coupling fatigue damage factor and lubricating medium corrosive strength index, and further integrating into mechatronic chemical coupling mode vector, the comprehensive health status of the equipment can be uniformly represented from the system level. This not only enables earlier and more sensitive detection of abnormalities, but also accurately locates the degradation source (whether it is caused by excessive mechanical load or lubricating oil deterioration), thereby providing a solid data foundation for subsequent differentiated maintenance decisions and avoiding "misdiagnosis"; a complete closed loop from sensing, diagnosis, decision making to optimization is formed, which greatly improves the automation and intelligence level of asset management. BRIEF DESCRIPTION OF DRAWINGS

[0039] Other features, objects and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments, made with reference to the accompanying drawings:

[0040] Figure 1A flowchart of a digital-twin-based equipment asset whole life cycle management method of embodiment 1 of the present application is shown in the figure.

[0041] Figure 2 A structural diagram of a digital-twin-based equipment asset whole life cycle management system of embodiment 2 of the present application is shown in the figure. DETAILED DESCRIPTION

[0042] Embodiment 1

[0043] The embodiment constructs a digital-twin-based equipment asset whole life cycle management method. By introducing a nonlinear coupling strength, the method provides a measurable, calculable and quantifiable index with clear physical meaning for the complex interaction between the mechanical stress field and the chemical corrosion field, which makes the coupling effect (such as the accelerated initiation of fatigue cracks at corrosion pits) that has been ignored or simplified become a core variable that can be directly adjusted in the digital-twin model, thereby improving the model prediction accuracy from “qualitative speculation” to “quantitative analysis” level. By constructing a mechanical-chemical coupling fatigue damage factor and a lubricating medium corrosion intensity index, and further integrating them into an electromechanical-chemical coupling modal vector, the comprehensive health status of the equipment can be uniformly represented from the system level. This not only enables earlier and more sensitive detection of abnormalities, but also accurately locates the degradation source (whether it is due to excessive mechanical load or lubricating oil deterioration), thereby providing a solid data foundation for subsequent differentiated maintenance decisions and avoiding “misdiagnosis”. A complete closed loop from sensing, diagnosis, decision-making to optimization is formed, greatly improving the automation and intelligence level of asset management.

[0044] The digital-twin-based equipment asset whole life cycle management method, as shown in Figure 1 includes the following specific steps:

[0045] S1, collecting and preprocessing original sensor data, the original sensor data including real-time salt mist concentration, real-time electrochemical noise, real-time lubricating oil temperature, real-time generator torque, real-time generator speed and real-time lubricating oil acid value, and outputting a real-time data set after preprocessing;

[0046] S2, based on the preprocessed real-time generator torque and real-time generator speed, calculating a real-time gear box equivalent load; inputting the real-time gear box equivalent load into a constructed gear contact stress finite element model, and outputting a real-time gear surface equivalent stress; based on the preprocessed real-time electrochemical noise and real-time lubricating oil acid value, obtaining a real-time instantaneous corrosion rate; based on the real-time gear surface equivalent stress and the real-time instantaneous corrosion rate, calculating a nonlinear coupling strength;

[0047] S3, based on the real-time gear surface equivalent stress and the nonlinear coupling strength, a real-time mechanical-chemical coupling fatigue damage factor is calculated, and based on the pretreated real-time lubricating oil acid value and the real-time instantaneous corrosion rate, a real-time lubricating medium corrosive strength index is calculated;

[0048] S4, the real-time mechanical-chemical coupling fatigue damage factor and the real-time lubricating medium corrosive strength index are combined to generate a real-time electro-mechanical-chemical coupling mode vector, all historical electro-mechanical-chemical coupling mode vectors of the gear box during historical health operation are extracted, a support vector data description algorithm is used to obtain a health boundary, a marginal distance of the real-time electro-mechanical-chemical coupling mode vector to the health boundary is calculated, and a decision is generated.

[0049] In the embodiment, the S2 includes the following specific steps:

[0050] S21, based on the pretreated real-time generator torque data and the real-time generator speed data, a real-time gear box equivalent load is calculated, and a calculation formula of the real-time gear box equivalent load is as follows:

[0051] ;

[0052] Wherein, represents the gear box equivalent load at t time, represents the rated power, represents the generator torque at t time, represents the generator speed at t time;

[0053] S22, the real-time gear box equivalent load is input into the built gear contact stress finite element model, and the real-time gear surface equivalent stress is output ;

[0054] S23, based on the pretreated real-time electrochemical noise data and the real-time lubricating oil acid value data, a real-time instantaneous corrosion rate is obtained through a pre-labeled electrochemical noise strength-corrosion rate mapping table .

[0055] In the embodiment, the S2 further includes:

[0056] S24, based on the real-time gear surface equivalent stress and the real-time instantaneous corrosion rate , a nonlinear coupling strength representing the coupling effect of gear mechanical stress and chemical corrosion strength is calculated, and a calculation formula of the nonlinear coupling strength is as follows:

[0057] ;

[0058] Wherein, ​denotes the nonlinear coupling strength at time t, is a fitting coefficient, is a fatigue limit of the gear material, is a standard corrosion rate of the gear material, is an equivalent stress of the gear tooth surface at time t, is an instantaneous corrosion rate at time t.

[0059] In the embodiment, the calculation formula of the real-time mechanical-chemical coupling fatigue damage factor in S3 is:

[0060] ;

[0061] wherein, denotes the mechanical-chemical coupling fatigue damage factor at time t, denotes the mechanical-chemical coupling fatigue damage factor at time t-1, is a coupling sensitivity coefficient, and m is a material S-N curve index, is a load cycle number increment.

[0062] In the embodiment, the calculation formula of the real-time lubricating medium corrosiveness strength index in S3 is:

[0063] ;

[0064] wherein, denotes the real-time lubricating medium corrosiveness strength index at time t, denotes the real-time lubricating oil acid value at time t, denotes a new oil acid value, denotes a standard corrosion rate reference value, is a temperature influence coefficient, denotes the difference between the real-time lubricating oil temperature at time t and the new oil temperature.

[0065] In the embodiment, S4 includes the following specific steps:

[0066] S41, combining the real-time mechanical-chemical coupling fatigue damage factor and the real-time lubricating medium corrosiveness strength index to construct a real-time mechatronic chemical coupling modal vector , ;

[0067] S42, extracting all historical mechatronic chemical coupling modal vectors of the gear box during the historical healthy operation period as healthy sample data, and obtaining a health boundary based on the healthy sample data by using a support vector data description algorithm; the support vector data description algorithm takes a radial basis function as a kernel;

[0068] S43, extracting real-time electromechanical-chemical coupling modal vector the signed distance to the healthy boundary as the marginal distance , determining whether the marginal distance is greater than 0, when the marginal distance is greater than 0, determining that the current state is within the healthy boundary, outputting a healthy signal, when the marginal distance is not greater than 0, determining that the current state reaches or exceeds the healthy boundary, outputting a warning signal.

[0069] In this embodiment, the S43 further comprises: when the marginal distance is not greater than 0, determining that the current state reaches or exceeds the healthy boundary, further analyzing the components of the real-time electromechanical-chemical coupling modal vector , calculating the real-time mechanical-chemical coupling fatigue damage factor relative to the change amount of the historical mechanical-chemical coupling fatigue damage factor mean , and calculating the real-time lubricating medium corrosive intensity index relative to the change amount of the historical lubricating medium corrosive intensity index mean , when , outputting a mechanical overload or corrosion fatigue acceleration warning signal, when , outputting a lubricating oil degradation warning signal, wherein k is a proportional coefficient.

[0070] Embodiment 2

[0071] This embodiment proposes a device asset full life cycle management system based on digital twinning, as shown in Figure 2 , comprising a data acquisition module, a nonlinear coupling module, a feature calculation module, and a judgment and warning module.

[0072] The data acquisition module is configured to acquire and preprocess original sensor data, wherein the original sensor data includes real-time salt mist concentration, real-time electrochemical noise, real-time lubricating oil temperature, real-time generator torque, real-time generator speed, and real-time lubricating oil acid value, and output a preprocessed real-time data set.

[0073] The nonlinear coupling module is configured to calculate a real-time gearbox equivalent load based on the preprocessed real-time generator torque and real-time generator speed, input the real-time gearbox equivalent load into a constructed gearbox contact stress finite element model, output a real-time gear surface equivalent stress, obtain a real-time instantaneous corrosion rate based on the preprocessed real-time electrochemical noise and real-time lubricating oil acid value, and calculate a nonlinear coupling intensity based on the real-time gear surface equivalent stress and the real-time instantaneous corrosion rate.

[0074] The feature calculation module is configured to calculate a real-time mechanical-chemical coupling fatigue damage factor based on the real-time gear face equivalent stress and the nonlinear coupling strength, and to calculate a real-time lubricating medium corrosive strength index based on the preprocessed real-time lubricating oil acid value and the real-time instantaneous corrosion rate.

[0075] The judgment and early warning module is configured to combine the real-time mechanical-chemical coupling fatigue damage factor and the real-time lubricating medium corrosive strength index to generate a real-time electromechanical-chemical coupling mode vector, to extract all historical electromechanical-chemical coupling mode vectors of the gearbox during historical health operation periods, to obtain a health boundary by using a support vector data description algorithm, to calculate a marginal distance from the real-time electromechanical-chemical coupling mode vector to the health boundary, and to generate a decision.

[0076] In the embodiment, the state data of the transformer through-flow test includes: winding current time series data collected by a current sensor; hot spot temperature time series data collected by an infrared temperature measuring instrument; iron core vibration time series data collected by a vibration sensor; discharge soundprint time series data collected by an acoustic sensor; and environment data time series data collected by an environment temperature and humidity sensor.

[0077] In the embodiment, the implementation of the nonlinear coupling module includes the following specific steps: first, based on the preprocessed real-time generator torque data and the real-time generator speed data, a real-time gearbox equivalent load is calculated, and the calculation formula of the real-time gearbox equivalent load is:

[0078] ;

[0079] wherein, represents the gearbox equivalent load at time t, represents the rated power, represents the generator torque at time t, represents the generator speed at time t; and then the real-time gearbox equivalent load is input into the built gear contact stress finite element model, and the real-time gear face equivalent stress is output. Further, based on the preprocessed real-time electrochemical noise data and the real-time lubricating oil acid value data, a real-time instantaneous corrosion rate is obtained by using a pre-labeled electrochemical noise strength-corrosion rate mapping table. Finally, based on the real-time gear face equivalent stress and the real-time instantaneous corrosion rate , a nonlinear coupling strength representing the coupling effect of the gear mechanical stress and the chemical corrosion strength is calculated, and the calculation formula of the nonlinear coupling strength is:

[0080] ;

[0081] wherein, represents the nonlinear coupling strength at time t, is a fitting coefficient, is the fatigue limit of the gear material, is the standard corrosion rate of the gear material, is the equivalent stress of the gear tooth surface at time t, is the instantaneous corrosion rate at time t.

[0082] In the embodiment, the calculation formula of the real-time mechanical-chemical coupling fatigue damage factor is:

[0083] ;

[0084] wherein, represents the mechanical-chemical coupling fatigue damage factor at time t, represents the mechanical-chemical coupling fatigue damage factor at time t-1, is a coupling sensitivity coefficient, and m is the material S-N curve index, is the load cycle number increment.

[0085] In the embodiment, the calculation formula of the real-time lubricating medium corrosiveness intensity index is:

[0086] ;

[0087] wherein, represents the real-time lubricating medium corrosiveness intensity index at time t, represents the real-time lubricating oil acid value at time t, represents the new oil acid value, represents the standard corrosion rate reference value, is a temperature influence coefficient, represents the difference between the real-time lubricating oil temperature at time t and the new oil temperature.

[0088] In the embodiment, the implementation of the judgment and early warning module includes the following specific steps: first, the real-time mechanical-chemical coupling fatigue damage factor and the real-time lubricating medium corrosiveness intensity index are combined to construct a real-time electromechanical-chemical coupling mode vector , Then, all historical electromechanical-chemical coupling mode vectors during the historical health operation period of the gearbox are extracted as health sample data, and based on the health sample data, a health boundary is obtained by using a support vector data description algorithm, the support vector data description algorithm takes a radial basis function as a kernel; further, the signed distance of the real-time electromechanical-chemical coupling mode vector to the health boundary is extracted as a marginal distance Determine the marginal distance Is it greater than 0, when the marginal distance When the value is greater than 0, it is determined that the current state is within the healthy boundary, and a healthy signal is output. When the boundary distance is greater than 0, it is determined that the current state is within the healthy boundary. When the value is not greater than 0, it is determined that the current state has reached or exceeded the health boundary, and a warning signal is output. When the boundary distance... If the value is not greater than 0, determine whether the current state has reached or exceeded the health boundary, and further analyze the real-time electromechanical-chemical coupled mode vector. The components are used to calculate the real-time mechanical-chemical coupled fatigue damage factor. The change relative to the historical mean of mechanical-chemical coupled fatigue damage factor Simultaneously calculate the real-time corrosion intensity index of the lubricating medium. Change relative to the historical average corrosiveness index of lubricating media ,when At that time, it outputs a warning signal for mechanical overload or accelerated corrosion fatigue. When the lubricating oil deterioration warning signal is output, k is the proportional coefficient.

[0089] The steps for implementing the corresponding functions of each parameter and each unit module in the digital twin-based equipment asset lifecycle management system of the present invention can be referred to the parameters and steps in the embodiment of the digital twin-based equipment asset lifecycle management method in Embodiment 1 above.

[0090] Example 3

[0091] This embodiment provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-described device asset lifecycle management method based on digital twin by calling the computer program stored in the memory.

[0092] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memories store at least one computer program, which is loaded and executed by the processor to implement the digital twin-based device asset lifecycle management method provided in the above-described embodiments. The electronic device may also include other components for implementing device functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Further details are omitted in this embodiment.

[0093] Those skilled in the art will appreciate that the application can be embodied in a system, a method, or a computer program product. Therefore, the disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.) or a combination of hardware and software that can all generally be referred to herein as a "circuit," "module" or "system." Furthermore, the disclosure can take the form of a program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon.

[0094] Any combination of one or more computer readable medium(s) can be utilized. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0095] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks or in conjunction with the flowcharts. Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks or in conjunction with the flowcharts. Figure 1 one or more functions specified in the flowchart block or blocks. Figure 1 one or more functions specified in the flowchart block or blocks.

[0097] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the above-described specific embodiments, and the above-described specific embodiments are merely illustrative, but not restrictive, and a person of ordinary skill in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, and these all belong to the protection of the present application.

Claims

1. A method for full lifecycle management of equipment assets based on digital twins, characterized by: The specific steps include the following: S1. Collect raw sensor data and preprocess it. The raw sensor data includes real-time salt spray concentration, real-time electrochemical noise, real-time lubricating oil temperature, real-time generator torque, real-time generator speed and real-time lubricating oil acid value. Output the preprocessed real-time dataset. S2. Based on the preprocessed real-time generator torque and real-time generator speed, calculate the real-time equivalent load of the gearbox; input the real-time equivalent load of the gearbox into the constructed gear contact stress finite element model, and output the real-time equivalent stress of the tooth surface; The real-time instantaneous corrosion rate is obtained based on the pre-processed real-time electrochemical noise and real-time lubricating oil acid value. The nonlinear coupling strength is calculated based on the real-time equivalent stress on the tooth surface and the real-time instantaneous corrosion rate. S3. Based on the real-time equivalent stress of the tooth surface and the nonlinear coupling strength, the real-time mechanical-chemical coupling fatigue damage factor is calculated. At the same time, based on the real-time acid value of the pretreated lubricating oil and the real-time instantaneous corrosion rate, the real-time corrosion intensity index of the lubricating medium is calculated. S4. Combine the real-time mechanical-chemical coupled fatigue damage factor with the real-time lubricating medium corrosion intensity index to construct a real-time electromechanical coupled mode vector. At the same time, extract all historical electromechanical coupled mode vectors during the gearbox's historical healthy operation period. Use the support vector data description algorithm to obtain the health boundary, calculate the marginal distance from the real-time electromechanical coupled mode vector to the health boundary, and generate a decision.

2. The method for full lifecycle management of equipment assets based on digital twins according to claim 1, characterized in that: S2 includes the following specific steps: S21. Based on the preprocessed real-time generator torque data and real-time generator speed data, calculate the real-time gearbox equivalent load. The calculation formula for the real-time gearbox equivalent load is as follows: ； in, This represents the equivalent load on the gearbox at time t. Indicates the rated power. This represents the generator torque at time t. This represents the generator speed at time t; S22, The real-time gearbox equivalent load Input the pre-constructed finite element model of gear contact stress and output the real-time equivalent stress on the tooth surface. ; S23. Based on the preprocessed real-time electrochemical noise data and real-time lubricating oil acid value data, the real-time instantaneous corrosion rate is obtained through a pre-calibrated electrochemical noise intensity-corrosion rate mapping table. .

3. The method for full lifecycle management of equipment assets based on digital twins according to claim 2, characterized in that: S2 further includes: S24. Based on the real-time tooth surface equivalent stress and the real-time instantaneous corrosion rate The nonlinear coupling strength, which characterizes the coupling effect between gear mechanical stress and chemical corrosion intensity, is calculated using the following formula: ； in, This represents the nonlinear coupling strength at time t. These are the fitting coefficients. For the fatigue limit of gear materials, The standard corrosion rate for gear materials. Let be the equivalent stress on the tooth surface at time t. Let t be the instantaneous corrosion rate at time t.

4. The method for full lifecycle management of equipment assets based on digital twins according to claim 3, characterized in that: The formula for calculating the real-time mechanical-chemical coupled fatigue damage factor in S3 is as follows: ； in, This represents the mechanochemical coupling fatigue damage factor at time t. This represents the mechanochemical coupling fatigue damage factor at time t-1. Here, m is the coupling sensitivity coefficient, and m is the exponent of the material's SN curve. This is the increment of the load cycle count.

5. The method for full lifecycle management of equipment assets based on digital twins according to claim 4, characterized in that: The formula for calculating the corrosiveness index of the real-time lubricating medium in S3 is as follows: ； in, This represents the real-time corrosivity index of the lubricating medium at time t. This represents the real-time acid value of the lubricating oil at time t. Indicates the new oleic acid value. This represents the standard corrosion rate reference value. This is the temperature influence coefficient. This represents the difference between the real-time lubricating oil temperature and the new oil temperature at time t.

6. The method for full lifecycle management of equipment assets based on digital twins according to claim 5, characterized in that, S4 includes the following specific steps: S41, Real-time mechanical-chemical coupled fatigue damage factor Corrosion Intensity Index of Real-Time Lubricating Medium Combining and constructing to generate real-time electromechanical coupled mode vectors , ; S42. Extract all historical electromechanical-chemical coupling mode vectors from the gearbox's historical healthy operation periods as health sample data. Based on the health sample data, use the support vector data description algorithm to obtain the health boundary. The support vector data description algorithm uses the radial basis function as its core; S43. Extracting real-time electromechanical-chemical coupling mode vectors The symbolic distance to the health boundary is used as the marginal distance. Determine the marginal distance Is it greater than 0, when the marginal distance When the value is greater than 0, it is determined that the current state is within the healthy boundary, and a healthy signal is output. When the boundary distance is greater than 0, it is determined that the current state is within the healthy boundary. If the value is not greater than 0, it is determined that the current state has reached or exceeded the health boundary, and an early warning signal is output.

7. The method for full lifecycle management of equipment assets based on digital twins according to claim 6, characterized in that, S43 further includes: when the marginal distance If the value is not greater than 0, determine whether the current state has reached or exceeded the health boundary, and further analyze the real-time electromechanical-chemical coupled mode vector. The components are used to calculate the real-time mechanical-chemical coupled fatigue damage factor. The change relative to the historical mean of mechanical-chemical coupled fatigue damage factor Simultaneously calculate the real-time corrosion intensity index of the lubricating medium. Change relative to the historical average corrosiveness index of lubricating media ,when At that time, it outputs a warning signal for mechanical overload or accelerated corrosion fatigue. When the lubricating oil deterioration warning signal is output, k is the proportional coefficient.

8. A digital twin-based equipment asset lifecycle management system, implemented based on any one of claims 1-7, characterized in that, The system includes: a data acquisition module, a nonlinear coupling module, a feature calculation module, and a judgment and early warning module; The data acquisition module is used to acquire raw sensor data and preprocess it. The raw sensor data includes real-time salt spray concentration, real-time electrochemical noise, real-time lubricating oil temperature, real-time generator torque, real-time generator speed, and real-time lubricating oil acid value, and outputs the preprocessed real-time dataset. The nonlinear coupling module is used to calculate the real-time equivalent load of the gearbox based on the pre-processed real-time generator torque and real-time generator speed; input the real-time equivalent load of the gearbox into the constructed gear contact stress finite element model, and output the real-time equivalent stress of the tooth surface; obtain the real-time instantaneous corrosion rate based on the pre-processed real-time electrochemical noise and real-time lubricating oil acid value; and calculate the nonlinear coupling strength based on the real-time equivalent stress of the tooth surface and the real-time instantaneous corrosion rate. The feature calculation module is used to calculate the real-time mechanical-chemical coupling fatigue damage factor based on the real-time tooth surface equivalent stress and the nonlinear coupling strength. At the same time, it calculates the real-time lubricating medium corrosion intensity index based on the pre-processed real-time lubricating oil acid value and the real-time instantaneous corrosion rate. The judgment and early warning module is used to combine the real-time mechanical-chemical coupled fatigue damage factor with the real-time lubricating medium corrosion intensity index to construct a real-time electromechanical coupled mode vector. At the same time, it extracts all historical electromechanical coupled mode vectors during the gearbox's historical healthy operation period, uses the support vector data description algorithm to obtain the health boundary, calculates the marginal distance from the real-time electromechanical coupled mode vector to the health boundary, and generates a decision.

Images