A prediction method and device for maintenance equipment information based on a digital twin model

Abstract

The present application relates to a method and device for predicting maintenance equipment information based on a digital twin model. The method includes: obtaining the record, detection, and environmental information of the equipment; based on this data, the system determines a three-layer description model of the digital twin and generates the physical twin status information of the equipment through interactive description. Using the equipment maintenance physical prediction model and the machine prediction model, faults are predicted based on the physical twin status information, and the relevant maintenance equipment fault information is obtained. Isolation prediction is performed on this fault information, and combined with feature extraction and data integration, the prediction information of each maintenance equipment is obtained. Combining the application scenario and efficiency parameters, the optimal maintenance equipment is selected from the prediction information to ensure that the selected equipment can efficiently and accurately meet the requirements in a specific scenario, and finally the optimal maintenance equipment information is obtained. Using this method can effectively improve the accuracy of maintenance material preparation, thereby improving the maintenance efficiency.

Description

Technical Field

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

[0002] With the development of computer technology, there has emerged a technology for predicting maintenance equipment. This technology usually uses the operating status and maintenance records of equipment to predict in advance which components may have problems, so as to prepare the required equipment in advance. This can not only reduce the waiting time during maintenance, but also help enterprises better manage inventory and ensure the smooth progress of maintenance work.

[0003] In traditional technologies, maintenance personnel roughly predict possible failures and required equipment based on the operating conditions, service life, and historical fault records of the equipment, and further through the manually recorded data mentioned above. Therefore, they often rely on experience judgment and fixed maintenance cycles to determine equipment requirements, lacking real-time data support and the characteristics of data that are difficult to extract records, resulting in inaccurate preparation of maintenance materials and thus affecting maintenance efficiency. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device, computer device, computer-readable storage medium, and computer program product for predicting maintenance equipment information based on a digital twin model, which can effectively improve the accuracy of preparing maintenance materials and thus improve maintenance efficiency for the above technical problems.

[0005] In a first aspect, the present application provides a method for predicting maintenance equipment information based on a digital twin model, including:

[0006] Obtain the equipment record information, equipment detection information, and equipment environment information of the target equipment;

[0007] Determine each digital twin description layer of the target equipment according to the equipment record information, the equipment detection information, and the equipment environment information;

[0008] Perform interactive description on each digital twin description layer according to the equipment record information, the equipment detection information, and the equipment environment information to obtain equipment physical twin status information;

[0009] Respectively use each equipment maintenance physical prediction model and equipment maintenance machine prediction model to predict the fault information of the target equipment according to the equipment physical twin status information to obtain each maintenance equipment fault information;

[0010] Perform information isolation prediction on the maintenance equipment information of the target equipment according to each maintenance equipment fault information to obtain each maintenance equipment prediction information;

[0011] Select the optimal information from each of the maintenance equipment prediction information according to the application scenario parameters and application efficiency parameters of the object equipment to obtain the optimal maintenance equipment information.

[0012] In a second aspect, the present application also provides a maintenance equipment information prediction device based on a digital twin model, including:

[0013] An equipment data acquisition module, configured to acquire equipment record information, equipment detection information, and equipment environment information of the object equipment;

[0014] A twin model determination module, configured to determine each digital twin description layer of the object equipment according to the equipment record information, the equipment detection information, and the equipment environment information;

[0015] A twin model description module, configured to perform interactive description on each of the digital twin description layers according to the equipment record information, the equipment detection information, and the equipment environment information to obtain equipment physical twin status information;

[0016] A fault information prediction module, configured to use each equipment maintenance physical prediction model and equipment maintenance machine prediction model respectively, and predict the fault information of the object equipment according to the equipment physical twin status information to obtain each maintenance equipment fault information;

[0017] A maintenance equipment prediction module, configured to perform information isolation prediction on the maintenance equipment information of the object equipment according to each of the maintenance equipment fault information to obtain each maintenance equipment prediction information;

[0018] A maintenance equipment determination module, configured to select the optimal information from each of the maintenance equipment prediction information according to the application scenario parameters and application efficiency parameters of the object equipment to obtain the optimal maintenance equipment information.

[0019] The above-mentioned maintenance equipment information prediction method and device based on a digital twin model can accurately reflect the actual working state of the equipment under different environmental conditions by constructing the digital twin description layer of the equipment, and then monitor and diagnose the operation of the equipment in real time. Further, with the help of the equipment maintenance physical prediction model and the machine learning prediction model, it can intelligently predict potential fault points according to the physical twin status information of the equipment, and optimize the selection of maintenance equipment through information isolation prediction. It can not only effectively improve the accuracy of maintenance material preparation, thereby improving the maintenance efficiency, but also improve the accuracy of fault prediction, identify and isolate possible fault information in advance, thereby reducing the maintenance time and cost caused by sudden faults, and significantly improving the maintainability and operation safety of the equipment. Description of the Drawings

[0020] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0021] Figure 1 It is an application environment diagram of a maintenance equipment information prediction method based on a digital twin model in an embodiment;

[0022] Figure 2 It is a flowchart of a maintenance equipment information prediction method based on a digital twin model in an embodiment;

[0023] Figure 3 It is a flowchart of a method for obtaining maintenance equipment fault information in an embodiment;

[0024] Figure 4 It is a flowchart of a method for obtaining equipment physical twin state information in an embodiment;

[0025] Figure 5 It is a flowchart of a method for obtaining maintenance equipment prediction information in an embodiment;

[0026] Figure 6 It is a flowchart of a method for obtaining optimal maintenance equipment information in an embodiment;

[0027] Figure 7 It is a flowchart of a method for obtaining optimal maintenance equipment information in another embodiment. Detailed implementation manners

[0028] In order to make the objectives, technical solutions and advantages of the present application more clear and understandable, the following further details the present application in combination with the 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.

[0029] A maintenance equipment information prediction method based on a digital twin model provided by an embodiment of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed in the cloud or other network servers. Among them, the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0030] In an exemplary embodiment, as Figure 2As shown, a prediction method for maintenance equipment information based on a digital twin model is provided. Taking the server in Figure 1 as an example for illustration, it includes the following steps 202 to step 212. Among them:

[0031] Step 202, obtain the equipment record information, equipment detection information, and equipment environment information of the target equipment.

[0032] Among them, the target equipment can be a specific mechanical equipment or system that needs to be monitored, maintained, and optimized. It can be equipment in any field such as industry, transportation, energy, etc., such as power equipment, manufacturing machinery, vehicles, or airplanes.

[0033] Among them, the equipment record information can be the historical data of the target equipment, including the production information of the equipment, maintenance history, fault records, component replacement cycles, maintenance plans, etc.

[0034] Among them, the equipment detection information can be real-time data on the current operating state of the equipment obtained through sensors, detection equipment, or manual inspections, including parameters such as temperature, pressure, vibration, flow rate, current, and power.

[0035] Among them, the equipment environment information can be the external environmental conditions where the equipment is located, such as factors such as temperature, humidity, air pressure, vibration, and pollution.

[0036] Specifically, through sensors and automated detection systems, various basic data of the target equipment are collected, including equipment record information, equipment detection information, and equipment environment information. The equipment record information usually includes the equipment composition structure data, equipment usage record data, equipment fault record data, and equipment maintenance record data of the target equipment, such as the history of fault occurrence, maintenance records, component replacement cycles, etc. The equipment detection information includes real-time data during the actual use of the equipment, such as temperature, pressure, vibration, power consumption, etc. The equipment environment information involves various parameters of the working environment where the equipment is located, such as the humidity, temperature, load condition, and external pressure of the workplace. These external factors directly affect the operating performance and lifespan of the equipment.

[0037] Step 204, determine each digital twin description layer of the target equipment according to the equipment record information, equipment detection information, and equipment environment information.

[0038] Among them, the digital twin description layer can be a component of the digital twin model, used to represent different dimensions or levels of the equipment, including the digital twin equipment layer (physical structure and performance layer), the digital twin system layer (control and operation layer), and the digital twin environment layer (external environment impact layer).

[0039] Specifically, since digital twin is a technology for digitally representing physical equipment and can simulate the behavior and state of the equipment, it can be decomposed into multiple different digital twin description layers for description according to the complexity and diversity of equipment record information, equipment detection information, and equipment environment information. Further, based on the equipment record information, equipment detection information, and equipment environment information, select the appropriate layers from the digital twin model created according to historical information to describe each of the above-mentioned information. For example, the digital twin equipment layer, digital twin system layer, and digital twin environment layer can be selected from the digital twin model. For example, the digital twin equipment layer focuses on the physical characteristics of the equipment, and real-time monitors the mechanical components, structural changes, and performance data of the equipment, such as temperature, pressure, vibration, etc., so as to reflect the current working state of the equipment. The digital twin system layer involves the control and information processing system inside the equipment, simulates the control logic of the equipment, sensor feedback, and the operation of the actuator, and helps to understand the operation behavior and intelligent decision-making process of the equipment at the system level. The digital twin environment layer takes into account the influence of external factors on the equipment, such as the temperature, humidity, air pressure, etc. of the working environment, and these factors will directly or indirectly affect the operation efficiency and health status of the equipment.

[0040] Step 206, according to the equipment record information, equipment detection information, and equipment environment information, perform interactive description in each digital twin description layer to obtain the equipment physical twin state information.

[0041] Among them, the interactive description can be the information exchange and fusion between the various description layers of the digital twin model to construct the comprehensive physical twin state of the equipment.

[0042] Among them, the equipment physical twin state information can be the current operating state of the equipment obtained through the interactive analysis of each description layer based on the digital twin model. These information include the mechanical, control, and environmental states of the equipment, and can reflect the health status, potential problems, and operating performance of the equipment.

[0043] Specifically, the equipment record information, equipment detection information, and equipment environment information are respectively input into the digital twin equipment layer, digital twin system layer, and digital twin environment layer. For the digital twin equipment layer, the operating conditions of the equipment are monitored in real time through the physical structure and performance status data of the target equipment. For example, information such as the temperature, vibration, and pressure of mechanical components is collected through sensors and real-time detection devices to evaluate the health status of the equipment. Further analysis can reveal equipment wear, deviation, or other potential faults. The digital twin system layer analyzes the operation logic of the equipment, actuator response, sensor feedback, and execution of control commands by integrating the control system data inside the equipment, helping to determine whether the system is operating according to the predetermined logic and whether there may be control deviations or faults inside the system. For example, when the control signal does not match the sensor feedback, it may mean that a certain module in the system has failed or shows signs of failure. Finally, the digital twin environment layer provides relevant data on the external environment where the equipment is located, such as temperature, humidity, air pressure, etc. These external factors can directly affect the performance of the equipment. For example, high temperature may cause components to overheat, and high humidity may cause electrical faults. By interactively fusing the data of the digital twin equipment layer, digital twin system layer, and digital twin environment layer, the operating status of the equipment can be comprehensively evaluated to form a complete physical twin status information of the equipment. The physical twin status information of the equipment can not only accurately reflect the current health status of the equipment but also predict future fault trends based on historical data and real-time data, thus providing data support for subsequent fault diagnosis and maintenance decision-making.

[0044] Step 208: Respectively use each equipment maintenance physical prediction model and equipment maintenance machine prediction model to predict the fault information of the target equipment according to the physical twin status information of the equipment, and obtain the fault information of each maintenance equipment.

[0045] Among them, the equipment maintenance physical prediction model can be a physical model based on the physical characteristics, usage history, and operating environment of the equipment for predicting equipment faults.

[0046] Among them, the equipment maintenance machine prediction model can be a model based on machine learning algorithms that uses historical fault data, equipment usage patterns, and real-time detection information to predict equipment faults.

[0047] Among them, the fault information can be relevant data on any abnormal status or problem that may occur during the operation of the equipment or in the future.

[0048] Among them, the fault information of the maintenance equipment can be the fault data of tools, components, or equipment related to the equipment.

[0049] Specifically, each equipment maintenance physical prediction model and equipment maintenance machine prediction model are used respectively to predict the fault information of the target equipment according to the equipment physical twin state information. The equipment maintenance physical prediction model includes an inherent fault calculation model, a usage fault calculation model, and an environmental stress fault calculation model, while the equipment maintenance machine prediction model includes a convolutional neural network (CNN), a long short-term memory network (LSTM), a deep belief network (DBN), etc. For the inherent fault calculation model, based on the design and manufacturing characteristics of the equipment, it analyzes the faults that may occur due to its own structural or material defects under normal operating conditions. Such models usually focus on the long-term wear, aging, and material fatigue of the equipment, and predict the inherent faults that the equipment may generate without external interference. For the usage fault calculation model, it focuses on the fault modes of the equipment under specific working conditions, taking into account the factors such as the load, operation mode, and frequent start and stop that the equipment is subjected to in actual applications, and predicts the faults that may occur during its use. For example, overload or frequent high-load operation may cause early damage to some components. For the environmental stress fault calculation model, it takes into account the external environmental conditions in which the equipment is located, analyzes the effects of external stress factors such as high temperature, high humidity, and severe vibration on the equipment, and predicts the faults caused by environmental factors. These models help identify equipment faults caused by changes in external conditions.

[0050] Meanwhile, using a convolutional neural network (CNN), a long short-term memory network (LSTM), a deep belief network (DBN), etc., deep learning and pattern recognition can be performed on complex equipment data to further improve the accuracy of fault prediction. For the convolutional neural network (CNN), by using the convolutional layer to extract the spatial features in the equipment data, it is suitable for analyzing fault modes related to image or time series data. For example, CNN can be used to process vibration waveforms, heat maps, or other time series data collected from equipment sensors to identify potential fault features. For the long short-term memory network (LSTM), it is good at processing time series data and can effectively capture the time series information of long-term dependencies during the operation of the equipment; through memory units, LSTM can analyze the historical states of the equipment at different time points and identify potential problems caused by historical faults or abnormal behaviors, especially suitable for predicting the occurrence time and development trend of equipment faults. For the deep belief network (DBN), it is usually used to extract features and perform pattern recognition from a large amount of unlabeled data. It can identify complex correlation patterns in the equipment state through multi-layer non-linear transformations, especially suitable for complex and multi-dimensional equipment data, and obtain high-level abstract features through layer-by-layer learning to predict potential fault information.

[0051] Step 210, according to the fault information of each maintenance equipment, perform information isolation prediction on the maintenance equipment information of the target equipment to obtain the prediction information of each maintenance equipment.

[0052] Among them, the information isolation prediction can be a technical method for multiple fault information. By independently packaging the characteristic data of different maintenance equipment or fault types combined with the original data, separate processing and analysis are carried out to avoid information interference or cross - influence.

[0053] Among them, the maintenance equipment prediction information can be the prediction data related to the equipment maintenance requirements obtained through the analysis of the fault prediction model.

[0054] Specifically, for each maintenance equipment fault information, the system extracts relevant fault characteristics, such as the frequency of fault occurrence, historical maintenance records, environmental influence factors (such as temperature, humidity, etc.), and key parameters such as the equipment usage mode. At the same time, the system packages each maintenance equipment fault information with the corresponding fault characteristic information. Each type of fault characteristic information corresponds to different maintenance equipment. For example, some faults may involve the maintenance of the electronic control system, while other faults may be related to the damage of mechanical components. Each packaged data packet can display the fault characteristics corresponding to each maintenance equipment fault information, that is, each maintenance equipment fault information and the corresponding fault characteristic information will be isolated into independent data packets. The prediction model matched by each data packet will independently analyze and predict the occurrence trend and severity of the fault, judge whether maintenance is required, and evaluate the equipment needed for maintenance. At this time, each prediction model works in parallel with each other, without mutual influence, and independently completes the fault prediction of different maintenance equipment. Through parallel processing, the system can quickly and accurately provide personalized prediction information for each maintenance equipment, thus avoiding redundant prediction or data interference, ensuring that the requirements of each maintenance equipment are fully analyzed and optimized, and obtaining the prediction information of each maintenance equipment.

[0055] Step 212: According to the application scenario parameters and application efficiency parameters of the target equipment, select the optimal information from each maintenance equipment prediction information to obtain the optimal maintenance equipment information.

[0056] Among them, the application scenario parameters can be the specific operating conditions of the equipment in a specific working environment, such as working load, operation frequency, environmental temperature, humidity, interaction, personnel protection, etc.

[0057] Among them, the application efficiency parameters can be used to evaluate the effect and efficiency of the maintenance process in a specific application scenario. This includes factors such as the time required for maintenance, cost - effectiveness, degree of maintenance, and repair integrity.

[0058] Among them, the optimal maintenance equipment information can be the most suitable maintenance tool or component selected from multiple optional maintenance equipment under specific application scenarios and efficiency requirements.

[0059] Specifically, the system obtains the application scenario parameters of the object equipment, where the application scenario parameters describe the specific working environment, operating conditions, and interaction with the outside of the equipment, such as factors like the temperature, humidity, load, pressure, vibration, whether there is danger, and whether it is necessary to operate with faults in the workplace. These parameters reflect the operating state of the equipment in different working environments and directly affect the tool selection during the maintenance process. For example, in high-temperature or extreme environments, specific protective tools or high-temperature-resistant materials may be required; while in scenarios with high-load operations, maintenance equipment with higher strength and wear resistance may be needed. Therefore, the system will select the most suitable maintenance equipment according to these scenario characteristics to adapt to the current working conditions. At the same time, the system also obtains the application efficiency parameters, that is, the maintenance efficiency requirements in specific working scenarios. These parameters not only include the time efficiency and cost-effectiveness of maintenance but also involve the degree of maintenance and the completeness of repair in the current scenario. For example, in some scenarios, equipment failures may be simply repaired locally according to the needs of the current scenario, while in other cases, multiple components may be completely repaired or replaced according to the needs of other scenarios. Moreover, the system will evaluate the effectiveness of different maintenance equipment during the repair process based on the complexity of the work tasks of the target equipment and the urgency of the repair, and consider the completeness of the repair (such as whether it is necessary to fully restore the original performance of the equipment or only perform temporary repairs to ensure short-term operation). Based on the application scenario parameters and application efficiency parameters, the system will comprehensively consider these factors and select the most suitable equipment for the current maintenance task from the maintenance equipment prediction information generated by each parallel prediction model to form the optimal maintenance equipment information.

[0060] In the above method for predicting maintenance equipment information based on the digital twin model, by constructing the digital twin description layer of the equipment, the actual working state of the equipment under different environmental conditions can be accurately reflected, and then the operation of the equipment can be monitored and diagnosed in real time. Further, with the help of the equipment maintenance physical prediction model and the machine learning prediction model, potential fault points can be intelligently predicted based on the physical twin state information of the equipment, and the selection of maintenance equipment can be optimized through information isolation prediction. This can not only effectively improve the accuracy of maintenance material preparation, thereby improving the maintenance efficiency, but also improve the accuracy of fault prediction, identify and isolate possible fault information in advance, thus reducing the maintenance time and cost caused by sudden faults, and significantly enhancing the maintainability and operation safety of the equipment.

[0061] In an exemplary embodiment, as Figure 3 shown, each equipment maintenance physical prediction model and the equipment maintenance machine prediction model are respectively used to predict the fault information of the target equipment according to the physical twin state information of the equipment, and the fault information of each maintenance equipment is obtained, including steps 302 to 306. Among them:

[0062] Step 302: Use each equipment maintenance physical prediction model to predict the maintenance equipment information of the target equipment based on the equipment physical twin status information, and obtain the physical model equipment failure information for each model.

[0063] Among them, the physical model equipment failure information can be the failure data obtained based on physical principles and the working environment of the equipment when predicting equipment failures through physical modeling methods.

[0064] Among them, the inherent failure calculation model can be a calculation model that focuses on the inherent defects in the design and manufacturing stages of the equipment, or the failures that are bound to occur after a certain period of use. These defects usually do not depend on the usage of the equipment or external environmental factors, but originate from design defects, material defects in the equipment itself, or problems existing during long-term use.

[0065] Among them, the usage failure calculation model can be a calculation model that focuses on the impact of factors such as the load, usage frequency, and operation mode of the equipment during actual operation on equipment failures.

[0066] Among them, the environmental stress failure calculation model can be a calculation model that focuses on the failure risk of the equipment under specific environmental conditions, especially those failures caused by external environmental factors such as temperature, humidity, corrosive substances, and vibration.

[0067] Specifically, since the equipment maintenance physical prediction models are respectively the inherent failure calculation model, the usage failure calculation model, and the environmental stress failure calculation model, the equipment physical twin status information is respectively input into the inherent failure calculation model, the usage failure calculation model, and the environmental stress failure calculation model for prediction.

[0068] The inherent failure calculation model also focuses on the possible defects in the design and manufacturing stages of the equipment, especially those failures caused by the material properties of components, processing technology, or improper design. These problems are usually latent and difficult to appear in the initial stage of the equipment, but may gradually emerge over time. For example, in a high-stress environment, some mechanical components may develop cracks or material fatigue due to improper material selection or minor defects in production. The inherent failure calculation model predicts the failures that may occur due to inherent factors in the equipment without external overloading or abnormal operation by deeply analyzing the equipment design, the mechanical properties of materials, and its manufacturing process, combined with the historical usage of the equipment.

[0069] For the inherent failure calculation model, the calculation formula of the inherent failure calculation model is:

[0070]

[0071]

[0072]

[0073] Among them, N(t) is the remaining life at time t, A is the material fatigue characteristic constant, which is obtained by obtaining the basic fatigue characteristics of the material under different stresses through laboratory material tests such as fatigue tests, E is the material elastic modulus, which is directly measured by tensile tests or other mechanical test methods to obtain the elastic modulus of the material, b and c are fitting coefficients, which are empirical coefficients obtained by using historical failure data and experimental data through regression analysis fitting, F i is the environmental factor, which is calculated by collecting environmental data in real time through environmental sensors (such as temperature, humidity, corrosion sensors) installed on the equipment, is the sensitivity coefficient of the environmental factor, which is obtained by controlling the environmental factor to conduct experiments, observing its influence on the material life, and fitting the sensitivity coefficient, m is the number of environmental factors, D(t) is the time Cumulative fatigue damage, which is obtained by calculating the microscopic damage index of the material using a material damage model (such as a fatigue damage model), D max is the maximum damage resistance of the material, which is determined by the material ultimate fatigue test to determine the maximum damage value that the material can withstand, is the microscopic structure damage influence coefficient, which is obtained by fatigue tests or stress tests, and fitting the life changes under different microscopic structure damage degrees, is the time stress, which is obtained by simulating the stress distribution of the equipment under different working conditions through FEA, is the reference stress of the material, which is determined by experiments under standard conditions for the material, k is the fatigue strength index, which is determined by fatigue test data using regression analysis or non-linear fitting methods, is the environmental influence index, which is estimated using multiple regression analysis based on environmental data and damage data, is the material microscopic structure change function, which is a function generated by simulating the microscopic structure change using material microscopic structure simulation software (such as MOOSE, Abaqus), is the inherent failure rate at time t, is the life change rate.

[0074] Among them, a fault calculation model is used to start from the actual operating conditions of the device, taking into account the impacts of factors such as the workload, usage frequency, and operating habits that the device is subjected to during operation on its performance. The focus of this model is to evaluate the faults that may be caused by overuse, incorrect operation, or high-load operation of the device in actual applications. For example, when the device is under high load or continuous operation for a long time, some components (such as motors, transmission systems, bearings, etc.) will fail prematurely due to excessive wear or fatigue. The fault calculation model is used to identify and predict the possible faults of the device under specific usage conditions by monitoring the real-time working state of the device and combining parameters such as load, operating speed, and working cycle. This method helps to formulate a maintenance plan according to the actual usage situation to ensure that the device maintains a good operating state under high load or high-frequency use.

[0075] For the use of the fault calculation model, the calculation formula of the fault calculation model is as follows:

[0076]

[0077]

[0078]

[0079] Among them, is the usage failure rate at time t, is the benchmark failure rate, which is determined by statistically analyzing the failure rate under standard operating conditions from the historical failure records of the equipment. P(t) is the actual operating load at time t, which is measured in real time by a load sensor for the operating load of the equipment. P max is the maximum design load of the equipment, which is the determined value by referring to the design specifications or technical manuals of the equipment. is the load sensitivity coefficient, which is determined by regression analysis using historical operating load and failure rate data. H(t) is the operating health index at time Combining multiple health indicators (such as temperature, vibration, wear degree, etc.), the comprehensive health index is calculated by weighted or machine learning methods. is the sensitivity coefficient of the health index on the failure rate, which is estimated and determined by regression analysis based on the data of historical health index and failure rate. is the usage failure rate after combining the operation behavior at time t. is the j-th operation behavior characteristic at time t, which is the characteristic data determined by extracting operation behavior data from the operating system or control system, such as start frequency, number of overload operations, number of emergency stops, etc. is the influence coefficient of the j-th operation on the failure rate, which is determined by multiple regression analysis using historical operation behavior data and failure rate data. n is the number of operation behavior characteristics. The failure rate of combined operation load, operation behavior and health status at time t.

[0080] The environmental stress failure calculation model focuses on the stress generated by the external environment on the equipment, especially the challenges that the equipment may face in extreme weather or harsh working environments. The equipment may encounter various stress sources under different environmental conditions, such as temperature fluctuations, humidity, dust, chemical corrosion, etc. These factors will have a long-term impact on the physical performance of the equipment. For example, at high temperatures, the internal electronic components of the equipment may fail due to thermal expansion, or in a high-humidity environment, metal parts are prone to corrosion. The environmental stress failure calculation model predicts the failure mode of the equipment under specific environmental stress by analyzing the characteristics of the environment where the equipment is located, such as climate conditions, humidity, pollutants, etc. This model helps to optimize the environmental stress resistance of the equipment in the design stage and guides how to take targeted protection measures during the maintenance process to extend the service life of the equipment.

[0081] For the environmental stress failure calculation model, the calculation formula of the environmental stress failure calculation model is:

[0082]

[0083]

[0084]

[0085] Among them, is the failure rate under the influence of environmental stress at time t, is the basic failure rate when there is no environmental influence, which is measured through experiments under controlled environmental conditions, E k (t) is the k-th environmental stress factor at time t, the stress factor monitored in real time by installing corresponding sensors (such as temperature sensors, humidity sensors, salt spray sensors, etc.), E max,k is the maximum design value of the k-th environmental stress factor, which is the maximum design value obtained by referring to the design specifications or technical manuals of the equipment, is the sensitivity coefficient of the k-th environmental stress factor, which is determined by regression analysis using historical environmental stress data and failure rate data. p is the number of environmental stress factors, D 环境 (t) is the cumulative environmental stress damage at time t, E k (t’) is the k-th environmental stress factor at time t, the stress factor monitored in real time by installing corresponding sensors (such as temperature sensors, humidity sensors, salt spray sensors, etc.), is the damage attenuation coefficient of the k-th environmental stress factor, which is determined by regression analysis using historical environmental stress data and damage data, is the failure rate after the combined influence of environmental stress at time t, It is the cumulative impact coefficient of environmental stress on the failure rate, which is determined by regression analysis using historical environmental stress cumulative damage data and failure rate data.

[0086] Step 304: Use each equipment maintenance machine prediction model respectively. According to the equipment physical twin state information, predict the maintenance equipment information of the target equipment to obtain the equipment failure information of each machine model.

[0087] Among them, the equipment failure information of the machine model can be the failure information obtained through machine learning or artificial intelligence model analysis. Different from the physical model, the machine learning model predicts the possible failures of the equipment through learning and training of a large amount of historical operation data.

[0088] Specifically, since the equipment maintenance machine prediction models are the convolutional neural network, long short-term memory network, and deep belief network respectively, the equipment physical twin state information is input into the convolutional neural network, long short-term memory network, and deep belief network respectively for prediction.

[0089] Among them, the convolutional neural network (CNN) is a deep learning model suitable for processing signals with spatial structure and local correlation. In equipment failure prediction, CNN is mainly used to automatically extract features from sensor data and perform fault mode recognition. Through convolutional operations, CNN can capture the local patterns of signals during equipment operation, especially in signals such as vibration, sound, and temperature. These patterns may reflect the subtle differences between normal operation and failure of the equipment. CNN is good at identifying abnormal waveforms, frequency changes, and irregular patterns in signals. Therefore, when processing multi-dimensional signals or time series signals, it can effectively extract the potential hidden fault patterns of the equipment. For example, CNN can perform convolutional processing on equipment vibration data to detect mutations or abnormalities in its spectrum, which are often precursors of equipment failures.

[0090] Among them, the long short-term memory network (LSTM) is specifically used to process time series data and can capture long-term dependencies in the data. Through its unique gating mechanism, LSTM can effectively remember and transmit important information in the time series, avoiding the problem of gradient disappearance encountered by traditional recurrent neural networks (RNNs) in long sequences. In equipment failure prediction, LSTM can identify the trend changes in the long-term operation of the equipment by analyzing historical operation data such as temperature changes, vibration intensity, and pressure fluctuations. For example, LSTM can identify the gradual increase trend of temperature or vibration over a long time, predict the possible failure time of the equipment, and issue an alarm in advance. This model is very suitable for processing fault patterns with time dependencies. Especially when the equipment shows progressive failures or cumulative damage, LSTM can make early warnings through long-term data analysis before the failure appears.

[0091] Among them, the Deep Belief Network (DBN) is a neural network model that learns complex data representations through layer-by-layer non-linear transformations. The structure of the DBN enables it to extract deep latent features from a large amount of complex historical data, especially suitable for the processing of multi-dimensional data. In equipment fault prediction, the DBN can automatically extract and model the fault features of different components during the operation of the equipment through a multi-layer unsupervised training process. This enables the DBN to effectively learn and identify potential fault signals even in the case of highly diverse data, the existence of various interference factors, or complex fault patterns. For example, in the face of different types of equipment, different fault patterns, and environmental interference, the DBN can automatically identify complex fault patterns of the equipment in a specific working environment through deep feature learning and predict potential systematic faults in advance. Since the DBN can extract complex non-linear features from large-scale historical data, it can provide more accurate pre-judgments and decision-making support when dealing with equipment fault prediction.

[0092] Step 306: Using the equipment accessory feature information of the target equipment as guiding information, perform consistency identification on the fault information of each physical model equipment and each machine model equipment to obtain the fault information of each maintenance equipment.

[0093] Among them, the equipment accessory feature information can be the detailed information of each accessory or component in the equipment, such as the model, material, usage, working environment, service life, manufacturer, etc. of the accessory.

[0094] Among them, the consistency identification can be to perform cross-comparison and analysis among the fault information generated by multiple prediction models to ensure the consistency and accuracy of the results output by different models in actual situations.

[0095] Specifically, since the fault information predicted by the physical model and the machine model may involve the same or similar maintenance equipment, the equipment part feature information of the target equipment is used as the guiding information for consistency identification, that is, the equipment part feature information of the target equipment is used to define the error calculation items for consistency identification. The output results of the physical model and the machine learning model are carefully compared according to the equipment part feature information of the parts, and the actual situations of the maintenance equipment involved in each prediction result are comprehensively considered (such as the material, durability, working conditions, etc. of the parts). For example, if the physical model predicts that a certain part may fail due to excessive environmental stress, while the machine learning model predicts that the part has problems due to excessive wear, through the consistency matching of the part characteristics, the system can determine whether these two predictions are for the same fault mode, or different fault risks caused by different reasons. If all are consistent, the fault information of each maintenance equipment is directly output. If not, the fault information of each maintenance equipment that is temporarily consistent is output, and the physical model and neural network corresponding to the inconsistent information are used to re-predict until consistency is achieved, and the fault information of each maintenance equipment after post-processing is output.

[0096] In this embodiment, by combining the equipment maintenance physical prediction model and the machine prediction model, the fault information of the maintenance equipment is predicted. The physical model can identify potential faults from the operating state and environmental stress of the equipment, while the machine learning model can mine complex patterns in historical data. Through the combination of the two, the possible faults of the maintenance equipment can be predicted comprehensively and accurately. At the same time, through consistency identification, the system can eliminate conflicts or repeated predictions between different models, ensure the unity and efficiency of the fault information of the maintenance equipment, provide more reliable data support for subsequent maintenance decisions and resource allocation, and thus improve the maintenance efficiency and reliability of the equipment.

[0097] In an exemplary embodiment, as Figure 4 shown, according to the equipment record information, equipment detection information, and equipment environment information, interactive descriptions are performed at each digital twin description layer to obtain the equipment physical twin state information, including steps 402 to 410. Among them:

[0098] Step 402, input the equipment record information, equipment detection information, and equipment environment information into the digital twin equipment layer, digital twin system layer, and digital twin environment layer respectively to obtain the equipment real-time operating state data, system overall operating stability data, and environmental impact simulation data.

[0099] Among them, the digital twin equipment layer can be a digital twin working layer that is digitally modeled and driven by real-time data, and virtually reproduces the working state and operation process of the actual equipment.

[0100] Among them, the digital twin system layer can be a digital reproduction of the entire system, including a digital twin working layer of multiple devices, subsystems, and their interrelationships and collaborative work.

[0101] Among them, the digital twin environment layer can be a digital twin working layer that simulates and analyzes the impact of external environmental factors on equipment and systems.

[0102] Among them, the real-time operating state data of the equipment can be the real-time monitoring data obtained by simulating on the digital twin equipment layer of the equipment, including various sensor data of the device (such as temperature, pressure, vibration, etc.), which is used to reflect the health status and operating performance of the device at the current moment.

[0103] Among them, the overall stability data of the system operation can be obtained by analyzing and integrating the operating states of multiple devices and system components through the digital twin system layer, and the overall stability and performance status of the system can be obtained.

[0104] Among them, the environmental impact simulation data can be the data generated by simulating the impact of external environmental factors (such as temperature, humidity, pressure, etc.) on the equipment and systems through the digital twin environment layer.

[0105] Specifically, the equipment record information, equipment detection information, and equipment environment information will be respectively input into the digital twin equipment layer, digital twin system layer, and digital twin environment layer at three different levels. In the digital twin equipment layer, the real-time operating state of the equipment will be processed and simulated to generate real-time operating state data of the equipment including data such as equipment health, performance, and workload; in the digital twin system layer, the system will conduct an overall performance evaluation, considering the interaction of each device and component, to generate overall stability data of the system operation, reflecting the operating stability of the entire system; while in the digital twin environment layer, the system will predict the potential impact of the external environment on the equipment by simulating environmental changes, generating environmental impact simulation data to help understand the interference or assistance to the equipment operation under different environmental conditions.

[0106] Step 404, apply the real-time operating state data of the equipment to the digital twin system layer and the digital twin environment layer to obtain equipment-system interaction data and equipment-environment state data.

[0107] Among them, the equipment-system interaction data can be the data generated by the interaction between the real-time operating state data of the equipment and other system components, and these data reflect how the device affects the overall performance and stability of the system during the process of collaborative work with other devices or subsystems.

[0108] Among them, the equipment-environment state data can be the data generated by combining the real-time operating state data of the equipment with the external environmental data, reflecting how the external environment affects the operation of the equipment.

[0109] Specifically, the real-time operation status data of the equipment is input into the digital twin system layer and the digital twin environment layer respectively. In the digital twin system layer, by combining these real-time data with the operation status of other components and devices in the system, the system can analyze the interaction between the equipment and other system components, identify potential influencing factors, and generate equipment system interaction data, which includes how the equipment affects the stability and efficiency of the system, whether there are problems such as load overload and equipment collaboration; at the same time, the real-time operation data is also applied to the digital twin environment layer to obtain equipment environment status data, which reflects the working performance and health status of the equipment in the actual environment and can illustrate the direct impact of the external environment (such as temperature, humidity, climate and other factors) on the equipment performance and efficiency, thus providing data support for the adaptability evaluation of the equipment.

[0110] Step 406, apply the overall system operation stability data to the digital twin equipment layer and the digital twin environment layer to obtain system equipment command data and system environment status data.

[0111] Among them, the system equipment command data can be the overall system operation stability data and the data generated in the digital twin system layer regarding system operation command. These data guide how the equipment operates and adjusts according to the overall requirements and goals of the system.

[0112] Among them, the system environment status data can be the combination of the overall system operation stability data and the external environmental conditions, generating the operation status reflecting the system under the influence of different environments.

[0113] Specifically, the overall system operation stability data is input into the digital twin equipment layer and the digital twin environment layer respectively. In the digital twin equipment layer, these stability data of the system layer are applied to the analysis of specific equipment to generate system equipment command data, which reflects how the overall operation status of the system affects the operation of each individual equipment, helps judge the response of the equipment to system load fluctuations, and whether the equipment needs to be adjusted to maintain the stable operation of the system; in the digital twin environment layer, the stability of the system is combined with external environmental factors to generate system environment status data, which reflects the mutual influence between external environmental factors and the overall system operation. For example, in extreme weather or high load conditions, whether the equipment can continue to operate stably under the existing environmental conditions, or whether the system will be affected by environmental changes resulting in reduced efficiency or failures.

[0114] Step 408, apply the environmental impact simulation data to the digital twin equipment layer and the digital twin system layer to obtain environmental equipment impact data and environmental system impact data.

[0115] Among them, the environmental equipment impact data can be data generated by combining environmental impact simulation data with the equipment operation status, reflecting the impact of the external environment on the operation of a single device.

[0116] Among them, the environmental system impact data can be data generated by the impact of environmental impact simulation data on the operation of the entire system. These data reveal the impact of environmental changes (such as extreme climate, temperature and humidity changes, etc.) on the overall operation of the system, and help to evaluate the potential risks of environmental factors on the system stability, efficiency and lifespan.

[0117] Specifically, the environmental impact simulation data is input into the digital twin equipment layer and the digital twin system layer. In the digital twin equipment layer, these environmental data help to simulate the performance of the equipment under specific environmental conditions, generating environmental equipment impact data, which describe how environmental conditions (such as temperature, humidity, pollution, etc.) affect the operation efficiency, health status and failure risk of the equipment. For example, extreme temperature may cause the cooling system to fail or the performance of electronic components to decline; in the digital twin system layer, the environmental data will be used to analyze the impact of the environment on the entire system, generating environmental system impact data, which reflect the impact of environmental factors on the overall load and performance of the system. For example, high humidity climate may cause electrical equipment failures, or high temperature environment makes the cooling system burden heavier, affecting the stability of the entire system.

[0118] Step 410, perform decision-level fusion on the equipment real-time operation status data, the overall system operation stability data, the environmental impact simulation data, the equipment-system interaction data, the equipment environmental status data, the system-equipment command data, the system environmental status data, the environmental equipment impact data and the environmental system impact data to obtain the equipment physical twin status information.

[0119] Among them, decision-level fusion can be a decision data set obtained by comprehensively analyzing multi-dimensional data from different levels (equipment, system, environment), eliminating redundancy and conflicts, and performing weighted processing through algorithms and models.

[0120] Specifically, the system will perform decision-level fusion on all the collected data. All data sources, including the equipment real-time operation status data, the overall system operation stability data, the environmental impact simulation data, the equipment-system interaction data, the equipment environmental status data, the system-equipment command data, the system environmental status data, the environmental equipment impact data and the environmental system impact data, will be integrated and analyzed through advanced data fusion algorithms. Specifically, data from different levels and dimensions (such as equipment real-time operation status, system stability, environmental impact, equipment adjustment data, etc.) are comprehensively processed and weighted analyzed. Combining algorithms, various types of data are integrated, redundant information is eliminated, and the mutual influence between data is modeled to generate the equipment physical twin status information.

[0121] In this embodiment, by inputting equipment record information, detection information, and environmental information into each level of the digital twin (equipment level, system level, environmental level) and performing data interaction and comprehensive analysis on these levels, it is possible to achieve comprehensive monitoring and simulation of the equipment operation status, system stability, and environmental impact. This multi-level and multi-dimensional information fusion not only enhances the control of the real-time operation status of the equipment but also reveals the comprehensive impact of different factors (such as environmental changes, system load, cooling adjustment, etc.) on the equipment performance. Through the decision-level fusion of various types of data, the system can generate accurate physical twin status information, providing a more accurate basis for equipment maintenance and optimization, thereby improving the operation efficiency, prediction ability, and fault warning ability of the equipment, and ultimately ensuring the efficient and safe operation of the equipment.

[0122] In an exemplary embodiment, as Figure 5 shown, according to the fault information of each maintenance equipment, information isolation prediction is performed on the maintenance equipment information of the target equipment to obtain the predicted information of each maintenance equipment, including steps 502 to 508. Among them:

[0123] Step 502, respectively extract features from the fault information of each maintenance equipment to obtain the marked feature data of each maintenance equipment.

[0124] Among them, the marked feature data of the maintenance equipment can be key data points extracted from the fault information of the maintenance equipment, used to describe and distinguish the possible fault characteristics of different maintenance equipment.

[0125] Specifically, respectively extracting features from the fault information of each maintenance equipment is mainly to analyze important data such as possible fault modes, fault frequencies, and fault types. The feature extraction process includes preprocessing the fault information, removing irrelevant data, and identifying important features related to faults through algorithms (such as statistical analysis, signal processing, or machine learning).

[0126] Step 504, perform packet processing on the fault information of each maintenance equipment and the marked feature data of the maintenance equipment corresponding to the fault information of each maintenance equipment to obtain the packetized fault information of each maintenance equipment.

[0127] Among them, packet processing can be a process of packing different types of data (such as fault information and feature data) into an overall data unit.

[0128] Among them, the packetized fault information of the maintenance equipment can be a data unit after packet processing, containing the fault information of the maintenance equipment and related marked feature data.

[0129] Specifically, match the fault information of each maintenance equipment and its corresponding marked characteristic data of the maintenance equipment. After the matching is completed, each group of data is respectively packetized, that is, the fault information of each maintenance equipment is packed together with its marked characteristic data to form "packetized maintenance equipment fault information", ensuring that each fault information is closely associated with its characteristic data and is not interfered by other data. The packetized maintenance equipment fault information will be displayed and shown together with the corresponding marked characteristic data of the maintenance equipment.

[0130] Step 506: Select the target maintenance equipment prediction model corresponding to each marked characteristic data of the maintenance equipment from the preset set of maintenance equipment prediction models.

[0131] Among them, the preset set of maintenance equipment prediction models can be a set composed of multiple trained maintenance equipment prediction models, which is used to handle different types of maintenance equipment fault prediction tasks.

[0132] Among them, the target maintenance equipment prediction model can be the final model selected through feature matching in the preset set of maintenance equipment prediction models.

[0133] Specifically, since the preset set of maintenance equipment prediction models contains multiple different types of maintenance equipment prediction models, these models are trained based on different fault characteristics and data processing methods. By matching the marked characteristic data of each packetized maintenance equipment fault information and the maintenance equipment prediction model, the system can accurately select the maintenance equipment prediction model most relevant to each packetized maintenance equipment fault information as the most matching target maintenance equipment prediction model, that is, pair according to the marked characteristic data of the maintenance equipment and the maintenance equipment prediction model to determine the maintenance equipment prediction model corresponding to each packetized maintenance equipment fault information.

[0134] Step 508: Using each marked characteristic data of the maintenance equipment as guiding information, input each packetized maintenance equipment fault information into the corresponding target maintenance equipment prediction model to obtain each maintenance equipment prediction information.

[0135] Specifically, using each marked characteristic data of the maintenance equipment as guiding information, that is, the pairing information between the marked characteristic data of the maintenance equipment and the target maintenance equipment prediction model, input each packetized maintenance equipment fault information into the corresponding target maintenance equipment prediction model respectively. Each target maintenance equipment prediction model uses the corresponding packetized maintenance equipment fault information to conduct demand prediction analysis of the maintenance equipment. Each target maintenance equipment prediction model will calculate the input data according to the trained algorithm and output its corresponding maintenance equipment prediction information. These prediction information usually includes the probability of fault occurrence, possible fault types, maintenance suggestions, etc., to help maintenance personnel make effective decisions in practical applications.

[0136] In this embodiment, by extracting features and performing packet processing on the fault information of maintenance equipment, the system is helped to extract key features from complex fault data. The packet processing ensures the structuring and consistency of the information, facilitating subsequent processing and analysis. By selecting the most suitable target model from a preset set of maintenance equipment prediction models and using the extracted feature data as the guiding input, the system can accurately predict the fault information of various maintenance equipment. This method not only optimizes the prediction process but also selects the most suitable prediction model according to the characteristics of different maintenance equipment, improving the efficiency of fault diagnosis, ensuring the accuracy of maintenance decisions, and ultimately enhancing the maintenance effectiveness and reliability of the equipment.

[0137] In an exemplary embodiment, as Figure 6 shown, according to the application scenario parameters and application efficiency parameters of the target equipment, the optimal information is selected from the prediction information of each maintenance equipment to obtain the optimal maintenance equipment information, including steps 602 to 606. Among them:

[0138] Step 602, according to the application scenario parameters and application efficiency parameters of the target equipment, determine the optimization target of the equipment information for the target equipment.

[0139] Among them, the optimization target of equipment information can be the optimization target determined based on the application scenario and application efficiency parameters of the equipment during the equipment maintenance process. These targets reflect how to select the most suitable maintenance equipment under specific environments and requirements.

[0140] Specifically, through the application scenario parameters of the target equipment (such as equipment working conditions, environmental temperature and humidity, load conditions, etc.) and the application efficiency parameters in the current scenario (such as maintenance timeliness, repair integrity, resource consumption, etc.), the system needs to comprehensively consider these factors to determine the optimization target of maintenance equipment. For example, if the equipment works in a high-temperature environment, heat-resistant maintenance equipment may need to be selected preferentially; if the equipment needs to resume operation quickly, the repair speed will become the optimization target. Therefore, the system will establish the optimization target by analyzing the current working scenario and the required maintenance efficiency, usually by using an optimization algorithm to weight and integrate multiple targets to form the optimization target of the equipment information for the target equipment.

[0141] Step 604, according to the optimization target of equipment information, use each equipment information optimization algorithm to select the optimal information from the prediction information of each maintenance equipment to obtain the optimization data of each equipment information.

[0142] Among them, the equipment information optimization algorithm can be a mathematical method and calculation process for processing and analyzing the prediction information of maintenance equipment. Based on the set optimization target of equipment information, it selects the most suitable maintenance equipment by simulating the impact of different selections on the maintenance effect.

[0143] Among them, the optimized equipment information data can be a set of maintenance equipment information data obtained after being processed by an optimization algorithm. Each piece of data represents information such as the characteristics of a maintenance equipment, the fault prediction result, and the maintenance suitability, and after being evaluated by the optimization algorithm, it meets the requirements of a specific optimization goal.

[0144] Specifically, according to the previously set equipment information optimization goal, various information optimization algorithms are used to process the prediction information of the maintenance equipment. These algorithms can include genetic algorithms, particle swarm optimization algorithms, simulated annealing algorithms, etc. The purpose is to optimize the optimal solution that meets the requirements from some or all of the maintenance equipment among many possible maintenance equipment prediction information options by simulating the impact of different selections on the maintenance effect. Each optimization algorithm will be evaluated according to multiple dimensions such as maintenance efficiency, cost, and equipment suitability. Finally, each optimization algorithm outputs the corresponding optimized equipment information data.

[0145] Step 606: Select the data set with the smallest difference from the equipment information optimization goal among the optimized equipment information data to obtain the optimal maintenance equipment information.

[0146] Specifically, the system will select the maintenance equipment information with the smallest difference from the optimization goal from each optimized equipment information data based on the target optimization standard. Specifically, the system will calculate the difference between each optimized equipment information data and the target optimization goal (such as maintenance timeliness, cost, equipment matching degree, etc.), and by screening the data with the smallest difference from the goal, the optimal maintenance equipment information is determined. The key in the calculation process is to calculate the "fitness" of each maintenance equipment, that is, its matching degree with the preset optimization goal, and finally select the optimal maintenance equipment plan as the optimal maintenance equipment information to ensure the optimal allocation of resources and the maximization of efficiency during the maintenance process.

[0147] In this embodiment, by combining the application scenario parameters and application efficiency parameters of the equipment, the system can accurately determine the optimization goal of the maintenance equipment information, so as to select the most suitable maintenance equipment according to different working environments and efficiency requirements. Using each equipment information optimization algorithm, the system can screen out the optimal data that meets the requirements from a large amount of maintenance equipment prediction information, ensuring that the selected equipment can meet the performance requirements under a specific application scenario to the greatest extent. By further screening the data set with the smallest difference from the optimization goal from multiple optimization results, the system can provide the most suitable maintenance equipment information. It significantly improves the accuracy and efficiency of the selection of maintenance equipment, ensures that the maintenance work can be carried out under optimal conditions, reduces unnecessary resource waste, and improves the reliability and service life of the equipment.

[0148] In an exemplary embodiment, such as Figure 7As shown, select the data set with the smallest difference from the equipment information optimization target in each piece of equipment information optimization data to obtain the optimal maintenance equipment information, including steps 702 to 708. Among them:

[0149] Step 702, using the equipment information optimization target as a constraint condition, apply various Pareto optimization algorithms to find the Pareto frontiers in each piece of equipment information optimization data respectively, and obtain the Pareto frontier data for each piece of equipment.

[0150] Among them, the Pareto optimization algorithm can be an algorithm for multi-objective optimization problems. Its core idea is to find a set of "Pareto optimal solutions", that is, solutions in which none of the multiple optimization objectives can be further optimized without sacrificing other objectives. The Pareto optimization algorithms include the non-dominated sorting genetic algorithm (NSGA-II), the multi-objective differential evolution algorithm (MODE), the multi-objective ant colony optimization algorithm (MOACO), and the multi-objective gradient descent method (MOGD), etc.

[0151] Among them, the equipment Pareto frontier data can be a set of optimal solutions obtained by the Pareto optimization algorithm, and these solutions find the best balance among multiple optimization objectives (such as maintenance time, cost, repair quality, etc.).

[0152] Specifically, still continue to use all the optimization sub-objectives of the equipment information optimization target as the constraint conditions (objective conditions) for Pareto optimization, and use different Pareto optimization algorithms to screen out the optimal solution sets from the equipment information optimization data. Among them, each different Pareto optimization algorithm analyzes the trade-off relationships among all the optimization sub-objectives of the equipment information optimization target and identifies the "Pareto frontiers" - that is, the data sets of solutions that cannot be further optimized among multiple objectives. During this process, the system will perform multi-objective optimization on each piece of equipment information optimization data, find the data that cannot be further optimized in some objectives without affecting other objectives, and combine the application of the Pareto optimal principle to obtain a set of optimal solution sets that can best meet all the optimization sub-objectives of the equipment information optimization target, which is called "equipment Pareto frontier data".

[0153] Step 704, according to the application scenario parameters and application efficiency parameters, adjust each piece of equipment Pareto frontier data to obtain the adjusted Pareto frontier data for each piece of equipment.

[0154] Among them, the adjusted Pareto frontier data can be the data obtained by further optimizing and adjusting the frontier data according to the application scenario parameters and application efficiency parameters after obtaining the preliminary Pareto frontier data.

[0155] Specifically, the previously obtained equipment Pareto front data is adjusted and optimized according to application scenario parameters and application efficiency parameters. The application scenario parameters usually include the specific working environment of the equipment, such as temperature, humidity, pressure, load, etc. These factors determine the working characteristics of the equipment in different environments. For example, some maintenance equipment may perform better when working in a high-temperature environment, while some equipment is more adaptable to low temperatures or extreme humidity. The application efficiency parameters involve efficiency indicators in the maintenance process, such as maintenance speed, maintenance time limit, repair quality requirements, etc., which determine the optimal maintenance equipment to be selected under specific conditions.

[0156] The system will perform weighted adjustment on each piece of Pareto front data based on these factors to ensure that the weight of each piece of data in the objective function reflects the actual working environment and efficiency requirements. The adjustment process includes re-evaluating the adaptability of the maintenance equipment according to the operating conditions of the equipment (such as operating load, environmental changes, etc.), and dynamically adjusting the performance of the maintenance equipment in actual operation. For example, under high-load conditions, the system may tend to select equipment with higher load-bearing capacity or stronger durability, and vice versa, it may tend to select lightweight and efficient equipment. The adjusted data is called the adjusted Pareto front data.

[0157] Step 706, using the front data simulated annealing algorithm, perform local optimization on each adjusted Pareto front data to obtain each locally optimized Pareto front data.

[0158] Among them, the locally optimized Pareto front data can be data refined through further optimization means (such as the simulated annealing algorithm, etc.) on the basis of the adjusted Pareto front data.

[0159] Specifically, the system will perform local optimization on each adjusted Pareto front data using the front data simulated annealing algorithm. The front data simulated annealing algorithm is an optimization algorithm used to find an approximate global optimal solution, inspired by the annealing process in physics. In this process, the system will simulate a gradual decrease in a "temperature" parameter, so that the system gradually tends to a low-temperature state from the initial high-temperature state, thus avoiding falling into a local optimal solution.

[0160] Specifically, by introducing randomness, the frontier data simulated annealing algorithm can jump out of the local optimum during the search process and explore a wider solution space. At each "temperature" state, the frontier data simulated annealing algorithm evaluates the quality of the current solution and accepts a new solution with a certain probability, even if this solution may be worse than the current solution in some aspects. As the temperature decreases, the probability of accepting a worse solution gradually decreases, and the system will eventually converge to a better solution. In the optimization of adjusting each Pareto frontier data, the frontier data simulated annealing algorithm randomly perturbs each adjusted Pareto frontier data and evaluates the pros and cons of the perturbed result, gradually refining various indicators to find the best maintenance equipment selection plan. The data set after each adjusted Pareto frontier data passes through the frontier data simulated annealing algorithm corresponds to each local optimized Pareto frontier data.

[0161] Step 708: Perform clustering processing on each local optimized Pareto frontier data to obtain the optimal maintenance equipment information.

[0162] Specifically, the system further performs clustering processing on each local optimized Pareto frontier data. The purpose of clustering processing is to divide the maintenance equipment information with similar characteristics in the optimized data set into different groups in order to select the most representative maintenance equipment from them. The purpose of clustering is to reduce redundant information, simplify the selection range, and ensure that the most suitable maintenance equipment is selected from multiple optimized solutions. The clustering algorithms used for clustering processing on each local optimized Pareto frontier data include K-means, DBSCAN, etc. These algorithms divide data points into the same class according to the similarity between data. For example, when using K-means clustering, the system will select an appropriate number of clusters K, and then adjust the center point of each cluster through iteration, and finally assign the data to the cluster where the nearest center point is located. Each cluster represents the maintenance equipment information with similar characteristics, and the clustering result helps to effectively summarize the multi-dimensional attributes of different equipment information. Clustering each local optimized Pareto frontier data separately is to screen out the maintenance equipment information that is the most prominent and meets the requirements of the application scenario among all optimized data. The clustered data set will select the optimal maintenance equipment according to criteria such as minimum distance, maximum resource utilization, and best repair effect to ensure that the equipment can obtain the best maintenance support. The clustered information is used as the optimal maintenance equipment information.

[0163] In this embodiment, by taking the equipment information optimization target as a constraint condition and using the Pareto optimization algorithm to find the Pareto front in each equipment information data, the best balance point between multiple targets can be effectively identified, and an optimal solution can be provided. Further adjusting the Pareto front data according to the application scenario and application efficiency parameters can optimize the solution for actual needs, ensuring that the selected maintenance equipment achieves the best performance in different usage environments. Using the simulated annealing algorithm to locally optimize the adjusted front data can further improve the accuracy of the solution and avoid the trap of local optimal solutions. Finally, by clustering the locally optimized front data, a set of optimal maintenance equipment information with high consistency can be obtained, thereby providing an accurate and effective maintenance equipment selection solution. This series of steps ensures that the selection of maintenance equipment not only meets the actual needs but also maximizes efficiency and reduces costs, ultimately enhancing the reliability and maintenance effectiveness of the equipment.

[0164] It should be understood that although the steps in the flowcharts involved in the above-mentioned embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows; moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same moment, but can be executed at different moments, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0165] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented.

[0166] In an embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0167] In an embodiment, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the steps in the above-mentioned method embodiments.

[0168] 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 for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties, and the collection, use, and processing of the relevant data need to comply with the relevant regulations.

[0169] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, 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, it should be considered as the scope recorded in this specification.

Claims

1. A prediction method for maintenance equipment information based on a digital twin model, characterized in that, The method includes: Obtaining the equipment record information, equipment detection information, and equipment environment information of the target equipment; Determining each digital twin description layer of the target equipment according to the equipment record information, the equipment detection information, and the equipment environment information; Performing interactive description on each of the digital twin description layers according to the equipment record information, the equipment detection information, and the equipment environment information to obtain the equipment physical twin status information; Respectively using each equipment maintenance physical prediction model and equipment maintenance machine prediction model, and predicting the fault information of the target equipment according to the equipment physical twin status information to obtain each maintenance equipment fault information; Wherein, the equipment maintenance physical prediction model includes an inherent fault calculation model, and the calculation formula of the inherent fault calculation model is: Where, N(t) is the remaining life at time t, A is the material fatigue characteristic constant, E is the material elastic modulus, b and c are fitting coefficients, F i is the environmental factor, is the sensitivity coefficient of the environmental factor, m is the number of environmental factors, D(t) is the time cumulative fatigue damage, D max is the maximum damage tolerance of the material, is the microstructure damage influence coefficient, is the time stress, is the reference stress of the material, k is the fatigue strength index, is the environmental impact index, is the material microstructure change function, is the inherent failure rate at time t, is the life change rate; Performing information isolation prediction on the maintenance equipment information of the target equipment according to each of the maintenance equipment fault information to obtain each maintenance equipment prediction information; Selecting the optimal information from each of the maintenance equipment prediction information according to the application scenario parameters and application efficiency parameters of the target equipment to obtain the optimal maintenance equipment information.

2. The method according to claim 1, characterized in that, Respectively using each equipment maintenance physical prediction model and equipment maintenance machine prediction model, and predicting the fault information of the target equipment according to the equipment physical twin status information to obtain each maintenance equipment fault information, including: Respectively using each of the equipment maintenance physical prediction models, and predicting the maintenance equipment information of the target equipment according to the equipment physical twin status information to obtain each physical model equipment fault information; Respectively using each of the equipment maintenance machine prediction models, and predicting the maintenance equipment information of the target equipment according to the equipment physical twin status information to obtain each machine model equipment fault information; Using the equipment accessory feature information of the target equipment as the guiding information to perform consistency identification on each of the physical model equipment fault information and each of the machine model equipment fault information to obtain each of the maintenance equipment fault information.

3. The method according to claim 2, wherein The equipment maintenance physical prediction model includes a usage fault calculation model, and the calculation formula of the usage fault calculation model is: Among them, is the usage failure rate at time t, is the reference failure rate, P(t) is the actual operating load at time t, and P max is the maximum design load of the equipment, is the load sensitivity coefficient, and H(t) is the operating health index at time t, is the sensitivity coefficient of the health index to the failure rate, is the usage failure rate at time t after combining the operation behavior, is the j-th operation behavior characteristic at time t, is the influence coefficient of the j-th operation on the failure rate, and n is the number of operation behavior characteristics, is the usage failure rate at time t after combining the operating load, operation behavior, and health status.

4. The method according to claim 2, wherein The equipment maintenance physical prediction model includes an environmental stress fault calculation model, and the calculation formula of the environmental stress fault calculation model is: Among them, is the failure rate under the influence of environmental stress at time t, is the basic failure rate when there is no environmental influence, E k (t) is the k-th environmental stress factor at time t, E max,k is the maximum design value of the k-th environmental stress factor, is the sensitivity coefficient of the k-th environmental stress factor, p is the number of environmental stress factors, D 环境 (t) is the cumulative environmental stress damage at time t, E k (t’) is the k-th environmental stress factor at time t, is the damage attenuation coefficient of the k-th environmental stress factor, is the failure rate after considering the combined environmental stress influence at time t, is the cumulative influence coefficient of environmental stress on the failure rate.

5. The method according to claim 1, characterized in that, The digital twin description layer includes a digital twin equipment layer, a digital twin system layer, and a digital twin environment layer; the performing interactive description on each of the digital twin description layers according to the equipment record information, the equipment detection information, and the equipment environment information to obtain the equipment physical twin status information includes: Respectively inputting the equipment record information, the equipment detection information, and the equipment environment information into the digital twin equipment layer, the digital twin system layer, and the digital twin environment layer to obtain the equipment real-time operation status data, the overall system operation stability data, and the environmental impact simulation data; Applying the equipment real-time operation status data to the digital twin system layer and the digital twin environment layer to obtain the equipment system interaction data and the equipment environment status data; Apply the overall stable data of the system operation to the digital twin equipment layer and the digital twin environment layer to obtain system equipment command data and system environment status data; Apply the environmental impact simulation data to the digital twin equipment layer and the digital twin system layer to obtain environmental equipment impact data and environmental system impact data; Perform decision-level fusion on the equipment real-time operation status data, the overall stable data of the system operation, the environmental impact simulation data, the equipment-system interaction data, the equipment environment status data, the system equipment command data, the system environment status data, the environmental equipment impact data, and the environmental system impact data to obtain the physical twin status information of the equipment.

6. The method according to claim 1, wherein According to the failure information of each maintenance equipment, perform information isolation prediction on the maintenance equipment information of the target equipment to obtain the prediction information of each maintenance equipment, including: Extract features from the failure information of each maintenance equipment respectively to obtain the marked feature data of each maintenance equipment; Perform packet processing on the failure information of each maintenance equipment and the marked feature data of the maintenance equipment corresponding to the failure information of each maintenance equipment to obtain the packet failure information of each maintenance equipment; the packet failure information of each maintenance equipment displays the corresponding marked feature data of the maintenance equipment; Select the target maintenance equipment prediction model corresponding to the marked feature data of each maintenance equipment from the preset maintenance equipment prediction model set; Use the marked feature data of each maintenance equipment as the guiding information, and input the packet failure information of each maintenance equipment into the corresponding target maintenance equipment prediction model to obtain the prediction information of each maintenance equipment.

7. The method according to any one of claims 1 to 6, characterized in that According to the application scenario parameters and application efficiency parameters of the target equipment, select the optimal information from the prediction information of each maintenance equipment to obtain the optimal maintenance equipment information, including: Determine the optimization target of the equipment information of the target equipment according to the application scenario parameters and application efficiency parameters of the target equipment; According to the optimization target of the equipment information, use each equipment information optimization algorithm to select the optimal information from the prediction information of each maintenance equipment to obtain the optimized data of each equipment information; Select the data set with the smallest difference from the optimization target of the equipment information in the optimized data of each equipment information to obtain the optimal maintenance equipment information.

8. The method according to claim 7, wherein The step of selecting the data set with the smallest difference from the optimization target of the equipment information in the optimized data of each equipment information to obtain the optimal maintenance equipment information includes: Using each Pareto optimization algorithm with the optimization target of the equipment information as the constraint condition, search for the Pareto front in the optimized data of each equipment information respectively to obtain the Pareto front data of each equipment; Adjust the Pareto front data of each equipment according to the application scenario parameters and the application efficiency parameters to obtain the adjusted Pareto front data of each equipment; Use the simulated annealing algorithm for the front data to perform local optimization on the adjusted Pareto front data of each equipment respectively to obtain the locally optimized Pareto front data of each equipment; Perform clustering processing on the locally optimized Pareto front data of each equipment to obtain the optimal maintenance equipment information.

9. A maintenance equipment information prediction device based on a digital twin model, characterized in that, The device includes: An equipment data acquisition module for acquiring equipment record information, equipment detection information, and equipment environment information of the object equipment; A digital twin model determination module for determining each digital twin description layer of the object equipment according to the equipment record information, the equipment detection information, and the equipment environment information; A digital twin model description module for performing interactive description on each of the digital twin description layers according to the equipment record information, the equipment detection information, and the equipment environment information to obtain equipment physical twin status information; A fault information prediction module for respectively using each equipment maintenance physical prediction model and equipment maintenance machine prediction model to predict the fault information of the object equipment according to the equipment physical twin status information to obtain each maintenance equipment fault information; Wherein, the equipment maintenance physical prediction model includes an inherent fault calculation model, and the calculation formula of the inherent fault calculation model is: Among them, N(t) is the remaining life at time t, A is the material fatigue characteristic constant, E is the material elastic modulus, b and c are fitting coefficients, F i is the environmental factor, is the sensitivity coefficient of the environmental factor, m is the number of environmental factors, D(t) is the time cumulative fatigue damage, D max is the maximum damage tolerance of the material, is the influence coefficient of microstructure damage, is the time stress, is the reference stress of the material, k is the fatigue strength index, is the environmental influence index, is the material microstructure change function, is the inherent failure rate at time t, is the life change rate; A maintenance equipment prediction module for performing information isolation prediction on the maintenance equipment information of the object equipment according to each of the maintenance equipment fault information to obtain each maintenance equipment prediction information; A maintenance equipment determination module for selecting the optimal information from each of the maintenance equipment prediction information according to the application scenario parameters and application efficiency parameters of the object equipment to obtain the optimal maintenance equipment information.

Images