Sensor-based electromechanical equipment installation detection method and system

Abstract

The invention provides an electromechanical equipment installation detection method and system based on a sensor. A vibration sensor is used for collecting vibration data of an electromechanical equipment bearing in the installation stage; performing difference envelope extraction on the vibration data to obtain a difference envelope sequence when the electromechanical equipment bearing vibrates, determining a vibration abrupt change factor of the electromechanical equipment bearing according to the difference envelope sequence, and performing anomaly detection based on the vibration abrupt change factor to obtain a vibration anomaly degree of the electromechanical equipment bearing; axial images of the electromechanical equipment bearing are collected in real time, track trend characteristics of the electromechanical equipment bearing during vibration are extracted in a concentrated mode from the collected axial images, and the axial extrusion degree of the electromechanical equipment bearing in the installation stage is determined through the track trend characteristics; and performing abnormal warning on the installation of the bearing of the electromechanical equipment based on the vibration abnormal degree and the axial extrusion degree. According to the scheme, the abnormal characteristics of the electromechanical equipment can be extracted from the data acquired by the sensor, so that the early warning accuracy of the detection system is improved.

Description

Technical Field

[0001] The present application relates to the technical field of electromechanical equipment installation detection, and more specifically, to a sensor-based electromechanical equipment installation detection method and system. Background Art

[0002] With the development of industrial automation and intelligent manufacturing, the installation and inspection of electromechanical equipment has become an important part of ensuring the long-term and stable operation of equipment. Sensor-based electromechanical equipment installation inspection technology uses high-precision inspection equipment such as laser displacement sensors, vibration sensors, and industrial cameras to monitor and analyze parameters such as equipment installation accuracy and vibration characteristics in real time to ensure that the equipment meets the design requirements during the installation phase and reduce potential failures during operation. This sensor-based detection method has the advantages of high precision, non-contact, and real-time monitoring, which can effectively improve the installation quality and reduce maintenance costs and sudden failure risks during equipment operation.

[0003] However, in the existing technology, the data collected by sensors often have the characteristics of high dimension and high frequency, and need to be effectively analyzed with the help of advanced signal processing technology, data analysis algorithms and machine learning methods. In addition, during the installation process, the sensor may be interfered by the outside world (such as electromagnetic interference, mechanical noise, etc.), resulting in a large amount of noise in the measurement data. In addition, due to the environmental complexity during the installation of electromechanical equipment, how to establish reasonable thresholds and alarm mechanisms is also a major challenge in data analysis. Therefore, how to extract the abnormal characteristics of electromechanical equipment from the data collected by the sensor to improve the early warning accuracy of the detection system is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a sensor-based electromechanical equipment installation detection method and system, which can extract abnormal characteristics of the electromechanical equipment from the data collected by the sensor to improve the early warning accuracy of the detection system.

[0005] In a first aspect, the present application provides a sensor-based electromechanical equipment installation detection method, comprising the following steps: Use vibration sensors to collect vibration data of electromechanical equipment bearings during the installation phase; Performing differential envelope extraction on the vibration data to obtain a differential envelope sequence when the electromechanical equipment bearing vibrates, determining a vibration mutation factor of the electromechanical equipment bearing according to the differential envelope sequence, and performing anomaly detection based on the vibration mutation factor to obtain a vibration anomaly degree of the electromechanical equipment bearing; Acquire the axial image of the electromechanical equipment bearing in real time, extract the trajectory trend characteristics of the electromechanical equipment bearing when vibrating from the acquired axial image set, and determine the axial extrusion degree of the electromechanical equipment bearing during the installation stage through the trajectory trend characteristics; Based on the vibration abnormality and the axial extrusion degree, an abnormal warning is issued for the installation of the electromechanical equipment bearing.

[0006] Preferably, performing difference envelope extraction on the vibration data to obtain a difference envelope sequence when the bearing of the electromechanical equipment vibrates specifically includes: Constructing a vibration difference sequence when the bearing of the electromechanical equipment vibrates by using the vibration data; Dynamically intercepting the vibration difference sequence to obtain a vibration interception sequence; The vibration interception sequence is subjected to a Hippert transformation to obtain a difference envelope sequence when the bearing of the electromechanical equipment vibrates.

[0007] Preferably, determining the vibration mutation factor of the electromechanical equipment bearing according to the difference envelope sequence specifically includes: Determining the vibration mutation degree of the electromechanical equipment bearing through the difference envelope sequence; Determining the impact vibration intensity of the electromechanical equipment bearing by using the difference envelope sequence; A vibration mutation factor of the electromechanical equipment bearing is determined based on the vibration mutation degree and the impact vibration intensity.

[0008] Preferably, performing anomaly detection based on the vibration mutation factor is to input the vibration mutation factor into a pre-trained deep learning-based anomaly detection model for anomaly detection.

[0009] Preferably, the axial image of the bearing of the electromechanical equipment is collected in real time by a visual sensor.

[0010] Preferably, extracting the trajectory trend characteristics of the electromechanical equipment bearing vibration from the collected axial image set specifically includes: For each axial image in the acquired axial image set, determining the axial optical path length of the axial image; Determine the axial illumination intensity of the axial image according to the axial optical path, and then obtain the axial illumination intensity of each axial image; Determine the illumination difference corresponding to each axial image through the corresponding axial illumination intensity; Constructing the axial differential trajectory of the electromechanical equipment bearing during vibration through all illumination differences; Feature extraction is performed on the axial differential trajectory to obtain trajectory trend characteristics of the electromechanical equipment bearing during vibration.

[0011] Preferably, the abnormal warning of the installation of the bearing of the electromechanical equipment based on the vibration abnormality and the axial extrusion degree specifically includes: Get the given abnormality degree interval and squeeze degree interval; comparing the vibration abnormality with the abnormality range, and comparing the axial extrusion with the extrusion range; Determine and generate installation abnormality information of the electromechanical equipment bearing according to the comprehensive comparison result; An abnormality alarm is issued based on the abnormal installation information.

[0012] In a second aspect, the present application provides a sensor-based electromechanical equipment installation detection system for executing a sensor-based electromechanical equipment installation detection method, wherein the sensor-based electromechanical equipment installation detection system includes a bearing installation abnormality detection unit, and the bearing installation abnormality detection unit includes: A data acquisition module, used to collect vibration data of the bearings of electromechanical equipment during the installation phase using a vibration sensor; A vibration detection module, used to perform differential envelope extraction on the vibration data to obtain a differential envelope sequence when the electromechanical equipment bearing vibrates, determine the vibration mutation factor of the electromechanical equipment bearing according to the differential envelope sequence, perform anomaly detection based on the vibration mutation factor, and obtain the vibration anomaly degree of the electromechanical equipment bearing; An extrusion determination module is used to collect axial images of the electromechanical equipment bearing in real time, extract trajectory trend characteristics of the electromechanical equipment bearing when vibrating from the collected axial images, and determine the axial extrusion degree of the electromechanical equipment bearing during the installation stage according to the trajectory trend characteristics; The installation warning module is used to issue an abnormal warning on the installation of the bearing of the electromechanical equipment based on the vibration abnormality and the axial extrusion degree.

[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned sensor-based electromechanical equipment installation detection method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned sensor-based electromechanical equipment installation detection method when executed.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: The present application provides a sensor-based electromechanical equipment installation detection method and system, which uses a vibration sensor to collect vibration data of the electromechanical equipment bearing during the installation stage; performs differential envelope extraction on the vibration data to obtain a differential envelope sequence when the electromechanical equipment bearing vibrates, determines the vibration mutation factor of the electromechanical equipment bearing according to the differential envelope sequence, performs anomaly detection based on the vibration mutation factor, and obtains the vibration anomaly degree of the electromechanical equipment bearing; collects the axial image of the electromechanical equipment bearing in real time, extracts the trajectory trend characteristics of the electromechanical equipment bearing when vibrating from the collected axial image set, and determines the axial extrusion degree of the electromechanical equipment bearing during the installation stage according to the trajectory trend characteristics; and issues an abnormal warning for the installation of the electromechanical equipment bearing based on the vibration anomaly degree and the axial extrusion degree.

[0016] It can be seen that in this application, first, the vibration data is subjected to differential envelope extraction to obtain a differential envelope sequence, and the vibration mutation factor is calculated based on this, which can effectively capture the slight abnormal changes of the bearings of the electromechanical equipment. The differential envelope sequence can highlight the mutation characteristics in the vibration signal and help extract more representative abnormal characteristics from the original signal. The vibration mutation factor combines the vibration mutation degree and the impact vibration intensity, which can comprehensively evaluate whether the equipment is in an abnormal state, thereby greatly improving the accuracy of the system's early warning of equipment failures; then, the axial image of the bearing of the electromechanical equipment is collected in real time and the trajectory trend characteristics during vibration are extracted, which helps to accurately monitor the working status of the bearing during the installation stage; finally, based on the vibration abnormality and axial extrusion degree, the installation of the bearing of the electromechanical equipment is abnormally warned, which can achieve accurate evaluation of the equipment installation quality and improve the accuracy and timeliness of fault warning.

[0017] In summary, the technical solution adopted in the present application can extract abnormal characteristics of electromechanical equipment from the data collected by the sensor to improve the early warning accuracy of the detection system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 is an exemplary flow chart of a sensor-based electromechanical equipment installation detection method according to some embodiments of the present application; Figure 2 is an exemplary flow chart of determining a difference envelope sequence when a bearing of an electromechanical device vibrates according to some embodiments of the present application; Figure 3 is an exemplary flow chart for extracting trajectory trend characteristics of mechanical and electrical equipment bearing vibration according to some embodiments of the present application; Figure 4 is a schematic diagram of exemplary hardware and / or software of a bearing installation abnormality detection unit according to some embodiments of the present application; Figure 5 It is a structural schematic diagram of a computer device for implementing a sensor-based electromechanical equipment installation detection method according to some embodiments of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] The embodiment of the present application provides a sensor-based electromechanical equipment installation detection method and system, the core of which is to use a vibration sensor to collect vibration data of the electromechanical equipment bearing during the installation stage; perform differential envelope extraction on the vibration data to obtain a differential envelope sequence when the electromechanical equipment bearing vibrates, determine the vibration mutation factor of the electromechanical equipment bearing based on the differential envelope sequence, perform abnormality detection based on the vibration mutation factor, and obtain the vibration abnormality of the electromechanical equipment bearing; collect the axial image of the electromechanical equipment bearing in real time, extract the trajectory trend characteristics of the electromechanical equipment bearing when vibrating from the collected axial image set, and determine the axial extrusion degree of the electromechanical equipment bearing during the installation stage through the trajectory trend characteristics; and issue an abnormal warning for the installation of the electromechanical equipment bearing based on the vibration abnormality and the axial extrusion degree. The above scheme can be used to extract abnormal characteristics of electromechanical equipment from the data collected by the sensor to improve the early warning accuracy of the detection system.

[0022] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a sensor-based electromechanical equipment installation detection method according to some embodiments of the present application. The sensor-based electromechanical equipment installation detection method 100 mainly includes the following steps: In step 101, vibration data of a bearing of an electromechanical device during installation is collected using a vibration sensor.

[0023] In specific implementation, the vibration sensor can be usually installed in the key parts of the bearing, such as the outer ring, inner ring or mounting seat of the bearing, to ensure that the vibration sensor can effectively sense the vibration signal caused by installation problems (such as looseness, uneven preload force, etc.), so that the vibration sensor can be used to collect the vibration data of the electromechanical equipment bearing during the installation stage. The vibration data is a time series data, which represents the vibration acceleration value of the electromechanical equipment bearing at different time points. The vibration data collected by the vibration sensor is sent to the detection system through a wireless or wired transmission system for real-time data processing and analysis.

[0024] In step 102, a difference envelope extraction is performed on the vibration data to obtain a difference envelope sequence when the electromechanical equipment bearing vibrates, a vibration mutation factor of the electromechanical equipment bearing is determined according to the difference envelope sequence, and anomaly detection is performed based on the vibration mutation factor to obtain the vibration anomaly degree of the electromechanical equipment bearing.

[0025] Preferably, in some embodiments, reference Figure 2 As shown in FIG. 1 , this figure is an exemplary flow chart of determining the difference envelope sequence of the electromechanical equipment bearing when vibrating in some embodiments of the present application. In this embodiment, the difference envelope extraction is performed on the vibration data to obtain the difference envelope sequence of the electromechanical equipment bearing when vibrating, which can be achieved by the following steps: In step 1021, a vibration difference sequence when the bearing of the electromechanical equipment vibrates is constructed using the vibration data; In step 1022, the vibration difference sequence is dynamically intercepted to obtain a vibration interception sequence; In step 1023, a Hippert transform is performed on the vibration interception sequence to obtain a difference envelope sequence when the bearing of the electromechanical equipment vibrates.

[0026] In specific implementation, first, a vibration difference sequence of the bearing of the electromechanical equipment when it vibrates can be constructed through vibration data, that is, the difference between adjacent data points in the vibration data can be calculated, so that a sequence composed of all differences can be used as a vibration difference sequence of the bearing of the electromechanical equipment when it vibrates. The vibration difference sequence can highlight the mutations and changes in the signal, help to identify abnormal fluctuations later, and capture the mutation features in the vibration signal, such as looseness or other failures of the equipment; then, the vibration difference sequence can be dynamically intercepted, that is, the maximum value in the vibration difference sequence and the time index corresponding to the maximum value are obtained by traversing, so as to intercept a segment in the vibration difference sequence with the time index corresponding to the maximum value as the center. The interception length can be set according to historical experience, so that the intercepted fragments are used as vibration interception sequences. The key features and event uniqueness are retained in the vibration interception sequence, thereby improving the quality of the data. Finally, the vibration interception sequence can be subjected to Hilbert transform. By performing Hilbert transform on the vibration interception sequence, the envelope of the signal can be obtained, and the absolute value of the envelope can be taken to obtain the difference envelope sequence of the bearing vibration of the electromechanical equipment, so that the low-frequency fluctuations, mutations and abnormal patterns in the signal can be observed more intuitively. The difference envelope sequence can provide detailed information about the vibration trend of the equipment, especially when the electromechanical equipment fails or is abnormal, the shape of the envelope signal will show obvious changes.

[0027] In some embodiments, the vibration mutation factor of the electromechanical equipment bearing may be determined according to the difference envelope sequence in the following manner, namely: Determining the vibration mutation degree of the electromechanical equipment bearing through the difference envelope sequence; Determining the impact vibration intensity of the electromechanical equipment bearing by using the difference envelope sequence; A vibration mutation factor of the electromechanical equipment bearing is determined based on the vibration mutation degree and the impact vibration intensity.

[0028] In specific implementation, first, the vibration mutation degree of the electromechanical equipment bearing can be determined by the difference envelope sequence, wherein the vibration mutation degree represents the degree of vibration mutation during the installation process of the electromechanical equipment bearing. In actual implementation, the vibration mutation degree can be determined by the following formula: in, represents the vibration mutation degree, T represents the time length of the difference envelope sequence, represents the difference envelope sequence; then, the impact vibration intensity of the electromechanical equipment bearing can be determined by the difference envelope sequence, wherein the impact vibration intensity represents the intensity of the impact signal during the installation process of the electromechanical equipment bearing. In actual implementation, the impact vibration intensity can be determined by the following formula: in, represents the shock vibration intensity, T represents the time length of the difference envelope sequence, represents the difference envelope sequence, Represents the difference envelope sequence The maximum value among them; finally, the vibration mutation factor of the electromechanical equipment bearing can be determined based on the vibration mutation degree and the impact vibration intensity, wherein the vibration mutation factor is a comprehensive indicator for measuring the mutation characteristics in the vibration signal when the electromechanical equipment bearing is installed. The vibration mutation degree and the impact vibration intensity can be weighted and summed, and the result is used as the vibration mutation factor of the electromechanical equipment bearing, wherein the weights corresponding to the vibration mutation degree and the impact vibration intensity can be set according to historical experiments and data analysis, which will not be repeated here.

[0029] In some embodiments, performing anomaly detection based on the vibration mutation factor is to input the vibration mutation factor into a pre-trained deep learning-based anomaly detection model for anomaly detection, thereby obtaining the vibration abnormality of the electromechanical equipment bearing.

[0030] In the specific implementation, first, historical abnormal vibration data can be obtained. The historical abnormal vibration data is usually obtained through long-term operation records of electromechanical equipment or historical fault data of electromechanical equipment; then, an appropriate deep learning model is selected. The deep learning-based anomaly detection model selected in this application is a recurrent neural network (RNN). In actual implementation, other deep learning-based anomaly detection models can also be selected, which are not limited here, so that the deep learning-based anomaly detection model is trained using the historical abnormal vibration data to obtain a trained anomaly detection model; finally, the vibration mutation factor can be input into the pre-trained deep learning-based anomaly detection model for anomaly detection. The deep learning model calculates the vibration anomaly degree of the electromechanical equipment bearing based on the input vibration mutation factor, and the vibration anomaly degree indicates the abnormal degree of the vibration of the electromechanical equipment bearing; by combining deep learning technology, the accuracy and robustness of anomaly detection are improved.

[0031] It should be noted that performing differential envelope extraction on vibration data to obtain differential envelope sequences and calculating vibration mutation factors based on this can effectively capture small abnormal changes in the bearings of electromechanical equipment. The differential envelope sequence can highlight the mutation characteristics in the vibration signal and help extract more representative abnormal features from the original signal. The vibration mutation factor combines the vibration mutation degree and the impact vibration intensity, and can comprehensively evaluate whether the equipment is in an abnormal state, thereby greatly improving the accuracy of the system's early warning of equipment failures.

[0032] In step 103, the axial image of the electromechanical equipment bearing is collected in real time, and the trajectory trend characteristics of the electromechanical equipment bearing during vibration are extracted from the collected axial image set, and the axial extrusion degree of the electromechanical equipment bearing during the installation stage is determined based on the trajectory trend characteristics.

[0033] In specific implementation, the axial image of the electromechanical equipment bearing can be collected in real time by a visual sensor; by collecting the axial image of the electromechanical equipment bearing in real time by a high-precision visual sensor (such as an industrial camera), the relative position of each component of the bearing during the installation process, the movement trajectory, and the stress distribution inside the equipment and other information can be intuitively displayed. In order to ensure the accuracy of the data, the acquisition process needs to maintain the real-time and high resolution of the image acquisition.

[0034] Preferably, in some embodiments, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart of extracting the trajectory trend characteristics of the electromechanical equipment bearing vibration in some embodiments of the present application. In this embodiment, the trajectory trend characteristics of the electromechanical equipment bearing vibration can be extracted from the collected axial image set by the following steps: In step 1031, for each axial image in the acquired axial image set, the axial optical path of the axial image is determined; In step 1032, the axial illumination intensity of the axial image is determined according to the axial optical path, thereby obtaining the axial illumination intensity of each axial image; In step 1033, the illumination difference corresponding to each axial image is determined by the corresponding axial illumination intensity; In step 1034, an axial differential trajectory of the electromechanical device bearing during vibration is constructed using all illumination differences; In step 1035, feature extraction is performed on the axial differential trajectory to obtain trajectory trend features of the electromechanical equipment bearing during vibration.

[0035] In specific implementation, first, for each axial image in the collected axial image set, the axial optical path of the axial image can be determined, wherein the axial optical path refers to the distance from the visual sensor to the bearing surface of the electromechanical equipment. By calculating the optical path in each axial image, the image deformation information at different positions during the vibration of the electromechanical equipment bearing can be obtained; then, the axial illumination intensity of the axial image can be determined according to the axial optical path, that is, the light intensity of the surrounding environment is obtained, and the ratio of the light intensity to the axial optical path is used as the axial illumination intensity of the axial image. The axial illumination intensity of each axial image can be obtained in the above manner; the illumination difference corresponding to each axial image can be determined by the corresponding axial illumination intensity, wherein the illumination difference indicates the degree of illumination difference of the bearing surface of the electromechanical equipment at different time points, and is usually an indicator of surface changes caused by equipment vibration and axial compression. The illumination intensity of each axial image can be compared with the previous axial image to calculate the pixel difference between the axial images, thereby obtaining the illumination difference corresponding to each axial image.

[0036] In addition, in the specific implementation, first, the axial differential trajectory of the electromechanical equipment bearing during vibration can be constructed through all the illumination differences, that is, all the illumination differences are connected to obtain a curve, which can be used as the axial differential trajectory of the electromechanical equipment bearing during vibration. The axial differential trajectory is a dynamic record of the axial position change of the electromechanical equipment bearing during the vibration process, which can effectively reflect the vibration state of the electromechanical equipment bearing; then, the axial differential trajectory can be feature extracted, that is, all illumination differences greater than the judgment threshold in the axial differential trajectory can be screened out, and the judgment threshold of the axial differential trajectory can be set by experts in related fields according to the changing law characteristics of the axial differential trajectory in historical experimental data and the purpose of analysis, so as to determine the slope of each illumination difference greater than the judgment threshold at the corresponding point in the axial differential trajectory, and each slope can be used as the value of the trajectory trend feature of the electromechanical equipment bearing during vibration. The trajectory trend feature of the electromechanical equipment bearing during vibration can be obtained in the above manner, wherein the trajectory trend feature represents the degree of change of the corresponding point in the axial differential trajectory.

[0037] In some embodiments, the axial extrusion degree of the electromechanical equipment bearing during the installation stage can be determined by using the trajectory trend characteristics in the following manner, namely: Determine the reference trend value according to the axial differential trajectory of the bearing of the electromechanical equipment during vibration; The axial extrusion degree of the electromechanical equipment bearing during the installation phase is determined according to the reference trend value and the trajectory trend feature.

[0038] In specific implementation, first, a reference trend value can be determined based on the axial differential trajectory of the electromechanical equipment bearing when it vibrates, wherein the reference trend value represents the overall change degree of the illumination difference in the axial differential trajectory, and the average slope of the axial differential trajectory can be used as the reference trend value; then, the axial extrusion degree of the electromechanical equipment bearing during the installation stage can be determined based on the reference trend value and the trajectory trend characteristics, wherein the axial extrusion degree represents the degree of axial extrusion of the bearing when the electromechanical equipment bearing vibrates, and the greater the axial extrusion degree, the higher the degree of axial deviation of the bearing when the electromechanical equipment bearing vibrates. In actual implementation, all values ​​of the trajectory trend characteristics can be subtracted from the trajectory reference trend value, and then the standard deviation of all the obtained differences can be calculated, so that the final result can be used as the axial extrusion degree of the electromechanical equipment bearing during the installation stage.

[0039] It should be noted that real-time collection of axial images of electromechanical equipment bearings and extraction of trajectory trend characteristics during vibration can help accurately monitor the working status of bearings during the installation phase. By analyzing the trajectory trend characteristics, the axial extrusion degree of the bearing can be effectively identified, and potential problems caused by improper installation can be discovered.

[0040] In step 104, an abnormality warning is issued for the installation of the electromechanical equipment bearing based on the vibration abnormality and the axial extrusion degree.

[0041] In some embodiments, the abnormal warning of the installation of the electromechanical equipment bearing based on the vibration abnormality and the axial extrusion degree can be specifically carried out in the following manner, namely: Get the given abnormality degree interval and squeeze degree interval; comparing the vibration abnormality with the abnormality range, and comparing the axial extrusion with the extrusion range; Determine and generate installation abnormality information of the electromechanical equipment bearing according to the comprehensive comparison result; An abnormality alarm is issued based on the abnormal installation information.

[0042] In specific implementation, first, a given abnormality interval and extrusion interval can be obtained, and the system will set the abnormality interval and extrusion interval according to the historical data, standard working parameters and engineering experience of the electromechanical equipment; then, the vibration abnormality can be compared with the abnormality interval, and the axial extrusion can be compared with the extrusion interval; further, the installation abnormality information of the electromechanical equipment bearing can be generated based on the comprehensive comparison result. For example, if the vibration abnormality exceeds the abnormality interval, but the axial extrusion is within the extrusion interval, the installation abnormality information generated by the system includes that the abnormal cause of the electromechanical equipment bearing comes from the vibration, and the bearing or related components may need to be inspected, adjusted or replaced; if both the vibration abnormality and the axial extrusion exceed the corresponding abnormality interval and extrusion interval, the installation abnormality information generated by the system includes that there are multiple abnormal problems in the electromechanical equipment bearing, and a comprehensive inspection is required, including installation accuracy, equipment balance, load distribution, etc.; finally, an abnormal alarm can be made based on the installation abnormality information, that is, based on the generated installation abnormality information, the system will display the installation abnormality information through a display or control panel, mark the abnormal components or parts, prompt the staff to check, and issue a warning sound to remind the staff to immediately pay attention to the installation status of the electromechanical equipment bearing.

[0043] It should be noted that abnormal warnings for the installation of electromechanical equipment bearings based on vibration anomalies and axial extrusion can accurately evaluate the quality of equipment installation and improve the accuracy and timeliness of fault warnings. Combined with vibration anomalies and axial extrusion, the system can detect potential installation defects before the equipment is officially put into operation, avoiding early damage, excessive wear or safety hazards caused by improper installation.

[0044] It can be seen that in this application, first, the vibration data is subjected to differential envelope extraction to obtain a differential envelope sequence, and the vibration mutation factor is calculated based on this, which can effectively capture the slight abnormal changes of the bearings of the electromechanical equipment. The differential envelope sequence can highlight the mutation characteristics in the vibration signal and help extract more representative abnormal characteristics from the original signal. The vibration mutation factor combines the vibration mutation degree and the impact vibration intensity, which can comprehensively evaluate whether the equipment is in an abnormal state, thereby greatly improving the accuracy of the system's early warning of equipment failures; then, the axial image of the bearing of the electromechanical equipment is collected in real time and the trajectory trend characteristics during vibration are extracted, which helps to accurately monitor the working status of the bearing during the installation stage; finally, based on the vibration abnormality and axial extrusion degree, the installation of the bearing of the electromechanical equipment is abnormally warned, which can achieve accurate evaluation of the equipment installation quality and improve the accuracy and timeliness of fault warning.

[0045] In summary, the technical solution adopted in the present application can extract abnormal characteristics of electromechanical equipment from the data collected by the sensor to improve the early warning accuracy of the detection system.

[0046] In addition, in another aspect of the present application, in some embodiments, the present application provides a sensor-based electromechanical equipment installation detection system, the sensor-based electromechanical equipment installation detection system includes a bearing installation abnormality detection unit, reference Figure 4 , which is a schematic diagram of exemplary hardware and / or software of a bearing installation abnormality detection unit according to some embodiments of the present application, the bearing installation abnormality detection unit 400 includes: a data acquisition module 401, a vibration detection module 402, an extrusion determination module 403 and an installation warning module 404, which are respectively described as follows: Data acquisition module 401, in this application, the data acquisition module 401 is mainly used to collect vibration data of the bearing of the electromechanical equipment during the installation stage using a vibration sensor; The vibration detection module 402 in the present application is mainly used to perform differential envelope extraction on the vibration data to obtain a differential envelope sequence when the electromechanical equipment bearing vibrates, determine the vibration mutation factor of the electromechanical equipment bearing according to the differential envelope sequence, perform abnormality detection based on the vibration mutation factor, and obtain the vibration abnormality degree of the electromechanical equipment bearing; An extrusion determination module 403, in the present application, is mainly used to collect axial images of the electromechanical equipment bearing in real time, extract trajectory trend characteristics of the electromechanical equipment bearing during vibration from the collected axial images, and determine the axial extrusion degree of the electromechanical equipment bearing during the installation stage through the trajectory trend characteristics; The warning module 404 is installed. In the present application, the warning module 404 is installed mainly for providing an abnormal warning for the installation of the bearing of the electromechanical equipment based on the abnormal vibration degree and the axial extrusion degree.

[0047] The above describes in detail the examples of the sensor-based electromechanical equipment installation detection method and system provided by the embodiments of the present application. It can be understood that the corresponding device includes a hardware structure and / or software module corresponding to each function in order to realize the above functions. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present application.

[0048] In some embodiments, the present application also provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned sensor-based electromechanical equipment installation detection method.

[0049] In some embodiments, reference Figure 5 , the dotted line in the figure indicates that the unit or the module is optional, and the figure is a structural schematic diagram of a computer device according to a sensor-based electromechanical device installation detection method provided in an embodiment of the present application. The sensor-based electromechanical device installation detection method described in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device 500 can be a terminal device, a server or a chip.

[0050] The processor 501 may be a general-purpose processor or a special-purpose processor. For example, the processor 501 may be a central processing unit (CPU), which may be used to control the computer device 500, execute software programs, and process data of the software programs. The computer device 500 may also include a communication unit 505 to implement signal input (reception) and output (transmission).

[0051] For example, the computer device 500 may be a chip, the communication unit 505 may be an input and / or output circuit of the chip, or the communication unit 505 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other device.

[0052] For another example, the computer device 500 may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0053] The computer device 500 may include one or more memories 502, on which a program 504 is stored. The program 504 can be executed by the processor 501 to generate instructions 503, so that the processor 501 performs the method described in the above method embodiment according to the instructions 503. Optionally, data (such as a target audit model) can also be stored in the memory 502. Optionally, the processor 501 can also read the data stored in the memory 502, and the data can be stored at the same storage address as the program 504, or the data can be stored at a different storage address from the program 504.

[0054] The processor 501 and the memory 502 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0055] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 501. The processor 501 can be a central processing unit, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, such as discrete gates, transistor logic devices or discrete hardware components.

[0056] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0057] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned sensor-based electromechanical equipment installation detection method when executed.

[0058] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A sensor-based electromechanical equipment installation detection method, characterized in that: The steps include: Use vibration sensors to collect vibration data of electromechanical equipment bearings during the installation phase; Performing differential envelope extraction on the vibration data to obtain a differential envelope sequence when the electromechanical equipment bearing vibrates, determining a vibration mutation factor of the electromechanical equipment bearing according to the differential envelope sequence, and performing anomaly detection based on the vibration mutation factor to obtain a vibration anomaly degree of the electromechanical equipment bearing; Acquire the axial image of the electromechanical equipment bearing in real time, extract the trajectory trend characteristics of the electromechanical equipment bearing when vibrating from the acquired axial image set, and determine the axial extrusion degree of the electromechanical equipment bearing during the installation stage through the trajectory trend characteristics; Based on the vibration abnormality and the axial extrusion degree, an abnormal warning is issued for the installation of the electromechanical equipment bearing.

2. A sensor-based electromechanical equipment installation detection method as claimed in claim 1, characterized in that: Performing differential envelope extraction on the vibration data to obtain a differential envelope sequence when the bearing of the electromechanical equipment vibrates specifically includes: Constructing a vibration difference sequence when the bearing of the electromechanical equipment vibrates by using the vibration data; Dynamically intercepting the vibration difference sequence to obtain a vibration interception sequence; The vibration interception sequence is subjected to a Hippert transformation to obtain a difference envelope sequence when the bearing of the electromechanical equipment vibrates.

3. A sensor-based electromechanical equipment installation detection method as claimed in claim 1, characterized in that: Determining the vibration mutation factor of the electromechanical equipment bearing according to the difference envelope sequence specifically includes: Determining the vibration mutation degree of the electromechanical equipment bearing through the difference envelope sequence; Determining the impact vibration intensity of the electromechanical equipment bearing by using the difference envelope sequence; A vibration mutation factor of the electromechanical equipment bearing is determined based on the vibration mutation degree and the impact vibration intensity.

4. A sensor-based electromechanical equipment installation detection method as claimed in claim 1, characterized in that: Performing anomaly detection based on the vibration mutation factor is to input the vibration mutation factor into a pre-trained deep learning-based anomaly detection model for anomaly detection.

5. A sensor-based electromechanical equipment installation detection method as claimed in claim 1, characterized in that: The axial image of the bearing of the electromechanical equipment is collected in real time by a visual sensor.

6. A sensor-based electromechanical equipment installation detection method as claimed in claim 1, characterized in that: Extracting the trajectory trend characteristics of the bearing vibration of the electromechanical equipment from the collected axial image set specifically includes: For each axial image in the acquired axial image set, determining the axial optical path length of the axial image; Determine the axial illumination intensity of the axial image according to the axial optical path, and then obtain the axial illumination intensity of each axial image; Determine the illumination difference corresponding to each axial image through the corresponding axial illumination intensity; Constructing the axial differential trajectory of the electromechanical equipment bearing during vibration through all illumination differences; Feature extraction is performed on the axial differential trajectory to obtain trajectory trend characteristics of the electromechanical equipment bearing during vibration.

7. A sensor-based electromechanical equipment installation detection method as claimed in claim 1, characterized in that: The abnormal warning for the installation of the bearing of the electromechanical equipment based on the abnormal vibration degree and the axial extrusion degree specifically includes: Get the given abnormality degree interval and squeeze degree interval; comparing the vibration abnormality with the abnormality range, and comparing the axial extrusion with the extrusion range; Determine and generate installation abnormality information of the bearing of the electromechanical equipment according to the comprehensive comparison result; An abnormality alarm is issued based on the abnormal installation information.

8. A sensor-based electromechanical equipment installation detection system, used to execute a sensor-based electromechanical equipment installation detection method according to any one of claims 1 to 7, the sensor-based electromechanical equipment installation detection system comprising a bearing installation abnormality detection unit, characterized in that: The bearing installation abnormality detection unit comprises: A data acquisition module is used to collect vibration data of the bearings of electromechanical equipment during the installation phase using a vibration sensor; A vibration detection module, used to perform differential envelope extraction on the vibration data to obtain a differential envelope sequence when the electromechanical equipment bearing vibrates, determine the vibration mutation factor of the electromechanical equipment bearing according to the differential envelope sequence, perform anomaly detection based on the vibration mutation factor, and obtain the vibration anomaly degree of the electromechanical equipment bearing; An extrusion determination module is used to collect axial images of the electromechanical equipment bearing in real time, extract trajectory trend characteristics of the electromechanical equipment bearing when vibrating from the collected axial images, and determine the axial extrusion degree of the electromechanical equipment bearing during the installation stage according to the trajectory trend characteristics; The installation warning module is used to issue an abnormal warning on the installation of the bearing of the electromechanical equipment based on the vibration abnormality and the axial extrusion degree.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the sensor-based electromechanical equipment installation detection method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the sensor-based electromechanical equipment installation detection method according to any one of claims 1 to 7.

Images