Intelligent management system based on metal structure and oil monitoring

Abstract

The present invention discloses an intelligent management system based on metal structure and oil monitoring, and specifically relates to the technical field of oil monitoring. The start and stop states of target equipment are accurately identified through a state detection division module, and the autocorrelation values ​​of the equipment at different delay times k are calculated according to the equipment start and stop time series. Whether the start and stop states of the target equipment are high-frequency start and stop states is judged according to the autocorrelation values ​​at different delay times k, and sudden anomalies occurring in the equipment during high-frequency start and stop processes are accurately captured. A high-frequency start and stop potential fault hazard model is constructed according to the stress fatigue accumulation coefficient, the oil film rupture abnormality coefficient, and the start and stop vibration overload coefficient, and a high-frequency start and stop potential fault hazard index is generated, which effectively evaluates the potential fault hazards of equipment during high-frequency start and stop processes, helps equipment managers formulate scientific maintenance and management strategies, and realizes early warning of fault hazards, thereby reducing the frequency of equipment failures and improving production efficiency and equipment service life.

Description

Technical Field

[0001] The present invention relates to the technical field of oil monitoring, and more specifically, to an intelligent management system based on metal structure and oil monitoring. Background Art

[0002] Intelligent management systems based on metal structure and oil monitoring can help industrial equipment and mechanical devices achieve real-time monitoring, diagnosis and predictive maintenance. This system combines metal structure status monitoring with oil status analysis to provide a full range of equipment operation health assessment and optimization management;

[0003] In the scenario of high-frequency start-stop operation of industrial equipment, the metal structure and lubrication system of the equipment will be subjected to the combined effects of transient stress, thermal cycle, vibration shock and other dynamic loads due to the frequent and rapid start-stop process. This operating characteristic may cause metal fatigue accumulation, local structural damage, and lubricant film rupture, performance degradation and other problems, seriously affecting the reliability and service life of the equipment.

[0004] Existing equipment monitoring and maintenance methods often rely on regular inspections and empirical judgments, and it is difficult to capture abnormalities caused by transient changes during the start-stop process. For example, metal parts are prone to stress concentration and crack propagation under instantaneous overload, and lubricants fail due to high shear forces and sharp increases in local temperatures. At the same time, unbalanced lubrication distribution may lead to insufficient lubrication of local parts, increasing the risk of wear and failure. In addition, changes in vibration and noise during frequent start-stop processes will further amplify the instability of the overall operation of the equipment and increase potential fault hazards. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an intelligent management system based on metal structure and oil monitoring to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] Intelligent management system based on metal structure and oil monitoring, including state detection division module, stress fatigue accumulation module, oil film rupture analysis module, start-stop vibration interference module, model output module, hidden danger warning module;

[0008] The state detection and classification module is used to obtain the start and stop state of the target device and express it in binary data to obtain the start and stop time series of the device, calculate the autocorrelation value of the device at different delay times k according to the start and stop time series of the device, and judge whether the start and stop state of the target device is a high-frequency start and stop state according to the autocorrelation value at different delay times k;

[0009] The stress fatigue accumulation module is used to obtain the transient stress information of the metal parts of the target equipment during the high-frequency start-stop period, and obtain the stress fatigue accumulation coefficient based on the transient stress information of the metal parts;

[0010] The oil film rupture analysis module is used to obtain the oil film rupture information of the lubricating oil during the high-frequency start-stop period of the target equipment, and obtain the oil film rupture abnormality coefficient based on the oil film rupture information of the lubricating oil;

[0011] A start-stop vibration interference module is used to obtain the start-stop vibration information of the target device during the high-frequency start-stop period of the target device, and obtain the start-stop vibration overload coefficient according to the start-stop vibration information of the target device;

[0012] The model output module is used to construct a high-frequency start-stop potential fault hidden danger model based on the stress fatigue accumulation coefficient, oil film rupture abnormal coefficient, and start-stop vibration overload coefficient, generate a high-frequency start-stop potential fault hidden danger index, and evaluate the potential fault hidden danger degree of the target equipment during the high-frequency start-stop period;

[0013] The hidden danger warning module is used to compare the high-frequency start-stop potential fault hidden danger index with the preset high-frequency start-stop potential fault hidden danger index threshold, and classify and warn the potential fault hidden danger degree of the target equipment during the high-frequency start-stop period.

[0014] In a preferred embodiment, the start and stop status of the target device is obtained from the start and stop records of the target device, and represented by binary data to obtain the device start and stop time series data. ,in, , Indicates that the target device is in the startup state at time i. Indicates that the target device is in a stopped state at time i; calculates the mean of the device start-stop time series data , the expression is as follows ; Calculate the autocorrelation value at different delay times k , the expression is as follows , according to the autocorrelation value at different delay time k Determine the start / stop status of the target device, as follows:

[0015] If the delay time is less than or equal to the preset delay time threshold and the autocorrelation value is greater than or equal to the preset autocorrelation threshold, the start / stop state of the target device is marked as a high-frequency start / stop state.

[0016] In a preferred embodiment, by acquiring transient stress information of metal parts during high-frequency start-stop of target equipment, analyzing the transient stress tolerance of metal parts during high-frequency start-stop of target equipment, and obtaining stress fatigue accumulation coefficient, the transient stress tolerance of metal parts during high-frequency start-stop of target equipment is measured;

[0017] The logic for obtaining the stress fatigue accumulation coefficient is as follows:

[0018] The transient stress data of the metal parts of the target equipment during the high-frequency start-stop process are collected through high-frequency stress sensors, the maximum and minimum stress values ​​during the stress loading to unloading cycle are recorded, and the stress amplitude of each stress loading to unloading cycle is calculated. , the expression is as follows ,in represents the maximum stress value, Indicates the minimum stress value; calculates the average stress value for each stress loading to unloading cycle , the expression is as follows ; Calculate stress fatigue value through stress fatigue function , the function expression is as follows ,in is the material constant; calculate the stress fatigue accumulation coefficient , the expression is as follows ,in Indicates The actual number of cycles of the stress cycle, Indicates The stress fatigue value calculated by the stress cycle, , Is a positive integer.

[0019] In a preferred embodiment, by obtaining the oil film rupture information of the lubricating oil during the high-frequency start-stop of the target equipment, analyzing the oil film rupture of the lubricating oil during the high-frequency start-stop of the target equipment, and obtaining the oil film rupture abnormality coefficient, the degree of oil film rupture of the lubricating oil during the high-frequency start-stop of the target equipment is measured;

[0020] The logic for obtaining the oil film rupture anomaly coefficient is as follows:

[0021] The actual temperature of the lubricating oil of the target equipment is collected through the temperature sensor, and the viscosity of the lubricating oil at different actual temperatures is calculated , the expression is as follows ,in Indicates the viscosity of the lubricating oil at the actual temperature T, Indicates the reference temperature The viscosity of the lubricating oil under represents the activation energy of lubricating oil, is the gas constant, Indicates the actual temperature, is the base of the natural logarithm; calculate the oil film thickness based on the lubricating oil viscosity , the expression is as follows ,in represents the contact pressure, is the relative sliding velocity, and the lubricating oil shear stress is calculated based on the oil film thickness , the expression is as follows ; Calculate the oil film rupture anomaly coefficient , the expression is as follows ,in represent the preset proportionality coefficients of actual temperature, oil film thickness, and lubricant shear stress, respectively, and Both are greater than 0.

[0022] In a preferred embodiment, by acquiring the start-stop vibration information of the target device during the high-frequency start-stop period of the target device, analyzing the start-stop vibration of the target device during the high-frequency start-stop period of the target device, and acquiring the start-stop vibration overload coefficient, the start-stop vibration degree of the target device during the high-frequency start-stop period of the target device is measured;

[0023] The logic for obtaining the start-stop vibration overload coefficient is as follows:

[0024] Vibration sensors are used to collect vibration signals of target equipment during high-frequency start-stop processes. , select Daubechies wavelet basis function to perform wavelet transform decomposition on the vibration signal. The wavelet transform formula is as follows: ,in represents the time-frequency component of the vibration signal after wavelet transformation, represents the complex conjugate of the wavelet basis function, represents the scale parameter, represents the time shift parameter, Expressing time; calculating scale The vibration intensity under the condition is expressed as follows ,in represents the mth time shift parameter, ; Calculate the start-stop vibration overload coefficient , the expression is as follows ,in Gets the function for the maximum value.

[0025] In a preferred embodiment, a high-frequency start-stop potential fault hazard model is constructed based on the stress fatigue accumulation coefficient, the oil film rupture abnormality coefficient, and the start-stop vibration overload coefficient to generate a high-frequency start-stop potential fault hazard index. The model is based on the following formula , where They represent the preset proportional coefficients of stress fatigue accumulation coefficient, oil film rupture abnormal coefficient, and start-stop vibration overload coefficient, respectively, and Both are greater than 0.

[0026] In a preferred embodiment, the high-frequency start-stop potential fault hidden danger index is compared with a preset high-frequency start-stop potential fault hidden danger index threshold, and a classified warning is performed on the potential fault hidden danger degree during the high-frequency start-stop period of the target equipment, as follows:

[0027] If the high-frequency start-stop potential fault hidden danger index is greater than the high-frequency start-stop potential fault hidden danger index threshold, a high warning signal is generated; if the high-frequency start-stop potential fault hidden danger index is less than or equal to the high-frequency start-stop potential fault hidden danger index threshold, a low warning signal is generated.

[0028] Technical effects and advantages of the present invention:

[0029] 1. The present invention accurately identifies the start and stop state of the target device through the state detection division module, calculates the autocorrelation value of the device at different delay times k according to the start and stop time series of the device, and judges whether the start and stop state of the target device is a high-frequency start and stop state according to the autocorrelation value at different delay times k, accurately captures the sudden abnormalities that may occur in the high-frequency start and stop process of the device, avoids the lag and inaccuracy of traditional periodic detection and empirical judgment, obtains the transient stress information of the metal parts of the target device during the high-frequency start and stop period through the stress fatigue accumulation module, and evaluates the fatigue state of the metal structure by calculating the stress fatigue accumulation coefficient, helps to timely identify the overload impact of the metal parts of the equipment under frequent start and stop, prevents structural damage or fracture caused by metal fatigue, and improves the safety of the equipment. The oil film rupture analysis module monitors the oil film rupture information of the lubricating oil, calculates the oil film rupture abnormality coefficient, evaluates the rupture risk of the lubricating oil film during the high-frequency start and stop period, and timely discovers the problem of insufficient lubrication caused by oil film rupture, avoids excessive wear and component damage caused by oil film rupture, and effectively extends the service life of the equipment. The start-stop vibration interference module calculates the start-stop vibration overload coefficient based on the start-stop vibration information of the monitored equipment, further analyzes the impact of equipment vibration on equipment stability and health status, and constructs a high-frequency start-stop potential fault hidden danger model according to the stress fatigue accumulation coefficient, oil film rupture abnormal coefficient and start-stop vibration overload coefficient. It generates a high-frequency start-stop potential fault hidden danger index, effectively evaluates the potential fault hidden dangers of equipment in the high-frequency start-stop process, helps equipment managers formulate scientific maintenance and management strategies, and realizes early warning of fault hidden dangers, thereby reducing the frequency of equipment failures and improving production efficiency and equipment service life. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0031] Figure 1 Flowchart of a system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] Embodiment: The present invention provides as Figure 1 The intelligent management system based on metal structure and oil monitoring shown includes a state detection division module, a stress fatigue accumulation module, an oil film rupture analysis module, a start-stop vibration interference module, a model output module, and a hidden danger warning module;

[0034] The state detection and classification module is used to obtain the start and stop state of the target device and express it in binary data to obtain the start and stop time series of the device, calculate the autocorrelation value of the device at different delay times k according to the start and stop time series of the device, and judge whether the start and stop state of the target device is a high-frequency start and stop state according to the autocorrelation value at different delay times k;

[0035] The stress fatigue accumulation module is used to obtain the transient stress information of the metal parts of the target equipment during the high-frequency start-stop period, and obtain the stress fatigue accumulation coefficient based on the transient stress information of the metal parts;

[0036] The oil film rupture analysis module is used to obtain the oil film rupture information of the lubricating oil during the high-frequency start-stop period of the target equipment, and obtain the oil film rupture abnormality coefficient based on the oil film rupture information of the lubricating oil;

[0037] A start-stop vibration interference module is used to obtain the start-stop vibration information of the target device during the high-frequency start-stop period of the target device, and obtain the start-stop vibration overload coefficient according to the start-stop vibration information of the target device;

[0038] The model output module is used to construct a high-frequency start-stop potential fault hidden danger model based on the stress fatigue accumulation coefficient, oil film rupture abnormal coefficient, and start-stop vibration overload coefficient, generate a high-frequency start-stop potential fault hidden danger index, and evaluate the potential fault hidden danger degree of the target equipment during the high-frequency start-stop period;

[0039] The hidden danger warning module is used to compare the high-frequency start-stop potential fault hidden danger index with the preset high-frequency start-stop potential fault hidden danger index threshold, and classify and warn the potential fault hidden danger degree of the target equipment during the high-frequency start-stop period;

[0040] The state detection and classification module is used to obtain the start and stop state of the target device and express it in binary data to obtain the start and stop time series of the device, calculate the autocorrelation value of the device at different delay times k according to the start and stop time series of the device, and judge whether the start and stop state of the target device is a high-frequency start and stop state according to the autocorrelation value at different delay times k;

[0041] Get the start and stop status of the target device from the start and stop records of the target device, and express it in binary data to obtain the start and stop time series data of the device ,in, , Indicates that the target device is in the startup state at time i. Indicates that the target device is in a stopped state at time i; calculates the mean of the device start-stop time series data , the expression is as follows ; Calculate the autocorrelation value at different delay times k , the expression is as follows , according to the autocorrelation value at different delay time k Determine the start / stop status of the target device, as follows:

[0042] If the delay time is less than or equal to the preset delay time threshold and the autocorrelation value is greater than or equal to the preset autocorrelation threshold, it means that the target device has a high degree of similarity within a short time interval, that is, the operating state of the target device switches rapidly within a short time, indicating that the start-stop mode occurs repeatedly within a short time, and the start-stop state of the target device is marked as a high-frequency start-stop state;

[0043] It should be noted that by calculating the autocorrelation values ​​of the target equipment at different delay moments and analyzing the values ​​of the autocorrelation values ​​at smaller delay moments, short-cycle, high-frequency start-stop behaviors can be quickly detected, and high-frequency patterns can be captured sensitively, avoiding the limitations of subjective judgment, and providing a reliable basis for alarm and operation and maintenance. Since the autocorrelation value is calculated based on the existing time series data, no additional sensors or complex hardware investment is required, which significantly reduces the monitoring cost. At the same time, it can easily adapt to different equipment types and start-stop signal modes, and has wide universality. By discovering the time pattern of high-frequency start-stop, the equipment operating parameters or external control logic can be adjusted in a targeted manner, thereby reducing unnecessary start-stops, extending equipment life, reducing energy consumption, and improving operating efficiency, and providing a basis for hidden danger warnings for subsequent target equipment.

[0044] The stress fatigue accumulation module is used to obtain the transient stress information of the metal parts of the target equipment during the high-frequency start-stop period, and obtain the stress fatigue accumulation coefficient based on the transient stress information of the metal parts;

[0045] The stress fatigue accumulation coefficient is a key indicator used to measure the degree of fatigue accumulation caused by repeated transient stress on metal parts of industrial equipment during high-frequency start-stop processes. Specifically, it reflects the impact of stress cycles on the structural strength and service life of metal parts due to frequent loading and unloading. When the transient stress during high-frequency start-stop exceeds the normal operating range, the stress fatigue accumulation coefficient will increase significantly, indicating that there may be abnormal operating conditions or hidden failure risks; based on the stress fatigue accumulation coefficient, it can provide a scientific basis for equipment maintenance and replacement to avoid sudden failure. A larger stress fatigue accumulation coefficient indicates that the metal parts are close to or have exceeded their fatigue limit after a high-frequency start-stop process, and there is a higher risk of structural damage. The greater the degree of potential failure of the target equipment, the smaller the stress fatigue accumulation coefficient, indicating that the fatigue damage to the metal parts after a high-frequency start-stop process is relatively light, and it is still within the safe operating range. There is still a large margin from its fatigue limit, the structural stability of the equipment is relatively high, and the potential failure risk is relatively low. This shows that the metal parts of the equipment can adapt well to the stress cycle under the current start-stop conditions, and are not prone to fatigue failure, so the reliability and operational safety of the equipment can be maintained;

[0046] Therefore, by obtaining the transient stress information of the metal parts during the high-frequency start-stop of the target equipment, the transient stress tolerance of the metal parts during the high-frequency start-stop of the target equipment is analyzed, and the stress fatigue accumulation coefficient is obtained to measure the transient stress tolerance of the metal parts during the high-frequency start-stop of the target equipment;

[0047] The logic for obtaining the stress fatigue accumulation coefficient is as follows:

[0048] The transient stress data of the metal parts of the target equipment during the high-frequency start-stop process are collected through high-frequency stress sensors, the maximum and minimum stress values ​​during the stress loading to unloading cycle are recorded, and the stress amplitude of each stress loading to unloading cycle is calculated. , the expression is as follows ,in represents the maximum stress value, Indicates the minimum stress value; calculates the average stress value for each stress loading to unloading cycle , the expression is as follows ; Calculate stress fatigue value through stress fatigue function , the function expression is as follows ,in is the material constant; calculate the stress fatigue accumulation coefficient , the expression is as follows ,in Indicates The actual number of cycles of the stress cycle, Indicates The stress fatigue value calculated by the stress cycle, , is a positive integer;

[0049] It should be noted that the material constants are set by those skilled in the art according to the actual metal material properties;

[0050] It should be noted that by obtaining the transient stress information that metal parts are subjected to during frequent start-stop processes in real time and calculating their cumulative fatigue damage, the fatigue state of key components of the equipment can be accurately identified, avoiding the limitation that traditional periodic detection methods cannot capture transient changes. The stress fatigue accumulation coefficient can fully reflect the cumulative effect of stress cycles caused by high-frequency start-stop, quickly locate potential fatigue hotspots, and provide a reliable basis for predicting the risk of equipment fracture failure. At the same time, this evaluation method effectively improves the transparency of the equipment's operating status, supports the optimization of start-stop strategies, reduces the probability of damage to key components due to excessive fatigue, and extends the overall service life of the equipment. With the help of this indicator, companies can plan maintenance cycles more scientifically, reduce the occurrence of unplanned downtime, and thus improve the reliability and operating efficiency of equipment.

[0051] The oil film rupture analysis module is used to obtain the oil film rupture information of the lubricating oil during the high-frequency start-stop period of the target equipment, and obtain the oil film rupture abnormality coefficient based on the oil film rupture information of the lubricating oil;

[0052] The oil film rupture abnormal coefficient is used to measure the degree of rupture or failure of the oil film when the lubricating oil is affected by transient stress and thermal load during the high-frequency start-stop of the equipment. The rupture of the oil film will cause direct contact between metal parts, increased friction, and aggravated wear. In severe cases, it may cause equipment damage. The oil film rupture abnormal coefficient is a quantitative indicator used to describe the impact of oil film rupture on the lubrication effect of the equipment, so as to evaluate the risk of equipment failure. A larger oil film rupture abnormal coefficient indicates a higher risk of lubricating oil film rupture, which usually means that the lubricating oil film of the equipment has been subjected to excessive transient stress and thermal load during the high-frequency start-stop process, resulting in thinning or rupture of the oil film thickness. Insufficient lubrication will cause direct contact between metal parts, increase wear, and may cause equipment damage, such as premature bearing wear or component damage. Therefore, a larger oil film rupture abnormal coefficient indicates that the equipment has a greater potential for failure, and maintenance or replacement of lubricating oil may be required to avoid failure. A smaller oil film rupture abnormal coefficient indicates that the lubricating oil film maintains a relatively stable thickness and performance during the start-stop process, the risk of oil film rupture is low, and the lubrication state of the equipment is relatively ideal. This means that during the high-frequency start-up and shutdown process of the equipment, the lubricating oil can better withstand transient stress and heat load, maintain sufficient oil film thickness, and effectively prevent direct friction and excessive wear of metal parts. A smaller oil film rupture abnormal coefficient indicates that the equipment has a smaller potential for failure, the equipment is operating normally, and no emergency maintenance is required;

[0053] Therefore, by obtaining the oil film rupture information of the lubricating oil during the high-frequency start-stop of the target equipment, analyzing the oil film rupture of the lubricating oil during the high-frequency start-stop of the target equipment, and obtaining the oil film rupture abnormality coefficient, the degree of oil film rupture of the lubricating oil during the high-frequency start-stop of the target equipment is measured;

[0054] The logic for obtaining the oil film rupture anomaly coefficient is as follows:

[0055] The actual temperature of the lubricating oil of the target equipment is collected through the temperature sensor, and the viscosity of the lubricating oil at different actual temperatures is calculated , the expression is as follows ,in Indicates the viscosity of the lubricating oil at the actual temperature T, Indicates the reference temperature The viscosity of the lubricating oil under represents the activation energy of lubricating oil, is the gas constant, Indicates the actual temperature, is the base of the natural logarithm; calculate the oil film thickness based on the lubricating oil viscosity , the expression is as follows ,in represents the contact pressure, Relative sliding velocity refers to the relative movement speed between two contact surfaces in the target device. Usually in the lubrication system, it refers to the speed at which two metal surfaces slide in the lubricating oil film. The lubricating oil shear stress is calculated based on the oil film thickness. , the expression is as follows ; Calculate the oil film rupture anomaly coefficient , the expression is as follows ,in represent the preset proportionality coefficients of actual temperature, oil film thickness, and lubricant shear stress, respectively, and All are greater than 0;

[0056] It should be noted that before calculating the oil film rupture anomaly coefficient, it is necessary to ensure that the actual temperature, oil film thickness, and lubricating oil shear stress are normalized. Commonly used normalization methods include Min-Max normalization, Z-Score normalization, etc. Set it according to the actual situation. For example, adopt the expert empowerment method, that is, invite experts in relevant fields to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0057] It should be noted that by quantifying the risk of lubricating oil film rupture, the lubrication condition and operating stability of the equipment can be accurately judged. By real-time monitoring of the risk of oil film rupture, potential lubrication failures can be identified early, providing a scientific basis for equipment maintenance decisions, thereby extending the service life of the equipment, reducing unplanned downtime and maintenance costs, and ensuring that the equipment can maintain good operating performance under complex working conditions with high frequency of start-up and shutdown;

[0058] A start-stop vibration interference module is used to obtain the start-stop vibration information of the target device during the high-frequency start-stop period of the target device, and obtain the start-stop vibration overload coefficient according to the start-stop vibration information of the target device;

[0059] The start-stop vibration overload coefficient is used to measure the impact of the vibration generated during the start-stop process on the load, stability and potential failure risk of the target equipment during high-frequency start-stop periods. During frequent start-stop processes, the equipment will undergo rapid acceleration and deceleration, which will not only cause stress on metal parts, but also induce mechanical vibration. If these vibrations exceed the tolerance limit of the equipment, it may cause equipment performance degradation, structural damage or even failure. Therefore, the start-stop vibration overload coefficient is an important indicator that reflects the degree of impact of vibration on the equipment. A larger start-stop vibration overload coefficient indicates that the target equipment is subjected to strong vibration during the start-stop process, which may cause structural fatigue, loose connections, increased wear of parts, etc., and there is a higher risk of failure. Therefore, a higher start-stop vibration overload coefficient can be used as an early warning signal, indicating that the equipment has a higher risk of failure during the start-stop process; a smaller start-stop vibration overload coefficient means that the vibration is relatively stable, the operating state of the equipment is relatively stable, and the risk of failure is low;

[0060] Therefore, by acquiring the start-stop vibration information of the target device during the high-frequency start-stop period of the target device, analyzing the start-stop vibration situation of the target device during the high-frequency start-stop period of the target device, and acquiring the start-stop vibration overload coefficient, the start-stop vibration degree of the target device during the high-frequency start-stop period of the target device is measured;

[0061] The logic for obtaining the start-stop vibration overload coefficient is as follows:

[0062] Vibration sensors are used to collect vibration signals of target equipment during high-frequency start-stop processes. , select Daubechies wavelet basis function to perform wavelet transform decomposition on the vibration signal. The wavelet transform formula is as follows: ,in represents the time-frequency component of the vibration signal after wavelet transformation, represents the complex conjugate of the wavelet basis function, represents the scale parameter, represents the time shift parameter, Expressing time; calculating scale The vibration intensity under the condition is expressed as follows ,in represents the mth time shift parameter, ; Calculate the start-stop vibration overload coefficient , the expression is as follows ,in Get function for maximum value;

[0063] It should be noted that by continuously monitoring and analyzing the start-stop vibration overload coefficient, potential fault hazards can be identified in time, so that corresponding maintenance measures can be taken in advance to reduce the probability of equipment failure, extend the service life of the equipment, and improve the reliability of equipment operation;

[0064] The model output module is used to construct a high-frequency start-stop potential fault hidden danger model based on the stress fatigue accumulation coefficient, oil film rupture abnormal coefficient, and start-stop vibration overload coefficient, generate a high-frequency start-stop potential fault hidden danger index, and evaluate the potential fault hidden danger degree of the target equipment during the high-frequency start-stop period;

[0065] A high-frequency start-stop potential fault hazard model is constructed based on the stress fatigue accumulation coefficient, oil film rupture abnormal coefficient, and start-stop vibration overload coefficient, and a high-frequency start-stop potential fault hazard index is generated. The model is based on the following formula , where They represent the preset proportional coefficients of stress fatigue accumulation coefficient, oil film rupture abnormal coefficient, and start-stop vibration overload coefficient, respectively, and All are greater than 0;

[0066] It should be noted that before constructing the high-frequency start-stop potential fault hazard model, it is necessary to ensure that the stress fatigue accumulation coefficient, oil film rupture abnormality coefficient, and start-stop vibration overload coefficient are all normalized; Set according to actual conditions, for example, adopt the expert empowerment method, that is, invite experts in relevant fields to determine the preset proportion coefficients of various indicators through professional opinion surveys and comprehensive evaluations;

[0067] It can be seen from the above calculation expression that the greater the stress fatigue accumulation coefficient, the greater the oil film rupture abnormal coefficient, and the greater the start-stop vibration overload coefficient, the greater the high-frequency start-stop potential fault hidden danger index, indicating that the target equipment has a greater fault hidden danger under the operating conditions of high-frequency start-stop, and there may be a high risk of damage, which requires maintenance or protection. On the contrary, the smaller the stress fatigue accumulation coefficient, the smaller the oil film rupture abnormal coefficient, and the smaller the start-stop vibration overload coefficient, the smaller the high-frequency start-stop potential fault hidden danger index, indicating that the operating state of the target equipment is relatively stable, the potential fault hidden danger is small, and the target equipment continues to operate stably;

[0068] The hidden danger warning module is used to compare the high-frequency start-stop potential fault hidden danger index with the preset high-frequency start-stop potential fault hidden danger index threshold, and classify and warn the potential fault hidden danger degree of the target equipment during the high-frequency start-stop period;

[0069] The high-frequency start-stop potential fault hidden danger index is compared with the preset high-frequency start-stop potential fault hidden danger index threshold, and the potential fault hidden danger degree of the target equipment during the high-frequency start-stop period is classified and warned as follows:

[0070] If the high-frequency start-stop potential fault hazard index is greater than the high-frequency start-stop potential fault hazard index threshold, it means that the target equipment has a large potential fault hazard, and the target equipment may face a high risk of damage or failure, and a high warning signal is generated, indicating that the equipment is at a high risk and may need emergency maintenance, shutdown inspection or other emergency measures. At this time, the equipment maintenance personnel or monitoring system should take positive actions to avoid failures; if the high-frequency start-stop potential fault hazard index is less than or equal to the high-frequency start-stop potential fault hazard index threshold, it means that the target equipment has a small potential fault hazard, the equipment is in good operating condition, and the risk of failure is low, and a low warning signal is generated. At this time, the equipment can continue to operate normally, but regular inspections should still be carried out to ensure the long-term stability of the equipment;

[0071] The present invention accurately identifies the start and stop state of the target device through the state detection division module, calculates the autocorrelation value of the device at different delay times k according to the start and stop time series of the device, and judges whether the start and stop state of the target device is a high-frequency start and stop state according to the autocorrelation value at different delay times k, accurately captures the sudden abnormalities that may occur in the device during the high-frequency start and stop process, avoids the lag and inaccuracy of traditional periodic detection and empirical judgment, obtains the transient stress information of the metal parts of the target device during the high-frequency start and stop period through the stress fatigue accumulation module, and evaluates the fatigue state of the metal structure by calculating the stress fatigue accumulation coefficient, helps to timely identify the overload impact of the metal parts of the equipment under frequent start and stop, prevents structural damage or fracture caused by metal fatigue, and improves the safety of the equipment. The oil film rupture analysis module monitors the oil film rupture information of the lubricating oil, calculates the oil film rupture abnormality coefficient, evaluates the rupture risk of the lubricating oil film during the high-frequency start and stop period, and timely discovers the problem of insufficient lubrication caused by oil film rupture, avoids the problems of excessive wear and component damage caused by oil film rupture, thereby effectively extending the service life of the equipment. The start-stop vibration interference module calculates the start-stop vibration overload coefficient based on the start-stop vibration information of the monitored equipment, further analyzes the impact of equipment vibration on equipment stability and health status, and constructs a high-frequency start-stop potential fault hidden danger model according to the stress fatigue accumulation coefficient, oil film rupture abnormal coefficient and start-stop vibration overload coefficient. It generates a high-frequency start-stop potential fault hidden danger index, effectively evaluates the potential fault hidden dangers of equipment in the high-frequency start-stop process, helps equipment managers formulate scientific maintenance and management strategies, and realizes early warning of fault hidden dangers, thereby reducing the frequency of equipment failures and improving production efficiency and equipment service life.

[0072] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0073] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0074] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0075] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0076] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Intelligent management system based on metal structure and oil monitoring, characterized by: It includes state detection division module, stress fatigue accumulation module, oil film rupture analysis module, start-stop vibration interference module, model output module, and hidden danger warning module; The state detection and classification module is used to obtain the start and stop state of the target device and express it in binary data to obtain the start and stop time series of the device, calculate the autocorrelation value of the device at different delay times k according to the start and stop time series of the device, and judge whether the start and stop state of the target device is a high-frequency start and stop state according to the autocorrelation value at different delay times k; The stress fatigue accumulation module is used to obtain the transient stress information of the metal parts of the target equipment during the high-frequency start-stop period, and obtain the stress fatigue accumulation coefficient based on the transient stress information of the metal parts; The oil film rupture analysis module is used to obtain the oil film rupture information of the lubricating oil during the high-frequency start-stop period of the target equipment, and obtain the oil film rupture abnormality coefficient based on the oil film rupture information of the lubricating oil; A start-stop vibration interference module is used to obtain the start-stop vibration information of the target device during the high-frequency start-stop period of the target device, and obtain the start-stop vibration overload coefficient according to the start-stop vibration information of the target device; The model output module is used to construct a high-frequency start-stop potential fault hidden danger model based on the stress fatigue accumulation coefficient, oil film rupture abnormal coefficient, and start-stop vibration overload coefficient, generate a high-frequency start-stop potential fault hidden danger index, and evaluate the potential fault hidden danger degree of the target equipment during the high-frequency start-stop period; The hidden danger warning module is used to compare the high-frequency start-stop potential fault hidden danger index with the preset high-frequency start-stop potential fault hidden danger index threshold, and classify and warn the potential fault hidden danger degree of the target equipment during the high-frequency start-stop period.

2. The intelligent management system based on metal structure and oil monitoring according to claim 1 is characterized in that: Get the start and stop status of the target device from the start and stop records of the target device, and express it in binary data to obtain the start and stop time series data of the device ,in, , Indicates that the target device is in the startup state at time i. Indicates that the target device is in a stopped state at time i; calculates the mean of the device start-stop time series data , the expression is as follows ; Calculate the autocorrelation value at different delay times k , the expression is as follows , according to the autocorrelation value at different delay time k Determine the start / stop status of the target device, as follows: If the delay time is less than or equal to the preset delay time threshold and the autocorrelation value is greater than or equal to the preset autocorrelation threshold, the start / stop state of the target device is marked as a high-frequency start / stop state.

3. The intelligent management system based on metal structure and oil monitoring according to claim 1 is characterized in that: By obtaining the transient stress information of the metal parts during the high-frequency start-stop of the target equipment, analyzing the transient stress tolerance of the metal parts during the high-frequency start-stop of the target equipment, and obtaining the stress fatigue accumulation coefficient, the transient stress tolerance of the metal parts during the high-frequency start-stop of the target equipment is measured; The logic for obtaining the stress fatigue accumulation coefficient is as follows: The transient stress data of the metal parts of the target equipment during the high-frequency start-stop process are collected through high-frequency stress sensors, the maximum and minimum stress values ​​during the stress loading to unloading cycle are recorded, and the stress amplitude of each stress loading to unloading cycle is calculated. , the expression is as follows ,in represents the maximum stress value, Indicates the minimum stress value; calculates the average stress value for each stress loading to unloading cycle , the expression is as follows ; Calculate stress fatigue value through stress fatigue function , the function expression is as follows ,in is the material constant; Calculation of stress fatigue accumulation factor , the expression is as follows ,in Indicates The actual number of cycles of the stress cycle, Indicates The stress fatigue value calculated by the stress cycle, , Is a positive integer.

4. The intelligent management system based on metal structure and oil monitoring according to claim 1 is characterized in that: By obtaining the oil film rupture information of the lubricating oil during the high-frequency start-stop of the target equipment, analyzing the oil film rupture of the lubricating oil during the high-frequency start-stop of the target equipment, and obtaining the oil film rupture abnormality coefficient, the degree of oil film rupture of the lubricating oil during the high-frequency start-stop of the target equipment is measured; The logic for obtaining the oil film rupture anomaly coefficient is as follows: The actual temperature of the lubricating oil of the target equipment is collected through the temperature sensor, and the viscosity of the lubricating oil at different actual temperatures is calculated , the expression is as follows ,in Indicates the viscosity of the lubricating oil at the actual temperature T, Indicates the reference temperature The viscosity of the lubricating oil under represents the activation energy of lubricating oil, is the gas constant, Indicates the actual temperature, is the base of natural logarithms; Calculate the oil film thickness based on the lubricating oil viscosity , the expression is as follows ,in represents the contact pressure, is the relative sliding velocity, and the lubricating oil shear stress is calculated based on the oil film thickness , the expression is as follows ; Calculation of oil film rupture anomaly coefficient , the expression is as follows ,in represent the preset proportionality coefficients of actual temperature, oil film thickness, and lubricant shear stress, respectively, and Both are greater than 0.

5. The intelligent management system based on metal structure and oil monitoring according to claim 1 is characterized in that: By acquiring the start-stop vibration information of the target device during the high-frequency start-stop period of the target device, analyzing the start-stop vibration situation of the target device during the high-frequency start-stop period of the target device, and acquiring the start-stop vibration overload coefficient, the start-stop vibration degree of the target device during the high-frequency start-stop period of the target device is measured; The logic for obtaining the start-stop vibration overload coefficient is as follows: Vibration sensors are used to collect vibration signals of target equipment during high-frequency start-stop processes. , select Daubechies wavelet basis function to perform wavelet transform decomposition on the vibration signal. The wavelet transform formula is as follows: ,in represents the time-frequency component of the vibration signal after wavelet transformation, represents the complex conjugate of the wavelet basis function, represents the scale parameter, represents the time shift parameter, Indicates time; Calculation scale The vibration intensity under the condition is expressed as follows ,in represents the mth time shift parameter, ; Calculate the start-stop vibration overload coefficient , the expression is as follows ,in Gets the function for the maximum value.

6. The intelligent management system based on metal structure and oil monitoring according to claim 1 is characterized in that: A high-frequency start-stop potential fault hazard model is constructed based on the stress fatigue accumulation coefficient, oil film rupture abnormal coefficient, and start-stop vibration overload coefficient, and a high-frequency start-stop potential fault hazard index is generated. The model is based on the following formula , where They represent the preset proportional coefficients of stress fatigue accumulation coefficient, oil film rupture abnormal coefficient, and start-stop vibration overload coefficient, respectively, and Both are greater than 0.

7. The intelligent management system based on metal structure and oil monitoring according to claim 6 is characterized by: The high-frequency start-stop potential fault hidden danger index is compared with the preset high-frequency start-stop potential fault hidden danger index threshold, and the potential fault hidden danger degree of the target equipment during the high-frequency start-stop period is classified and warned as follows: If the high-frequency start-stop potential fault hidden danger index is greater than the high-frequency start-stop potential fault hidden danger index threshold, a high warning signal is generated; if the high-frequency start-stop potential fault hidden danger index is less than or equal to the high-frequency start-stop potential fault hidden danger index threshold, a low warning signal is generated.

Images