Centrifugal pump performance degradation assessment method based on twin data

Abstract

The application discloses a kind of based on twinborn data's centrifugal pump performance degradation evaluation method, comprising: the operating data of centrifugal pump is collected to obtain measured vibration signal;Build the digital twin model of centrifugal pump in service state, generate the twinborn vibration signal of different health state centrifugal pump;The twinborn vibration signal under different health states of centrifugal pump is decomposed to obtain product function component;According to the similarity between product function component and original vibration signal determines candidate product function component;Extract the candidate singular value component corresponding to each candidate product function component;Each candidate singular value component is regarded as the input of fast search clustering model, determines clustering center;Introduce quantitative index confidence function to determine degradation index, according to degradation index judges the degradation state of centrifugal pump.The application introduces digital twin technology and advanced algorithm, improves the degree of automation and accuracy of evaluation, provides a novel and effective solution for the health management of centrifugal pump.

Description

Technical Field

[0001] This invention relates to the field of intelligent industrial technology, and in particular to a method for evaluating the performance degradation of centrifugal pumps based on twin data. Background Technology

[0002] Centrifugal pumps are common and critical equipment in the machinery industry, widely used in complex product systems such as large-scale nuclear power, water supply and drainage, and marine propulsion. Their efficient and reliable operation is an important guarantee for the safety and stability of the system. Therefore, research on centrifugal pump performance degradation assessment methods is of great significance and has broad engineering application prospects for ensuring the safe and efficient operation of complex product systems.

[0003] Currently, traditional performance degradation assessment modeling methods, such as single or multiple time-frequency domain indicators (e.g., root mean square value, kurtosis and other values) and signal decomposition models (wavelet transform, empirical mode decomposition, etc.), all require rich human experience (e.g., selecting appropriate wavelet functions and fault frequency bands for decomposition) to select suitable feature indicators and cross-integrate them with the model. Moreover, the above modeling methods are quite cumbersome.

[0004] To address the problems existing in traditional performance degradation assessment methods, this invention proposes a centrifugal pump performance degradation assessment method based on twin data, which reduces the reliance on human experience and solves the problem that signal performance degradation states are difficult to classify due to continuous changes, thus saving economic costs. Summary of the Invention

[0005] In view of this, the present invention provides a centrifugal pump performance degradation assessment method based on twin data, which solves the technical problem that existing centrifugal pump performance degradation assessment technologies require rich human experience to select appropriate feature indicators to judge the degradation status, resulting in low assessment efficiency and too strong subjective dependence.

[0006] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for evaluating the performance degradation of centrifugal pumps based on twin data, comprising:

[0008] Real-time acquisition of centrifugal pump operating data, and obtaining measured vibration signals based on the operating data;

[0009] Based on the physical entity information, operating conditions and measured vibration signals of the centrifugal pump, a digital twin model of the centrifugal pump under service conditions is constructed, and twin vibration signals of centrifugal pumps under different health conditions are generated.

[0010] Twin vibration signals of a centrifugal pump under different health conditions are decomposed using the local mean decomposition method to obtain product function components; the similarity between each product function component and the original vibration signal is calculated; the product function components are sorted based on the similarity, and several candidate product function components with the highest similarity are selected.

[0011] The singular value decomposition method is used to extract the candidate singular value components corresponding to each candidate product function component;

[0012] Each candidate singular value component is used as input to a fast search clustering model to determine the number of clusters and cluster centers under different degradation states.

[0013] Feature vectors are constructed based on candidate singular value components. A quantitative index confidence function is introduced, and the distance between the feature vector and the cluster center is used as a degradation index. The degradation state of the centrifugal pump is determined based on the degradation index.

[0014] Furthermore, the distance between the feature vector and the cluster center is used as a degradation index, expressed by the formula:

[0015]

[0016] Where CV represents the similarity between the i-th candidate singular value and the cluster center under normal circumstances; D represents the distance between any two candidate singular values; and S represents the scaling factor associated with the cluster center.

[0017] Furthermore, based on the physical entity information, operating conditions, and measured vibration signals of the centrifugal pump, a digital twin model of the centrifugal pump in service condition is constructed, including:

[0018] Based on the physical entity information and operating conditions of the centrifugal pump, a finite element model of the centrifugal pump is established using finite element analysis software, and simulation data is generated.

[0019] Kalman filtering was used to update and correct the simulation data of the centrifugal pump finite element model through measured vibration signals, and a digital twin model of the centrifugal pump was constructed.

[0020] Using a digital twin model of a centrifugal pump, twin vibration signals of centrifugal pumps in different health states under service conditions are generated.

[0021] Furthermore, a finite element model of the centrifugal pump is established using finite element analysis software, including:

[0022] Import the centrifugal pump geometric model into the finite element analysis software and define material properties for each part of the geometric model;

[0023] The geometric model is divided into multiple basic elements using finite element analysis software, and the properties of the mesh are adjusted to ensure simulation accuracy and computational efficiency.

[0024] Boundary conditions and loads are applied to the geometric model based on the operating conditions of the centrifugal pump to simulate the actual operating state;

[0025] The model response information is obtained by solving the simulation model, and simulation data corresponding to the measured data is generated.

[0026] Furthermore, each candidate singular value component is used as input to a fast search clustering model to determine the number of clusters and cluster centers under different degradation states, including:

[0027] Based on each candidate singular value component at different runtime times, a sample dataset is formed, and the Euclidean distance between any two samples in the dataset is calculated.

[0028] The local density of each element is calculated based on Euclidean distance. The local densities of each data point in the sequence are sorted in descending order, and the decision distance of each data point is calculated.

[0029] Cluster values ​​are assigned to each data point based on local density and decision distance;

[0030] Cluster centers are determined based on the sorted cluster values. Elements with the highest sorted cluster values ​​are prioritized as potential cluster centers. The points where cluster values ​​change abruptly are identified and used as cluster centers for different degeneration states to determine the number of clusters and the location of the center points.

[0031] Based on whether the distance between the data point and the cluster center of different degradation states exceeds the preset cutoff distance, the data points are automatically divided into clusters of different degradation states.

[0032] Furthermore, the local density of each element calculated based on Euclidean distance is expressed by the formula:

[0033]

[0034] in, Let i be the Euclidean distance between data points i and j; This is the preset cutoff distance.

[0035] Furthermore, the step of sorting the local density of each data point in the sequence in descending order and calculating the decision distance for each data point includes:

[0036] If a data point has the highest local density, its determination distance is the distance from that data point to the farthest point in the dataset; for other points whose local density is not the highest, the determination distance is the distance to the nearest point with a higher density than that point; expressed by the formula:

[0037]

[0038] The data points are arranged in descending order of local density. When i=1, The data point with the highest local density; Representing data points With data points The Euclidean distance between them Representing data points Compared to High-density data points The Euclidean distance between them.

[0039] Secondly, the present invention also provides a centrifugal pump performance degradation assessment system based on twin data, comprising:

[0040] The data acquisition module is used to collect the operating data of the centrifugal pump in real time and obtain the measured vibration signal based on the operating data;

[0041] The twin model construction module is used to construct a digital twin model of a centrifugal pump in service condition based on the physical entity information, operating conditions and measured vibration signals of the centrifugal pump, and generate twin vibration signals of centrifugal pumps in different health states under service conditions.

[0042] The signal decomposition module is used to decompose the twin vibration signals of the centrifugal pump under different health conditions using the local mean decomposition method to obtain product function components; calculate the similarity between each product function component and the original vibration signal; sort the product function components based on the similarity and select several candidate product function components with the highest similarity.

[0043] The feature extraction module is used to extract the candidate singular value components corresponding to each candidate product function component using the singular value decomposition method.

[0044] The clustering module is used to take each candidate singular value component as input to a fast search clustering model to determine the number of clusters and cluster centers under different degradation states.

[0045] The evaluation module is used to construct feature vectors based on singular value components, introduce a quantitative index confidence function, use the distance between the feature vector and the cluster center as a degradation index, and determine the degradation status of the centrifugal pump based on the degradation index.

[0046] Thirdly, the present invention also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the centrifugal pump performance degradation assessment method based on twin data as described in any of the above technical solutions.

[0047] Compared with existing technologies, the centrifugal pump performance degradation assessment method based on twin data proposed in this invention has the following advantages:

[0048] (1) Taking into full account the fact that most centrifugal pumps are in normal condition in actual engineering applications and lack abnormal sample data, the digital twin technology is introduced to generate twin vibration signals to simulate the performance of centrifugal pumps under different health conditions, effectively expanding the sample size and ensuring that a comprehensive performance evaluation can be carried out even under normal conditions.

[0049] (2) The product function (PF) components extracted by Local Mode Decomposition (LMD) and the singular values ​​(SV) extracted by Singular Value Decomposition (SVD) in step 4 provide rich feature information for performance degradation assessment. This comprehensive feature extraction method can more comprehensively reflect the health status of the centrifugal pump and improve the accuracy of the assessment.

[0050] (3) By using the Fast Search Clustering (CFS) algorithm, the automatic division of sample labels is realized, which can accurately identify and classify different degradation states (normal state, early degradation and severe degradation), reduce the dependence on human experience, and improve the objectivity and accuracy of the assessment.

[0051] The centrifugal pump performance degradation assessment method based on twin data of the present invention not only solves the problem of insufficient sample size, but also improves the automation and accuracy of the assessment by introducing advanced algorithms and technologies, providing a novel and effective solution for the health management of centrifugal pumps. Attached Figure Description

[0052] Figure 1 A schematic flowchart of the centrifugal pump performance degradation assessment method based on twin data provided by the present invention;

[0053] Figure 2 This is a schematic diagram illustrating the application of the method provided by the present invention;

[0054] Figure 3 A schematic diagram of the centrifugal pump performance degradation assessment system based on twin data provided by the present invention. Detailed Implementation

[0055] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0056] Please see Figure 1 This embodiment provides a method for evaluating the performance degradation of centrifugal pumps based on twin data, including:

[0057] Step S101: Collect the operating data of the centrifugal pump in real time, and obtain the measured vibration signal based on the operating data;

[0058] Step S102: Based on the physical entity information, operating conditions and measured vibration signals of the centrifugal pump, construct a digital twin model of the centrifugal pump under service conditions, and generate twin vibration signals of centrifugal pumps under different health conditions under service conditions.

[0059] Step S103: Decompose the twin vibration signals of the centrifugal pump under different health conditions using the local mean decomposition method to obtain product function components; calculate the similarity between each product function component and the original vibration signal; sort the product function components based on the similarity and select several candidate product function components with the highest similarity.

[0060] Step S104: Extract the candidate singular value components corresponding to each candidate product function component using singular value decomposition.

[0061] Step S105: Use each candidate singular value component as input to the fast search clustering model to determine the number of clusters and cluster centers under different degradation states;

[0062] Step S106: Construct feature vectors based on candidate singular value components, introduce a quantitative index confidence function, use the distance between the feature vector and the cluster center as a degradation index, and determine the degradation state of the centrifugal pump based on the degradation index.

[0063] The method in this embodiment acquires centrifugal pump operating data in real time to obtain the equipment's operating status and ensures real-time monitoring of equipment performance. By constructing a digital twin model of the centrifugal pump, it can simulate the behavior of real equipment and generate twin vibration signals under different health states, which helps to comprehensively understand the equipment's performance under various operating conditions. By calculating the similarity between the product function components and the original signal, it can quickly screen out the features closest to the actual state, improving the effectiveness of the assessment. The CFS clustering algorithm is used to automatically classify sample labels, reducing reliance on human experience. A quantitative confidence function is introduced, using the distance between the feature vector and the cluster center as a degradation index, making the degradation assessment more objective and quantifiable. The method in this embodiment can achieve early warning of equipment, reduce the risk of failure, and reduce maintenance costs.

[0064] As a specific embodiment, in step S101, the method for collecting the operating data of the centrifugal pump is as follows: based on the original plant SCADA system, vibration sensors are installed on both sides of the centrifugal pump unit, and OPC UA technology is used to collect the vertical and horizontal vibration signals of the equipment and extract the pressure signals from the SCADA system; data is collected once every 1 second and stored as a sample, and each sample records 10 measured vibration data.

[0065] In a preferred embodiment, in step S102, a digital twin model of the centrifugal pump in its service state is constructed based on the physical entity information, operating conditions, and measured vibration signals of the centrifugal pump, including:

[0066] Based on the physical entity information and operating conditions of the centrifugal pump, a finite element model of the centrifugal pump is established using finite element analysis software, and simulation data is generated.

[0067] Kalman filtering was used to update and correct the simulation data of the centrifugal pump finite element model through measured vibration signals, and a digital twin model of the centrifugal pump was constructed.

[0068] Using a digital twin model of a centrifugal pump, twin vibration signals of centrifugal pumps in different health states under service conditions are generated.

[0069] As a preferred embodiment, a finite element model of the centrifugal pump is established using finite element analysis software, including:

[0070] Import the centrifugal pump geometric model into the finite element analysis software and define material properties for each part of the geometric model;

[0071] The geometric model is divided into multiple basic elements using finite element analysis software, and the properties of the mesh are adjusted to ensure simulation accuracy and computational efficiency.

[0072] Boundary conditions and loads are applied to the geometric model based on the operating conditions of the centrifugal pump to simulate the actual operating state;

[0073] The model response information is obtained by solving the simulation model, and simulation data corresponding to the measured data is generated.

[0074] As a specific example, the detailed steps for constructing a digital twin model are as follows:

[0075] Step 1: Create a geometric model: Import the 3D model created in Solidworks into COMSOL (finite element software), and define material properties for each part of the geometric model, such as elastic modulus, Poisson's ratio, density, thermal conductivity, etc.

[0076] Step 2: Mesh generation: The geometric model is automatically divided into a series of small units (such as triangles, quadrilaterals, tetrahedrons, or hexahedrons) using COMSOL software, and the size, shape, and distribution of the mesh are manually adjusted to ensure the accuracy and computational efficiency of critical areas.

[0077] Step 3: Boundary conditions and loads: Based on the actual working conditions (the running data collected in step S101), apply appropriate boundary conditions and loads to the model to ensure that they conform to the actual situation and simulate the state of the object being analyzed as accurately as possible.

[0078] Step 4: Generate simulation data: Based on the defined model, material properties, mesh generation, boundary conditions, and loads, solve for the model's response (such as displacement, stress, temperature, etc.) to generate simulation data similar to the measured data.

[0079] Step 5: Constructing a digital twin model: Using the Kalman filter method, the simulation data of the centrifugal pump finite element model is updated and corrected using measured data from normal operation, thus constructing a digital twin model of the centrifugal pump.

[0080] Finally, using the constructed digital twin model of the centrifugal pump, twin vibration signals of centrifugal pumps in different health states under service conditions are generated.

[0081] Through the steps described above, the constructed digital twin model of the centrifugal pump can generate twin vibration signals for centrifugal pumps in different health states under service conditions. Even in practical engineering applications, centrifugal pumps are mostly in normal conditions, lacking abnormal sample data; the digital twin model can still simulate vibration signals under various possible abnormal health states based on physical principles and model predictions, supplementing the lack of abnormal sample data. This provides complete and comprehensive data support for subsequent vibration signal analysis, fault diagnosis, and health status assessment, avoiding the problems of inaccurate or incomplete analysis due to a lack of abnormal sample data.

[0082] Based on complete data including both normal and abnormal states, abnormal vibration signals and changes in the health status of centrifugal pumps can be identified more accurately, improving the accuracy and reliability of fault diagnosis. This is of great significance for timely detection and handling of potential faults in centrifugal pumps.

[0083] In a specific embodiment, in step S103, the twin vibration signals of the centrifugal pump under different health states are decomposed using LMD (Low Damage Decomposition). In actual calculations, the first two product function (PF) components are generally selected. Specifically:

[0084] First, the product function (PF) components of twin vibration signals from different health states of the centrifugal pump are extracted using the LMD method. Then, the similarity between each PF component and the original vibration signal is calculated using the correlation coefficient. Finally, the first two PF components are selected based on the correlation coefficient values.

[0085] It's important to note that Local Mean Decomposition (LMD) is a signal processing technique used to decompose complex signals into several simpler components. Its core idea is to decompose the signal into several Intrinsic Mode Functions (IMFs) and a residual using local averaging. Each IMF represents a specific frequency component of the signal. The Power Factor (PF) is typically a combination of IMFs, reflecting the interactions between different frequency components in the signal.

[0086] The correlation function used is the Pearson correlation coefficient, which measures the linear relationship between two variables, with values ​​ranging from -1 to 1. Based on the calculated correlation coefficient values, the two PF components with the highest similarity to the original vibration signal are selected. These two PF components are the two components with the largest correlation coefficient values. For example, PF1 might be IMF1 + 0.5 * IMF2, and PF2 might be 0.8 * IMF3 - IMF4.

[0087] As a specific embodiment, in step S104, the Singular Value Decomposition (SVD) algorithm is used to extract the singular values ​​(SVs) corresponding to the first two PF components in step 3, where PF1 corresponds to SV1 and PF2 corresponds to SV2. Singular value decomposition is a matrix factorization method that can decompose an arbitrary matrix A into the product of three matrices, expressed by the formula:

[0088]

[0089] in, Σ is a column orthogonal matrix containing left singular vectors, and Σ is a diagonal matrix containing singular values ​​(SV). The singular values ​​are non-negative and are arranged in descending order. It is the transpose of the right singular vector.

[0090] By performing SVD on the first two PF components, we obtain two singular values, SV1 and SV2. These two singular values ​​can form a vector or matrix. Assuming we have multiple samples (e.g., PF components at different time points), we can organize the singular values ​​of each sample into a vector matrix X. Using the first two SV components as input to the Clustering by Fast Search (CFS) algorithm, the number of clusters and their centers are automatically determined for different degradation states (normal state, early degradation, and severe degradation). Specifically, assuming there are N samples, then:

[0091] (1) Calculate the dataset The Euclidean distance between any two samples in the dataset is given by: It is a vector matrix of all SV components obtained in step S104.

[0092] (2) Calculate data points Local density ,

[0093]

[0094] in, For data points and The Euclidean distance between them; The cutoff distance is usually given manually; this method uses a genetic algorithm to optimize the setting. The value is set to 1.5% (meaning the number of adjacent points accounts for 1.5% of the total number of data points).

[0095] (3) Local density of each data point in the sequence Sort by size from largest to smallest; then calculate the judgment distance. Determine distance The calculation method is as follows:

[0096] If a data point has the highest local density, its determination distance is the distance from that data point to the farthest point in the dataset; for other points whose local density is not the highest, the determination distance is the distance to the nearest point with a higher density than that point; expressed by the formula:

[0097]

[0098] The data points are arranged in descending order of local density. When i=1, The data point with the highest local density; Representing data points With data points The Euclidean distance between them Representing data points Compared to High-density data points The Euclidean distance between them.

[0099] (4) Following the calculation process in steps (2) and (3), assign a point to each point in the dataset. The values ​​are then sorted in descending order.

[0100] (5) Based on each data point The values ​​determine the cluster centers. These... The values ​​are sorted in descending order, and points with higher values ​​are given priority as potential cluster centers. Data points whose values ​​change abruptly are identified and selected as cluster centers for different states.

[0101] (6) Determine whether the distance between the data point and the cluster centers of different degradation states exceeds the cutoff distance. It automatically divides data points into clusters with different degradation states.

[0102] Finally, a confidence value (CV) function is introduced to evaluate the feature vectors [SV1, SV2] obtained in real time during the evaluation process. The distance between the feature vectors and the cluster centers determined by the clustering model S105 is used as a performance degradation index.

[0103] Please refer to Figure 2 The flowchart of the method in practical application is as follows: Figure 2 As shown.

[0104] like Figure 3 As shown, this embodiment of the invention also provides a centrifugal pump performance degradation assessment system 300 based on twin data, comprising:

[0105] The data acquisition module 301 is used to acquire the operating data of the centrifugal pump in real time and obtain the measured vibration signal based on the operating data;

[0106] The twin model construction module 302 is used to construct a digital twin model of the centrifugal pump in service condition based on the physical entity information, operating conditions and measured vibration signals of the centrifugal pump, and generate twin vibration signals of centrifugal pumps in different health states under service conditions.

[0107] The signal decomposition module 303 is used to decompose the twin vibration signals of the centrifugal pump under different health conditions using the local mean decomposition method to obtain product function components; calculate the similarity between each product function component and the original vibration signal; sort the product function components based on the similarity and select several candidate product function components with the highest similarity.

[0108] Feature extraction module 304 is used to extract the candidate singular value components corresponding to each candidate product function component using singular value decomposition.

[0109] Clustering module 305 is used to take each candidate singular value component as input to a fast search clustering model to determine the number of clusters and cluster centers under different degradation states;

[0110] Evaluation module 306 is used to construct feature vectors based on singular value components, introduce a quantitative index confidence function, use the distance between the feature vector and the cluster center as a degradation index, and determine the degradation state of the centrifugal pump based on the degradation index.

[0111] In a preferred embodiment, the data acquisition module 201 includes a plant monitoring module, a sensor module, and a data transmission module;

[0112] The plant monitoring module is used to acquire pressure signals during the operation of the centrifugal pump unit;

[0113] The sensor module is a vibration displacement sensor installed on the rolling bearing seats on both sides of the centrifugal pump unit, used to acquire vibration signals of the centrifugal pump in the vertical and horizontal directions.

[0114] The data transmission module is used to acquire the operating data of the centrifugal pump using OPC UA communication.

[0115] It should be noted that OPC UA's cross-platform features (supporting Windows / Linux / embedded systems) adapt to diverse hardware environments in factories. In addition, the OPC UA client subscribes to changes in data points, and vibration data is updated and pushed to SCADA in milliseconds, avoiding polling delays.

[0116] This embodiment also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the centrifugal pump performance degradation assessment method based on twin data as described in any of the above technical solutions.

[0117] The computer-readable storage medium and computing device provided in the above embodiments of the present invention can be implemented with reference to the content specifically described above regarding the centrifugal pump performance degradation assessment method based on twin data, and have similar beneficial effects to the centrifugal pump performance degradation assessment method based on twin data as described above, which will not be repeated here.

[0118] This invention discloses a centrifugal pump performance degradation assessment method based on twin data. By collecting real-time operating data of the centrifugal pump, it obtains the equipment's operating status in a timely manner, ensuring real-time monitoring of equipment performance. By constructing a digital twin model of the centrifugal pump, it can simulate the behavior of the real equipment and generate twin vibration signals under different health states, which helps to comprehensively understand the equipment's performance under various operating conditions. By calculating the similarity between the product function components and the original signal, it can quickly screen out the features closest to the actual state, improving the effectiveness of the assessment. The CFS clustering algorithm is used to automatically classify sample labels, reducing reliance on human experience. A quantitative confidence function is introduced, using the distance between the feature vector and the cluster center as a degradation index, making the degradation assessment more objective and quantifiable. This invention enables early warning of equipment failures, reduces the risk of malfunctions, and lowers maintenance costs.

[0119] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for evaluating the performance degradation of centrifugal pumps based on twin data, characterized in that, include: Real-time acquisition of centrifugal pump operating data, and obtaining measured vibration signals based on the operating data; Based on the physical entity information, operating conditions and measured vibration signals of the centrifugal pump, a digital twin model of the centrifugal pump under service conditions is constructed, and twin vibration signals of centrifugal pumps under different health conditions are generated. The twin vibration signals of the centrifugal pump under different health conditions are decomposed by the local mean decomposition method to obtain the product function components; Calculate the similarity between each component of the product function and the original vibration signal; The product function components are sorted based on similarity, and the candidate product function components with the highest similarity are selected. The singular value decomposition method is used to extract the candidate singular value components corresponding to each candidate product function component; Each candidate singular value component is used as input to a fast search clustering model to determine the number of clusters and cluster centers under different degradation states. Feature vectors are constructed based on candidate singular value components. A quantitative index confidence function is introduced, and the distance between the feature vector and the cluster center is used as a degradation index. The degradation state of the centrifugal pump is determined based on the degradation index.

2. The centrifugal pump performance degradation assessment method based on twin data according to claim 1, characterized in that, The distance between the feature vector and the cluster centroid is used as a degradation index, expressed by the formula: Where CV represents the similarity between the i-th candidate singular value and the cluster center under normal circumstances; D represents the distance between any two candidate singular values; and S represents the scaling factor associated with the cluster center.

3. The centrifugal pump performance degradation assessment method based on twin data according to claim 1, characterized in that, Based on the physical information, operating conditions, and measured vibration signals of the centrifugal pump, a digital twin model of the centrifugal pump in service condition is constructed, including: Based on the physical entity information and operating conditions of the centrifugal pump, a finite element model of the centrifugal pump is established using finite element analysis software, and simulation data is generated. Kalman filtering was used to update and correct the simulation data of the centrifugal pump finite element model through measured vibration signals, and a digital twin model of the centrifugal pump was constructed. Using a digital twin model of a centrifugal pump, twin vibration signals of centrifugal pumps in different health states under service conditions are generated.

4. The centrifugal pump performance degradation assessment method based on twin data according to claim 3, characterized in that, A finite element model of a centrifugal pump was established using finite element analysis software, including: Import the centrifugal pump geometric model into the finite element analysis software and define material properties for each part of the geometric model; The geometric model is divided into multiple basic elements using finite element analysis software, and the properties of the mesh are adjusted to ensure simulation accuracy and computational efficiency. Boundary conditions and loads are applied to the geometric model based on the operating conditions of the centrifugal pump to simulate the actual operating state; The model response information is obtained by solving the simulation model, and simulation data corresponding to the measured data is generated.

5. The centrifugal pump performance degradation assessment method based on twin data according to claim 1, characterized in that, Each candidate singular value component is used as input to a fast search clustering model to determine the number of clusters and cluster centers under different degradation states, including: Based on each candidate singular value component at different runtime times, a sample dataset is formed, and the Euclidean distance between any two samples in the dataset is calculated. The local density of each element is calculated based on Euclidean distance. The local densities of each data point in the sequence are sorted in descending order, and the decision distance of each data point is calculated. Cluster values ​​are assigned to each data point based on local density and decision distance; Cluster centers are determined based on the sorted cluster values. Elements with the highest sorted cluster values ​​are prioritized as potential cluster centers. The points where cluster values ​​change abruptly are identified and used as cluster centers for different degeneration states to determine the number of clusters and the location of the center points. Based on whether the distance between the data point and the cluster center of different degradation states exceeds the preset cutoff distance, the data points are automatically divided into clusters of different degradation states.

6. The centrifugal pump performance degradation assessment method based on twin data according to claim 5, characterized in that, The local density of each element calculated based on Euclidean distance is expressed by the following formula: in, For data points Local density, For data points and The Euclidean distance between them; This is the preset cutoff distance.

7. The centrifugal pump performance degradation assessment method based on twin data according to claim 5, characterized in that, The process of sorting the local density of each data point in the sequence from largest to smallest and calculating the decision distance for each data point includes: If a data point has the highest local density, its determination distance is the distance from that data point to the farthest point in the dataset; for other points whose local density is not the highest, the determination distance is the distance to the nearest point with a higher density than that data point; this can be expressed by the formula: in, For data points The distance for determining the distance is calculated by arranging the data points in descending order of local density. When i=1, The data point with the highest local density; Representing data points With data points The Euclidean distance between them Representing data points Compared to High-density data points The Euclidean distance between them.

8. A centrifugal pump performance degradation assessment system based on twin data, characterized in that, include: The data acquisition module is used to collect the operating data of the centrifugal pump in real time and obtain the measured vibration signal based on the operating data; The twin model construction module is used to construct a digital twin model of a centrifugal pump in service condition based on the physical entity information, operating conditions and measured vibration signals of the centrifugal pump, and generate twin vibration signals of centrifugal pumps in different health states under service conditions. The signal decomposition module is used to decompose the twin vibration signals of the centrifugal pump under different health conditions using the local mean decomposition method to obtain the product function components. Calculate the similarity between each component of the product function and the original vibration signal; The product function components are sorted based on similarity, and the candidate product function components with the highest similarity are selected. The feature extraction module is used to extract the candidate singular value components corresponding to each candidate product function component using the singular value decomposition method. The clustering module is used to take each candidate singular value component as input to a fast search clustering model to determine the number of clusters and cluster centers under different degradation states. The evaluation module is used to construct feature vectors based on singular value components, introduce a quantitative index confidence function, use the distance between the feature vector and the cluster center as a degradation index, and determine the degradation status of the centrifugal pump based on the degradation index.

9. The centrifugal pump performance degradation assessment system based on twin data according to claim 8, characterized in that, The data acquisition module includes a plant monitoring module, a sensor module, and a data transmission module; The plant monitoring module is used to acquire pressure signals during the operation of the centrifugal pump unit; The sensor module is a vibration displacement sensor installed on the rolling bearing seats on both sides of the centrifugal pump unit, used to acquire vibration signals of the centrifugal pump in the vertical and horizontal directions. The data transmission module is used to acquire the operating data of the centrifugal pump using OPC UA communication.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the centrifugal pump performance degradation assessment method based on twin data as described in any one of claims 1-7.

Images