Mechanical equipment maintenance monitoring method and system based on big data

Abstract

The invention discloses a mechanical equipment maintenance monitoring method and system based on big data, and relates to the technical field of mechanical equipment maintenance monitoring, and the method comprises the steps: setting a corresponding monitoring environment threshold value for mechanical equipment based on the historical operation data monitoring quality of the mechanical equipment, and recognizing the operation environment condition of the mechanical equipment based on the monitoring environment threshold value; for the mechanical equipment in the non-abnormal operation environment condition, whether the mechanical equipment has an abnormal condition or not is identified based on the operation data; for the mechanical equipment with the abnormal operation environment condition, the relation between the state of the mechanical equipment and the magnetic field is used for analyzing the current operation magnetic field of the mechanical equipment, whether the mechanical equipment has the abnormal condition or not is judged, and finally a mechanical equipment maintenance monitoring report is output and comprises the abnormal condition marking condition of the mechanical equipment. Fault prediction and early diagnosis are realized, the downtime and maintenance cost of equipment are reduced, and the reliability and maintenance efficiency of equipment operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical equipment maintenance monitoring, and specifically to a mechanical equipment maintenance monitoring method and system based on big data. Background Art

[0002] With the rapid development of information technology, especially the maturity of big data technology, the popularization of various sensors and Internet of Things (IoT) devices has enabled mechanical equipment to generate a large amount of data during operation. These data include temperature, pressure, vibration, speed and other parameters. By collecting, analyzing and processing these data in real time, abnormal conditions of equipment can be discovered in time and possible failures of equipment can be predicted, thereby achieving accurate and predictive maintenance.

[0003] However, traditional equipment monitoring methods often ignore the impact of external environmental changes on monitoring data. Under some special environmental conditions, traditional monitoring methods may not be able to effectively monitor the health status of equipment. For example, traditional vibration, temperature or pressure sensors cannot provide accurate feedback in abnormal environments, resulting in equipment failures that are difficult to detect in a timely manner. In addition, traditional equipment failure prediction methods often rely on single sensor data and lack comprehensive analysis of multi-dimensional data. In many cases, a single monitoring data cannot fully reflect the health status of the equipment, resulting in low accuracy in fault prediction. At the same time, due to reliance on predetermined time intervals for maintenance, it is not only inefficient, but may also lead to unnecessary maintenance work or ignore emergency failures, resulting in waste of resources or unexpected equipment downtime.

[0004] Therefore, in response to the above problems, there is an urgent need for a mechanical equipment maintenance monitoring method and system based on big data. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a mechanical equipment maintenance monitoring method and system based on big data, which solves the problems of inaccurate fault identification and low maintenance efficiency in mechanical equipment maintenance monitoring.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a mechanical equipment maintenance monitoring method based on big data, comprising the following steps: obtaining the monitoring quality of historical operation data of mechanical equipment; setting a corresponding monitoring environment threshold for the mechanical equipment based on the monitoring quality of the historical operation data of the mechanical equipment; real-time monitoring of the operating environment of the mechanical equipment, and then identifying the operating environment status of the mechanical equipment based on the monitoring environment threshold, and the specific operating environment status includes a non-abnormal operating environment status and an abnormal operating environment status; for mechanical equipment with a non-abnormal operating environment status, obtaining operation data, and then analyzing the operation data based on the fault characteristics of the mechanical equipment to identify whether the mechanical equipment has an abnormal condition; for mechanical equipment with an abnormal operating environment status, obtaining the historical operating magnetic field data of the mechanical equipment and the corresponding mechanical equipment status, and based on the analysis of the historical operating magnetic field data of the mechanical equipment and the corresponding mechanical equipment status, identifying the relationship between the mechanical equipment status and the magnetic field, and then using the relationship between the mechanical equipment status and the magnetic field to analyze the current mechanical equipment operating magnetic field to determine whether the mechanical equipment has an abnormal condition; outputting a mechanical equipment maintenance monitoring report, the mechanical equipment maintenance monitoring report specifically includes the abnormal condition marking of the mechanical equipment.

[0007] Furthermore, the specific analysis of setting the corresponding monitoring environment threshold for the mechanical equipment based on the monitoring quality of the historical operation data of the mechanical equipment is as follows: the monitoring quality of the historical operation data of the mechanical equipment is specifically the monitoring quality of the mechanical equipment operation data under various environmental conditions; the environmental condition is specifically the comprehensive value of temperature, humidity and noise level, that is, the environmental condition evaluation value; the monitoring quality of the mechanical equipment operation data is specifically the comprehensive value of the integrity of the mechanical equipment operation data, the stability of the mechanical equipment operation data and the accuracy of the mechanical equipment operation data, that is, the mechanical equipment operation data quality evaluation value; the mechanical equipment operation data quality evaluation value is compared with the data quality threshold to screen out the instantaneous time point when the mechanical equipment operation data quality evaluation value is lower than the data quality threshold; the environmental condition evaluation value of the mechanical equipment at that instantaneous time point is identified, and then the average of the environmental condition evaluation values ​​of the mechanical equipment at that instantaneous time point is taken and marked as the monitoring environment threshold of the mechanical equipment.

[0008] Furthermore, the specific analysis of real-time monitoring of the operating environment of the mechanical equipment and then identifying the operating environment status of the mechanical equipment based on the monitoring environment threshold is as follows: acquiring the operating environment data of the mechanical equipment in real time, the operating environment data including temperature, humidity and noise level, and then obtaining the real-time environmental status evaluation value of the mechanical equipment based on the temperature, humidity and noise level; comparing the real-time environmental status evaluation value of the mechanical equipment with the monitoring environment threshold of the mechanical equipment respectively, marking the operating environment status of the mechanical equipment whose environmental status evaluation value is lower than the monitoring environment threshold as a non-abnormal operating environment status; marking the operating environment status of the mechanical equipment whose environmental status evaluation value is higher than or equal to the monitoring environment threshold as an abnormal operating environment status.

[0009] Furthermore, for mechanical equipment in non-abnormal operating environment conditions, operating data is obtained, and then the operating data is analyzed based on the fault characteristics of the mechanical equipment. The specific analysis to identify whether the mechanical equipment has an abnormal condition is as follows: historical fault records of the mechanical equipment in non-abnormal operating environment conditions are obtained, and the vibration amplitude and motor speed of the mechanical equipment in non-abnormal operating environment conditions at each fault are identified based on the historical fault records; a reference range of vibration amplitude and a reference range of motor speed when the mechanical equipment in non-abnormal operating environment conditions fails are obtained based on the vibration amplitude and the motor speed at each fault; operating data of the mechanical equipment in non-abnormal operating environment conditions is obtained, the operating data including the vibration amplitude and the motor speed; the vibration amplitude and the motor speed of the mechanical equipment in non-abnormal operating environment conditions are respectively compared with the reference range of vibration amplitude and the reference range of motor speed when the mechanical equipment fails, and when the vibration amplitude is within the reference range of vibration amplitude at the fault, or the motor speed is within the reference range of motor speed at the fault, the mechanical equipment is marked as having an abnormal condition.

[0010] Furthermore, for mechanical equipment with abnormal operating environment conditions, historical operating magnetic field data of the mechanical equipment and the corresponding mechanical equipment status are obtained, and based on the analysis of the historical operating magnetic field data of the mechanical equipment and the corresponding mechanical equipment status, the relationship between the mechanical equipment status and the magnetic field is identified. The specific analysis is as follows: the historical operating magnetic field data of the mechanical equipment is specifically the numerical value of the magnetic field intensity, and the mechanical equipment status is specifically the health index; based on the numerical value of the magnetic field intensity in the historical records and the mechanical equipment health index at the corresponding time node, the relationship between the numerical value of the magnetic field intensity and the mechanical equipment health index at the corresponding time node is identified, and the specific relationship includes a linear relationship or a nonlinear relationship.

[0011] Furthermore, the current operating magnetic field of the mechanical equipment is analyzed using the relationship between the state of the mechanical equipment and the magnetic field. The specific analysis to determine whether the mechanical equipment is in an abnormal condition is as follows: the numerical value of the magnetic field strength of the mechanical equipment in the current abnormal operating environment is obtained, and then the health index of the mechanical equipment in the current abnormal operating environment is obtained using the relationship between the numerical value of the magnetic field strength and the health index of the mechanical equipment at the corresponding time node; the health index of the mechanical equipment in the abnormal operating environment is compared with the health index threshold, and when the health index is lower than the health index threshold, it is marked whether the mechanical equipment is in an abnormal condition.

[0012] The mechanical equipment maintenance monitoring system based on big data applies the above-mentioned mechanical equipment maintenance monitoring method based on big data, including: a data acquisition module, used to acquire the historical operation data monitoring quality of mechanical equipment; a threshold setting module, used to set the corresponding monitoring environment threshold for mechanical equipment based on the historical operation data monitoring quality of mechanical equipment; an environment recognition module, used to monitor the operating environment of mechanical equipment in real time, and then identify the operating environment status of mechanical equipment based on the monitoring environment threshold, and the specific operating environment status includes non-abnormal operating environment status and abnormal operating environment status; a non-abnormal operating environment analysis module, used to acquire operating data for mechanical equipment in non-abnormal operating environment status, and then identify the operating environment status of mechanical equipment based on the monitoring environment threshold; The module analyzes the operating data based on the fault characteristics of the equipment to identify whether the mechanical equipment is in an abnormal condition; an abnormal operating environment analysis module is used to obtain the historical operating magnetic field data and the corresponding mechanical equipment status of the mechanical equipment in an abnormal operating environment, and analyze the historical operating magnetic field data and the corresponding mechanical equipment status based on the mechanical equipment The relationship between the mechanical equipment status and the magnetic field is identified, and then the current mechanical equipment operating magnetic field is analyzed using the relationship between the mechanical equipment status and the magnetic field to determine whether the mechanical equipment is in an abnormal condition; a report output module is used to output a mechanical equipment maintenance monitoring report, and the mechanical equipment maintenance monitoring report specifically includes the abnormal condition marking of the mechanical equipment.

[0013] The present invention has the following beneficial effects:

[0014] This mechanical equipment maintenance monitoring method and system based on big data can identify potential abnormal conditions and hidden faults in advance by comprehensively analyzing the historical operation data and real-time monitoring data of mechanical equipment, especially the identification and diagnosis of abnormal operating environments, so that the equipment can take corresponding measures in time when the environment changes, reducing the occurrence of equipment failures caused by environmental inadaptability. Based on the correlation analysis between magnetic field signals and equipment status, it can more accurately predict the failure mode of the equipment, so as to take preventive maintenance measures before the equipment fails; the differentiated processing of non-abnormal operating environment conditions and abnormal operating environment conditions enables the system to formulate different measures according to different environmental conditions. Different monitoring strategies can improve the accuracy of fault diagnosis; magnetic field data can still provide equipment health information in harsh environments, so that even in complex and changing environments, equipment status monitoring can still be effectively carried out; it automatically identifies the operating environment conditions of the equipment and makes automatic judgments based on the monitoring environment thresholds, which greatly reduces the need for manual intervention, improves the real-time and accuracy of monitoring, and helps maintenance personnel take measures in advance to avoid serious equipment failures, reducing the risk of equipment downtime and maintenance costs; it can flexibly adjust the monitoring strategy according to the differences between different equipment and different working environments, and perform differentiated processing on equipment status monitoring and environmental monitoring to adapt to various changing environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a flow chart of the mechanical equipment maintenance monitoring method based on big data of the present invention.

[0016] Figure 2 This is a structural diagram of the mechanical equipment maintenance monitoring system based on big data of the present invention. DETAILED DESCRIPTION

[0017] The embodiment of the present application realizes fault prediction and early diagnosis through a mechanical equipment maintenance monitoring method and system based on big data, reduces equipment downtime and maintenance costs, and improves equipment operation reliability and maintenance efficiency.

[0018] The overall idea of ​​the embodiments of this application is:

[0019] By obtaining the historical operation data of mechanical equipment, firstly, data collection and quality monitoring are carried out to extract the operation characteristics of each device, laying the foundation for setting the corresponding monitoring threshold and diagnostic model; according to the historical operation data of mechanical equipment, combined with the use environment and working conditions of the equipment, reasonable monitoring environment thresholds are set for each device. These thresholds are used to monitor the environmental conditions of the equipment in real time and distinguish whether the operating environment of the equipment is in a normal state; the real-time monitored equipment operating environment data is compared with the preset environmental threshold to determine whether the equipment is in a normal operating environment. According to the judgment results, it is divided into two categories: non-abnormal operating environment conditions: if the equipment is operating in a normal environment, the equipment operation data is further analyzed, and the fault feature analysis method is used to determine whether the equipment has an abnormal condition; abnormal operating environment conditions: if the equipment's operating environment is abnormal, timely diagnosis is carried out, and the relationship between the historical operation magnetic field data and the equipment status is analyzed to determine whether the abnormal environmental factors will cause the equipment to fail; based on the above analysis results, it is identified whether the equipment is in an abnormal state, and an alarm or maintenance reminder is issued in time.

[0020] See also Figure 1 The embodiment of the present invention provides a technical solution: a mechanical equipment maintenance monitoring method based on big data, comprising the following steps: obtaining the monitoring quality of historical operation data of mechanical equipment; setting a corresponding monitoring environment threshold for the mechanical equipment based on the monitoring quality of the historical operation data of the mechanical equipment; monitoring the operating environment of the mechanical equipment in real time, and then identifying the operating environment status of the mechanical equipment based on the monitoring environment threshold, and the specific operating environment status includes a non-abnormal operating environment status and an abnormal operating environment status; for mechanical equipment in a non-abnormal operating environment status, obtaining operation data, and then analyzing the operation data based on the fault characteristics of the mechanical equipment to identify whether the mechanical equipment has an abnormal condition; for mechanical equipment in an abnormal operating environment status, obtaining the historical operation magnetic field data of the mechanical equipment and the corresponding mechanical equipment status, and identifying the relationship between the mechanical equipment status and the magnetic field based on the analysis of the historical operation magnetic field data of the mechanical equipment and the corresponding mechanical equipment status, and then analyzing the current mechanical equipment operating magnetic field using the relationship between the mechanical equipment status and the magnetic field to determine whether the mechanical equipment has an abnormal condition; outputting a mechanical equipment maintenance monitoring report, the mechanical equipment maintenance monitoring report specifically includes the abnormal condition marking of the mechanical equipment.

[0021] Specifically, the specific analysis of setting the corresponding monitoring environment threshold for the mechanical equipment based on the historical operation data monitoring quality of the mechanical equipment is as follows: the historical operation data monitoring quality of the mechanical equipment is specifically the monitoring quality of the mechanical equipment operation data under various environmental conditions; the environmental state is specifically the comprehensive value of temperature, humidity and noise level, that is, the environmental state evaluation value, and the specific environmental state evaluation value is obtained by the expression: HJ = Tem*a1+Hum*a2+Noi*a3, where HJ represents the environmental state evaluation value, Tem represents temperature, Hum represents humidity, Noi represents noise level, a1 represents the weight value of temperature, a2 represents the weight value of humidity, and a3 represents the weight value of noise level; the monitoring quality of the mechanical equipment operation data is specifically the comprehensive value of the mechanical equipment operation data integrity, mechanical equipment operation data stability and mechanical equipment operation data accuracy, that is, the mechanical equipment operation data quality evaluation value, and the specific mechanical equipment operation data quality evaluation value is obtained by the expression: Wherein, JX represents the quality assessment value of mechanical equipment operation data, IM represents the integrity of mechanical equipment operation data, SM represents the stability of mechanical equipment operation data, and AM represents the accuracy of mechanical equipment operation data; the quality assessment value of mechanical equipment operation data is compared with the data quality threshold, and the instantaneous time point at which the quality assessment value of mechanical equipment operation data is lower than the data quality threshold is screened out; the environmental status assessment value of the mechanical equipment at the instantaneous time point is identified, and then the average of the environmental status assessment value of the mechanical equipment at the instantaneous time point is taken and marked as the monitoring environment threshold of the mechanical equipment.

[0022] In this implementation scheme, temperature refers to the heat of the environment surrounding the mechanical equipment, which is measured in real time by temperature sensors (such as thermocouples, RTD sensors, etc.) and uploaded to the monitoring system for acquisition; humidity refers to the humidity level of the environment in which the mechanical equipment is located, which is acquired by humidity sensors (such as capacitive or resistive humidity sensors); noise level reflects the intensity of sound waves generated when the equipment is running, which is related to the movement and vibration of the mechanical equipment, etc., and is acquired by real-time collection of noise data by acoustic sensors (such as microphones, piezoelectric sensors, etc.); the integrity of the mechanical equipment operation data indicates whether the data collected by the system is complete and without loss, ensuring that all key data points have been captured and recorded, which is crucial for fault diagnosis and performance analysis. , through the data acquisition system of the equipment, the data output by various sensors are collected in real time for sorting and identification of integrity; the stability of mechanical equipment operation data refers to the degree of smoothness of the change of equipment operation data within a certain period of time. If the equipment operation data fluctuates violently, it may mean that the equipment operation is unstable and there are hidden dangers of failure (such as excessive vibration, uneven load, etc.). Through statistical analysis of the real-time monitoring data of the equipment (such as vibration, power, pressure, etc.), the fluctuation of the data is detected, and the stability of the data is evaluated through trend analysis, standard deviation, coefficient of variation, etc.; the accuracy of mechanical equipment operation data indicates whether the operation data collected by the equipment truly reflects the actual operating status of the equipment, which is obtained through calibration and comparison.

[0023] The instantaneous time point represents the moment when the mechanical equipment operation data quality assessment value is lower than the data quality threshold. By comparing the mechanical equipment operation data quality assessment value with the data quality threshold, the instantaneous time point below the threshold is screened out; the weight values ​​of temperature, humidity and noise level are set as follows: the temperature weight value is set according to factors such as the equipment's sensitivity to temperature and the degree of influence of temperature on equipment operation; the humidity weight value is set according to factors such as the equipment's sensitivity to humidity and the degree of influence of humidity on equipment operation; the weight value is set according to factors such as the equipment's sensitivity to noise and the degree of influence of noise on equipment operation; the sum of the weight values ​​is 1. It can also be set by professionals in related fields based on their understanding of the impact of temperature, humidity and noise levels on the quality of mechanical equipment operation data.

[0024] By comprehensively analyzing the historical operating data of mechanical equipment, the monitoring environment threshold of each device can be accurately set, thereby avoiding unnecessary waste of monitoring resources and improving monitoring efficiency; by setting reasonable monitoring environment thresholds, abnormal conditions of equipment under different environmental conditions can be discovered in time, and corresponding maintenance measures can be taken to enhance the stability of the equipment; by monitoring and analyzing the operating data of equipment under different environmental conditions, possible equipment failures can be predicted, maintenance can be performed in advance, and production interruptions and equipment damage can be avoided; according to the monitoring environment threshold of the equipment, monitoring resources can be reasonably allocated to make monitoring work more targeted and improve resource utilization efficiency.

[0025] Specifically, the specific analysis of real-time monitoring of the operating environment of mechanical equipment and then identifying the operating environment status of the mechanical equipment based on the monitoring environment threshold is as follows: acquiring the operating environment data of the mechanical equipment in real time, the operating environment data including temperature, humidity and noise level, and then obtaining the real-time environmental status evaluation value of the mechanical equipment based on the temperature, humidity and noise level; comparing the real-time environmental status evaluation value of the mechanical equipment with the monitoring environment threshold of the mechanical equipment, and marking the operating environment status of the mechanical equipment with an environmental status evaluation value lower than the monitoring environment threshold as a non-abnormal operating environment status; marking the operating environment status of the mechanical equipment with an environmental status evaluation value higher than or equal to the monitoring environment threshold as an abnormal operating environment status.

[0026] In this implementation scheme, environmental data around mechanical equipment is collected in real time by installing environmental monitoring sensors (such as temperature sensors, humidity sensors, and noise sensors). These sensors will continuously monitor environmental variables and transmit data to the control system or cloud platform in real time for system analysis and evaluation, thereby generating real-time environmental status evaluation values ​​for each device, and comparing them with preset monitoring environment thresholds to determine whether the device is in an abnormal environmental state. By real-time monitoring of the operating environment of mechanical equipment and combining with preset monitoring environment thresholds, it is possible to timely identify whether the equipment is in an abnormal environmental state, effectively prevent equipment failures caused by environmental factors (such as excessive temperature, excessive humidity, or excessive noise), improve equipment reliability and maintenance efficiency, and avoid losses or production interruptions caused by environmental abnormalities.

[0027] Specifically, for mechanical equipment in non-abnormal operating environment conditions, operating data is obtained, and then the operating data is analyzed based on the fault characteristics of the mechanical equipment. The specific analysis to identify whether the mechanical equipment has an abnormal condition is as follows: historical fault records of the mechanical equipment in non-abnormal operating environment conditions are obtained, and the vibration amplitude and motor speed of the mechanical equipment in non-abnormal operating environment conditions at each fault are identified based on the historical fault records; a reference range of vibration amplitude and a reference range of motor speed when the mechanical equipment in non-abnormal operating environment conditions fails are obtained based on the vibration amplitude and the motor speed at each fault; operating data of the mechanical equipment in non-abnormal operating environment conditions is obtained, the operating data including the vibration amplitude and the motor speed; the vibration amplitude and the motor speed of the mechanical equipment in non-abnormal operating environment conditions are respectively compared with the reference range of vibration amplitude and the reference range of motor speed when the mechanical equipment fails, and when the vibration amplitude is within the reference range of vibration amplitude at the fault, or the motor speed is within the reference range of motor speed at the fault, the mechanical equipment is marked as having an abnormal condition.

[0028] In this implementation scheme, the vibration amplitude represents a measure of the vibration intensity generated by the device during operation. When a fault occurs, the device often shows obvious vibration changes. When the vibration amplitude is large, it may indicate some kind of mechanical fault (such as bearing damage, gear wear, etc.). The vibration data is obtained by installing a vibration sensor or accelerometer on the device. Sensors are usually installed at different parts of the device to monitor the vibration in real time. When a fault occurs, the vibration amplitude value in each state is recorded; the motor speed represents the rotation speed of the motor during operation, usually in RPM (revolutions per minute). When a fault occurs, the motor speed may fluctuate or deviate from the normal value (such as reduced speed, unstable fluctuations, etc.), which can be used as an important feature of the fault; the motor speed is measured in real time by a motor speed sensor (such as an encoder or a Hall sensor). A sensor is usually installed at the power supply end or the mechanical transmission end of the motor to monitor the change in speed.

[0029] The specific acquisition of the vibration amplitude reference range and the motor speed reference range is as follows: collect the vibration amplitude and motor speed data of the equipment under various fault conditions, which usually come from the equipment's fault maintenance records, sensor data, experimental data or equipment operation logs; perform statistical analysis on historical fault data to identify the distribution range of the vibration amplitude and motor speed when the fault occurs, for example, calculate statistical features such as the mean, standard deviation, maximum and minimum values ​​of the vibration amplitude and speed, and identify typical features under different fault types; determine the normal range of the vibration amplitude and motor speed and the abnormal range during the fault based on the distribution of historical fault data, usually by setting a threshold or interval to identify the reference range of the vibration amplitude and speed during the equipment fault. For example, if the vibration amplitude during the fault is usually between 2mm / s and 5mm / s, this range can be used as the reference range of the vibration amplitude. Similarly, if the motor speed is between 2000RPM and 3000RPM, this interval can be used as the reference range of the motor speed.

[0030] By continuously monitoring the equipment's operating data and comparing it with historical fault data, possible equipment failures can be identified early to prevent serious damage and reduce maintenance and downtime costs. By establishing a "normal state" reference range for equipment operation (such as vibration amplitude and motor speed), engineers can quickly identify signs of deviation from the normal state, so that preventive or repair measures can be taken in a timely manner. Traditional fault diagnosis relies on manual experience and hearing, while data-based analysis can automatically and accurately identify potential problems and reduce the impact of human errors and subjective judgments. The combination of equipment operating data and historical fault data can provide maintenance personnel with more targeted suggestions, reasonably arrange equipment maintenance, and reduce unnecessary downtime.

[0031] Specifically, for mechanical equipment in abnormal operating environment conditions, historical operating magnetic field data of the mechanical equipment and the corresponding mechanical equipment status are obtained, and based on the analysis of the historical operating magnetic field data of the mechanical equipment and the corresponding mechanical equipment status, the specific analysis of identifying the relationship between the mechanical equipment status and the magnetic field is as follows: the historical operating magnetic field data of the mechanical equipment is specifically the numerical value of the magnetic field intensity, and the mechanical equipment status is specifically the health index; based on the numerical value of the magnetic field intensity recorded in the historical records and the mechanical equipment health index at the corresponding time node, the relationship between the numerical value of the magnetic field intensity and the mechanical equipment health index at the corresponding time node is identified, and the specific relationship includes a linear relationship or a nonlinear relationship, wherein, when the relationship between the numerical value of the magnetic field intensity and the mechanical equipment health index at the corresponding time node is a linear relationship, the relationship expression is: H(t)=c*M(t)+b, wherein H(t) represents the mechanical equipment health index at time point t, M(t) represents the numerical value of the magnetic field intensity at time point t, and c and b represent linear coefficients, which are used to describe the relationship between the numerical value of the magnetic field intensity and the mechanical equipment health index at the corresponding time node, and are determined by minimizing the sum of squares of the error between the model prediction value and the actual observation value by the least squares method;

[0032] When the relationship between the magnetic field intensity value and the mechanical equipment health index at the corresponding time node is nonlinear, the relationship expression is: H(t) = ε1*M(t) 2 +ε2*M(t)+ε3, where ε1, ε2, and ε3 represent the coefficients of the polynomial regression model, where ε1 represents the influence of the quadratic term of the magnetic field intensity on the health index, that is, the acceleration effect of the change in magnetic field intensity, ε2 represents the linear influence of the linear term of the magnetic field intensity on the health index, that is, the linear relationship between the magnetic field intensity and the health index, and ε3 is a constant term, which represents the baseline value of the health index when the magnetic field intensity is zero. The coefficients of the polynomial regression model are also determined by minimizing the sum of squares of the errors between the model prediction value and the actual observation value using the least squares method.

[0033] In this implementation, the relationship between the state of the mechanical equipment and the magnetic field is used to analyze the current operating magnetic field of the mechanical equipment. The specific analysis to determine whether the mechanical equipment is in an abnormal condition is as follows: the numerical value of the magnetic field strength of the mechanical equipment in the current abnormal operating environment is obtained, and then the relationship between the numerical value of the magnetic field strength and the health index of the mechanical equipment at the corresponding time node is used to obtain the health index of the mechanical equipment in the current abnormal operating environment; the health index of the mechanical equipment in the abnormal operating environment is compared with the health index threshold, and when the health index is lower than the health index threshold, it is marked whether the mechanical equipment is in an abnormal condition.

[0034] The magnetic field strength value refers to the strength of the external electromagnetic field of mechanical equipment. The change of the magnetic field is closely related to the operating status of the equipment, especially when the equipment fails. The change of the magnetic field strength can reflect the health status of the equipment. For example, when there is a fault inside the motor (such as winding damage, bearing wear, etc.), it will cause changes in the electromagnetic field, thereby affecting the magnetic field strength. The specific magnetic field strength value can be collected in real time through the magnetic field sensor installed on the equipment (such as Hall sensor, magnetometer, etc.). The sensor usually monitors the magnetic field strength around or inside the equipment and generates real-time data.

[0035] The health index of mechanical equipment is an indicator that comprehensively reflects the health status of the equipment. It is usually calculated based on a variety of monitoring data (such as temperature, vibration, pressure, magnetic field strength, etc.). When the health index is high, it means that the equipment is in normal working condition; when the health index is low, it means that the equipment is at risk of failure or is about to fail. The specific health index is obtained by weighted multi-dimensional data input, and the characteristic values ​​of the mechanical equipment are extracted based on sensor data (such as vibration, temperature, pressure, magnetic field, etc.). The characteristic values ​​are then integrated through data mining, machine learning and other algorithms to obtain the health index. It can also be obtained through manual quality inspection marking by mechanical equipment operation and maintenance managers.

[0036] The specific steps for determining whether the relationship between the numerical value of the magnetic field intensity and the mechanical equipment health index at the corresponding time node is linear are as follows: plot the magnetic field signal (input feature) and the equipment status (output value) into a scatter plot, visually identify the distribution of the data, and observe whether the magnetic field signal and the equipment status show a certain linear trend. If the data points in the scatter plot are roughly distributed along a straight line, there may be a linear relationship; or use a linear regression model to fit the relationship between the magnetic field signal and the equipment status. If the linear regression model has a good fitting effect and the model residual is small, it indicates that there is a linear relationship between the magnetic field signal and the equipment status.

[0037] By utilizing the relationship between the magnetic field strength value and the health index of the equipment, it is possible to adapt to various environmental interferences, especially harsh operating environments (such as high temperature, high humidity, electromagnetic interference, etc.), and can effectively monitor and diagnose the health status of the equipment even in environments where traditional monitoring methods are difficult to work; by combining historical magnetic field data and equipment health index, by analyzing the relationship between them, the actual status of the equipment can be more comprehensively reflected, avoiding the limitation that a single monitoring method cannot capture potential faults; through the correlation analysis of magnetic field data and health index, the potential relationship between faults and magnetic field strength can be identified, and possible equipment faults can be warned in advance, especially some inherent motor problems, bearing damage or structural faults, which may not be obvious on traditional sensors; based on the relationship between historical magnetic field data and health index, the system can accurately determine whether the equipment is in an abnormal state under abnormal operating environment conditions, so as to take preventive measures in time to avoid equipment shutdown or failure.

[0038] See also Figure 2 The mechanical equipment maintenance monitoring system based on big data applies the above-mentioned mechanical equipment maintenance monitoring method based on big data, including: a data acquisition module, used to acquire the historical operation data monitoring quality of mechanical equipment; a threshold setting module, used to set the corresponding monitoring environment threshold for mechanical equipment based on the historical operation data monitoring quality of mechanical equipment; an environment recognition module, used to monitor the operating environment of mechanical equipment in real time, and then identify the operating environment status of mechanical equipment based on the monitoring environment threshold, and the specific operating environment status includes non-abnormal operating environment status and abnormal operating environment status; a non-abnormal operating environment analysis module, used to acquire operating data for mechanical equipment in non-abnormal operating environment status, and then identify the operating environment status of mechanical equipment based on the monitoring environment threshold; The module analyzes the operation data based on the fault characteristics of the equipment to identify whether the mechanical equipment is in an abnormal condition; the module for analyzing the abnormal operation environment is used to obtain the historical operation magnetic field data of the mechanical equipment and the corresponding mechanical equipment status for the mechanical equipment in an abnormal operation environment, and analyzes the historical operation magnetic field data of the mechanical equipment and the corresponding mechanical equipment status to identify the relationship between the mechanical equipment status and the magnetic field, and then uses the relationship between the mechanical equipment status and the magnetic field to analyze the current mechanical equipment operation magnetic field to determine whether the mechanical equipment is in an abnormal condition; the module for outputting a report outputting a mechanical equipment maintenance monitoring report, which specifically includes the abnormal condition marking of the mechanical equipment.

[0039] In summary, this application has at least the following effects:

[0040] Discover potential faults in advance through environmental change monitoring and magnetic field data analysis; identify equipment failure modes and achieve early warning through big data analysis; reduce manual intervention through automated monitoring, real-time fault analysis and maintenance report generation; reduce maintenance and downtime and production losses through early fault diagnosis; improve equipment health management through high-quality data and dynamic environmental thresholds; conduct intelligent analysis of massive equipment data to improve fault prediction capabilities; and make flexible adjustments for different equipment and environments to ensure accurate and effective monitoring.

[0041] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods and systems. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take 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.

[0042] The present invention is described with reference to the flowcharts and structure diagrams of the methods and systems according to the embodiments of the present invention. It should be understood that each process and combination of modules in the flowcharts and structure diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 process or multiple processes and structures Figure 1 A device that specifies functionality in a module or modules.

[0043] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 process or multiple processes and structures Figure 1 A function specified in a module or multiple modules.

[0044] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 process or multiple processes and structures Figure 1 Steps to specify functionality in a module or multiple modules.

[0045] Although the preferred embodiments of the present invention 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 that fall within the scope of the present invention.

[0046] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A mechanical equipment maintenance monitoring method based on big data, characterized in that: The following steps are involved: Obtain historical operating data of mechanical equipment to monitor quality; Set corresponding monitoring environment thresholds for mechanical equipment based on the monitoring quality of the historical operation data of the mechanical equipment; Monitor the operating environment of mechanical equipment in real time, and then identify the operating environment status of mechanical equipment based on the monitoring environment threshold. The specific operating environment status includes normal operating environment status and abnormal operating environment status; For mechanical equipment in a non-abnormal operating environment, obtain operating data, and then analyze the operating data based on the fault characteristics of the mechanical equipment to identify whether the mechanical equipment is in an abnormal condition; For mechanical equipment with abnormal operating environment conditions, obtain the historical operating magnetic field data of the mechanical equipment and the corresponding mechanical equipment status, analyze the historical operating magnetic field data of the mechanical equipment and the corresponding mechanical equipment status, identify the relationship between the mechanical equipment status and the magnetic field, and then use the relationship between the mechanical equipment status and the magnetic field to analyze the current mechanical equipment operating magnetic field to determine whether the mechanical equipment is in an abnormal condition; Outputting a mechanical equipment maintenance monitoring report, wherein the mechanical equipment maintenance monitoring report specifically includes abnormal condition marking of the mechanical equipment.

2. The mechanical equipment maintenance monitoring method based on big data according to claim 1 is characterized in that: The specific analysis of setting the corresponding monitoring environment threshold for mechanical equipment based on the monitoring quality of the historical operation data of the mechanical equipment is as follows: The historical operation data monitoring quality of the mechanical equipment specifically refers to the operation data monitoring quality of the mechanical equipment under various environmental conditions; The environmental state is specifically a comprehensive value of temperature, humidity and noise level, that is, an environmental state assessment value; The monitoring quality of the mechanical equipment operation data is specifically the comprehensive value of the integrity, stability and accuracy of the mechanical equipment operation data, that is, the mechanical equipment operation data quality assessment value; Compare the mechanical equipment operation data quality assessment value with the data quality threshold, and filter out the instantaneous time point when the mechanical equipment operation data quality assessment value is lower than the data quality threshold; Identify the environmental status evaluation value of the mechanical equipment at that instantaneous time point, and then take the average of the environmental status evaluation values ​​of the mechanical equipment at that instantaneous time point and mark it as the monitoring environment threshold of the mechanical equipment.

3. The mechanical equipment maintenance monitoring method based on big data according to claim 2 is characterized in that: Real-time monitoring of the operating environment of mechanical equipment, and then identifying the operating environment status of mechanical equipment based on the monitoring environment threshold, are as follows: Acquire the operating environment data of mechanical equipment in real time, including temperature, humidity and noise level, and then obtain the real-time environmental status evaluation value of the mechanical equipment based on the temperature, humidity and noise level; The real-time environmental status evaluation value of the mechanical equipment is compared with the monitoring environmental threshold of the mechanical equipment, and the operating environmental condition of the mechanical equipment whose environmental status evaluation value is lower than the monitoring environmental threshold is marked as a non-abnormal operating environmental condition; The operating environment condition of mechanical equipment whose environmental status evaluation value is higher than or equal to the monitoring environment threshold is marked as an abnormal operating environment condition.

4. The mechanical equipment maintenance monitoring method based on big data according to claim 1 is characterized in that: For mechanical equipment in a non-abnormal operating environment, the operating data is obtained, and then the operating data is analyzed based on the fault characteristics of the mechanical equipment to identify whether the mechanical equipment has an abnormal condition. The specific analysis is as follows: Obtain historical fault records of mechanical equipment in non-abnormal operating environment conditions, and identify the vibration amplitude and motor speed of each fault of the mechanical equipment in non-abnormal operating environment conditions based on the historical fault records; Based on the vibration amplitude and motor speed at each fault, a reference range of vibration amplitude and a reference range of motor speed when the mechanical equipment fails in a non-abnormal operating environment are obtained; Obtaining the operating data of mechanical equipment in normal operating environment conditions, including vibration amplitude and motor speed; The vibration amplitude and motor speed of the mechanical equipment in the non-abnormal operating environment are compared with the vibration amplitude reference range and motor speed reference range of the mechanical equipment when it fails. When the vibration amplitude is within the vibration amplitude reference range when it fails, or the motor speed is within the motor speed reference range when it fails, the mechanical equipment is marked as abnormal.

5. The mechanical equipment maintenance monitoring method based on big data according to claim 1 is characterized in that: For mechanical equipment in abnormal operating environment conditions, the historical operating magnetic field data of the mechanical equipment and the corresponding mechanical equipment status are obtained. Based on the historical operating magnetic field data of the mechanical equipment and the corresponding mechanical equipment status analysis, the specific analysis to identify the relationship between the mechanical equipment status and the magnetic field is as follows: The historical operation magnetic field data of the mechanical equipment is specifically the numerical value of the magnetic field intensity, and the mechanical equipment status is specifically the health index; Based on the numerical values ​​of the magnetic field strength in the historical records and the health index of the mechanical equipment at the corresponding time nodes, the relationship between the numerical values ​​of the magnetic field strength and the health index of the mechanical equipment at the corresponding time nodes is identified, and the specific relationship includes a linear relationship or a nonlinear relationship.

6. The mechanical equipment maintenance monitoring method based on big data according to claim 5 is characterized in that: The relationship between the state of the mechanical equipment and the magnetic field is used to analyze the current operating magnetic field of the mechanical equipment. The specific analysis to determine whether the mechanical equipment has an abnormal condition is as follows: Obtain the numerical value of the magnetic field strength of the mechanical equipment in the current abnormal operating environment, and then use the relationship between the numerical value of the magnetic field strength and the mechanical equipment health index at the corresponding time node to obtain the mechanical equipment health index of the current abnormal operating environment; The health index of the mechanical equipment in the abnormal operating environment condition is compared with the health index threshold value. When the health index is lower than the health index threshold value, it is marked whether the mechanical equipment has an abnormal condition.

7. A mechanical equipment maintenance monitoring system based on big data, applying the mechanical equipment maintenance monitoring method based on big data according to any one of claims 1 to 6, characterized in that: include: Data acquisition module, used to obtain historical operation data of mechanical equipment to monitor quality; A threshold setting module, which is used to monitor the quality of the historical operation data of mechanical equipment and set the corresponding monitoring environment threshold for the mechanical equipment; An environment recognition module is used to monitor the operating environment of mechanical equipment in real time, and then identify the operating environment status of the mechanical equipment based on the monitoring environment threshold. The specific operating environment status includes a normal operating environment status and an abnormal operating environment status; A non-abnormal operating environment analysis module is used to obtain operating data for mechanical equipment in a non-abnormal operating environment, and then analyze the operating data based on the fault characteristics of the mechanical equipment to identify whether the mechanical equipment has an abnormal condition; The abnormal operation environment analysis module is used to obtain the historical operation magnetic field data of the mechanical equipment and the corresponding mechanical equipment state for the mechanical equipment with abnormal operation environment conditions, identify the relationship between the mechanical equipment state and the magnetic field based on the historical operation magnetic field data of the mechanical equipment and the corresponding mechanical equipment state, and then use the relationship between the mechanical equipment state and the magnetic field to analyze the current mechanical equipment operation magnetic field to determine whether the mechanical equipment has an abnormal condition; The report output module is used to output a mechanical equipment maintenance monitoring report, wherein the mechanical equipment maintenance monitoring report specifically includes abnormal condition marking conditions of the mechanical equipment.

Images