Electromechanical equipment information integration management method and system based on Internet of Things

Abstract

The invention relates to the technical field of information management of the Internet of Things, and particularly discloses an electromechanical equipment information integration management method and system based on the Internet of Things. Vibration data and surface image data of equipment are collected in real time through a vibration sensor and a machine vision system, and fluctuation analysis is performed on the vibration data by adopting a wavelet transform technology; calculating an abnormal fluctuation coefficient; using an image processing algorithm to extract fault features of the equipment surface, and generating a fault feature index; carrying out fusion analysis on the abnormal fluctuation coefficient of the vibration data and the fault feature index of the image data, and calculating a comprehensive risk coefficient through a weighted summation mode; through comparison with a preset threshold value, the system can realize fault early warning and generate a corresponding early warning signal.

Description

Technical Field

[0001] The present invention relates to the technical field of information management of the Internet of Things, and in particular to a method and system for integrating and managing electromechanical equipment information based on the Internet of Things. Background Art

[0002] With the continuous improvement of industrial automation, electromechanical equipment plays a vital role in various production processes. The operating status of the equipment is directly related to production efficiency, quality and safety. Therefore, how to monitor and diagnose equipment failures in real time and ensure the long-term stable operation of the equipment has become a core issue that needs to be urgently solved in the field of intelligent manufacturing. In recent years, the combination of Internet of Things technology, vibration monitoring and machine vision systems has made the fault detection of electromechanical equipment more intelligent and efficient. By acquiring the vibration data and surface images of the equipment in real time through sensors and cameras, the operating status of the equipment can be more comprehensively reflected, and potential fault hazards can be identified in advance, reducing the losses caused by sudden equipment failures.

[0003] Although the existing technology has been able to achieve a certain degree of equipment monitoring and fault diagnosis, there are still some limitations. Traditional vibration analysis methods mostly rely on single vibration data for fault detection, ignoring the impact of equipment surface faults, resulting in insufficient accuracy and comprehensiveness of fault diagnosis. In addition, data analysis based on a single sensor often has false positives and false negatives, and cannot effectively deal with failure modes in complex environments. Existing machine vision systems are also mostly limited to image recognition, fail to fully integrate multiple data sources, and lack comprehensive and accurate equipment status assessment. In response to these problems, the present invention combines vibration data with image data and adopts advanced analysis algorithms to more accurately assess the failure risk of electromechanical equipment, solves the shortcomings of existing technologies in comprehensiveness, accuracy and real-time performance, and achieves smarter and more efficient equipment monitoring and maintenance management. Summary of the invention

[0004] The purpose of the present invention is to provide an electromechanical equipment information integration management method and system based on the Internet of Things to solve the above-mentioned background problems.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The electromechanical equipment information integration management method based on the Internet of Things includes the following steps:

[0007] S1: Real-time collection of operating status data of electromechanical equipment, including vibration data obtained by vibration sensors and equipment surface image data obtained by machine vision systems;

[0008] S2: Analyze the fluctuation degree of the collected vibration data, and calculate the abnormal fluctuation coefficient of the vibration data according to the fluctuation degree of the vibration data, so as to identify the vibration characteristics of the equipment and evaluate the operating status of the equipment;

[0009] S3: Process the equipment surface image data through the machine vision system, use the image processing algorithm to detect cracks, wear and foreign matter intrusion on the equipment surface, extract the corresponding fault features, and generate a fault feature index based on the fault features to evaluate the surface fault of the equipment;

[0010] S4: Fusion analysis of vibration data and image data, including fusion calculation of abnormal fluctuation coefficient of vibration data and fault characteristic index, to obtain comprehensive risk coefficient, which is used for fault warning of electromechanical equipment and generation of warning signal;

[0011] S5: Perform maintenance and shutdown of equipment based on early warning signals.

[0012] Preferably, the analysis of the fluctuation degree of the collected vibration data and calculation of the abnormal fluctuation coefficient of the vibration data according to the fluctuation degree of the vibration data specifically includes:

[0013] Acquire a vibration data signal x(t) according to a time series, where t represents time and x(t) represents the amplitude value of the vibration signal at time t;

[0014] The wavelet basis function is selected as the transformation formula of the vibration data signal. The discrete wavelet transform of the vibration data signal x(t) is decomposed into approximate coefficients and detail coefficients of different frequency bands. The calculation expression is:

[0015]

[0016] Wherein, the wavelet basis function is Daubechies wavelet;

[0017] In the formula, a j represents the approximation coefficient, d j represents the detail coefficient, ψ aj (t) and ψ dj (t) are the wavelet functions of the corresponding scales, and j represents the number of layers of wavelet decomposition;

[0018] Calculate the volatility of each wavelet decomposition layer, and the calculation expression is:

[0019]

[0020] Where N j represents the total number of data points in the jth layer, i represents a data point, and d j (i) represents the detail coefficient of the i-th data point in the j-th layer, V jrepresents the volatility of the jth layer;

[0021] Calculate the standard deviation of the j-th layer vibration signal to represent the fluctuation amplitude of the vibration;

[0022] The standard deviation of each layer is calculated by ratio to the fluctuation degree to obtain the abnormal fluctuation coefficient of each layer. The fluctuation coefficients of all layers are summed up to obtain the abnormal fluctuation coefficient of vibration data.

[0023] Preferably: the step of evaluating the operating status of the equipment specifically includes:

[0024] It is determined whether the abnormal fluctuation coefficient of the vibration data is greater than or equal to a preset threshold value. If so, the corresponding electromechanical equipment operating state is abnormal; if not, the corresponding electromechanical equipment operating state is not abnormal.

[0025] Preferably, the device surface image data is processed by a machine vision system, cracks, wear and foreign matter intrusion on the device surface are detected using an image processing algorithm, and corresponding fault features are extracted, specifically including:

[0026] Preprocess the collected equipment surface image data and extract effective fault features, including:

[0027] Convert the original color image to a grayscale image, use a Gaussian filter to smooth the image, remove noise, perform a convolution operation on the grayscale image, and use the smoothed image for subsequent calculations;

[0028] Calculate the gradient amplitude of the image, the calculation expression is:

[0029]

[0030] In the formula, G x represents the gradient in the x direction, G y represents the gradient in the y direction, and G represents the gradient amplitude;

[0031] Calculate the gradient direction of the image, the calculation expression is:

[0032]

[0033] In the formula, θ represents the gradient direction;

[0034] Extract the length and width of the crack, calculate the length and width of the crack according to the edge pixel coordinates, calculate the crack characteristics, and the calculation expression is:

[0035]

[0036] In the formula, x start ,y start represents the crack starting point coordinates, x end ,yend represents the coordinates of the crack end point, L c Indicates crack characteristics;

[0037] The size of the wear area is calculated based on the area of ​​the edge closed area and recorded as the wear feature T w , the size of the wear area is calculated by multiplying the number of pixels in the area by the area of ​​a single pixel;

[0038] Discrete edge areas are detected, foreign objects are identified through shape complexity calculation, and the foreign object intrusion characteristics are obtained. The calculation expression is:

[0039]

[0040] Where P e represents the perimeter, the sum of the edge lengths, A e Represents the area of ​​the edge closed region, C e Indicates the characteristics of foreign body invasion.

[0041] Preferably, the process of obtaining the fault characteristic index is as follows:

[0042] The crack features, wear features and foreign body intrusion features are input into the feature matrix I = [L c ,T w ,C e ];

[0043] Standardize the features;

[0044] Calculate the convolution output features, the calculation expression is:

[0045]

[0046] In the formula, F ij represents the convolution output feature, i, j represents the position coordinates, I i+m-1,j+n-1 represents the position coordinates of the input feature matrix at (i+m-1,j+n-1), m, n represent the convolution kernel size, K represents the convolution kernel, the maximum convolution kernel size of M and N, and b represents the bias term;

[0047] Calculate the convolution output features of each convolution layer;

[0048] The maximum pooling is used to reduce the dimension of the convolution output features of each convolution layer. The calculation expression is:

[0049]

[0050] In the formula, l represents the convolutional layer, represents the convolution output feature after the pooling operation, represents the convolution output feature of convolution layer l, M ′ and N′ is the size of the pooling window;

[0051] The convolution output features of all convolutional layers after the pooling operation are summed up to obtain the fault feature index.

[0052] Preferably, the fusion analysis of the vibration data and the image data includes fusion calculation of the abnormal fluctuation coefficient of the vibration data and the fault characteristic index to obtain a comprehensive risk coefficient, which specifically includes:

[0053] Obtain the abnormal fluctuation coefficient and fault characteristic index of vibration data of several identical electromechanical equipment in history, and the comprehensive risk coefficient of each electromechanical equipment in history as training data;

[0054] Obtain the abnormal fluctuation coefficient and fault characteristic index of vibration data of real-time electromechanical equipment as test data;

[0055] Calculate the Euclidean distance between the test data and the training data using the Euclidean calculation formula;

[0056] Sort the Euclidean distances of all electromechanical equipment in order of size, select the abnormal fluctuation coefficients of vibration data and fault characteristic indexes corresponding to the three smallest Euclidean distances, and record them as selected data;

[0057] According to the selected vibration data abnormal fluctuation coefficient and fault characteristic index, the comprehensive risk coefficient is calculated by weighted summation. The calculation expression is:

[0058]

[0059] In the formula, R new represents the comprehensive risk factor of real-time electromechanical equipment, k represents the selected data, K represents the total number of selected data, the value of K is 3, Z fk represents the fault characteristic index of the kth selected data, Z Tk represents the abnormal fluctuation coefficient of vibration data of k selected data, R k Represents the historical comprehensive risk factor.

[0060] Preferably: the generating of an early warning signal specifically includes:

[0061] If the comprehensive risk factor is greater than or equal to the preset threshold, a warning signal is generated; if not, a non-warning signal is generated.

[0062] Furthermore, an electromechanical equipment information integration management system based on the Internet of Things is proposed, including:

[0063] A data acquisition module, wherein the data acquisition module is used to collect operating status data of the electromechanical equipment in real time, including vibration data obtained by a vibration sensor and equipment surface image data obtained by a machine vision system;

[0064] An operating status identification module, which is used to analyze the fluctuation degree of the collected vibration data and calculate the abnormal fluctuation coefficient of the vibration data according to the fluctuation degree of the vibration data, so as to identify the vibration characteristics of the equipment and evaluate the operating status of the equipment;

[0065] A fault assessment module, which processes the device surface image data through a machine vision system, uses an image processing algorithm to detect cracks, wear and foreign matter intrusion on the device surface, extracts corresponding fault features, and generates a fault feature index based on the fault features for evaluating the device surface fault;

[0066] A risk assessment module, which is used to fuse and analyze vibration data and image data, including fusing and calculating the abnormal fluctuation coefficient of vibration data with the fault characteristic index to obtain a comprehensive risk coefficient for fault warning of electromechanical equipment and generate a warning signal;

[0067] An early warning module performs maintenance and shutdown processing on the equipment based on the early warning signal.

[0068] Beneficial effects of the present invention:

[0069] (1) The present invention combines the Internet of Things technology and advanced data analysis algorithms to collect vibration data and surface image data of electromechanical equipment in real time, and comprehensively monitors the health status of the equipment from multiple dimensions. Wavelet transform is used to efficiently process vibration data and extract abnormal fluctuation coefficients, which can accurately identify vibration anomalies that may occur during the operation of the equipment, thereby making a detailed assessment of the operating status of the equipment. At the same time, the image processing algorithm performs in-depth analysis on the surface of the equipment, extracts fault features such as cracks, wear, and foreign body intrusion, and comprehensively reflects the health status of the surface of the equipment by calculating the fault feature index. The fusion analysis of vibration data and image data can not only more accurately identify potential faults of the equipment, but also generate a comprehensive risk coefficient. This coefficient is compared with the set threshold to provide real-time fault warning, timely discover and predict the risk of equipment failure, and prevent irreversible damage to the equipment. The present invention improves the accuracy and reliability of fault detection through multi-source data fusion, and effectively reduces the common false alarm and missed alarm problems in traditional monitoring methods. Through timely warning, production interruption, equipment damage or safety accidents caused by failure to be discovered in time are avoided, thereby significantly improving the reliability of the equipment, reducing maintenance costs, and ensuring the continuity and stability of the production process.

[0070] (2) The invention integrates the Internet of Things technology and the intelligent data processing system, and uses the real-time collected equipment status data, including vibration signals and surface image data, to build an efficient remote monitoring and fault diagnosis platform. The equipment's operating data is transmitted to the cloud platform in real time via wireless communication. The system performs powerful data processing and analysis in the cloud, automatically identifies the equipment's operating status and potential faults, and generates corresponding fault characteristic indexes. This process not only realizes real-time fault detection and early warning, but also accurately judges the risk level of the equipment by comparing it with the preset risk factor threshold, and then automatically triggers the scheduled maintenance or shutdown processing. The intelligent management system significantly reduces the reliance on manual monitoring and judgment, improves the equipment's operating efficiency and fault response speed, and ensures the long-term stable operation of the equipment. On this basis, the system provides a scientific basis for the maintenance and management of the equipment, optimizes the maintenance cycle, avoids premature or late maintenance decisions, and thus reduces unnecessary maintenance costs. At the same time, because the system can accurately predict equipment failures and intervene in time, it greatly reduces production losses caused by equipment downtime and failures. By comprehensively improving the automation level of equipment management, the present invention lays a solid foundation for the intelligent operation and maintenance of industrial equipment and promotes the efficient, stable and sustainable development of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 It is a flowchart of the specific steps of the electromechanical equipment information integration management method based on the Internet of Things of the present invention;

[0072] Figure 2 It is a flow chart of the electromechanical equipment information integration management system based on the Internet of Things in the present invention. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0074] See also Figure 1 As shown, the present invention is a method for integrating and managing electromechanical equipment information based on the Internet of Things, comprising the following steps:

[0075] S1: Real-time collection of operating status data of electromechanical equipment, including vibration data obtained by vibration sensors and equipment surface image data obtained by machine vision systems;

[0076] S2: Analyze the fluctuation degree of the collected vibration data, and calculate the abnormal fluctuation coefficient of the vibration data according to the fluctuation degree of the vibration data, so as to identify the vibration characteristics of the equipment and evaluate the operating status of the equipment;

[0077] S3: Process the equipment surface image data through the machine vision system, use the image processing algorithm to detect cracks, wear and foreign matter intrusion on the equipment surface, extract the corresponding fault features, and generate a fault feature index based on the fault features to evaluate the surface fault of the equipment;

[0078] S4: Fusion analysis of vibration data and image data, including fusion calculation of abnormal fluctuation coefficient of vibration data and fault characteristic index, to obtain comprehensive risk coefficient, which is used for fault warning of electromechanical equipment and generation of warning signal;

[0079] S5: Perform maintenance and shutdown of equipment based on early warning signals.

[0080] In S1, the operating status data of the electromechanical equipment is collected in real time, including vibration data obtained by the vibration sensor and equipment surface image data obtained by the machine vision system, specifically including:

[0081] The vibration data is collected by a vibration sensor installed on the electromechanical equipment;

[0082] Vibration data is collected in time series through vibration sensors installed on electromechanical equipment and transmitted to the cloud platform in real time through wireless communication;

[0083] The system records the timestamp, sampling value and sensor identification of the vibration data to form a time series data set;

[0084] The image data is collected by a machine vision system (including a camera, an infrared camera, and a high-definition camera);

[0085] It should be noted that the machine vision system needs to perform high-resolution imaging of the surface of the equipment in order to detect cracks, wear, corrosion or foreign matter intrusion fault characteristics;

[0086] According to the time series, the image data of the equipment surface is collected in real time through the machine vision system;

[0087] The collected image data is transmitted to the cloud storage in real time via the network;

[0088] Each image is accompanied by metadata such as timestamp, camera number and device location to ensure data traceability;

[0089] An efficient data compression algorithm should be used when storing image data, and the high-quality data of the original image should be retained for subsequent image processing;

[0090] Image data is usually stored in distributed storage systems to ensure efficient management of large-scale image data.

[0091] In S2, the fluctuation degree of the collected vibration data is analyzed, and according to the fluctuation degree of the vibration data, the abnormal fluctuation coefficient of the vibration data is calculated to identify the vibration characteristics of the equipment and evaluate the operating status of the equipment, including:

[0092] Acquire a vibration data signal x(t) according to a time series, where t represents time and x(t) represents the amplitude value of the vibration signal at time t;

[0093] The wavelet basis function is selected as the transformation formula of the vibration data signal. The discrete wavelet transform of the vibration data signal x(t) is decomposed into approximate coefficients and detail coefficients of different frequency bands. The calculation expression is:

[0094]

[0095] Wherein, the wavelet basis function is Daubechies wavelet;

[0096] In the formula, a j represents the approximation coefficient, d j represents the detail coefficient, ψ aj (t) and ψ dj (t) are the wavelet functions of the corresponding scales, and j represents the number of layers of wavelet decomposition;

[0097] Calculate the volatility of each wavelet decomposition layer, and the calculation expression is:

[0098]

[0099] Where N j represents the total number of data points in the jth layer, i represents a data point, and d j (i) represents the detail coefficient of the i-th data point in the j-th layer, V j represents the volatility of the jth layer;

[0100] Calculate the standard deviation of the j-th layer vibration signal to represent the fluctuation amplitude of the vibration;

[0101] The standard deviation of each layer is calculated by ratio with the fluctuation degree to obtain the abnormal fluctuation coefficient of each layer. The fluctuation coefficients of all layers are summed up to obtain the abnormal fluctuation coefficient of vibration data.

[0102] It should be noted that the abnormal fluctuation coefficient of vibration data reflects the abnormal vibration situation of electromechanical equipment during operation, and the larger the value of the abnormal fluctuation coefficient of vibration data is, the higher the degree of abnormal vibration of the corresponding electromechanical equipment is.

[0103] Compare the abnormal fluctuation coefficient of vibration data of electromechanical equipment with a preset threshold value;

[0104] If the abnormal fluctuation coefficient of the vibration data of the electromechanical equipment is greater than or equal to the preset threshold, it means that the operation status of the corresponding electromechanical equipment is abnormal;

[0105] If the abnormal fluctuation coefficient of the vibration data of the electromechanical equipment is less than a preset threshold, it means that there is no abnormality in the operating state of the corresponding electromechanical equipment.

[0106] In S3, the machine vision system is used to process the image data of the equipment surface, and the image processing algorithm is used to detect cracks, wear and foreign matter intrusion on the equipment surface, and the corresponding fault features are extracted. According to the fault features, a fault feature index is generated to evaluate the surface faults of the equipment, including:

[0107] Preprocess the collected equipment surface image data and extract effective fault features, including:

[0108] Convert the original color image (RGB image) to a grayscale image, use a Gaussian filter to smooth the image, remove noise, avoid pseudo edges during edge detection, perform convolution on the grayscale image, and use the smoothed image for subsequent calculations;

[0109] Calculate the gradient amplitude of the image, the calculation expression is:

[0110]

[0111] In the formula, G x represents the gradient in the x direction, G y represents the gradient in the y direction, and G represents the gradient amplitude;

[0112] Calculate the gradient direction of the image, the calculation expression is:

[0113]

[0114] In the formula, θ represents the gradient direction;

[0115] For each pixel, according to the gradient direction, compare the amplitudes of the two adjacent pixels with the corresponding gradient direction. If the amplitude of the current pixel is not the largest in the neighborhood, set the current pixel to 0;

[0116] Double thresholding and edge connection were performed on each image;

[0117] Extract the length and width of the crack, calculate the length and width of the crack according to the edge pixel coordinates, calculate the crack characteristics, and the calculation expression is:

[0118]

[0119] In the formula, x start ,y start represents the crack starting point coordinates, x end ,y end represents the crack end point coordinate, L c Indicates crack characteristics;

[0120] The size of the wear area is calculated based on the area of ​​the edge closed area and recorded as the wear feature T w , the size of the wear area is calculated by multiplying the number of pixels in the area by the area of ​​a single pixel;

[0121] Discrete edge areas are detected, foreign objects are identified through shape complexity calculation, and the foreign object intrusion characteristics are obtained. The calculation expression is:

[0122]

[0123] Where P e represents the perimeter, the sum of the edge lengths, A e Represents the area of ​​the edge closed region, C e Indicates the characteristics of foreign body invasion;

[0124] The crack features, wear features and foreign body intrusion features are input into the feature matrix I = [L c ,T w ,C e ];

[0125] Standardize the features;

[0126] Calculate the convolution output features, the calculation expression is:

[0127]

[0128] In the formula, F ij represents the convolution output feature, i, j represents the position coordinates, I i+m-1,j+n-1 represents the position coordinates of the input feature matrix at (i+m-1,j+n-1), m, n represent the convolution kernel size, K represents the convolution kernel, the maximum convolution kernel size of M and N, and b represents the bias term;

[0129] Calculate the convolution output features of each convolution layer;

[0130] The maximum pooling is used to reduce the dimension of the convolution output features of each convolution layer. The calculation expression is:

[0131]

[0132] In the formula, l represents the convolutional layer, represents the convolution output feature after the pooling operation, represents the convolution output feature of convolution layer l, M ′ and N ′ is the size of the pooling window;

[0133] The convolution output features of all convolutional layers after the pooling operation are summed up to obtain the fault feature index, denoted as Z f ;

[0134] It should be noted that the fault characteristic index reflects the fault degree of the surface of the electromechanical equipment, and when the value of the fault characteristic index is larger, the corresponding fault degree of the surface of the electromechanical equipment is higher.

[0135] comparing a fault characteristic index of the surface of the electromechanical device with a preset threshold value;

[0136] If the fault characteristic index of the surface of the electromechanical equipment is greater than or equal to the preset threshold, it means that the corresponding electromechanical equipment surface fault degree is high;

[0137] If the fault characteristic index of the surface of the electromechanical equipment is less than a preset threshold, it means that the corresponding surface fault degree of the electromechanical equipment is low.

[0138] In S4, the vibration data and image data are fused and analyzed, including fusion calculation of the abnormal fluctuation coefficient of the vibration data and the fault characteristic index to obtain a comprehensive risk coefficient, which is used to provide fault warning for electromechanical equipment and generate a warning signal, including:

[0139] Obtain the abnormal fluctuation coefficient and fault characteristic index of vibration data of several identical electromechanical equipment in history, and the comprehensive risk coefficient of each electromechanical equipment in history as training data;

[0140] Obtain the abnormal fluctuation coefficient and fault characteristic index of vibration data of real-time electromechanical equipment as test data;

[0141] Calculate the Euclidean distance between the test data and the training data using the Euclidean calculation formula;

[0142] Sort the Euclidean distances of all electromechanical equipment in order of size, select the abnormal fluctuation coefficients of vibration data and fault characteristic indexes corresponding to the three smallest Euclidean distances, and record them as selected data;

[0143] According to the selected vibration data abnormal fluctuation coefficient and fault characteristic index, the comprehensive risk coefficient is calculated by weighted summation. The calculation expression is:

[0144]

[0145] In the formula, R new represents the comprehensive risk factor of real-time electromechanical equipment, k represents the selected data, K represents the total number of selected data, the value of K is 3, Zfk represents the fault characteristic index of the kth selected data, Z Tk represents the abnormal fluctuation coefficient of vibration data of k selected data, R k Represents the historical comprehensive risk factor;

[0146] Compare the comprehensive risk factor with the preset threshold;

[0147] If the comprehensive risk factor is greater than or equal to the preset threshold, it means that the risk level of the corresponding electromechanical equipment abnormality is high, and a warning signal is generated;

[0148] If the comprehensive risk factor is less than the preset threshold, it means that the risk level of the corresponding electromechanical equipment abnormality is low, and a non-warning signal is generated;

[0149] It should be noted that the comprehensive risk coefficient reflects the abnormal risk level of electromechanical equipment, and when the value of the comprehensive risk coefficient is larger, the corresponding electromechanical equipment abnormal risk level is higher, and the corresponding electromechanical equipment needs timely warning.

[0150] See also Figure 2 As shown in the figure, the electromechanical equipment information integration management system based on the Internet of Things includes:

[0151] A data acquisition module, wherein the data acquisition module is used to collect operating status data of the electromechanical equipment in real time, including vibration data obtained by a vibration sensor and equipment surface image data obtained by a machine vision system;

[0152] An operating status identification module, which is used to analyze the fluctuation degree of the collected vibration data and calculate the abnormal fluctuation coefficient of the vibration data according to the fluctuation degree of the vibration data, so as to identify the vibration characteristics of the equipment and evaluate the operating status of the equipment;

[0153] A fault assessment module, which processes the device surface image data through a machine vision system, uses an image processing algorithm to detect cracks, wear and foreign matter intrusion on the device surface, extracts corresponding fault features, and generates a fault feature index based on the fault features for evaluating the device surface fault;

[0154] A risk assessment module, which is used to fuse and analyze vibration data and image data, including fusing and calculating the abnormal fluctuation coefficient of vibration data with the fault characteristic index to obtain a comprehensive risk coefficient for fault warning of electromechanical equipment and generate a warning signal;

[0155] An early warning module performs maintenance and shutdown processing on the equipment based on the early warning signal.

[0156] The working principle of the present invention is as follows: by real-time acquisition and analysis of vibration data and equipment surface image data of electromechanical equipment, early warning of equipment failure is realized; vibration data of equipment is acquired by vibration sensor, and the fluctuation degree of vibration data is analyzed by wavelet transform, and abnormal fluctuation coefficient of vibration data is calculated to evaluate the vibration state of equipment; secondly, high-resolution image acquisition of equipment surface is performed by machine vision system, and fault characteristics such as cracks, wear and foreign body intrusion on the equipment surface are detected by image processing algorithm, and fault characteristic index is generated; then, abnormal fluctuation coefficient of vibration data is fused and calculated with fault characteristic index to obtain comprehensive risk coefficient as the basis of equipment failure early warning; finally, based on the size of comprehensive risk coefficient, the failure risk of equipment is judged, corresponding early warning signal is generated, and maintenance and shutdown processing of equipment are guided. This method effectively improves the accuracy of equipment fault detection and the timeliness of early warning by comprehensively analyzing vibration characteristics and surface fault characteristics, and can realize intelligent management and maintenance of electromechanical equipment.

[0157] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0158] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0159] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0160] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0161] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for integrating and managing electromechanical equipment information based on the Internet of Things, characterized in that: The following steps are involved: S1: Real-time collection of operating status data of electromechanical equipment, including vibration data obtained by vibration sensors and equipment surface image data obtained by machine vision systems; S2: Analyze the fluctuation degree of the collected vibration data, and calculate the abnormal fluctuation coefficient of the vibration data according to the fluctuation degree of the vibration data, so as to identify the vibration characteristics of the equipment and evaluate the operating status of the equipment; S3: Process the equipment surface image data through the machine vision system, use the image processing algorithm to detect cracks, wear and foreign matter intrusion on the equipment surface, extract the corresponding fault features, and generate a fault feature index based on the fault features to evaluate the surface fault of the equipment; S4: Fusion analysis of vibration data and image data, including fusion calculation of abnormal fluctuation coefficient of vibration data and fault characteristic index, to obtain comprehensive risk coefficient, which is used for fault warning of electromechanical equipment and generation of warning signal; S5: Perform maintenance and shutdown of equipment based on early warning signals.

2. The method for integrated management of electromechanical equipment information based on the Internet of Things according to claim 1, characterized in that: The analysis of the fluctuation degree of the collected vibration data and calculation of the abnormal fluctuation coefficient of the vibration data according to the fluctuation degree of the vibration data specifically includes: Acquire a vibration data signal x(t) according to a time series, where t represents time and x(t) represents the amplitude value of the vibration signal at time t; The wavelet basis function is selected as the transformation formula of the vibration data signal. The discrete wavelet transform of the vibration data signal x(t) is decomposed into approximate coefficients and detail coefficients of different frequency bands. The calculation expression is: Wherein, the wavelet basis function is Daubechies wavelet; In the formula, a j represents the approximation coefficient, d j represents the detail coefficient, and are the wavelet functions of the corresponding scales, and j represents the number of layers of wavelet decomposition; Calculate the volatility of each wavelet decomposition layer, and the calculation expression is: Where N j represents the total number of data points in the jth layer, i represents a data point, and d j (i) represents the detail coefficient of the i-th data point in the j-th layer, V j represents the volatility of the jth layer; Calculate the standard deviation of the j-th layer vibration signal to represent the fluctuation amplitude of the vibration; The standard deviation of each layer is calculated by ratio to the fluctuation degree to obtain the abnormal fluctuation coefficient of each layer. The fluctuation coefficients of all layers are summed up to obtain the abnormal fluctuation coefficient of vibration data.

3. The method for integrated management of electromechanical equipment information based on the Internet of Things according to claim 2, characterized in that: Describe and evaluate the operating status of the equipment, including: It is determined whether the abnormal fluctuation coefficient of the vibration data is greater than or equal to a preset threshold value. If so, the corresponding electromechanical equipment operating state is abnormal; if not, the corresponding electromechanical equipment operating state is not abnormal.

4. The method for integrated management of electromechanical equipment information based on the Internet of Things according to claim 3 is characterized in that: The device surface image data is processed by a machine vision system, and image processing algorithms are used to detect cracks, wear and foreign matter intrusion on the device surface, and to extract corresponding fault features, including: Preprocess the collected equipment surface image data and extract effective fault features, including: Convert the original color image to a grayscale image, use a Gaussian filter to smooth the image, remove noise, perform a convolution operation on the grayscale image, and use the smoothed image for subsequent calculations; Calculate the gradient amplitude of the image, the calculation expression is: In the formula, G x represents the gradient in the x direction, G y represents the gradient in the y direction, and G represents the gradient amplitude; Calculate the gradient direction of the image, the calculation expression is: In the formula, θ represents the gradient direction; Extract the length and width of the crack, calculate the length and width of the crack according to the edge pixel coordinates, calculate the crack characteristics, and the calculation expression is: In the formula, x start ,y start represents the crack starting point coordinates, x end ,y end represents the crack end point coordinate, L c Indicates crack characteristics; The size of the wear area is calculated based on the area of ​​the edge closed area and recorded as the wear feature T w , the size of the wear area is calculated by multiplying the number of pixels in the area by the area of ​​a single pixel; Discrete edge areas are detected, foreign objects are identified through shape complexity calculation, and the foreign object intrusion characteristics are obtained. The calculation expression is: Where P e represents the perimeter, the sum of the edge lengths, A e Represents the area of ​​the edge closed region, C e Indicates the characteristics of foreign body invasion.

5. The method for integrated management of electromechanical equipment information based on the Internet of Things according to claim 4 is characterized in that: The process of obtaining the fault characteristic index is as follows: The crack features, wear features and foreign body intrusion features are input into the feature matrix I = [L c ,T w ,C e ]; Standardize the features; Calculate the convolution output features, the calculation expression is: In the formula, F ij represents the convolution output feature, i, j represents the position coordinates, I i+m-1,j+n-1 Represents the position coordinates of the input feature matrix at (i+m-1,j+n-1), m, n represent the convolution kernel size, K represents the convolution kernel, the maximum convolution kernel size of M and N, and b represents the bias term; Calculate the convolution output features of each convolution layer; The maximum pooling is used to reduce the dimension of the convolution output features of each convolution layer. The calculation expression is: In the formula, l represents the convolutional layer, represents the convolution output feature after the pooling operation, represents the convolution output feature of convolution layer l, M ′ and N ′ is the size of the pooling window; The convolution output features of all convolutional layers after the pooling operation are summed up to obtain the fault feature index.

6. The method for integrated management of electromechanical equipment information based on the Internet of Things according to claim 5, characterized in that: The fusing and analyzing the vibration data and the image data includes fusing and calculating the abnormal fluctuation coefficient of the vibration data and the fault characteristic index to obtain a comprehensive risk coefficient, which specifically includes: Obtain the abnormal fluctuation coefficient and fault characteristic index of vibration data of several identical electromechanical equipment in history, and the comprehensive risk coefficient of each electromechanical equipment in history as training data; Obtain the abnormal fluctuation coefficient and fault characteristic index of vibration data of real-time electromechanical equipment as test data; Calculate the Euclidean distance between the test data and the training data using the Euclidean calculation formula; Sort the Euclidean distances of all electromechanical equipment in order of size, select the abnormal fluctuation coefficients of vibration data and fault characteristic indexes corresponding to the three smallest Euclidean distances, and record them as selected data; According to the selected vibration data abnormal fluctuation coefficient and fault characteristic index, the comprehensive risk coefficient is calculated by weighted summation. The calculation expression is: In the formula, R new represents the comprehensive risk factor of real-time electromechanical equipment, k represents the selected data, K represents the total number of selected data, the value of K is 3, Z fk represents the fault characteristic index of the kth selected data, Z Tk represents the abnormal fluctuation coefficient of vibration data of k selected data, R k Represents the historical comprehensive risk factor.

7. The method for integrated management of electromechanical equipment information based on the Internet of Things according to claim 1, characterized in that: The above-mentioned and generating early warning signals specifically include: If the comprehensive risk factor is greater than or equal to the preset threshold, a warning signal is generated; if not, a non-warning signal is generated.

8. The electromechanical equipment information integration management system based on the Internet of Things is characterized by: The method for integrated management of electromechanical equipment information based on the Internet of Things as claimed in any one of claims 1 to 7 comprises: A data acquisition module, wherein the data acquisition module is used to collect operating status data of the electromechanical equipment in real time, including vibration data obtained by a vibration sensor and equipment surface image data obtained by a machine vision system; An operating status identification module, which is used to analyze the fluctuation degree of the collected vibration data and calculate the abnormal fluctuation coefficient of the vibration data according to the fluctuation degree of the vibration data, so as to identify the vibration characteristics of the equipment and evaluate the operating status of the equipment; A fault assessment module, which processes the device surface image data through a machine vision system, uses an image processing algorithm to detect cracks, wear and foreign matter intrusion on the device surface, extracts corresponding fault features, and generates a fault feature index based on the fault features for evaluating the device surface fault; A risk assessment module, which is used to fuse and analyze vibration data and image data, including fusing and calculating the abnormal fluctuation coefficient of vibration data with the fault characteristic index to obtain a comprehensive risk coefficient for fault warning of electromechanical equipment and generate a warning signal; An early warning module performs maintenance and shutdown processing on the equipment based on the early warning signal.

Images