Equipment monitoring visualization system based on digital twinborn technology

Abstract

The invention relates to the technical field of visual monitoring, in particular to an equipment monitoring visualization system based on a digital twinning technology, which comprises a data acquisition module, a virtual model creation module, a virtual-real mapping module and an anomaly detection module. Through cooperative work of the modules, real-time monitoring, fault prediction, performance optimization and remote operation guidance of equipment such as a motor are achieved, the operation and maintenance efficiency and reliability of the equipment are remarkably improved, and analysis logic of a temperature detection unit, a vibration detection unit and a rotating speed detection unit of the protection self-checking sub-module is described in detail. And the working principle of the power failure detection sub-module is determined. Through application of the technologies, the system can accurately identify and early warn various potential faults, and a powerful guarantee is provided for stable operation of equipment.

Description

Technical Field

[0001] The present invention relates to the field of visual monitoring technology, and in particular to an equipment monitoring visualization system based on digital twin technology. Background Art

[0002] With the continuous development of industrial automation and intelligence, motors are an indispensable power source in industrial production. The stability and efficiency of their operation have a direct impact on the continuity and economic benefits of the entire production system. Traditional motor monitoring systems mostly rely on decentralized sensors and control units. Although these systems can provide basic monitoring data, they have obvious deficiencies in data integration, real-time and fault prediction. In existing technical solutions, motor monitoring usually focuses on threshold monitoring of specific parameters, such as temperature, vibration or speed. When these parameters exceed the preset threshold, the system will sound an alarm. However, this reactive monitoring method cannot warn of potential faults in advance, and it is difficult to achieve comprehensive analysis and optimization due to the scattered monitoring data. In addition, for motor maintenance and fault diagnosis, on-site staff often need to rely on experience to make judgments and handle them, which not only requires high skills of personnel, but also cannot guarantee the timeliness and accuracy of the treatment measures. In a complex industrial environment, motor failures may cause production lines to stagnate, resulting in huge economic losses and safety hazards. The emergence of digital twin technology provides a new idea for solving the above problems. By creating a virtual model of physical equipment and realizing seamless connection between virtual and real data, digital twin technology can reflect the operating status of physical equipment in real time and realize early detection and warning of faults.

[0003] For example, the Chinese patent with the authorization announcement number CN105205295B involves a modeling method for a traveling wave type rotary ultrasonic motor, which is a modeling method for a TRUM "electric-mechanical-force" hybrid model, including the following steps: the first step: establishing a stator equivalent circuit model for the "electrical energy-high-frequency vibration mechanical energy" process; the second step: establishing a stator-rotor discrete contact model for the "high-frequency vibration mechanical energy-rotational kinetic energy" process; the third step, determining the interface parameters, and obtaining the TRUM "electric-mechanical-force" hybrid model. This method is to deconstruct the motor mechanism according to the electromechanical transduction relationship, and to model each part by using different methods, and finally to connect the models of each part through reasonable interface parameters, so as to establish a motor hybrid model that can reflect the motor characteristics and is easy to analyze, and overcome the defects of the existing TRUM modeling method that cannot describe the stator tooth structure, the difficulty of calculation, the increased complexity and the impracticality.

[0004] The above patents all have the problems raised by this background technology: the motor has a complex internal structure and geometric shape, and it is difficult to accurately model the internal structure of the ultrasonic motor only through circuit simulation analysis. Although digital twin technology can realize fault visualization, it lacks in-depth fault prediction and diagnosis capabilities and cannot provide strong support for maintenance decisions. There is a delay in the synchronous update of the virtual model and the physical equipment, which affects the real-time and accuracy of monitoring. To solve the above problems, this application designs an equipment monitoring visualization system based on digital twin technology. Summary of the invention

[0005] The technical problem to be solved by the present invention is to address the deficiencies of the prior art and provide an equipment monitoring visualization system based on digital twin technology, which includes a data acquisition module, a virtual model creation module, a virtual-to-real mapping module, and an anomaly detection module. Through the collaborative work of these modules, real-time monitoring, fault prediction, performance optimization, and remote operation guidance of equipment such as motors are realized, which significantly improves the operation and maintenance efficiency and reliability of the equipment. The analysis logic of the temperature detection unit, vibration detection unit, and speed detection unit of the protection self-test submodule, as well as the working principle of the power outage detection submodule are also described in detail. The application of these technologies enables the system to accurately identify and warn of various potential faults, providing a strong guarantee for the stable operation of the equipment.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An equipment monitoring visualization system based on digital twin technology, the system comprising a data acquisition module, a virtual model creation module, a virtual-reality mapping module and an anomaly detection module;

[0008] The data acquisition module is used to obtain appearance data and operation data of the motor, wherein the appearance data includes an external image of the motor and internal point cloud data of the motor;

[0009] The virtual model creation module is configured with a motor modeling strategy, and the motor modeling strategy is used to pre-process the appearance data, analyze the pre-processed appearance data, and output a three-dimensional model of the motor;

[0010] The virtual-real mapping module is used to construct a motor logic model, map the motor logic model to the information space, and construct a digital twin motor in combination with the motor three-dimensional model;

[0011] The abnormality detection module is used to check suspected faulty motors, locate the number and position of the faulty motors, and issue an alarm for the fault during the visual monitoring of the motors.

[0012] The motor modeling strategy includes external feature extraction logic, internal feature extraction logic and three-dimensional modeling logic. The virtual model creation module includes an image processing unit, a point cloud processing unit and a model modeling unit. The external feature extraction logic is configured in the image processing unit, the internal feature extraction logic is configured in the point cloud processing unit, and the three-dimensional modeling logic is configured in the model modeling unit. The image processing unit is used to process the external image of the motor according to the external image of the motor and extract external structural features. The point cloud processing unit is used to process the internal point cloud data of the motor according to the internal point cloud data of the motor and extract internal point cloud features. The model modeling unit is used to process the external structural features and internal point cloud features and output a three-dimensional model of the motor.

[0013] The specific steps of the external feature extraction logic are as follows:

[0014] S3.1: De-noising the external image of the motor;

[0015] S3.2: Perform histogram statistics on the grayscale values ​​of the motor external image after denoising, and cut out the target area of ​​the motor external image pixel points through a statistical learning method;

[0016] S3.3: Smooth the target area image by edge detection, calculate Gaussian difference based on the smoothed target area image, extract key points of the target area image, calculate the medium strength of the key points, divide the target area image into four components of R, G, B and Deep for pixel decomposition, and calculate the medium strength of the key points after decomposition;

[0017] S3.4: According to the medium strength of the key point and the medium strength of the four components of the key point after decomposition, the medium strength of the image is matched and the external structure features are calculated. The calculation formula of the external structure features is:

[0018]

[0019] Among them, O c represents the external structural features, j represents a single key point, N represents the total number of key points, δ represents the Fourier transform factor, x j Represents the pixel horizontal coordinate of the jth key point, y j represents the pixel ordinate of the jth key point, max[·] represents the maximum value of the function, M(·) represents the medium strength matching score matrix, m Rk Indicates the R component medium strength at the key point, m Gk Indicates the G component medium strength at the key point, m Bk Indicates the B component medium strength at the key point, m Dk Indicates the medium strength of the Deep component at the key point, m kIndicates the dielectric strength at the critical point.

[0020] The specific steps of the internal feature extraction logic are as follows:

[0021] S4.1: Preprocessing the internal point cloud data of the motor according to the internal point cloud data of the motor, and performing coordinate transformation on the preprocessed internal point cloud data of the motor through rigid body transformation;

[0022] S4.2: Divide the grid into equal intervals, voxelize the point cloud data inside the motor, project it to the corresponding grid according to the voxel index, connect the points in the voxel, strengthen the local feature information, and obtain the point cloud voxel features;

[0023] S4.3: Obtain standard point cloud data of the motor internal structure, classify the point cloud voxel features through a clustering algorithm, merge the grids containing the point cloud voxel features under the same central cluster, and calculate the internal point cloud features.

[0024] The three-dimensional modeling logic includes a feature classification sub-logic and a motor modeling sub-logic, the feature classification sub-logic includes constructing a feature classification network, training the feature classification network through the external structural features and the internal point cloud features, and outputting the motor component type corresponding to the features, the motor modeling sub-logic includes setting the rendering parameters of the motor component corresponding to the motor component type through the modeling software, rendering the external structural features and the internal point cloud features corresponding to the motor component type, and outputting the three-dimensional model of the ultrasonic motor;

[0025] The feature classification network includes an input layer, a hidden layer and an output layer;

[0026] The input layer is used to input external structural features and internal point cloud features, perform logarithmic operations and size reconstruction on the external structural features and the internal point cloud features, and obtain input parameters of the hidden layer;

[0027] The hidden layer is used to train the input parameters of the hidden layer and calculate the motor component type parameters through the attention mechanism;

[0028] The output layer is used to output classification results according to the motor component type parameters.

[0029] The virtual-reality mapping module includes a data integration unit, a physical mapping unit and a visualization display unit. The data integration unit is used to receive input from sensors and control systems, convert the input into a unified format, and display it on the motor dashboard. The physical mapping unit is used to convert the physical properties of the motor into a digital model and map the digital model to the information space. The visualization display unit is used to provide an interactive page and build a digital twin motor through a three-dimensional model of the motor.

[0030] The abnormality detection module includes a protection self-check submodule, a power failure detection submodule and a fault warning submodule;

[0031] The protection self-check submodule is used to detect fault problems during the operation of the motor;

[0032] The power failure detection submodule is used to detect fault problems that cannot be found during the operation of the motor;

[0033] The fault warning submodule is used to warn of the faults detected by the protection self-checking submodule and the power failure detection submodule, and send a notification to the staff.

[0034] The protection self-detection submodule includes a temperature detection unit, a vibration detection unit and a rotation speed detection unit;

[0035] The temperature detection unit includes a temperature analysis logic, which is used to monitor the temperature data of the motor according to the temperature sensor installed on the motor, clean and pre-process the collected temperature data, draw a frequency distribution histogram of the temperature data, and output the temperature state analysis result of the motor according to the frequency distribution histogram, wherein the temperature state analysis result includes the motor overheating and the motor temperature being normal;

[0036] The vibration detection unit includes a vibration signal analysis logic, which includes vibration signal preprocessing, vibration signal feature extraction and vibration signal feature analysis, and outputs a vibration signal analysis result, which includes improper motor balance, motor bearing damage and shaft bending;

[0037] The speed detection unit includes a speed analysis logic, which is used to monitor the speed data of the motor according to the speed sensor installed on the motor, clean and pre-process the collected speed data, draw a speed change trend graph, determine whether there is a long-term drift phenomenon in the speed fluctuation, and compare the actual speed with the predetermined working speed range to determine whether it is in the best working state, and output the speed analysis result, which includes motor speed overspeed, motor speed underspeed and motor speed instability.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1. The three-dimensional modeling technology of the present invention visualizes the motor and realizes real-time monitoring of various parameters of the motor through the dashboard, which enhances the intuitive understanding of the operation status of the equipment by the operation and maintenance personnel, optimizes resource allocation, and improves equipment utilization;

[0040] 2. Through the virtual-to-real mapping module, the system can ensure the real-time synchronization update of the virtual model and the physical device, thus improving the real-time and accuracy of monitoring. This helps to timely discover abnormal conditions of the equipment and reduce the risk of failure;

[0041] 3. The present invention can discover potential hidden faults through in-depth analysis of operating data and issue early warnings in a timely manner, which provides strong support for maintenance decisions, reduces equipment downtime and maintenance costs, and improves production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0043] Figure 1 This is a module diagram of an equipment monitoring visualization system based on digital twin technology according to Embodiment 1 of the present invention;

[0044] Figure 2 This is a schematic diagram of the calculation of dielectric strength at key points in Example 1 of the present invention;

[0045] Figure 3 This is a flow chart of point cloud voxel feature clustering in Example 1 of the present invention;

[0046] Figure 4 This is a grid clustering result diagram of Example 1 of the present invention;

[0047] Figure 5 This is a flow chart of vibration signal analysis according to Example 1 of the present invention. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0049] Embodiment 1:

[0050] See also Figure 1 , an embodiment provided by the present invention: an equipment monitoring visualization system based on digital twin technology, the system comprising a data acquisition module, a virtual model creation module, a virtual-to-real mapping module and an anomaly detection module;

[0051] The data acquisition module is used to obtain appearance data and operation data of the motor, wherein the appearance data includes an external image of the motor and internal point cloud data of the motor;

[0052] The virtual model creation module is configured with a motor modeling strategy, and the motor modeling strategy is used to pre-process the appearance data, analyze the pre-processed appearance data, and output a three-dimensional model of the motor;

[0053] The motor modeling strategy includes external feature extraction logic, internal feature extraction logic and three-dimensional modeling logic. The virtual model creation module includes an image processing unit, a point cloud processing unit and a model modeling unit. The external feature extraction logic is configured in the image processing unit, the internal feature extraction logic is configured in the point cloud processing unit, and the three-dimensional modeling logic is configured in the model modeling unit. The image processing unit is used to process the external image of the motor according to the external image of the motor and extract external structural features. The point cloud processing unit is used to process the internal point cloud data of the motor according to the internal point cloud data of the motor and extract internal point cloud features. The model modeling unit is used to process the external structural features and internal point cloud features and output a three-dimensional model of the motor.

[0054] The specific steps of the external feature extraction logic are as follows:

[0055] S3.1: De-noising the external image of the motor, wherein the external image noise of the motor includes AD quantization noise, dark current noise and part reflection noise;

[0056] S3.2: Perform histogram statistics on the grayscale values ​​of the motor external image after denoising, take the peak-to-valley grayscale value between the two peaks as the segmentation threshold 1, calculate the segmentation threshold 2 according to the probability density function of the motor external image, obtain the optimal segmentation threshold by weighted summing the segmentation threshold 1 and the segmentation threshold 2, compare the pixel point of the motor external image with the optimal segmentation threshold, if it is greater than or equal to the optimal segmentation threshold, mark the pixel point as the target area, if it is less than the optimal segmentation threshold, mark the pixel point as the background area;

[0057] S3.3: Connecting the pixel points marked as the target area to obtain the target area image, and smoothing the target area image by edge detection, wherein the edge detection includes image Gaussian filtering, calculating the gradient amplitude and direction by difference method, performing non-maximum suppression on the gradient amplitude, and double threshold edge connection;

[0058] See also Figure 2 , Schematic diagram of key point medium strength calculation in an embodiment of the present invention, S3.4: Calculate Gaussian difference according to the smoothed target area image, extract key points of the target area image, calculate the medium strength of the key points, divide the target area image into four components of R, G, B and Deep for pixel decomposition, calculate the medium strength of the key points after decomposition, and the calculation formula of the medium strength of the key points is:

[0059]

[0060] Among them, m k represents the medium strength of the key point at the pixel position k, m represents the total number of pixel positions, n represents the number of spectral bands, arg min(·) represents the minimum value of the function, μ k represents the average intensity value of pixel position k, x ik Represents the pixel intensity value at pixel position k in the spectral band;

[0061] S3.5: According to the medium intensity of the key point and the medium intensity of the four components of the key point after decomposition, the fused medium intensity is obtained, and the medium intensity matching of the image is performed to obtain the medium intensity matching score matrix. According to the Sinkhorn algorithm, normalization is first performed row by row, that is, each element of the first row is divided by the value obtained by the sum of each element of the first row to obtain a new row. The same operation is performed on each row, and then normalization is performed column by column. Finally, the maximum value of the allocation matrix is ​​obtained, and the maximum value is compared to obtain the optimal allocation result. The external structure feature is calculated according to the score matrix. The calculation formula of the external structure feature is:

[0062]

[0063] Among them, O c represents the external structural features, j represents a single key point, N represents the total number of key points, δ represents the Fourier transform factor, x j Represents the pixel horizontal coordinate of the jth key point, y j represents the pixel ordinate of the jth key point, max[·] represents the maximum value of the function, M(·) represents the medium strength matching score matrix, m Rk Indicates the R component medium strength at the key point, m Gk Indicates the G component medium strength at the key point, m Bk Indicates the B component medium strength at the key point, m Dk Indicates the medium strength of the Deep component at the key point, m k Indicates the dielectric strength at the critical point.

[0064] The specific steps of the internal feature extraction logic are as follows:

[0065] S4.1: Preprocessing the internal point cloud data of the motor according to the internal point cloud data of the motor;

[0066] S4.2: Find the most suitable three-dimensional plane through plane fitting, perform coordinate transformation on the pre-processed internal point cloud data of the motor through rigid body transformation, and transfer the internal point cloud data of the motor from the radar coordinate system to the world coordinate system;

[0067] S4.3: Divide the world coordinate system into grids at equal intervals, voxelize the point cloud data inside the motor, project it into the corresponding grid according to the voxel index, connect the points in the voxel, strengthen the local feature information, and obtain the point cloud voxel features;

[0068] S4.4: obtaining standard point cloud data of the internal structure of the motor, performing preliminary clustering on the standard point cloud data of the internal structure of the motor according to the DBSCAN clustering algorithm, obtaining core points, and determining the number of cluster center clusters according to the number of the core points;

[0069] S4.5: using the core points after DBSCAN clustering as the initial center clusters of the K-means clustering algorithm, and calculating the Euclidean distance from the voxel features of the laser scanning point cloud to each of the initial center clusters;

[0070] S4.6: performing clustering according to the Euclidean distance, and calculating the average clustering error of the initial central cluster, updating the central cluster according to the average clustering error, and judging whether the central cluster after the update satisfies the convergence condition, if it does not satisfy the convergence condition, continuing to update the central cluster, and if it satisfies the convergence condition, outputting the clustering result;

[0071] S4.7: Extract the point cloud voxel features after clustering, merge the grids where the point cloud voxel features are located under the same central cluster, and extract the internal point cloud features. The calculation formula of the internal point cloud features is:

[0072]

[0073] Among them, T a represents the internal point cloud features corresponding to the voxel features of the laser scanning point cloud in the same central cluster after clustering, i represents a single voxel feature of the laser scanning point cloud in the central cluster, M represents the total number of voxel features of the laser scanning point cloud in the central cluster, and η i represents the eigenvalue of the voxel feature of the i-th laser scanning point cloud, d represents the clustering threshold corresponding to the central cluster, r2 represents the farthest distance scanned by the laser scanner, r1 represents the closest distance scanned by the laser scanner, and p i_x represents the voxel horizontal coordinate of the i-th laser scanning point cloud voxel feature, p i_y The voxel ordinate represents the feature of the i-th laser scanning point cloud voxel, p i_z The vertical coordinate of the voxel representing the feature of the i-th laser scanning point cloud voxel;

[0074] See also Figure 3, the flow chart of point cloud voxel feature clustering in the embodiment of the present invention, specifically, by combining the two clustering algorithms of DBSCAN and K-means, the standard point cloud data of the internal structure of the motor is clustered and analyzed, and by iteratively optimizing the central cluster, a more accurate clustering result is obtained, so as to better understand the classification status of the point cloud data, which is helpful to improve the classification efficiency and reduce energy loss. DBSCAN is a density clustering algorithm used to identify closely connected data points in space and divide them into clusters. DBSCAN can be used for preliminary clustering to obtain core points. Core points refer to the core area containing at least a specified number of data points within a given radius. Since each core point may represent a cluster, the number of core points can be used to preliminarily determine the number of central clusters of clustering.

[0075] The kernel points obtained by preliminary clustering of DBSCAN are used as the initial center cluster of the K-means clustering algorithm, providing an initial cluster center position for the K-means algorithm; the Euclidean distance is used for clustering, and each work operation information is assigned to the nearest center cluster by calculating the Euclidean distance from the voxel features of the laser scanning point cloud to each initial center cluster. The clustering average error refers to the average value of the Euclidean distance from all the data points to the center. The clustering average error can be used to update the initial center cluster to improve the clustering effect. The position of the center cluster can be adjusted according to the calculated clustering average error, so as to update the center cluster, and the convergence condition is defined to determine whether the updated center cluster meets the convergence condition to determine whether to end the iteration. If the convergence condition is met, the clustering result is output.

[0076] See also Figure 4 , the grid clustering result diagram of the embodiment of the present invention first traverses the grid map, finds the first unmarked grid containing the laser scanning point cloud voxel feature, marks it as 1, then searches for other grids containing the laser scanning point cloud voxel feature in the neighborhood of the grid, and determines whether the central cluster of the laser scanning point cloud voxel feature is the same as the central cluster of the previous laser scanning point cloud voxel feature. If they are the same, they are also marked as 1. If they are different, continue to search for other grids, repeatedly mark the neighborhood of the grid until all grids in the connected domain are successfully marked, record the positions of all grids in the connected domain, and then repeat the above operation to find the remaining connected domains in the grid map, and mark them according to the digital sequence, and finally obtain several connected areas, that is, several grids with the same central cluster in the grid map. At this time, the laser scanning point cloud voxel features stored in each grid in the same connected domain are merged to obtain internal point cloud features.

[0077] The specific steps of preprocessing the internal point cloud data of the motor are as follows:

[0078] S4.1.1: Calculate the y-axis coordinates of all the internal point cloud data of the motor. If the y-axis coordinate of a point is less than 0, delete the point from the internal point cloud data of the motor.

[0079] S4.1.2: traverse and query the internal point cloud data of the motor, and delete the internal point cloud data of the motor with the same radar rotation angle and echo distance;

[0080] S4.1.3: Set the fitting plane equation, calculate the coefficient of the fitting plane equation according to the internal point cloud data of the motor, and calculate the distance from all the internal point cloud data of the motor to the fitting plane, and compare the distance from the internal point cloud data of the motor to the fitting plane with the plane distance threshold. If it is less than or equal to the plane distance threshold, save the internal point cloud data of the motor; if it is greater than the plane distance threshold, delete the internal point cloud data of the motor;

[0081] S4.1.4: Gather the internal point cloud data of the motor in the normal direction and adjust the positions and coordinates of the sampling points to denoise the internal point cloud data of the motor.

[0082] The three-dimensional modeling logic includes a feature classification sub-logic and a motor modeling sub-logic. The feature classification sub-logic includes constructing a feature classification network, training the feature classification network through the external structural features and the internal point cloud features, and outputting the motor component type corresponding to the features. The motor modeling sub-logic includes setting the rendering parameters of the motor component corresponding to the motor component type through the modeling software, rendering the external structural features and the internal point cloud features corresponding to the motor component type, and outputting the three-dimensional model of the ultrasonic motor, wherein the motor component type includes an external shell, an external base, an internal stator, an internal rotor, an internal bearing, an internal friction substrate and a piezoelectric ceramic sheet, and the rendering includes scene rendering and texture rendering.

[0083] The feature classification network includes an input layer, a hidden layer and an output layer;

[0084] The input layer is used to input external structural features and internal point cloud features, perform logarithmic operations and size reconstruction on the external structural features and the internal point cloud features, and obtain input parameters of the hidden layer;

[0085] The hidden layer is used to train the input parameters of the hidden layer, and calculate the motor component type parameters through the attention mechanism. The calculation formula of the motor component type parameters is:

[0086] Sesc p =σ{f 3×3 [AvgPool(γ·F+β)],MaxPool(F')},

[0087] Among them, Sesc prepresents the motor component type parameter, σ{·} represents the activation function, AvgPool(·) represents the average pooling function, γ represents the scale factor, β represents the translation factor, MaxPool(·) represents the maximum pooling function, and F' represents the input features through the attention mechanism;

[0088] The output layer is used to output classification results according to the motor component type parameters.

[0089] The input layer includes logarithmic operation, size reconstruction and convolution;

[0090] The hidden layer includes a processing module A and a processing module B, wherein the processing module A is used to process external structural features, and includes a block A1 and a block A2, wherein the blocks A1 and A2 include two convolutional layers, a normalization layer, and an average pooling layer, and the processing module B is used to process internal point cloud features, and includes a block B1 and a block B2, wherein the block B1 includes a channel attention module and a spatial attention module, and the block B2 includes three convolutional layers and a maximum pooling layer;

[0091] The output layer includes error reconstruction and activation function. The error reconstruction is used to perform reverse error analysis on the motor component type parameters to determine whether the error threshold is met. If not, retraining is performed. If so, the classification category is output according to the activation function.

[0092] The virtual-reality mapping module includes a data integration unit, a physical mapping unit and a visualization display unit. The data integration unit is used to receive inputs from sensors and control systems, convert the inputs into a unified format, and display them in the motor dashboard. The physical mapping unit is used to convert the physical properties of the motor into a digital model and map the digital model to the information space. The visualization display unit is used to provide an interactive page and build a digital twin motor through a three-dimensional model of the motor.

[0093] The sensors include vibration sensors, temperature sensors and speed sensors. The control system includes an actuator, which operates the motor through control instructions. The physical mapping unit specifically includes: 1): According to the functions of the motor, the motor functions are decomposed into corresponding logical nodes, and the logical nodes are encapsulated according to data objects and attributes; 2): An abstract communication service interface is established for the encapsulated logical nodes, and the information interaction service of the logical nodes is implemented according to the abstract communication service interface; 3): The information interaction service of the logical nodes is mapped to the intelligent list of the virtual motor, and an intelligent list information model is established; 4): The signal connection point description information of the motor is extracted according to the intelligent list information model, and the signal connection point description information is combined with the motor physics to obtain a digital model, and the digital model is mapped to the information space.

[0094] The visualization display unit intuitively displays the motor's structure and operating status through three-dimensional graphics and animations, enhancing the user's understanding of the motor's structure and operating conditions. It provides a user-friendly operation interface so that operators can easily obtain motor information, perform monitoring operations, and view history and maintenance records. According to the needs of different users, it provides a variety of view options, such as overall layout diagrams, partial enlarged diagrams, schematic diagrams, and superimposed displays of various information layers to meet different monitoring and management needs.

[0095] The abnormality detection module includes a protection self-check submodule, a power failure detection submodule and a fault warning submodule;

[0096] The protection self-check submodule is used to detect fault problems during the operation of the motor;

[0097] The power failure detection submodule is used to detect fault problems that cannot be found during the operation of the motor;

[0098] The fault warning submodule is used to warn of faults detected by the protection self-checking submodule and the power failure detection submodule, and send notifications to staff;

[0099] The protection self-check submodule includes a temperature detection unit, a vibration detection unit and a speed detection unit. The temperature detection unit includes a temperature analysis logic. The temperature analysis logic is used to monitor the temperature data of the motor according to the temperature sensor installed on the motor, clean and pre-process the collected temperature data, draw a frequency distribution histogram of the temperature data, and output the temperature state analysis result of the motor according to the frequency distribution histogram. The temperature state analysis result includes motor overheating and normal motor temperature;

[0100] The vibration detection unit includes a vibration signal analysis logic, which includes vibration signal preprocessing, vibration signal feature extraction and vibration signal feature analysis, and outputs a vibration signal analysis result, which includes improper motor balance, motor bearing damage and shaft bending;

[0101] The speed detection unit includes a speed analysis logic, which is used to monitor the speed data of the motor according to the speed sensor installed on the motor, clean and pre-process the collected speed data, draw a speed change trend graph, determine whether there is a long-term drift phenomenon in the speed fluctuation, and compare the actual speed with the predetermined working speed range to determine whether it is in the best working state, and output the speed analysis result, which includes motor speed overspeed, motor speed underspeed and motor speed instability.

[0102] See also Figure 5 , the present invention provides an embodiment: a vibration signal analysis flow chart, the specific steps are as follows:

[0103] S7.1: Adaptively decompose the vibration signal, calculate the kurtosis value of each component, sort the components in descending order according to the kurtosis value, select the top ten components for signal reconstruction, and eliminate the vibration signal noise;

[0104] S7.2: Perform Fourier transform on the reconstructed vibration signal, divide the frequency domain boundary of the Fourier spectrum of the vibration signal by scale space transform, and divide the Fourier spectrum of the vibration signal into frequency bands with different center frequencies. Each frequency band corresponds to an intrinsic mode function u k ;

[0105] S7.3: Iterate each eigenmode function and calculate the optimal solution that satisfies the minimum sum of the bandwidths of each modal component;

[0106] S7.4: Calculate the power spectrum according to the optimal solution of each modal component, obtain the characteristic frequency of the vibration signal, select the component with the largest energy in the power spectrum as the bearing inner ring signal, the component with the second largest energy in the power spectrum as the bearing outer ring signal, and the component with the third largest energy in the power spectrum as the bearing balance frame signal;

[0107] S7.5: Compare the characteristic frequency of the rolling bearing signal with the vibration frequency under normal conditions, and output the vibration signal analysis result, wherein the comparison also includes time domain analysis and pattern recognition.

[0108] The power outage detection submodule includes:

[0109] Power Monitoring Unit: This unit is responsible for real-time monitoring of the power status of the motor, including key indicators such as current and voltage. It can detect abnormal conditions such as power outages and voltage fluctuations, and record the time, duration and degree of occurrence.

[0110] Historical data comparison unit: This unit compares and analyzes the data collected by the power monitoring unit with historical data to identify any anomalies or trends that deviate from normal patterns. Through comparative analysis, potential power problems can be predicted and provide a basis for preventive measures.

[0111] Fault location unit: When a power supply anomaly is detected, the fault location unit is used to determine the specific location and cause of the fault. It can distinguish whether it is an external power supply problem or a problem with the motor itself, helping maintenance personnel to respond quickly and take correct repair measures

[0112] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. Equipment monitoring visualization system based on digital twin technology, characterized by: The system includes a data acquisition module, a virtual model creation module, a virtual-reality mapping module and an anomaly detection module; The data acquisition module is used to obtain appearance data and operation data of the motor, wherein the appearance data includes an external image of the motor and internal point cloud data of the motor; The virtual model creation module is configured with a motor modeling strategy, and the motor modeling strategy is used to pre-process the appearance data, analyze the pre-processed appearance data, and output a three-dimensional model of the motor; The virtual-real mapping module is used to construct a motor logic model, map the motor logic model to the information space, and construct a digital twin motor in combination with the motor three-dimensional model; The abnormality detection module is used to check suspected faulty motors, locate the number and position of the faulty motors, and issue an alarm for the fault during the visual monitoring of the motors.

2. According to the equipment monitoring visualization system based on digital twin technology according to claim 1, it is characterized in that: The motor modeling strategy includes external feature extraction logic, internal feature extraction logic and three-dimensional modeling logic. The virtual model creation module includes an image processing unit, a point cloud processing unit and a model modeling unit. The external feature extraction logic is configured in the image processing unit, the internal feature extraction logic is configured in the point cloud processing unit, and the three-dimensional modeling logic is configured in the model modeling unit. The image processing unit is used to process the external image of the motor according to the external image of the motor and extract external structural features. The point cloud processing unit is used to process the internal point cloud data of the motor according to the internal point cloud data of the motor and extract internal point cloud features. The model modeling unit is used to process the external structural features and internal point cloud features and output a three-dimensional model of the motor.

3. The equipment monitoring visualization system based on digital twin technology according to claim 2 is characterized in that: The specific steps of the external feature extraction logic are as follows: S3.1: De-noising the external image of the motor; S3.2: Perform histogram statistics on the grayscale values ​​of the motor external image after denoising, and cut out the target area of ​​the motor external image pixel points through a statistical learning method; S3.3: Smooth the target area image by edge detection, calculate Gaussian difference based on the smoothed target area image, extract key points of the target area image, calculate the medium strength of the key points, divide the target area image into four components of R, G, B and Deep for pixel decomposition, and calculate the medium strength of the key points after decomposition; S3.4: According to the medium strength of the key point and the medium strength of the four components of the key point after decomposition, the medium strength of the image is matched and the external structure features are calculated. The calculation formula of the external structure features is: Among them, O c represents the external structural features, j represents a single key point, N represents the total number of key points, δ represents the Fourier transform factor, x j Represents the pixel horizontal coordinate of the jth key point, y j represents the pixel ordinate of the jth key point, max[·] represents the maximum value of the function, M(·) represents the medium strength matching score matrix, m Rk Indicates the R component medium strength at the key point, m Gk Indicates the G component medium strength at the key point, m Bk Indicates the B component medium strength at the key point, m Dk Indicates the medium strength of the Deep component at the key point, m k Indicates the dielectric strength at the critical point.

4. The equipment monitoring visualization system based on digital twin technology according to claim 2 is characterized in that: The specific steps of the internal feature extraction logic are as follows: S4.1: Preprocessing the internal point cloud data of the motor according to the internal point cloud data of the motor, and performing coordinate transformation on the preprocessed internal point cloud data of the motor through rigid body transformation; S4.2: Divide the grid into equal intervals, voxelize the point cloud data inside the motor, project it to the corresponding grid according to the voxel index, connect the points in the voxel, strengthen the local feature information, and obtain the point cloud voxel features; S4.3: Obtain standard point cloud data of the motor internal structure, classify the point cloud voxel features through a clustering algorithm, merge the grids containing the point cloud voxel features under the same central cluster, and calculate the internal point cloud features.

5. The equipment monitoring visualization system based on digital twin technology according to claim 2 is characterized in that: The three-dimensional modeling logic includes a feature classification sub-logic and a motor modeling sub-logic, the feature classification sub-logic includes constructing a feature classification network, training the feature classification network through the external structural features and the internal point cloud features, and outputting the motor component type corresponding to the features, the motor modeling sub-logic includes setting the rendering parameters of the motor component corresponding to the motor component type through the modeling software, rendering the external structural features and the internal point cloud features corresponding to the motor component type, and outputting the three-dimensional model of the ultrasonic motor; The feature classification network includes an input layer, a hidden layer and an output layer; The input layer is used to input external structural features and internal point cloud features, perform logarithmic operations and size reconstruction on the external structural features and the internal point cloud features, and obtain input parameters of the hidden layer; The hidden layer is used to train the input parameters of the hidden layer and calculate the motor component type parameters through the attention mechanism; The output layer is used to output classification results according to the motor component type parameters.

6. The equipment monitoring visualization system based on digital twin technology according to claim 5 is characterized in that: The virtual-reality mapping module includes a data integration unit, a physical mapping unit and a visualization display unit. The data integration unit is used to receive input from sensors and control systems, convert the input into a unified format, and display it on the motor dashboard. The physical mapping unit is used to convert the physical properties of the motor into a digital model and map the digital model to the information space. The visualization display unit is used to provide an interactive page and build a digital twin motor through a three-dimensional model of the motor.

7. The equipment monitoring visualization system based on digital twin technology according to claim 6 is characterized in that: The abnormality detection module includes a protection self-check submodule, a power failure detection submodule and a fault warning submodule; The protection self-check submodule is used to detect fault problems during the operation of the motor; The power failure detection submodule is used to detect fault problems that cannot be found during the operation of the motor; The fault warning submodule is used to warn of the faults detected by the protection self-checking submodule and the power failure detection submodule, and send a notification to the staff.

8. The equipment monitoring visualization system based on digital twin technology according to claim 7 is characterized in that: The protection self-detection submodule includes a temperature detection unit, a vibration detection unit and a rotation speed detection unit; The temperature detection unit includes a temperature analysis logic, which is used to monitor the temperature data of the motor according to the temperature sensor installed on the motor, clean and pre-process the collected temperature data, draw a frequency distribution histogram of the temperature data, and output the temperature state analysis result of the motor according to the frequency distribution histogram, wherein the temperature state analysis result includes the motor overheating and the motor temperature being normal; The vibration detection unit includes a vibration signal analysis logic, which includes vibration signal preprocessing, vibration signal feature extraction and vibration signal feature analysis, and outputs a vibration signal analysis result, which includes improper motor balance, motor bearing damage and shaft bending; The speed detection unit includes a speed analysis logic, which is used to monitor the speed data of the motor according to the speed sensor installed on the motor, clean and pre-process the collected speed data, draw a speed change trend graph, determine whether there is a long-term drift phenomenon in the speed fluctuation, and compare the actual speed with the predetermined working speed range to determine whether it is in the best working state, and output the speed analysis result, which includes motor speed overspeed, motor speed underspeed and motor speed instability.

Images