Intelligent detection method and device for operation state of equipment

Through intelligent detection methods, the problem of low accuracy in equipment operation status detection in hydraulic stations and lubrication stations is solved, and more accurate status monitoring and automated detection are achieved, and equipment maintenance efficiency is improved.

CN118999660APending Publication Date: 2024-11-22TANGSHAN GANGLU IRON & STEEL
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202410999586.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-24
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

In the field of hydraulic stations and lubrication stations, traditional equipment operating status detection technology has the problem of low accuracy of monitoring data in certain specific situations, and has failed to effectively consider the impact of environmental instability on temperature and vibration data.

Method used

Using an intelligent detection method for the operation status of the device, by obtaining monitoring data from multiple sensors of the target device, if the data does not contain temperature or vibration data, a first feature vector is generated and a pre-trained intelligent detection model is input; if the temperature or Vibration data, generates a second feature vector for data change parameters, and uses intelligent detection models to process it more cautiously to improve detection accuracy.

Benefits of technology

It realizes accurate detection of the operating status of the equipment, improves monitoring accuracy, can promptly detect potential abnormal status, supports equipment maintenance and management, realizes automation and intelligence of the monitoring process, and improves work efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118999660A_ABST
    Figure CN118999660A_ABST
Patent Text Reader

Abstract

The invention provides an equipment operation state intelligent detection method and device, and belongs to the technical field of equipment detection, and the method comprises the steps: obtaining a plurality of pieces of monitoring data of target equipment from a plurality of sensors; and if the monitoring data does not contain the temperature data or the vibration data, generating a first feature vector corresponding to the target equipment based on various monitoring data in the first time period, and inputting the first feature vector into a pre-trained intelligent detection model to obtain an operation state monitoring result. And if the monitoring data contains temperature data or vibration data, data extraction is carried out on change parameters of each type of monitoring data in a second time period, a second feature vector is generated based on extracted data corresponding to each type of monitoring data, the second feature vector is input into the intelligent detection model, and an operation state monitoring result is obtained. The time period end point of the second time period and the first time period is the current moment, and the duration of the second time period is greater than that of the first time period. The accuracy of equipment detection can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure belongs to the technical field of equipment detection, and more specifically, to an intelligent detection method and device for equipment operating status. Background Art

[0002] Modern industrial production processes are increasingly dependent on efficient and stable mechanical equipment. As the power transmission and lubrication guarantee system of many key equipment, the normal operation of hydraulic stations and lubrication stations is crucial to the continuity of the entire production process and the stability of product quality. Equipment operation status detection is an important means to ensure the normal operation of equipment, improve production efficiency, prevent failures and ensure safety. Equipment operation status detection can evaluate and judge the current working condition of the equipment based on monitoring information such as various parameters, performance indicators, working environment, etc. This may include the use of sensors, data acquisition systems, remote monitoring technology, etc. to obtain relevant information about the equipment.

[0003] In the field of hydraulic stations and lubrication stations, due to the instability of the environment, some monitoring data often have low accuracy in certain specific situations. Current equipment operation status detection often does not take this issue into account, resulting in low accuracy of equipment operation status detection results in certain specific situations. Summary of the invention

[0004] The purpose of the present disclosure is to provide a method and apparatus for intelligently detecting the operation status of an equipment, so as to solve the problem that the detection results of the operation status of an equipment under certain specific circumstances are low in accuracy in conventional equipment detection technology.

[0005] A first aspect of an embodiment of the present disclosure provides a method for intelligently detecting a device operating status, comprising: Acquire multiple monitoring data of the target device from multiple sensors corresponding to the target device.

[0006] If the monitoring data does not include temperature data or vibration data, a first feature vector corresponding to the target device is generated based on multiple monitoring data within the first time period, and the first feature vector is input into a pre-trained intelligent detection model to obtain an operating status monitoring result of the target device.

[0007] If the monitoring data contains temperature data or vibration data, data extraction is performed on the change parameters of each monitoring data within the second time period, and a second feature vector is generated based on the extracted data corresponding to each monitoring data. The second feature vector is input into the intelligent detection model to obtain the operating status monitoring result of the target device.

[0008] The end points of the second time period and the first time period are the current time, and the duration of the second time period is greater than the duration of the first time period.

[0009] A second aspect of the embodiments of the present disclosure provides an intelligent device for detecting the operation status of a device, including: The data acquisition module is used to acquire multiple monitoring data of the target device from multiple sensors corresponding to the target device.

[0010] The first calculation module is used to generate a first feature vector corresponding to the target device based on multiple monitoring data within a first time period if the monitoring data does not contain temperature data or vibration data, and input the first feature vector into a pre-trained intelligent detection model to obtain an operating status monitoring result of the target device.

[0011] The second calculation module is used to extract data on the change parameters of each monitoring data within the second time period if the monitoring data includes temperature data or vibration data, generate a second feature vector based on the extracted data corresponding to each monitoring data, input the second feature vector into the intelligent detection model, and obtain the operating status monitoring result of the target device.

[0012] The end points of the second time period and the first time period are the current time, and the duration of the second time period is greater than the duration of the first time period.

[0013] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned method for intelligently detecting the operating status of the device when executing the computer program.

[0014] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for intelligently detecting the operating status of a device are implemented.

[0015] The beneficial effect of the intelligent detection method and device for the equipment operating status provided by the embodiments of the present disclosure is that by adopting the above method, accurate detection of the operating status of the target equipment can be achieved. Taking into account that in some situations, the environment has a greater impact on temperature and vibration data, the method can automatically perform different processing for different equipment detection scenarios. When the monitored data does not contain temperature data or vibration data, a first feature vector can be generated using a variety of monitoring data within a first time period, and analyzed through a pre-trained intelligent detection model to derive the operating status of the target equipment. This method can reflect the overall operating status of the equipment to a certain extent.

[0016] However, when the monitoring data contains temperature data or vibration data, a more cautious and meticulous processing method is chosen. Data extraction is performed on the changing parameters of each monitoring data in the second period, and a second feature vector is generated based on these data. Since the second period is longer, the dynamic changes of the data can be captured more comprehensively, and then more accurate operating status monitoring results can be obtained through the intelligent detection model. This method not only improves the accuracy of monitoring, but also can timely detect potential abnormal conditions of equipment, providing strong support for equipment maintenance and management. At the same time, through the use of intelligent detection models, the automation and intelligence of the monitoring process can be realized, which improves work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, 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 disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic diagram of a process flow of a method for intelligently detecting the operation status of a device provided in an embodiment of the present disclosure; Figure 2 A structural block diagram of an intelligent device for detecting the operation status of equipment provided by an embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0020] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0021] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for intelligently detecting the operating status of a device provided in an embodiment of the present disclosure. The method may include S101 to S103.

[0022] S101: Acquire multiple monitoring data of a target device from multiple sensors corresponding to the target device.

[0023] In this embodiment, the target device may include a device to be detected, the multiple sensors may include at least one of a pressure sensor, a flow sensor, a temperature sensor, a liquid level sensor, a vibration sensor, an oil cleanliness sensor, a speed sensor, an acoustic sensor and a torque sensor, and the multiple monitoring data may include the pressure of the oil pipeline, the flow of hydraulic oil or lubricating oil, the oil temperature or the ambient temperature, the vibration data of different key parts of the equipment, if rotating parts are involved, such as the speed of the oil pump, the stroke of the oil cylinder or the displacement of other parts, the torque size on some parts with torque transmission, and at least one of the sound data generated when the equipment is running.

[0024] For example, in the hydraulic station of a hot rolling mill, the pressure sensor can monitor the pressure data of the oil pipeline. If it shows that the pressure of the oil pipeline is too low, it may mean that there is a leak. For example, the flow sensor detects a decrease in the flow of hydraulic oil, indicating that the oil pump may be faulty. For example, the temperature sensor detects that the oil temperature is too high, which may be due to poor heat dissipation or excessive friction of components. The vibration sensor detects abnormal vibration in key parts, which may be due to loose components. In the lubrication station, the liquid level sensor detects that the oil level is too low, and lubricating oil may need to be added. The torque sensor detects abnormal torque, which may be due to excessive load. The acoustic sensor captures abnormal noise, indicating that the equipment may have hidden dangers of failure. These data can be used to accurately judge the operating status of the equipment.

[0025] S102: If the monitoring data does not include temperature data or vibration data, a first feature vector corresponding to the target device is generated based on multiple monitoring data within the first time period, and the first feature vector is input into a pre-trained intelligent detection model to obtain an operating status monitoring result of the target device.

[0026] In this embodiment, multiple monitoring data of the target device can be obtained through multiple sensors. If these monitoring data do not contain temperature data or vibration data, other multiple monitoring data within the first time period will be selected. These data are processed and analyzed, key features that can reflect the operating status of the device are extracted, and a first feature vector corresponding to the target device is generated. This first feature vector contains feature information of multiple monitoring data and can be regarded as a digital representation of the operating status of the device during this period. This first feature vector is input into a pre-trained intelligent detection model. The intelligent detection model may include an algorithm model obtained by training with a large amount of data and algorithms. It has learned the relationship pattern between different feature vectors and the operating status of the device. When a new first feature vector is input, the intelligent detection model can analyze and judge the feature vector based on the knowledge and pattern it has learned, thereby obtaining the operating status monitoring result of the target device.

[0027] For example, in the hydraulic station of a hot rolling mill, it is assumed that the initially acquired monitoring data does not contain temperature and vibration data, but contains data such as the pressure of the oil pipeline, the flow and liquid level of the hydraulic oil. Then select the first time period, such as these data in the past 30 minutes. For pressure data, calculate its average value, maximum value, minimum value, etc. For flow data, analyze its changing trend and fluctuation. For liquid level data, determine its stability. Use these processed data as feature values ​​to generate the first feature vector corresponding to the hydraulic station. Input the first feature vector into the pre-trained intelligent detection model.

[0028] If the output result of the intelligent detection model shows that the hydraulic station is in good operating condition, it means that the pressure is stable, the flow is normal, and the liquid level remains in a reasonable range within these 30 minutes. If the intelligent detection model determines that there is a problem with the operating status, it may be that the pressure has fluctuated greatly, the flow has decreased significantly, or the liquid level has decreased abnormally, etc., prompting the staff to check and maintain in time to avoid affecting the normal production of the hot rolling mill. If the average pressure is normal but fluctuates greatly, the flow is slightly reduced, the oil pump speed is normal, and the cylinder stroke is also as expected, the intelligent detection model determines that the operating status of the hydraulic station is slightly abnormal, and there may be some potential problems, such as a slight leak in the hydraulic oil or the adjustment of a valve is not accurate enough. After receiving this monitoring result, the staff can further check the hydraulic station, find out the problem and perform maintenance or adjustments in time to ensure that the production of the hot rolling mill can be carried out stably and efficiently.

[0029] S103: If the monitoring data includes temperature data or vibration data, data extraction is performed on the change parameters of each monitoring data within the second time period, a second feature vector is generated based on the extracted data corresponding to each monitoring data, and the second feature vector is input into the intelligent detection model to obtain the operating status monitoring result of the target device.

[0030] The end points of the second time period and the first time period are the current time, and the duration of the second time period is greater than the duration of the first time period.

[0031] In this embodiment, it is determined whether the acquired monitoring data contains temperature data or vibration data. If contained, then the change parameters of each type of monitoring data in the second time period are extracted. The end point of the second time period is the current moment, and its duration is greater than the duration of the first time period, so that the data changes in a longer time range can be obtained. A second feature vector is generated based on the extracted data corresponding to each type of monitoring data. This second feature vector can reflect the change characteristics of data such as temperature or vibration in the second time period. The second feature vector is input into the pre-trained intelligent detection model. The intelligent detection model has learned the relationship pattern between different feature vectors and the operating status of the equipment through a large amount of data. When the newly generated second feature vector is input, the intelligent detection model can analyze and judge the vector according to its internal pattern and knowledge, so as to obtain the operating status monitoring result of the target device.

[0032] For example, in the lubrication station of a hot rolling mill, it is assumed that the monitoring data includes temperature data. The second time period is selected as the past hour, and the system will extract the temperature data change parameters within this hour, such as the maximum, minimum, and average values ​​of the temperature, as well as the temperature change trend. The corresponding second eigenvector is generated by these temperature data change parameters and input into the intelligent detection model. If the model output result shows that the operating status is normal, it may mean that in the past hour, the temperature of the lubrication station is within a reasonable range and relatively stable, and there is no abnormal temperature fluctuation or too high or too low.

[0033] If the intelligent detection model determines that there is a problem with the operating status, such as an unusually steep temperature trend or a maximum value outside the normal range, this may indicate that there are some potential problems with the lubrication station. Perhaps the heat dissipation of the lubrication system has failed, causing the temperature to rise. Or a component is excessively rubbed and generates too much heat. After receiving this monitoring result, the staff can promptly inspect and repair the lubrication station to avoid lubrication problems affecting the normal production of the hot rolling mill. Vibration data can also be analyzed and monitored in a similar way.

[0034] It can be concluded from the above that by adopting the above method, accurate detection of the operating status of the target device can be achieved. Taking into account that in some situations, the environment has a greater impact on temperature and vibration data, this method can automatically perform different processing for different equipment detection scenarios. When the monitored data does not contain temperature data or vibration data, a first feature vector can be generated using a variety of monitoring data within the first time period, and analyzed through a pre-trained intelligent detection model to derive the operating status of the target device. This method can reflect the overall operating status of the device to a certain extent.

[0035] However, when the monitoring data contains temperature data or vibration data, a more cautious and meticulous processing method is chosen. Data extraction is performed on the changing parameters of each monitoring data in the second period, and a second feature vector is generated based on these data. Since the second period is longer, the dynamic changes of the data can be captured more comprehensively, and then more accurate operating status monitoring results can be obtained through the intelligent detection model. This method not only improves the accuracy of monitoring, but also can timely detect potential abnormal conditions of equipment, providing strong support for equipment maintenance and management. At the same time, through the use of intelligent detection models, the automation and intelligence of the monitoring process can be realized, which improves work efficiency.

[0036] In one embodiment of the present disclosure, generating a first feature vector corresponding to a target device based on a plurality of monitoring data in a first time period includes: Feature extraction is performed on each type of monitoring data to obtain a feature vector corresponding to each type of monitoring data.

[0037] Perform vector concatenation on the feature vectors corresponding to each monitoring data to obtain a first feature vector corresponding to the target device.

[0038] In this embodiment, for the multiple monitoring data obtained by the target device within the first time period, feature extraction is performed on each type of monitoring data. This process can use specific algorithms and methods according to the characteristics and properties of the data to extract information that can reflect the essence and key features of the monitoring data, thereby obtaining the feature vectors corresponding to each type of monitoring data. The feature vectors corresponding to each type of monitoring data are concatenated in a certain order. Vector concatenation (FeatureConcatenation) is simply to append feature vectors together to create a longer feature vector. Through this concatenation operation, the originally scattered feature vectors for a single monitoring data are combined into a whole to form the first feature vector corresponding to the target device.

[0039] For example, in the lubrication station of the hot rolling mill, the first time period is set to the past half hour. The monitoring data obtained include oil pump pressure, lubricating oil flow, oil tank level, etc. For the oil pump pressure data, its average value, variance, etc. are extracted as features to form a corresponding feature vector. For the lubricating oil flow data, its maximum value, minimum value and other features are extracted to form a feature vector. For the oil tank level data, features such as the difference between the current liquid level and the set liquid level are extracted to form a feature vector. Finally, these three feature vectors are spliced ​​together in sequence to obtain the first feature vector of the lubrication station. By inputting this vector into the subsequent detection model, it is possible to comprehensively evaluate the operating status of the lubrication station within this half hour, such as judging whether there are problems such as unstable oil pump pressure, abnormal lubricating oil flow or low oil tank level.

[0040] This embodiment can efficiently and accurately generate a first feature vector reflecting the operating status of the target device for various monitoring data in the first period of time. This feature vector not only contains key information of various monitoring data, but also integrates the features of single data into a whole through vector splicing, providing strong data support for subsequent fault detection, performance evaluation, etc.

[0041] In one embodiment of the present disclosure, corresponding to certain monitoring data, feature extraction is performed on the monitoring data to obtain a feature vector corresponding to the monitoring data, including: N feature extraction methods are selected from a plurality of feature extraction methods based on the data type of the monitoring data.

[0042] Among them, N is a preset value, and various feature extraction methods include: statistical feature extraction, frequency domain feature extraction, time domain feature extraction, morphological feature extraction, wavelet transform feature extraction, and model-based feature extraction.

[0043] Based on the selected N feature extraction methods, feature extraction is performed on the monitoring data, and feature vectors corresponding to the N feature extraction methods are connected to obtain a feature vector corresponding to the monitoring data.

[0044] In this embodiment, the data type of a certain monitoring data to be processed is determined. According to a preset value N, N appropriate methods are selected from a variety of feature extraction methods. These methods cover different angles and methods, such as statistical feature extraction focusing on the central trend and discreteness of the data, frequency domain feature extraction analyzing the characteristics of the data in the frequency domain, and time domain feature extraction focusing on the changes in data over time. The monitoring data is processed using the selected N feature extraction methods. Each method extracts specific features to form its own feature vector. By connecting these N feature vectors in sequence, a complete feature vector corresponding to the monitoring data can be obtained.

[0045] For example, in the hydraulic station of a hot rolling mill, take pressure monitoring data as an example. According to the data type, three feature extraction methods are preset, such as statistical feature extraction (calculating the mean and variance of the pressure), frequency domain feature extraction (obtaining the main frequency components of the pressure signal) and time domain feature extraction (analyzing the rise and fall time of the pressure). Three feature vectors are obtained by extracting features in these three ways, and then they are connected. The feature vector obtained in this way comprehensively reflects the characteristics of the pressure data in different aspects. By subsequently inputting it into the intelligent detection model, the operating status of the hydraulic station can be evaluated more comprehensively and accurately, such as judging whether there are abnormal pressure fluctuations, untimely pressure response, and other problems, providing a basis for maintenance and optimization.

[0046] This embodiment combines multiple feature extraction methods, flexibly selects and combines feature vectors for different monitoring data types, and effectively captures comprehensive information of the data. Taking the pressure monitoring data of the hot rolling mill as an example, through multi-dimensional analysis such as statistics, frequency domain, and time domain, the feature vector is made more comprehensive, providing an accurate basis for intelligent detection, thereby improving the evaluation accuracy and reliability of the monitoring system.

[0047] In one embodiment of the present disclosure, data extraction is performed for the change parameters of each monitoring data in the second time period, including: For certain monitoring data, the monitoring data in the second time period is analyzed based on a preset sliding window and a preset sliding step length. The window length of the sliding window is the time length corresponding to the first time period.

[0048] During the sliding process of the sliding window, the change parameter corresponding to the monitoring data in the sliding window is calculated. The change parameter is the average value of the absolute value of the change rate corresponding to the monitoring data.

[0049] Extract the monitoring data within the sliding window when the variation parameter is the highest.

[0050] In this embodiment, a preset sliding window and sliding step length are set for a certain target monitoring data, and the length of the sliding window is the same as the duration of the first period. In the second period, the sliding window is gradually slid according to the preset sliding step length. During the sliding process, the change rate corresponding to the target monitoring data in the sliding window is calculated, and the average value of its absolute value is calculated as the change parameter. This process is continued, and the change parameter corresponding to each sliding window is recorded. Find the moment when the change parameter is the highest, and extract the monitoring data in the sliding window at this time.

[0051] For example, in the hydraulic station of a hot rolling mill, take the pressure monitoring data of the hydraulic oil as an example. Assume that the first period is 10 minutes, set the sliding window to 10 minutes, and the sliding step is 1 minute. In the second period, such as 1 hour, the sliding window slides from the starting position in steps of 1 minute. Calculate the average value of the absolute value of the rate of change of the pressure data in each sliding window as the change parameter. It may be found that the change parameter is the highest at a certain moment, indicating that the pressure fluctuation is the most violent at this time. Extract the pressure data in the sliding window at this moment, and then deeply analyze whether there is any abnormality in the hydraulic system during this period, such as a sudden failure of a valve, unstable operation of the oil pump, etc., so as to take timely measures for maintenance and adjustment to ensure the normal operation of the hydraulic station.

[0052] This embodiment accurately extracts the period in which the monitoring data changes most dramatically within the second period by setting the sliding window and step size. This targeted data extraction method helps to quickly locate potential problems, such as failures or instability of the hydraulic system, so that maintenance measures can be taken earlier to ensure the stable operation of the production line and reduce production risks.

[0053] In one embodiment of the present disclosure, the intelligent detection model calculates the failure probability corresponding to the target device based on the first formula to achieve status monitoring of the target device.

[0054] The first formula is:

[0055] in, Indicates the failure probability corresponding to the target device. Indicates the usage time of the target device. Indicates the ambient temperature. Indicates the ambient humidity. Indicates the dust concentration in the environment. Indicates the target device's operating parameters. Indicates the monitoring data corresponding to the target device. and represents the weight coefficient of the corresponding variable, and n represents the number of operating parameters.

[0056] In this embodiment, the use time of the target device reflects the impact of wear and aging caused by long-term operation of the device on the probability of failure. Generally, the longer the use time, the higher the probability of failure. Considering the impact of external environmental conditions on device reliability, ambient temperature, ambient humidity, and ambient dust concentration are introduced. For example, an environment with high temperature, high humidity, or high dust concentration may accelerate the damage of the device and increase the possibility of failure. It can represent various operating parameters of the target equipment, which can include pressure, temperature, vibration, flow rate, speed and other indicators that directly reflect the working status of the equipment. Each operating parameter has its corresponding weight coefficient, which reflects the relative importance of the parameter in evaluating the probability of failure.

[0057] By multiplying these variables by the corresponding weight coefficients and performing comprehensive calculations, a numerical value is obtained, namely the failure probability corresponding to the target device. This probability value comprehensively considers the device's own usage, operating parameters, and environmental conditions, and can more comprehensively and accurately reflect the possibility of equipment failure, providing an important basis for equipment maintenance and management.

[0058] This embodiment uses the target device's usage time, ambient temperature and humidity, dust concentration, and multiple operating parameters, combined with weight coefficients, to accurately calculate the probability of failure, thereby achieving real-time monitoring of the target device's status. This comprehensive evaluation method improves the accuracy and efficiency of fault prediction, helps to take preventive measures in advance, and reduces the risk of equipment failure.

[0059] In one embodiment of the present disclosure, the device operation status intelligent detection method further includes: If the failure probability is greater than the first threshold, a failure cause analysis result is generated based on a plurality of monitoring data of the target device and the corresponding failure probability.

[0060] In this embodiment, multiple monitoring data of the target device are obtained and the failure probability is calculated using these data. When the failure probability is greater than a preset first threshold, the multiple monitoring data obtained can be further analyzed. Through comprehensive evaluation and correlation analysis of various data, key factors and abnormal data that may lead to increased failure probability are found. Based on these analysis results, detailed failure cause analysis results are generated.

[0061] For example, in the lubrication station of the hot rolling mill, monitoring data such as lubricating oil temperature, pressure, flow, and oil cleanliness are obtained, and the failure probability of the lubrication station is calculated. Assume that the first threshold is 20%, and the currently calculated failure probability is 25%. The monitoring data is then analyzed, and abnormal conditions such as excessive temperature, unstable pressure, reduced flow, and decreased oil cleanliness are determined based on multiple preset thresholds, and the results of the failure cause analysis are given. For example, excessive temperature is due to a cooling system failure, unstable pressure is due to wear of oil pump components, reduced flow is due to partial blockage of the oil circuit, and decreased oil cleanliness is due to the need to replace the filter device. The failure cause analysis results can provide a clear direction for subsequent repairs and maintenance, enabling maintenance personnel to quickly and accurately solve problems with the lubrication station and ensure the normal production of the hot rolling mill.

[0062] In one embodiment of the present disclosure, the device operation status intelligent detection method further includes: Based on multiple monitoring data of the target device and the failure probability corresponding to the target device, an alarm message is generated.

[0063] In this embodiment, after the detection of the operating status of the target device is completed and its failure probability is calculated, the multiple monitoring data obtained are combined with the obtained failure probability. According to the preset rules and thresholds, if the failure probability exceeds a certain safety limit, an alarm message is generated. The generation of the alarm message can inform relevant personnel of the possible failure risk of the equipment so that they can take corresponding measures for maintenance or repair to prevent greater losses caused by equipment failure.

[0064] For example, in the lubrication station of a hot rolling mill, monitoring data such as oil temperature, vibration, oil pressure, oil level, and oil pump speed are obtained through multiple sensors, and the failure probability of the lubrication station is calculated. If the oil temperature is too high, the oil pressure is abnormal, and the failure probability reaches 30% (the preset alarm threshold is 25%), an alarm message is generated immediately. The alarm message may clearly indicate that the oil temperature is beyond the normal range and the oil pressure is unstable, and remind the staff to check the cooling system, oil pump, and oil circuit for blockage and other problems as soon as possible. In this way, the staff can respond quickly and take measures to avoid more serious failures in the lubrication station and ensure the smooth production of the hot rolling mill.

[0065] Corresponding to the device operation status intelligent detection method of the above embodiment, Figure 2 This is a block diagram of a device operating status intelligent detection apparatus provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 , the equipment operation status intelligent detection device 20 comprises: The data acquisition module 21 is used to acquire a plurality of monitoring data of the target device from a plurality of sensors corresponding to the target device.

[0066] The first calculation module 22 is used to generate a first feature vector corresponding to the target device based on multiple monitoring data within a first time period if the monitoring data does not contain temperature data or vibration data, and input the first feature vector into a pre-trained intelligent detection model to obtain an operating status monitoring result of the target device.

[0067] The second calculation module 23 is used to extract data on the change parameters of each monitoring data within the second time period if the monitoring data includes temperature data or vibration data, generate a second feature vector based on the extracted data corresponding to each monitoring data, input the second feature vector into the intelligent detection model, and obtain the operating status monitoring result of the target device.

[0068] The end points of the second time period and the first time period are the current time, and the duration of the second time period is greater than the duration of the first time period.

[0069] In one embodiment of the present disclosure, the first calculation module 22 includes: The first calculation unit is used to extract features from each monitoring data to obtain a feature vector corresponding to each monitoring data.

[0070] Perform vector concatenation on the feature vectors corresponding to each monitoring data to obtain a first feature vector corresponding to the target device.

[0071] In an embodiment of the present disclosure, corresponding to certain monitoring data, the first computing unit is specifically configured to select N feature extraction methods from a plurality of feature extraction methods based on the data type of the monitoring data.

[0072] Among them, N is a preset value, and various feature extraction methods include: statistical feature extraction, frequency domain feature extraction, time domain feature extraction, morphological feature extraction, wavelet transform feature extraction, and model-based feature extraction.

[0073] Based on the selected N feature extraction methods, feature extraction is performed on the monitoring data, and feature vectors corresponding to the N feature extraction methods are connected to obtain a feature vector corresponding to the monitoring data.

[0074] In one embodiment of the present disclosure, the second calculation module 23 is specifically used to analyze the monitoring data in the second time period based on a preset sliding window and a preset sliding step length for certain monitoring data. The window length of the sliding window is the duration corresponding to the first time period.

[0075] During the sliding process of the sliding window, the change parameter corresponding to the monitoring data in the sliding window is calculated. The change parameter is the average value of the absolute value of the change rate corresponding to the monitoring data.

[0076] Extract the monitoring data within the sliding window when the variation parameter is the highest.

[0077] In one embodiment of the present disclosure, the first calculation module 22 further includes: The second calculation unit is used for the intelligent detection model to calculate the failure probability corresponding to the target device based on the first formula to realize the status monitoring of the target device.

[0078] The first formula is:

[0079] in, Indicates the failure probability corresponding to the target device. Indicates the usage time of the target device. Indicates the ambient temperature. Indicates the ambient humidity. Indicates the dust concentration in the environment. Indicates the target device's operating parameters. Indicates the monitoring data corresponding to the target device. and represents the weight coefficient of the corresponding variable, and n represents the number of operating parameters.

[0080] In one embodiment of the present disclosure, the second calculation unit is specifically configured to generate a fault cause analysis result based on multiple monitoring data of the target device and the fault probability corresponding to the target device if the fault probability is greater than the first threshold.

[0081] In an embodiment of the present disclosure, the second calculation unit is further configured to generate alarm information based on a plurality of monitoring data of the target device and a failure probability corresponding to the target device.

[0082] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above-mentioned device embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0083] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0084] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0085] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0086] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the intelligent detection method for the device operating status provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device 300 described in the embodiments of the present disclosure, which will not be repeated here.

[0087] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0088] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0089] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software 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 this disclosure.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0091] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0092] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0093] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0094] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for intelligently detecting the operation status of equipment, characterized in that: include: Acquire multiple monitoring data of the target device from multiple sensors corresponding to the target device; If the monitoring data does not include temperature data or vibration data, a first feature vector corresponding to the target device is generated based on the multiple monitoring data in the first time period, and the first feature vector is input into a pre-trained intelligent detection model to obtain a monitoring result of the operating status of the target device; If the monitoring data includes temperature data or vibration data, data extraction is performed for the change parameters of each monitoring data within the second time period, a second feature vector is generated based on the extracted data corresponding to each monitoring data, and the second feature vector is input into the intelligent detection model to obtain the operating status monitoring result of the target device; The end points of the second time period and the first time period are the current time, and the duration of the second time period is greater than the duration of the first time period.

2. The intelligent detection method for equipment operation status according to claim 1, characterized in that: The generating a first feature vector corresponding to the target device based on the multiple monitoring data in the first time period includes: Extract features from each monitoring data to obtain a feature vector corresponding to each monitoring data; Vector concatenation is performed on the feature vectors corresponding to each type of monitoring data to obtain a first feature vector corresponding to the target device.

3. The intelligent detection method for equipment operation status according to claim 2, characterized in that: Corresponding to a certain monitoring data, feature extraction is performed on the monitoring data to obtain the feature vector corresponding to the monitoring data, including: Selecting N feature extraction methods from a plurality of feature extraction methods based on the data type of the monitoring data; Among them, N is a preset value, and multiple feature extraction methods include: statistical feature extraction, frequency domain feature extraction, time domain feature extraction, morphological feature extraction, wavelet transform feature extraction, and model-based feature extraction; Based on the selected N feature extraction methods, feature extraction is performed on the monitoring data, and feature vectors corresponding to the N feature extraction methods are connected to obtain a feature vector corresponding to the monitoring data.

4. The intelligent detection method for equipment operation status according to claim 1, characterized in that: The extracting data from the change parameters of each monitoring data in the second time period includes: For certain monitoring data, the monitoring data in the second time period is analyzed based on a preset sliding window and a preset sliding step; the window length of the sliding window is the duration corresponding to the first time period; During the sliding process of the sliding window, a change parameter corresponding to the monitoring data in the sliding window is calculated; the change parameter is an average value of the absolute value of the change rate corresponding to the monitoring data; The monitoring data within the sliding window when the variation parameter is the highest is extracted.

5. The intelligent detection method for equipment operation status according to claim 1, characterized in that: The intelligent detection model calculates the failure probability corresponding to the target device based on the first formula to achieve status monitoring of the target device; The first formula is: in, Indicates the failure probability corresponding to the target device; Indicates the usage time of the target device; Indicates the ambient temperature; Indicates ambient humidity; Indicates the dust concentration in the environment; Indicates the target device's operating parameters; Indicates the monitoring data corresponding to the target device; and represents the weight coefficient of the corresponding variable, and n represents the number of operating parameters.

6. The intelligent detection method for equipment operation status according to claim 5, characterized in that: Also includes: If the failure probability is greater than a first threshold, a failure cause analysis result is generated based on a plurality of monitoring data of the target device and the failure probability corresponding to the target device.

7. The intelligent detection method for equipment operation status according to claim 5, characterized in that: Also includes: Based on the multiple monitoring data of the target device and the failure probability corresponding to the target device, alarm information is generated.

8. An intelligent device for detecting the operation status of equipment, characterized in that: include: A data acquisition module, used to acquire a plurality of monitoring data of the target device from a plurality of sensors corresponding to the target device; A first calculation module is used for generating a first feature vector corresponding to the target device based on multiple monitoring data within a first time period if the monitoring data does not include temperature data or vibration data, and inputting the first feature vector into a pre-trained intelligent detection model to obtain a running status monitoring result of the target device; A second calculation module is used for, if the monitoring data includes temperature data or vibration data, extracting data for a change parameter of each monitoring data within a second period, generating a second feature vector based on the extracted data corresponding to each monitoring data, inputting the second feature vector into the intelligent detection model, and obtaining an operating status monitoring result of the target device; The end points of the second time period and the first time period are the current time, and the duration of the second time period is greater than the duration of the first time period.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Cited By

  • Plastic packaging barrel content state real-time monitoring method and system integrating multiple sensors

    CN120890502A

  • A method and system for real-time monitoring of the state of the contents of a plastic packaging drum integrated with multiple sensors

    CN120890502B