Fault prediction method and device based on digital twinning, terminal and medium

Abstract

The invention discloses a fault prediction method and device based on digital twinning, a terminal and a medium. The method comprises the following steps: performing three-dimensional modeling on equipment; constructing a digital twinborn model of the equipment by using the three-dimensional model of the equipment, constructing a simulation program in the digital twinborn model to simulate the running state of the equipment, and collecting equipment running data generated in the simulation process; in the digital twin model, constructing a plurality of fault simulation programs for simulating the fault state of the equipment, and collecting equipment operation data generated in the fault simulation process; and collecting equipment operation data in the actual operation process of the equipment, and predicting the equipment fault by comparing the equipment operation data with the obtained equipment operation data generated in the fault simulation process. According to the method, the operation state of the equipment is simulated through the digital twin model, the data in the simulation process are collected, and the capability and accuracy of equipment fault prediction are improved according to the data.

Description

Technical Field

[0001] The present application relates to the field of fault prediction technology, and in particular to a fault prediction method, device, terminal and medium based on digital twins. Background Art

[0002] In daily production and life, equipment failures such as elevators, lifts, vehicles, forklifts, etc. occur frequently, which not only seriously affects daily production and life, but may also cause serious safety accidents.

[0003] At present, the monitoring and fault prediction of the above equipment depends on the collection of equipment fault data. However, when the above equipment is in operation, most of the data are normal, which leads to a small amount of data strongly related to equipment failure, resulting in low fault prediction ability. Often, the system can only predict the occurrence of a fault after the fault is about to occur or has already occurred. The prediction is not advanced enough, making it difficult to effectively guide equipment maintenance and fault prevention. Summary of the invention

[0004] The present application provides a fault prediction method, device, terminal and medium based on digital twins, which has the advantage of improving the fault prediction capability of equipment.

[0005] The technical solution of this application is as follows: On the one hand, the present application provides a fault prediction method based on digital twins, comprising the following steps: S1: 3D modeling of the equipment; S2: Use the three-dimensional model of the equipment to build a digital twin model of the equipment. In the digital twin model, build a simulation program to simulate the equipment operation status and collect the equipment operation data generated during the simulation process; S3: In the digital twin model, several fault simulation programs are constructed to simulate the fault status of the equipment and collect the equipment operation data generated during the fault simulation process; S4: Collecting equipment operation data during the actual operation of the equipment, and predicting equipment failure by comparing it with the data obtained in step S3.

[0006] Furthermore, in steps S2 and S3, the Unity3D engine is used to build a simulation program and a fault simulation program, and the three-dimensional model of the equipment is given material mapping and physical properties, including light and shadow effects, quality, strength, collision properties and a real kinematic model.

[0007] Further, in step S2, the simulation program is used to simulate the operating state of the device when it is operating normally; In step S3, the fault simulation program is used to simulate the operating state of the device when one or more faults occur.

[0008] Furthermore, step S4 specifically includes: According to step S3, data is obtained, and feature extraction is performed on the equipment operation data when the equipment fails to obtain a first data feature; According to the device operation data during the actual operation of the device, feature extraction is performed on the device operation data during the actual operation of the device to obtain a second data feature; The consistency of the second data feature and the first data feature is detected in real time, and when the consistency of the second data feature and the first data feature reaches a preset threshold, it is determined that the device fails.

[0009] Furthermore, the method further includes step S5: building a fault prediction model based on a deep learning algorithm, training the fault prediction model using the data obtained in step S3, and performing fault prediction on the equipment using the trained fault prediction model; The fault prediction model is based on a convolutional neural network algorithm, and includes an input layer, a convolution layer, a pooling layer, a fully connected layer, and an output layer. The operating data of the equipment failure obtained in step S3 is used as input, and the fault type is used as output to train the model.

[0010] Furthermore, the method further comprises step S6: S61: According to the data obtained in steps S2 and S3, the fault type and the equipment data are correlated to obtain Related device data ; The process of associating the fault type with the equipment data comprises the following steps: According to the data obtained in steps S2 and S3, a correlation analysis is performed on the single fault type and the equipment data, and the fault type and the equipment data whose correlation is greater than a preset threshold are associated; S62: Collect historical operation data of the equipment and extract equipment data associated with the fault type ; S63: Traverse the device data of each natural day in the historical data , calculate device data The extreme value in each natural day and , d represents natural day; S64: Calculate the device data for several natural days in history Middle extreme value and The mean and variance of , , and ; By curve fitting, we can obtain , , and The law of change of , , and The time to change to the dangerous interval value is used to predict the occurrence time of the fault; The , , and The risk interval value is determined by the following method: Use the data obtained in S3 to calculate the device data when the device fails. The extreme values ​​of , and calculate the mean and variance of the extreme values ​​as , , and The danger interval value.

[0011] Furthermore, it also includes step S7: collecting the operation data of the equipment in real time, and importing it into the digital twin model for real-time updating of the digital twin model, and visually displaying the operation status of the equipment through the digital twin model.

[0012] On the other hand, the present application provides a fault prediction device based on digital twins, comprising: A model building unit, used for three-dimensional modeling of the equipment; The digital twin unit is used to construct a digital twin model of the device using a three-dimensional model of the device. In the digital twin model, a simulation program is constructed to simulate the device operation status and collect the device operation data generated during the simulation process. In the digital twin model, several fault simulation programs are constructed to simulate the fault status of the device and collect the device operation data generated during the fault simulation process. A data collection unit collects the running status data of the equipment by using the equipment host and sensors arranged on the equipment; The first fault prediction unit collects the equipment operation data during the actual operation of the equipment, and predicts the equipment failure by comparing it with the equipment failure operation data obtained by the digital twin unit; A second fault prediction unit is used to build a fault prediction model based on a deep learning algorithm, train the fault prediction model using the data obtained in step S3, and predict faults of the equipment using the trained fault prediction model; The third fault prediction unit is used to predict the fault of the device according to the following steps: According to the data obtained by the digital twin unit, the fault type and equipment data are correlated to obtain Related device data ; Collect historical operation data of the equipment and extract equipment data associated with the fault type ; Traverse the device data of each natural day in the historical data , calculate device data The extreme value in each natural day and , d represents natural day; Calculate the equipment data for several natural days in history Middle extreme value and The mean and variance of , , and ; By curve fitting, we can obtain , , and The law of change of , , and The time to change to the dangerous interval value is used to predict the occurrence time of the fault; And a visual management and control platform, which is used to visually display the operating status of the equipment.

[0013] On the other hand, the present application provides a fault prediction terminal, including a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is called and executed by the processor, the method as described above is implemented.

[0014] On the other hand, the present application provides a computer-readable medium, wherein the computer-readable medium stores a computer program, and when the computer program is called and executed by a computer, the method as described above is implemented.

[0015] In summary, the beneficial effects of this application are: 1. This application simulates the operation status of the equipment through the digital twin model and collects data during the simulation process, including the equipment operation data when the fault occurs. Based on this data, it can be used to judge whether the equipment has failed through data comparison, and it can also be used to train the fault prediction model, increase the amount of training data to improve the model training effect, and help improve the ability and accuracy of equipment fault prediction; 2. This application selects data related to equipment failures from the historical operation data of the equipment, calculates the extreme values ​​of the data on each natural day, and the mean and variance of the extreme values, and finds out the rules of the historical operation data of the equipment through curve fitting, so as to achieve long-term failure prediction, effectively improve the forward-looking nature of the prediction, and provide data basis for equipment maintenance; converting massive historical equipment data into the extreme values ​​of each natural day not only reduces the amount of data, but also the extreme values ​​of each natural day can better reflect the extreme conditions of the equipment's operation, can characterize the aging of the equipment, and can be used to predict the time when the equipment failure occurs, so as to achieve the purpose of forward-looking failure prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is the system architecture diagram of this application; Figure 2 This is the digital twin model diagram of this application; Figure 3 It is the data flow diagram in this application; Figure 4 It is a typical data diagram in this application. DETAILED DESCRIPTION

[0017] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0018] A specific embodiment of the present application provides a fault prediction method based on digital twins, which is used to predict faults of equipment. The equipment described in this embodiment includes special equipment such as elevators, escalators, lifts, forklifts, etc. Figure 2 , the method comprises the following steps: S1: Perform 3D modeling of the equipment. Taking the elevator as an example, this step creates a one-to-one 3D model of the elevator and the building environment, including details such as the building, elevator shaft, and various parts of the elevator, to ensure high-precision restoration of the model.

[0019] S2: Use the three-dimensional model of the equipment to build a digital twin model of the equipment. In the digital twin model, build a simulation program to simulate the operating status of the equipment and collect the equipment operating data generated during the simulation process; the simulation program is used to simulate the operating status of the equipment during normal operation.

[0020] S3: In the digital twin model, several fault simulation programs are constructed to simulate the fault status of the equipment and collect the equipment operation data generated during the fault simulation process. The fault simulation program is used to simulate the operation status of the equipment when one or more faults occur. The fault simulation program simulates the typical fault types of the equipment. For elevators, typical fault types include emergency stop, door opening and closing faults, top collision, and bottom squat.

[0021] The Unity3D simulation engine is used to import the 3D model and give it material mapping and physical properties, including light and shadow effects, mass, strength, collision properties and real kinematics, so that the model behaves in a virtual environment in the same way as the real world. The Unity3D engine is used to build simulation programs and fault simulation programs, which use C# script programming. C# script programming can simulate different faults through programming. The Unity3D simulation engine also supports multi-person online collaboration, making it convenient for multiple departments to participate in the supervision and operation and maintenance of elevators.

[0022] S4: Collect the equipment operation data during the actual operation of the equipment, and predict the equipment failure by comparing it with the data obtained in step S3. For elevators, the collected data includes various data (such as static data and dynamic data) of the elevator and its operating environment, including but not limited to the basic attribute data of the elevator, historical working data, historical fault data, building environment data (such as building drawing data, three-dimensional point cloud data, etc.), meteorological environment data (such as temperature, humidity, etc.), historical elevator operation data (such as the cumulative number of elevator operations, cumulative duration, etc.) and real-time elevator operation data (such as the direction of elevator operation, floor, door opening and closing action, whether there is someone, alarm button, etc.). By comparing the real-time monitoring data with the simulation results, potential failure risks can be discovered in time, and early warnings can be issued to operation and maintenance personnel.

[0023] Specifically, according to step S3, data is obtained, and feature extraction is performed on the equipment operation data when the equipment fails to obtain a first data feature; According to the device operation data during the actual operation of the device, feature extraction is performed on the device operation data during the actual operation of the device to obtain a second data feature; The consistency of the second data feature and the first data feature is detected in real time, and when the consistency of the second data feature and the first data feature reaches a preset threshold, it is determined that the device fails.

[0024] In particular, for numerical data, such as voltage and temperature, the difference method is used to judge the consistency. When the difference reaches the preset threshold, the inconsistency between the two is judged to have reached the preset threshold. For vibration signals, the frequency domain features of the signal are extracted during feature extraction, and the consistency is judged by comparing the frequency domain features.

[0025] S5: Building a fault prediction model based on a deep learning algorithm, using the data obtained in step S3 to train the fault prediction model, and using the trained fault prediction model to predict equipment faults; The fault prediction model is based on a convolutional neural network algorithm, and includes an input layer, a convolution layer, a pooling layer, a fully connected layer, and an output layer. The operating data of the equipment failure obtained in step S3 is used as input, and the fault type is used as output to train the model.

[0026] Step S6: S61: According to the data obtained in steps S2 and S3, the fault type and the equipment data are correlated to obtain Related device data ; The process of associating the fault type with the equipment data comprises the following steps: According to the data obtained in steps S2 and S3, a correlation analysis is performed on the single fault type and the equipment data, and the fault type and the equipment data whose correlation is greater than a preset threshold are associated; S62: Collect historical operation data of the equipment and extract equipment data associated with the fault type ; S63: Traverse the device data of each natural day in the historical data , calculate device data The extreme value in each natural day and , d represents natural day; S64: Calculate the device data for several natural days in history Middle extreme value and The mean and variance of , , and ; By curve fitting, we can obtain , , and The law of change of , , and The time to change to the dangerous interval value is used to predict the occurrence time of the fault; The , , and The risk interval value is determined by the following method: Use the data obtained in S3 to calculate the device data when the device fails. The extreme values ​​of , and calculate the mean and variance of the extreme values ​​as , , and The danger interval value.

[0027] Step S7: Collect the operation data of the equipment in real time and import it into the digital twin model for real-time updating of the digital twin model, and visualize the operation status of the equipment through the digital twin model. The operation status and fault warning information of the elevator are intuitively displayed in the form of charts, animations, etc., to improve supervision efficiency and decision-making support capabilities.

[0028] Another embodiment of the present application provides a fault prediction device based on digital twins, such as Figure 1 and 3 ,include: A model building unit, used for three-dimensional modeling of the equipment; The digital twin unit is used to construct a digital twin model of the device using a three-dimensional model of the device. In the digital twin model, a simulation program is constructed to simulate the device operation status and collect the device operation data generated during the simulation process. In the digital twin model, several fault simulation programs are constructed to simulate the fault status of the device and collect the device operation data generated during the fault simulation process. The data acquisition unit uses the equipment host and sensors arranged on the equipment to collect the operating status data of the equipment; the data acquisition unit is responsible for obtaining various data (such as static data and dynamic data) of the elevator and its operating environment, including but not limited to the basic attribute data of the elevator, historical working data, historical fault data, building environment data (such as building drawing data, three-dimensional point cloud data, etc.), meteorological environment data (such as temperature, humidity, etc.), historical operation data of the elevator (such as the cumulative number of elevator operations, cumulative duration, etc.) and real-time operation data of the elevator (such as the direction of elevator operation, floor, door opening and closing action, whether there is someone, alarm button, etc.).

[0029] The data acquisition unit is connected to the data processing unit to clean, integrate and pre-process the collected data. The data acquisition unit and the data processing unit constitute the Internet of Things platform.

[0030] The first fault prediction unit collects the equipment operation data during the actual operation of the equipment, and predicts the equipment failure by comparing it with the equipment failure operation data obtained by the digital twin unit; A second fault prediction unit is used to build a fault prediction model based on a deep learning algorithm, train the fault prediction model using the data obtained in step S3, and predict faults of the equipment using the trained fault prediction model; The third fault prediction unit is used to predict the fault of the device according to the following steps: According to the data obtained by the digital twin unit, the fault type and equipment data are correlated to obtain Related device data ; Collect historical operation data of the equipment and extract equipment data associated with the fault type ; Traverse the device data of each natural day in the historical data , calculate device data The extreme value in each natural day and , d represents natural day; Calculate the equipment data for several natural days in history Middle extreme value and The mean and variance of , , and ; By curve fitting, we can obtain , , and The law of change of , , and The time to change to the dangerous interval value is used to predict the occurrence time of the fault; And a visual management and control platform, which is used to visually display the operating status of the equipment.

[0031] Another embodiment of the present application provides a fault prediction terminal, including a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is called and executed by the processor, the method described above is implemented.

[0032] Another embodiment of the present application provides a computer-readable medium, wherein the computer-readable medium stores a computer program, and when the computer program is called and executed by a computer, the method described above is implemented.

[0033] The above is only a preferred implementation of the present application. It should be pointed out that a person skilled in the art can make several modifications and improvements without departing from the inventive concept of the present application, and these all fall within the scope of protection of the present application.

Claims

1. A fault prediction method based on digital twins, characterized in that: The following steps are involved: S1: 3D modeling of the equipment; S2: Use the three-dimensional model of the equipment to build a digital twin model of the equipment. In the digital twin model, build a simulation program to simulate the equipment operation status and collect the equipment operation data generated during the simulation process; S3: In the digital twin model, several fault simulation programs are constructed to simulate the fault status of the equipment and collect the equipment operation data generated during the fault simulation process; S4: Collecting equipment operation data during the actual operation of the equipment, and predicting equipment failure by comparing it with the data obtained in step S3.

2. The fault prediction method based on digital twin according to claim 1, characterized in that: In the steps S2 and S3, the Unity3D engine is used to build a simulation program and a fault simulation program, and the three-dimensional model of the equipment is given material mapping and physical properties, including light and shadow effects, quality, strength, collision properties and a real kinematic model.

3. The fault prediction method based on digital twin according to claim 2, characterized in that: In step S2, the simulation program is used to simulate the operating state of the device when it is operating normally; In step S3, the fault simulation program is used to simulate the operating state of the device when one or more faults occur.

4. The fault prediction method based on digital twin according to claim 1, characterized in that: Step S4 specifically includes: According to step S3, data is obtained, and feature extraction is performed on the equipment operation data when the equipment fails to obtain a first data feature; According to the device operation data during the actual operation of the device, feature extraction is performed on the device operation data during the actual operation of the device to obtain a second data feature; The consistency of the second data feature and the first data feature is detected in real time, and when the consistency of the second data feature and the first data feature reaches a preset threshold, it is determined that the device fails.

5. The fault prediction method based on digital twin according to claim 1, characterized in that: The method further includes step S5: building a fault prediction model based on a deep learning algorithm, training the fault prediction model using the data obtained in step S3, and predicting faults of the equipment using the trained fault prediction model; The fault prediction model is based on a convolutional neural network algorithm, and includes an input layer, a convolution layer, a pooling layer, a fully connected layer, and an output layer. The operating data of the equipment failure obtained in step S3 is used as input, and the fault type is used as output to train the model.

6. The fault prediction method based on digital twin according to claim 1, characterized in that: The step S6 is also included: S61: According to the data obtained in steps S2 and S3, the fault type and the equipment data are correlated to obtain Related device data ; The process of associating the fault type with the equipment data comprises the following steps: According to the data obtained in steps S2 and S3, a correlation analysis is performed on the single fault type and the equipment data, and the fault type and the equipment data whose correlation is greater than a preset threshold are associated; S62: Collect historical operation data of the equipment and extract equipment data associated with the fault type ; S63: Traverse the device data of each natural day in the historical data , calculate device data The extreme value in each natural day and , d represents natural day; S64: Calculate the device data for several natural days in history Middle extreme value and The mean and variance of , , and ; By curve fitting, we can obtain , , and The law of change of , , and The time to change to the dangerous interval value is used to predict the occurrence time of the fault; The , , and The risk interval value is determined by the following method: Use the data obtained in S3 to calculate the device data when the device fails. The extreme values ​​of , and calculate the mean and variance of the extreme values ​​as , , and The danger interval value.

7. The fault prediction method based on digital twin according to claim 1, characterized in that: It also includes step S7: collecting the operating data of the equipment in real time and importing it into the digital twin model for real-time updating of the digital twin model, and visually displaying the operating status of the equipment through the digital twin model.

8. A fault prediction device based on digital twins, characterized in that: include: A model building unit, used for three-dimensional modeling of the equipment; The digital twin unit is used to construct a digital twin model of the device using a three-dimensional model of the device. In the digital twin model, a simulation program is constructed to simulate the device operation status and collect the device operation data generated during the simulation process. In the digital twin model, several fault simulation programs are constructed to simulate the fault status of the device and collect the device operation data generated during the fault simulation process. A data collection unit collects the running status data of the equipment by using the equipment host and sensors arranged on the equipment; The first fault prediction unit collects the equipment operation data during the actual operation of the equipment, and predicts the equipment failure by comparing it with the equipment failure operation data obtained by the digital twin unit; A second fault prediction unit is used to build a fault prediction model based on a deep learning algorithm, train the fault prediction model using the data obtained in step S3, and predict faults of the equipment using the trained fault prediction model; The third fault prediction unit is used to predict the fault of the device according to the following steps: According to the data obtained by the digital twin unit, the fault type and equipment data are correlated to obtain Related device data ; Collect historical operation data of the equipment and extract equipment data associated with the fault type ; Traverse the device data of each natural day in the historical data , calculate device data The extreme value in each natural day and , d represents natural day; Calculate the equipment data for several natural days in history Middle extreme value and The mean and variance of , , and ; By curve fitting, we can obtain , , and The law of change of , , and The time to change to the dangerous interval value is used to predict the occurrence time of the fault; And a visual management and control platform, which is used to visually display the operating status of the equipment.

9. A fault prediction terminal, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer program, and when the computer program is called and executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable medium, characterized in that The computer-readable medium stores a computer program, and when the computer program is called and executed by a computer, the method according to any one of claims 1 to 7 is implemented.

Images