Multi-parameter intelligent monitoring method and system for coal mine equipment lubricating oil

Abstract

The application relates to the technical field of lubricating oil monitoring, and provides a multi-parameter intelligent monitoring method and system for coal mine equipment lubricating oil.The method comprises the following steps: assembling a monitoring point set; extracting a first point in the monitoring point set, and performing dynamic monitoring on the first point through an intelligent monitoring device to obtain a first initial monitoring result; introducing an error calibration mechanism to calibrate the first initial monitoring result, and obtaining a first target monitoring result; combining a predetermined weight distribution to perform normalized weighted calculation on the first target monitoring result, and obtaining a real-time lubricating oil deterioration degree of a coal mining machine.The application solves the technical problem that, in the process of monitoring the lubricating oil of the coal mine equipment, the monitoring data is inaccurate due to environmental interference and equipment errors, so that the lubricating oil deterioration condition cannot be accurately evaluated, and the service life of the coal mining machine is affected, and the technical effect that the monitoring accuracy of the lubricating oil deterioration degree is improved, and the service life of the equipment is prolonged is achieved through the combination of the multi-parameter intelligent monitoring and the error calibration mechanism.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of lubricating oil monitoring, in particular to a multi-parameter intelligent monitoring method and system for lubricating oil of coal mine equipment. BACKGROUND

[0002] The lubricating system of coal mining machines and other coal mine equipment is crucial to the normal operation of the equipment, and the lubricating oil in the lubricating system plays an important role in lubrication, cooling, rust prevention and cleaning in key friction pairs such as gearboxes and bearings. However, in the harsh working environment of coal mines, the lubricating oil is easily affected by coal dust pollution, water immersion and high-temperature oxidation, which leads to rapid deterioration of its lubricating performance, and further causes abnormal wear and even mechanical failure of the equipment, which seriously threatens the safety production of coal mines. The current industry generally uses the manual periodic sampling detection method, which has the defects of long detection period and serious data lag, and it is difficult to timely find the sudden deterioration of the lubricating oil performance. The existing online monitoring technology is often limited to the monitoring of a single parameter, such as only detecting the viscosity or the number of particles of the oil, and cannot comprehensively reflect the overall deterioration state of the lubricating oil. In addition, the complex and changeable working environment of coal mines, including the severe vibration of the coal mining machine during operation, high dust concentration and fluctuation of temperature and humidity, often causes significant deviation of the monitoring data, making the traditional fixed threshold alarm mechanism frequently produce false alarms or miss alarms. This technical situation makes it difficult for coal mining enterprises to achieve precise monitoring of the lubrication state and preventive maintenance of the equipment, which not only increases the risk of unplanned downtime, but also greatly increases the equipment maintenance cost. Therefore, it is urgent to develop a multi-parameter intelligent monitoring system that can adapt to the special working conditions of coal mines, and realize real-time and accurate evaluation of the deterioration state of the lubricating oil by fusing multiple sensor data and eliminating environmental interference. SUMMARY

[0003] The application provides a multi-parameter intelligent monitoring method and system for lubricating oil of coal mine equipment, which aims to solve the technical problem that the monitoring data is inaccurate due to environmental interference and equipment error during the monitoring of the lubricating oil of coal mine equipment, so that the deterioration of the lubricating oil cannot be accurately evaluated, and the service life of the coal mining machine is affected.

[0004] The first aspect of the application provides a multi-parameter intelligent monitoring method for lubricating oil of coal mine equipment, which comprises the following steps: assembling a monitoring point set, wherein the monitoring point set refers to a set of selected points for monitoring the lubricating oil in the lubricating circuit of the coal mining machine; extracting a first point in the monitoring point set, and obtaining a first initial monitoring result by dynamically monitoring the first point through an intelligent monitoring device; introducing an error calibration mechanism to calibrate the first initial monitoring result, and obtaining a first target monitoring result; combining a predetermined weight distribution to perform normalized weighted calculation on the first target monitoring result, and obtaining a real-time lubricating oil deterioration degree of the coal mining machine.

[0005] In another aspect of the present disclosure, a multi-parameter intelligent monitoring system for coal mine equipment lubricating oil is provided, which comprises: a monitoring point selection module: a monitoring point set is established, wherein the monitoring point set refers to a collection of selected points for monitoring lubricating oil in a lubricating circuit of a coal mining machine; a dynamic monitoring module: a first point in the monitoring point set is extracted, and the first point is dynamically monitored by an intelligent monitoring device to obtain a first initial monitoring result; a calibration processing module: an error calibration mechanism is introduced to calibrate the first initial monitoring result to obtain a first target monitoring result; a deterioration degree calculation module: the first target monitoring result is normalized and weighted in combination with a predetermined weight distribution to obtain a real-time lubricating oil deterioration degree of the coal mining machine.

[0006] The one or more technical solutions provided in the present disclosure have at least the following technical effects or advantages:

[0007] The above multi-parameter intelligent monitoring method for coal mine equipment lubricating oil first selects a plurality of monitoring points in the lubricating circuit to form a monitoring point set, then extracts a point therefrom, and dynamically monitors the point by an intelligent device to obtain preliminary lubricating oil monitoring data. In order to improve the accuracy of the monitoring data, an error calibration mechanism is introduced to calibrate the initial data, thereby obtaining more accurate monitoring results. Finally, the calibrated monitoring results are weighted in combination with a predetermined weight distribution to obtain a value that reflects the lubricating oil deterioration degree in real time, so as to provide a scientific basis for the maintenance and management of the equipment.

[0008] The above description is only a summary of the technical solutions of the present disclosure. In order to more clearly understand the technical means of the present disclosure, the specific embodiments of the present disclosure can be implemented in accordance with the content of the description, and in order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the following specific embodiments of the present disclosure are described. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can also be obtained by those skilled in the art without creative labor.

[0010] Figure 1 It is a flowchart of a multi-parameter intelligent monitoring method for coal mine equipment lubricating oil in an embodiment.

[0011] Figure 2 It is an architecture diagram of a multi-parameter intelligent monitoring system for coal mine equipment lubricating oil in an embodiment.

[0012] Explanation of reference numerals in the attached diagram: Module 11 for selecting monitoring points, Module 12 for dynamic monitoring, Module 13 for calibration processing, and Module 14 for deterioration calculation. Detailed Implementation

[0013] This application provides a multi-parameter intelligent monitoring method and system for lubricating oil in coal mining equipment. This solves the technical problem that inaccurate monitoring data caused by environmental interference and equipment errors during the lubricating oil monitoring process in coal mining equipment makes it impossible to accurately assess the deterioration of lubricating oil and affect the service life of coal mining machines.

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0015] It should be noted that the terms “comprising” and “having”, and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to such process, method, product, or device.

[0016] Example 1, as Figure 1 As shown, this application provides a multi-parameter intelligent monitoring method for lubricating oil in coal mine equipment, the method comprising:

[0017] A set of monitoring points is established, wherein the set of monitoring points refers to the collection of points selected in the lubrication circuit of the coal mining machine for monitoring lubricating oil.

[0018] In this embodiment, the lubrication circuit of the coal mining machine is divided into equal-spaced sections based on monitoring interval parameters to determine multiple monitoring points. These points uniformly cover the entire flow of lubricating oil in the pipeline, facilitating the acquisition of distributed monitoring data under overall operating conditions. Subsequently, to enhance the sensitivity and criticality of monitoring, structurally significant changes in the lubrication circuit are identified, such as bends, connection nodes, or inflection points at critical lubrication components. These locations are also designated as monitoring points to reflect the dynamic characteristics of the oil at structural changes, facilitating the detection of local anomalies or signs of deterioration. Finally, all determined points are merged to form a complete monitoring point set. This monitoring point set encompasses both spatial distribution balance and structural criticality, ensuring that subsequent multi-parameter monitoring is both comprehensive and accurate, providing effective support for real-time dynamic assessment of the lubricating oil condition.

[0019] Further, the application provides a set of monitoring points, comprising:

[0020] A predetermined monitoring interval is obtained, and interval analysis is performed on the lubrication circuit based on the predetermined monitoring interval to obtain a first set of points; a position of an inflection point of the lubrication circuit is obtained to form a second set of points; the first set of points and the second set of points form the set of monitoring points.

[0021] Preferably, when setting the monitoring points of the lubrication circuit of the coal mining machine, a predetermined monitoring interval is first obtained, which is set according to the flow characteristics of the lubricating oil and the requirements of the equipment operation. For example, if the oil flow speed in the lubrication circuit is fast, a shorter monitoring interval is required; if the flow speed is slow, the interval can be appropriately extended. Based on the predetermined monitoring interval, interval analysis is performed on the entire flow path of the lubrication circuit, that is, the flow path of the lubricating oil is equally divided to obtain a plurality of equal interval sections, and the starting or ending point of each interval section is a monitoring point. By summarizing these monitoring points, a first set of points is formed. Subsequently, a structural design drawing of the lubrication circuit is obtained, and key positions where flow changes, pressure changes or direction changes exist are identified. Typically, these positions are inflection points in the lubrication circuit, such as pipe elbows, connectors, distribution valves, filters, etc. These inflection point positions are usually important change points in the flow of lubricating oil, and there may be large pressure fluctuations, oil contamination or flow speed changes, so they are also key positions that need to be monitored. By setting these inflection point positions as monitoring points, a second set of points can be formed. Finally, the first set of points and the second set of points are merged to obtain the final set of monitoring points, which includes both evenly distributed points and key structural positions, ensuring comprehensive monitoring of the lubricating oil state and laying a foundation for subsequent dynamic monitoring and data collection.

[0022] A first point in the set of monitoring points is extracted, and a first initial monitoring result is obtained by dynamically monitoring the first point through the intelligent monitoring device.

[0023] In one embodiment, a monitoring point is randomly selected from the constructed set of monitoring points as the first point. For this first point, the intelligent monitoring device of the point is activated and monitored in real time. The intelligent monitoring device continuously tracks and collects various lubricating oil parameters of the point, such as metal element concentration, particulate contamination, viscosity, moisture content, etc. By summarizing these monitored data into a set, a first initial monitoring result of the first point is constructed, which reflects the current state of the lubricating oil at the point and preliminarily describes the performance and possible degradation of the lubricating oil, providing a basis for subsequent error calibration and data processing, and providing necessary information for evaluating the health status of the lubricating oil and timely adjusting the equipment maintenance strategy.

[0024] Further, the application provides that the intelligent monitoring device comprises a metal element monitoring component, a particle monitoring component, and a performance monitoring component, wherein the metal element monitoring component is an atomic emission spectrometer, the particle monitoring component at least comprises a rotary ferrograph, a laser particle counter, and a ferrographic microscope, and the performance monitoring component at least comprises a viscosity sensor, a capacitive moisture sensor, and an acid value tester.

[0025] Preferably, in order to realize multi-dimensional and accurate perception of the state of lubricating oil, an intelligent monitoring device is configured, which is composed of a metal element monitoring component, a particle monitoring component, and a performance monitoring component, and is respectively used for detecting metal wear elements, particle pollution conditions, and basic performance parameters of lubricating oil. The metal element monitoring component adopts an atomic emission spectrometer, which can detect the types and concentrations of specific metal elements such as iron, copper, and aluminum in lubricating oil through spectral analysis means, and these information has important value for judging the wear condition of equipment parts. The particle monitoring component mainly comprises three devices, i.e., a rotary ferrograph, a laser particle counter, and a ferrographic microscope. The rotary ferrograph can obtain the distribution state of particles in lubricating oil; the laser particle counter is used for counting the number and concentration of particles of different sizes; and the ferrographic microscope can visually identify the morphology and type of particles, helping to distinguish wear particles, pollutants, or aging deposits, etc. The performance monitoring component comprises a viscosity sensor (used for measuring the kinematic viscosity of oil), a capacitive moisture sensor (used for monitoring the water content), and an acid value tester (used for judging the change of the acidity level of oil), and the changes of these parameters can reflect whether the lubricating oil appears aging, deterioration, or water mixing, etc. Through the cooperative work of the three types of monitoring components, the state of lubricating oil can be comprehensively monitored, and multi-source and reliable basic data can be provided for health state evaluation and operation and maintenance decision of the coal mining machine.

[0026] Further, the application provides that a first point in the set of monitoring points is extracted, and a first initial monitoring result is obtained by dynamically monitoring the first point through the intelligent monitoring device, comprising:

[0027] The predetermined metal elements are obtained, and the concentration of the predetermined metal elements in the first point is monitored by the atomic emission spectrometer to obtain a first metal concentration value; the first particle monitoring parameter of the first point is obtained by dynamic monitoring of the particle monitoring assembly; the first performance monitoring parameter of the first point is obtained by dynamic monitoring of the performance monitoring assembly; and the first initial monitoring result of the first point is obtained based on the first metal concentration value, the first particle monitoring parameter and the first performance monitoring parameter. The first particle monitoring parameter of the first point obtained by dynamic monitoring of the particle monitoring assembly comprises: the first particle pollutant size distribution data of the first point obtained by cooperative monitoring of the rotary ferrograph and the laser particle counter; and the first particle pollutant type of the first point obtained by monitoring of the ferrographic microscope, and the first particle monitoring parameter obtained by combining the first particle pollutant size distribution data.

[0028] Optionally, according to the wear parts that may be involved in the lubricating oil of the coal mining machine, the types of metal elements that need to be monitored are pre-set, such as iron (Fe), copper (Cu), aluminum (Al), chromium (Cr) and the like. Once the abnormal concentration of these elements appears in the lubricating oil, it means that the parts composed of the corresponding materials in the equipment are being worn. The atomic emission spectrometer in the intelligent monitoring equipment is used to analyze the lubricating oil at the first point, to monitor the concentration values of these predetermined metal elements, so as to obtain the first metal concentration value as a preliminary judgment basis for the wear condition. The particle monitoring assembly of the intelligent monitoring equipment is used to perform real-time dynamic monitoring on the particle pollutants in the lubricating oil at the first point. The rotary ferrograph and the laser particle counter of the particle monitoring assembly cooperatively collect the size distribution and concentration information of the particles in the oil, and the ferrographic microscope performs image recognition and classification on the morphology and component type of the particles. Then, the first particle monitoring parameter of the first point is generated by integrating these monitoring data, for describing the severity and cause of the particle pollution. The performance monitoring assembly is used to monitor the physicochemical properties of the lubricating oil at the first point. The viscosity sensor of the performance monitoring assembly is used to measure the kinematic viscosity of the current oil, to judge whether the fluidity is normal. The capacitive moisture sensor is used to detect the moisture content in the oil, to identify whether there is external pollution or emulsification problem. The acid value tester is used to evaluate the acid value change of the oil, to reflect the oxidation aging degree. Then, the monitoring data is summarized to form the first performance monitoring parameter, for comprehensively evaluating the basic performance state of the oil. Finally, the obtained first metal concentration value, first particle monitoring parameter and first performance monitoring parameter are sequentially added to the same set to generate the first initial monitoring result of the first point. The result can be used to preliminarily judge the comprehensive health condition of the lubricating oil at the current monitoring position, to lay a foundation for subsequent error calibration and deterioration evaluation.

[0029] In the monitoring of the lubricating oil of the first point by the particle monitoring assembly, the rotating ferrograph of the particle monitoring assembly forms a ferrograph on the rotating disc by the oil sample, and then obtains the size distribution characteristics of the magnetic particles in the oil by the migration and deposition rules of the particles in the magnetic field. The laser particle counter of the particle monitoring assembly uses the light blocking method or the scattering method to count the size of the particles passing through the detection cavity, and can provide the particle size distribution and concentration information of all particles (including non-magnetic particles) in the lubricating oil. By using the rotating ferrograph and the laser particle counter for cooperative monitoring, more comprehensive and detailed size distribution data of the particle contaminants of the first point can be provided, and these data are stored as the first particle contaminant size distribution data. Subsequently, the ferrograph microscope is used to perform image analysis on the ferrograph collected at the first point, and through microscopic imaging and image recognition technology, the type characteristics of the particles can be identified and stored as the first particle contaminant type. The first particle contaminant type can be fatigue wear particles, cutting wear particles, oxidation wear particles, sand particles or oil sludge deposition, etc. The particle type information reveals the source and formation mechanism of the particles, and is particularly crucial for judging the equipment wear pattern and external pollution source. Finally, the obtained first particle contaminant size distribution data and first particle contaminant type are stored in a set to form the first particle monitoring parameter, which is an important indicator for measuring the current particle pollution condition of the lubricating oil, and is used for subsequent generation of initial monitoring results and evaluation of the degradation of the lubricating oil.

[0030] Further, the application provides a first performance monitoring parameter of the first point obtained by dynamic monitoring of the performance monitoring assembly, including:

[0031] The first kinematic viscosity of the first point is obtained by dynamic monitoring of the viscosity sensor; the first moisture content of the first point is obtained by dynamic monitoring of the capacitive moisture sensor; the first acid value of the first point is obtained by dynamic monitoring of the acid value tester; and the first performance monitoring parameter is composed based on the first kinematic viscosity, the first moisture content and the first acid value.

[0032] Optionally, when the performance monitoring component monitors the lubricating oil at the first point, the viscosity sensor of the performance monitoring component dynamically monitors the lubricating oil at the first point, measures the kinematic viscosity of the oil, and generates a first kinematic viscosity of the first point. The first kinematic viscosity is an important indicator of the flowability of the first point, which can reflect the flow behavior of the oil at different temperatures. During the operation of the coal mining machine, the viscosity of the lubricating oil changes with temperature, and too high viscosity will affect the flowability of the oil, resulting in a decrease in lubrication effect, while too low viscosity may cause oil film rupture and wear. The capacitance type moisture sensor is used to monitor the moisture content in the lubricating oil. The capacitance type moisture sensor detects the moisture content by measuring the change in the capacitance of the oil, and obtains a first moisture content of the first point. The presence of moisture in the lubricating oil changes the insulation of the oil, causing the capacitance value to change, affecting its lubrication performance, and even accelerating the oxidation and corrosion of the oil. The acid value tester is used to dynamically monitor the acid value of the lubricating oil. The acid value is an important indicator of the acidity of the oil, which usually increases with the oxidation process of the oil. The increase in acid value means that the lubricating oil is gradually aging and the lubrication performance is decreasing. The acid value tester measures the concentration of acidic substances in the oil by acid-base indicator reaction, and generates a first acid value of the first point. Finally, the first kinematic viscosity, the first moisture content and the first acid value are sequentially added to the same set to form the first performance monitoring parameter. The first performance monitoring parameter comprehensively reflects the flowability, contamination and aging degree of the lubricating oil, and is a key indicator for evaluating the performance and health status of the lubricating oil, which can help the system to fully understand the actual working state of the lubricating oil at the first point, and provide a basis for the operation health assessment, maintenance decision and lubricating oil replacement of the equipment.

[0033] The error calibration mechanism is introduced to calibrate the first initial monitoring result to obtain a first target monitoring result.

[0034] In one embodiment, in order to improve the accuracy and reliability of the initial monitoring data, an error calibration mechanism is introduced, which includes a spectrum calibration method based on ferrography analysis and a comparison correction method of adjacent monitoring points. For example, in the spectrum calibration path, a ferrography is prepared based on the lubricating oil sample of the first point, and the spectrum information of the particles is obtained by using spectrum analysis technology, and the characteristic indexes are extracted, and then compared with the specific monitoring index (such as metal concentration, moisture or acid value) matched in the first initial monitoring result for comparative analysis and correction. In addition, the data of the adjacent points around the point are also retrieved for horizontal comparison to correct the monitoring deviation caused by local fluctuation or equipment error. Through these calibration operations, the influence of accidental interference, sensor drift or environmental noise on the monitoring result in the monitoring process can be eliminated. Finally, the first initial monitoring result processed by the error calibration mechanism is integrated into the first target monitoring result, which is a set of core data more close to the actual lubricating oil state after high-precision processing, which will be used as the basis for subsequent deterioration evaluation and oil health judgment.

[0035] Further, the application provides an error calibration mechanism for calibrating the first initial monitoring result to obtain the first target monitoring result, including:

[0036] extracting the first calibration mechanism in the error calibration mechanism; preparing the first ferrography of the first point based on the first calibration mechanism, and performing spectrum analysis on the first ferrography to obtain first spectrum information; reading any monitoring feature and matching the first arbitrary monitoring parameter in the first initial monitoring result; obtaining any predetermined related index of the arbitrary monitoring feature; extracting the first spectrum information based on the any predetermined related index to obtain the first spectrum index parameter; calibrating the first arbitrary monitoring parameter based on the first spectrum index parameter, and composing the first target monitoring result.

[0037] Optionally, first, a first calibration mechanism is extracted from the error calibration mechanism, which defines how to correct the errors that may exist in the initial monitoring results through spectral analysis technology. Based on the first calibration mechanism, the lubricating oil sample at the first point is processed using a rotary ferrograph to make the metal particles in the oil form a deposit and make a first ferrograph. Subsequently, detailed analysis is performed on these ferrograph using spectral analysis technology (such as atomic emission spectrometer) to obtain first spectral information, which contains the element composition, concentration, etc. of the particles. At the same time, read any monitoring features (such as particle concentration, metal element concentration, acid value, temperature, etc.), and identify the specific monitoring parameter value of the feature from the first initial monitoring result as the first arbitrary monitoring parameter, which will be compared and correlated with the spectral information obtained by the ferrograph analysis to ensure the accuracy of the data. Then, for the read any monitoring features, the relevant predetermined correlation indicators are also obtained, which are standard values determined based on historical data, for example, if the monitored is the metal concentration, the predetermined correlation indicator is the average concentration of the metal element under normal operating conditions. Then, based on the obtained predetermined correlation indicators, the corresponding indicator feature is extracted from the first spectral information, and the first spectral indicator parameter is obtained by ratio calculation, which provides the quantitative features of the spectral data for calibrating and adjusting the initial monitoring results. For example, when the predetermined correlation indicator is the standard metal concentration, the metal concentration feature is extracted from the first spectral information, and the metal concentration feature is calculated by ratio with the standard metal concentration, and the ratio is the first spectral indicator parameter used to adjust the first metal concentration value in the first initial monitoring result; when the predetermined correlation indicator is the standard viscosity, the features related to the viscosity are extracted from the first spectral information, such as the spectral intensity of the large particle interval, because the decrease of viscosity will cause the oil film to become thinner, which is more prone to boundary contact wear, thus increasing the number and size of particles, and the particle peak value in the corresponding particle size section of the spectrum is enhanced, by calculating the spectral intensity of the large particle interval with the standard viscosity, the first spectral indicator parameter for adjusting the first kinematic viscosity in the first initial monitoring result is obtained. Finally, the first arbitrary monitoring parameter (such as metal concentration, particle pollutant concentration, etc.) in the initial monitoring result is calibrated using the first spectral indicator parameter, and this calibration process is achieved by multiplying the first arbitrary monitoring parameter with the first spectral indicator parameter, which can correct the effects caused by measurement deviation, equipment error or environmental change, and ensure that the monitoring results are more accurate and reliable. The calibrated data is summarized as the first target monitoring result, which can truly reflect the health status of the lubricating oil for subsequent analysis and decision-making.

[0038] Further, the application provides an error calibration mechanism for calibrating the first initial monitoring result to obtain the first target monitoring result, which further comprises:

[0039] extracting a second calibration mechanism in the error calibration mechanism; based on the second calibration mechanism, obtaining a first neighboring point set of the first point; obtaining a second initial monitoring result of a second point in the first neighboring point set; calibrating the first initial monitoring result with the second initial monitoring result, and composing the first target monitoring result.

[0040] Optionally, a second calibration mechanism is extracted from the error calibration mechanism. The second calibration mechanism identifies and corrects the monitoring deviation of individual points caused by local disturbance, sensor error or instantaneous abnormality by comparing the data of neighboring points. Based on the second calibration mechanism, a number of points adjacent to the first point are obtained according to the topology of the lubrication circuit to form a first neighboring point set. The data trend of these points should have a certain logical relationship or trend coupling with the first point, which is helpful to judge the rationality of the monitoring data of the first point. Then, an optional point in the first neighboring point set is selected as the second point, and the second initial monitoring result collected by the second point is called. These data are comparable with the first point in time and physical space, and therefore can be used as calibration basis. After that, the initial monitoring data of the second point and the initial monitoring data of the first point are compared, and the deviation between the two data is calculated. If the deviation is within the tolerance range, it means that the first initial monitoring result has no obvious abnormality, and the first initial monitoring result is directly used as the first target monitoring result. Otherwise, the interval harmonic method is used to adjust the first initial monitoring result, that is, a plurality of initial monitoring results of the first point in the nearest plurality of monitoring periods are obtained, combined with the current first initial monitoring result to calculate the historical initial monitoring average of the first point, and then the historical initial monitoring average and the second initial monitoring result are processed by mean value to obtain the first target monitoring result. Compared with the initial data without correction, the result has higher credibility and stability, effectively reduces the influence of single point error on the overall judgment, and improves the accuracy and reliability of the multi-parameter intelligent monitoring result.

[0041] The first target monitoring result is normalized and weighted calculated combined with the predetermined weight distribution to obtain the real-time lubricating oil degradation degree of the coal mining machine.

[0042] In one embodiment, a predetermined weight is assigned to each target monitoring parameter in the first target monitoring result, which represents the importance of different target monitoring parameters to the evaluation of the lubricating oil degradation degree. For example, the concentration of metal elements may have a greater impact on the wear condition of the oil, and thus may be assigned a higher weight, while the change in water content may have a smaller impact on the lubricating performance, and thus may be assigned a lower weight. Subsequently, to ensure that the values of different monitoring parameters are effectively compared in the same dimension, the first target monitoring result is processed using the maximum-minimum normalization method. The normalization process converts data of different dimensions into standardized values, so that they fall within a unified range (usually between 0 and 1), eliminating the influence of dimensional differences on the calculation results. The normalized data facilitates weighted calculation, allowing each parameter to contribute reasonably to the final result. Then, according to the predetermined weight, the normalized target monitoring parameters are multiplied and summed to obtain a comprehensive lubricating oil degradation degree index, representing the real-time degradation degree of the lubricating oil. The higher the real-time lubricating oil degradation degree, the more serious the degradation of the oil, which may require timely replacement or further maintenance. By monitoring and calculating the degradation degree of the lubricating oil in real time, equipment maintenance personnel can take timely measures to avoid equipment failure due to poor lubrication and ensure long-term stable operation of the equipment.

[0043] Further, the application provides a normalization and weighted calculation of the first target monitoring result combined with the predetermined weight distribution, to obtain the real-time lubricating oil degradation degree of the coal mining machine, further comprising:

[0044] The real-time running information of the coal mining machine is dynamically monitored and subjected to variation weighting analysis to obtain a real-time running fitness. The real-time lubricating oil degradation degree is corrected with the real-time running fitness as the weight. The real-time running information at least includes real-time vibration time series and real-time temperature time series.

[0045] Preferably, the state information during operation is collected in real time by using sensors (such as temperature sensors, vibration sensors) installed on the coal mining machine, and real-time operation information is obtained, which includes but is not limited to real-time vibration time series and real-time temperature time series. The real-time vibration time series records the vibration amplitude, frequency change and other data of the equipment during operation, which can reflect whether the coal mining machine has abnormal working conditions (such as poor gear engagement, bearing wear, etc.); the real-time temperature time series records the temperature change of the lubrication circuit and related structure, and abnormal temperature rise may mean poor lubrication, increased friction and other problems. Subsequently, based on the collected real-time operation information, the fluctuation degree of the running state and the amplitude of deviation from the normal working condition are identified by a variation analysis method (such as z-score standardization, outlier analysis, dynamic threshold algorithm, etc.), and these features are weighted and calculated to calculate a comprehensive index, i.e. real-time operation fitness, which reflects the adaptability of the lubricating oil under the current operating conditions, i.e. whether the equipment is in a stable and reasonable state. Then, the real-time operation fitness is used as a dynamic weight factor to adjust the previously calculated lubricating oil degradation degree (the adjustment method is to multiply the dynamic weight factor by the lubricating oil degradation degree). Through this dynamic correction method, the lubricating oil degradation evaluation and the actual running state of the coal mining machine are combined, making the monitoring result more close to the actual working condition, and improving the accuracy of prediction and the timeliness of maintenance.

[0046] Further, the application provides dynamic monitoring of the real-time operation information of the coal mining machine, and performing variation weighting analysis on the real-time operation information to obtain real-time operation fitness, including:

[0047] Assembling a vibration feature set of the real-time vibration time series; assembling a temperature feature set of the real-time temperature time series; performing variation weighting analysis on the vibration feature set and the temperature feature set to obtain the real-time operation fitness; wherein the vibration feature set at least includes vibration time series features and vibration frequency spectrum features, and the temperature feature set at least includes temperature time series features and temperature frequency spectrum features.

[0048] Optionally, first, real-time vibration time series data is obtained from the vibration sensor of the coal mining machine, and the real-time vibration data is analyzed to determine a vibration feature set, which includes but is not limited to vibration time series features and vibration frequency spectrum features. The vibration time series features record the vibration amplitude, frequency, phase and other information of the coal mining machine at different time points, and are obtained by data extraction on real-time vibration time series. The vibration frequency spectrum features are obtained by Fourier transform or wavelet transform from the vibration time series data to extract the frequency components of the vibration signal, which helps to identify the running state of the equipment in a specific frequency band and reveal possible mechanical failures (such as gear meshing, bearing failure, etc.). Similarly, real-time temperature time series is also collected from the temperature sensor, and the real-time temperature time series is processed in the same way as described above to obtain a temperature feature set, which includes but is not limited to temperature time series features and temperature frequency spectrum features. Subsequently, the vibration feature set and the temperature feature set are processed based on the maximum-minimum normalization method to make the data in the same dimension, and then the ratio of standard deviation to mean is used to calculate the feature variation coefficient of each feature, and the calculated feature variation coefficient is used as the weight of the feature. Then, the normalized vibration feature set and the temperature feature set are weighted and summed according to the calculated weight to obtain a real-time running fitness, which will be used as a weight for lubricating oil degradation correction and further affect the health assessment result of the lubricating oil, providing a more accurate basis for equipment maintenance and early warning.

[0049] In summary, the embodiments of the present application have at least the following technical effects:

[0050] The embodiments of the present application establish a monitoring point set, wherein the monitoring point set refers to a collection of points selected in the lubrication circuit of the coal mining machine for monitoring the lubricating oil; a first point in the monitoring point set is extracted, and a first initial monitoring result is obtained by dynamically monitoring the first point through an intelligent monitoring device; an error calibration mechanism is introduced to calibrate the first initial monitoring result to obtain a first target monitoring result; and the first target monitoring result is normalized and weighted according to a predetermined weight distribution to obtain a real-time lubricating oil degradation degree of the coal mining machine. These technical effects collectively solve the technical problem that the monitoring data is inaccurate due to environmental interference and equipment errors in the process of monitoring the lubricating oil of the coal mine equipment, thereby failing to accurately assess the lubricating oil degradation and affecting the service life of the coal mining machine. The technical effects of combining multi-parameter intelligent monitoring with an error calibration mechanism to improve the monitoring accuracy of the lubricating oil degradation degree and prolong the service life of the equipment are achieved.

[0051] Embodiment two, based on the same inventive concept as the multi-parameter intelligent monitoring method for coal mine equipment lubricating oil in the foregoing embodiments, such as Figure 2As shown, the present application provides a multi-parameter intelligent monitoring system for coal mine equipment lubricating oil, which comprises: a monitoring point selection module 11: a monitoring point set is established, wherein the monitoring point set refers to a collection of selected points for monitoring lubricating oil in the lubricating circuit of the coal mining machine; a dynamic monitoring module 12: a first point in the monitoring point set is extracted, and the first point is dynamically monitored by an intelligent monitoring device to obtain a first initial monitoring result; a calibration processing module 13: an error calibration mechanism is introduced to calibrate the first initial monitoring result to obtain a first target monitoring result; a deterioration degree calculation module 14: the first target monitoring result is normalized and weighted in combination with a predetermined weight distribution to obtain the real-time lubricating oil deterioration degree of the coal mining machine.

[0052] Further, the monitoring point selection module 11 is also used to execute the following method:

[0053] A predetermined monitoring interval is obtained, and interval analysis is performed on the lubricating circuit based on the predetermined monitoring interval to obtain a first point set; an inflection point position of the lubricating circuit is obtained to form a second point set; the first point set and the second point set form the monitoring point set.

[0054] Further, the dynamic monitoring module 12 is also used to execute the following method:

[0055] The intelligent monitoring device comprises a metal element monitoring component, a particle monitoring component and a performance monitoring component, wherein the metal element monitoring component is an atomic emission spectrometer, the particle monitoring component at least includes a rotary ferrograph, a laser particle counter and a ferrographic microscope, and the performance monitoring component at least includes a viscosity sensor, a capacitive moisture sensor and an acid value tester.

[0056] Further, the dynamic monitoring module 12 is also used to execute the following method:

[0057] The predetermined metal elements are acquired, and concentration monitoring of the predetermined metal elements is performed on the first point by the atomic emission spectrometer to obtain a first metal concentration value; the first particle monitoring parameter of the first point is obtained by dynamic monitoring of the particle monitoring assembly; the first performance monitoring parameter of the first point is obtained by dynamic monitoring of the performance monitoring assembly; and the first initial monitoring result is obtained based on the first metal concentration value, the first particle monitoring parameter and the first performance monitoring parameter; wherein the first particle monitoring parameter of the first point is obtained by dynamic monitoring of the particle monitoring assembly, including: the first particle pollutant size distribution data of the first point is obtained by cooperative monitoring of the rotary ferrograph and the laser particle counter; the first particle pollutant type of the first point is obtained by monitoring of the ferrographic microscope, and the first particle monitoring parameter is obtained in combination with the first particle pollutant size distribution data.

[0058] Further, the dynamic monitoring module 12 is further used to execute the following method:

[0059] The first kinematic viscosity of the first point is obtained by dynamic monitoring of the viscosity sensor; the first moisture content of the first point is obtained by dynamic monitoring of the capacitive moisture sensor; the first acid value of the first point is obtained by dynamic monitoring of the acid value tester; and the first performance monitoring parameter is composed based on the first kinematic viscosity, the first moisture content and the first acid value.

[0060] Further, the calibration processing module 13 is further used to execute the following method:

[0061] The first calibration mechanism in the error calibration mechanism is extracted; the first ferrography film of the first point is prepared based on the first calibration mechanism, and spectrum analysis is performed on the first ferrography film to obtain first spectrum information; any monitoring feature is read, and a first arbitrary monitoring parameter in the first initial monitoring result is matched; any predetermined related index of the any monitoring feature is acquired; the first spectrum index parameter is obtained by feature extraction on the first spectrum information based on the any predetermined related index; the first target monitoring result is composed by calibrating the first arbitrary monitoring parameter based on the first spectrum index parameter.

[0062] Further, the calibration processing module 13 is further used to execute the following method:

[0063] The second calibration mechanism in the error calibration mechanism is extracted; the first adjacent point set of the first point is acquired based on the second calibration mechanism; the second initial monitoring result of a second point in the first adjacent point set is acquired; and the first target monitoring result is composed by calibrating the first initial monitoring result based on the second initial monitoring result.

[0064] Further, the deterioration degree calculation module 14 is further configured to execute the following method:

[0065] The real-time running information of the coal mining machine is dynamically monitored, and the real-time running information is subjected to variation weighting analysis to obtain a real-time running fitness; the real-time lubricating oil deterioration degree is corrected with the real-time running fitness as a weight; wherein the real-time running information at least includes a real-time vibration time sequence and a real-time temperature time sequence.

[0066] Further, the deterioration degree calculation module 14 is further configured to execute the following method:

[0067] The vibration feature set of the real-time vibration time sequence is established; the temperature feature set of the real-time temperature time sequence is established; the vibration feature set and the temperature feature set are subjected to variation weighting analysis to obtain the real-time running fitness; wherein the vibration feature set at least includes a vibration time sequence feature and a vibration frequency spectrum feature, and the temperature feature set at least includes a temperature time sequence feature and a temperature frequency spectrum feature.

[0068] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above describes a specific embodiment of the present application. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0069] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0070] The present specification and drawings are merely exemplary of the present application, and are considered to cover any and all modifications, variations, combinations or equivalents that fall within the scope of the present application. Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A multi-parameter intelligent monitoring method for coal mine equipment lubricating oil, characterized in that, The method comprises the following steps: Assembling a monitoring point set, wherein the monitoring point set refers to a set of selected points in a lubrication circuit of a coal mining machine for monitoring lubricating oil; Assembling a monitoring point set comprises: Obtaining a predetermined monitoring interval and performing interval analysis on the lubrication circuit based on the predetermined monitoring interval to obtain a first point set; Obtaining the inflection point position of the lubrication circuit and assembling a second point set, and then combining the first point set and the second point set to obtain the monitoring point set; Extracting a first point in the monitoring point set and performing dynamic monitoring on the first point by an intelligent monitoring device to obtain a first initial monitoring result; Introducing an error calibration mechanism to calibrate the first initial monitoring result to obtain a first target monitoring result; Wherein, obtaining the first target monitoring result comprises: Extracting a first calibration mechanism in the error calibration mechanism; Based on the first calibration mechanism, the first ferrography of the first point is prepared, and the first ferrography is subjected to spectral analysis to obtain first spectral information; Reading an arbitrary monitoring feature and matching a first arbitrary monitoring parameter in the first initial monitoring result; Obtaining an arbitrary predetermined correlation index of the arbitrary monitoring feature; Based on the arbitrary predetermined correlation index, the first spectral information is subjected to feature extraction to obtain a first spectral index parameter; Based on the first spectral index parameter, the first arbitrary monitoring parameter is calibrated to form the first target monitoring result; Combining a predetermined weight allocation to perform normalized weighted calculation on the first target monitoring result to obtain a real-time lubricating oil degradation degree of the coal mining machine; Dynamic monitoring obtains real-time running information of the coal mining machine, and the real-time running information is subjected to variation weighting analysis to obtain a real-time running fitness, wherein the real-time running information at least includes real-time vibration time sequence and real-time temperature time sequence; The real-time running fitness is used as a weight to correct the real-time lubricating oil degradation degree; Wherein, obtaining the real-time running fitness comprises: Assembling a vibration feature set of the real-time vibration time sequence and a temperature feature set of the real-time temperature time sequence, wherein the vibration feature set at least includes vibration time sequence features and vibration spectrum features, and the temperature feature set at least includes temperature time sequence features and temperature spectrum features; Based on normalization processing, the vibration feature set and the temperature feature set are subjected to coefficient of variation calculation, and based on the coefficient of variation, variation weighting analysis is performed to obtain the real-time running fitness.

2. The method for multi-parameter intelligent monitoring of coal mine equipment lubricating oil according to claim 1, characterized in that, The intelligent monitoring device comprises a metal element monitoring component, a particle monitoring component and a performance monitoring component, wherein the metal element monitoring component is an atomic emission spectrometer, the particle monitoring component at least includes a rotary ferrograph, a laser particle counter and a ferrographic microscope, and the performance monitoring component at least includes a viscosity sensor, a capacitive moisture sensor and an acid value tester.

3. The method for multi-parameter intelligent monitoring of coal mine equipment lubricating oil according to claim 2, characterized in that, Extracting a first point in the monitoring point set and performing dynamic monitoring on the first point by an intelligent monitoring device to obtain a first initial monitoring result, comprising: acquire a predetermined metal element, and monitor the concentration of the predetermined metal element at the first point by the atomic emission spectrometer to obtain a first metal concentration value; acquire a first particle monitoring parameter of the first point by dynamic monitoring of the particle monitoring assembly; acquire a first performance monitoring parameter of the first point by dynamic monitoring of the performance monitoring assembly; obtain the first initial monitoring result based on the first metal concentration value, the first particle monitoring parameter, and the first performance monitoring parameter; wherein the first particle monitoring parameter of the first point is acquired by dynamic monitoring of the particle monitoring assembly, including: acquire first particle pollutant size distribution data of the first point by cooperative monitoring of the rotary ferrograph and the laser particle counter; acquire first particle pollutant types of the first point by monitoring of the ferrographic microscope, and acquire the first particle monitoring parameter in combination with the first particle pollutant size distribution data.

4. The method for multi-parameter intelligent monitoring of coal mine equipment lubricating oil according to claim 3, characterized in that, acquire the first performance monitoring parameter of the first point by dynamic monitoring of the performance monitoring assembly, including: acquire a first kinematic viscosity of the first point by dynamic monitoring of the viscosity sensor; acquire a first moisture content of the first point by dynamic monitoring of the capacitive moisture sensor; acquire a first acid value of the first point by dynamic monitoring of the acid value tester; compose the first performance monitoring parameter based on the first kinematic viscosity, the first moisture content, and the first acid value.

5. The method for multi-parameter intelligent monitoring of coal mine equipment lubricating oil as claimed in claim 1, characterized in that, introduce an error calibration mechanism to calibrate the first initial monitoring result to obtain a first target monitoring result, further including: extract a second calibration mechanism in the error calibration mechanism; acquire a first adjacent point set of the first point based on the second calibration mechanism; acquire a second initial monitoring result of a second point in the first adjacent point set; calibrate the first initial monitoring result with the second initial monitoring result, and compose the first target monitoring result.

6. A multi-parameter intelligent monitoring system for coal mine equipment lubricating oil, characterized in that, the system is used to execute the multi-parameter intelligent monitoring method for coal mine equipment lubricating oil according to any one of claims 1-5, including: a monitoring point selection module: compose a monitoring point set, wherein the monitoring point set refers to a set of points selected for monitoring lubricating oil in the lubricating circuit of the coal mining machine; a dynamic monitoring module: extract a first point in the monitoring point set, and acquire a first initial monitoring result by dynamic monitoring of the first point by intelligent monitoring equipment; a calibration processing module: introduce an error calibration mechanism to calibrate the first initial monitoring result to obtain a first target monitoring result; a deterioration degree calculation module: combine a predetermined weight distribution to perform normalized weighted calculation on the first target monitoring result to obtain a real-time lubricating oil deterioration degree of the coal mining machine.

Images