A method for evaluating the lubrication reliability of industrial equipment

Abstract

This invention relates to the field of mechanical equipment technology, specifically to a method for evaluating the reliability of lubrication in industrial equipment, comprising the following steps: S1, collecting operational data: collecting operational data of the mechanical equipment; S2, evaluating lubrication performance: calculating the flow properties and lubrication performance of the lubricating oil using the Arrhenius and Barus models; S3, dynamic monitoring and adjustment of lubricating film thickness: implementing a technique for dynamically monitoring the lubricating film thickness, monitoring and adjusting the thickness of the lubricating film in real time; S4, evaluating lubrication effect: evaluating the lubrication effect of the lubricating oil under current operating conditions; S5, determining the reliability level: determining the reliability level of the lubricating oil; S6, proposing improvement measures: if the reliability of the mechanical equipment lubrication does not meet the preset standard, proposing improvement measures for the lubrication scheme. This invention ensures that mechanical equipment maintains optimal lubrication under constantly changing conditions, reducing the risks caused by improper lubrication.

Description

[0001] This application is a divisional application of the application filed on November 4, 2024, with application number 2024115570389 and invention title "A method and system for evaluating the lubrication reliability of industrial equipment". Technical Field

[0002] This invention relates to the field of mechanical equipment technology, and in particular to a method for evaluating the lubrication reliability of industrial equipment. Background Technology

[0003] In modern industry, the stable operation of mechanical equipment places extremely high demands on the performance of the lubrication system. Traditional lubrication reliability assessment methods rely heavily on experience and periodic inspections, which are not only time-consuming and labor-intensive, but also often fail to accurately reflect the actual lubrication conditions, especially in situations where equipment operating conditions are complex or frequently changing. Furthermore, the flow properties and lubrication performance of lubricating oil change under different temperature and pressure conditions, and traditional methods struggle to accurately assess these performance changes in real time, thus failing to make timely adjustments to optimize lubrication effects.

[0004] Currently, although various sensor technologies exist for monitoring equipment operating status, these technologies are still insufficient in integrating and analyzing the collected data to achieve intelligent management of lubrication systems. In particular, there is a lack of a systematic evaluation method to monitor the thickness of the lubricating film in real time and dynamically adjust the lubrication strategy according to the monitoring results to cope with changes in working conditions. In addition, there is usually no unified quantitative standard for the reliability assessment of lubricating oils, making it difficult to evaluate and compare the performance of different lubricating oils, resulting in the overall reliability of equipment lubrication being difficult to guarantee. Summary of the Invention

[0005] To achieve the above objectives, the present invention provides a method for evaluating the lubrication reliability of industrial equipment.

[0006] A method for evaluating the lubrication reliability of industrial equipment includes the following steps:

[0007] S1, Collect operating data: Collect operating data of mechanical equipment, including equipment operating time, temperature, load, and lubricating oil pressure;

[0008] S2, Evaluate lubrication performance: Based on the collected data, the flow properties and lubrication performance of the lubricating oil are calculated using the Arrhenius model and the Barus model. The Arrhenius model and the Barus model respectively consider the relationship between the viscosity of the lubricating oil and the changes in temperature and pressure.

[0009] S3, Dynamic Lubricating Film Thickness Monitoring and Adjustment: Implements technology for dynamically monitoring the thickness of the lubricating film, monitoring and adjusting the thickness of the lubricating film in real time to adapt to changes in equipment operating conditions. It uses sensor technology to monitor the film thickness in the lubrication contact area and automatically adjusts the supply of lubricating oil to ensure optimal lubrication effect.

[0010] S4, Evaluate lubrication effect: Based on the flow performance, lubrication performance and real-time monitoring results of the lubricating film, evaluate the lubrication effect of the lubricating oil under the current working conditions, including evaluating whether the lubricating film formed by the lubricating oil prevents metal contact and reduces wear;

[0011] S5, Determine the reliability level: Based on the lubrication effect, determine the reliability level of the lubricating oil and compare it with the preset reliability level standard to evaluate the overall reliability of the lubrication of mechanical equipment.

[0012] S6, propose improvement measures: If the reliability of lubrication of mechanical equipment does not meet the preset standard, propose improvement measures for the lubrication scheme, including replacing the lubricating oil, adjusting the working parameters of the lubrication scheme, or improving the design of the lubrication scheme.

[0013] Furthermore, the collection of operational data in S1 includes:

[0014] Equipment operation time recording: Automatically record the start-up, operation, and shutdown times of the equipment by installing a time recorder on the mechanical equipment;

[0015] Temperature monitoring: Using temperature sensors, temperature changes in moving parts and lubrication points of mechanical equipment are monitored and recorded in real time. By monitoring the temperature of the equipment body and lubricating oil, the thermal stability of the lubricating oil and the thermal load of the equipment under different working conditions can be analyzed.

[0016] Load monitoring: Measuring and recording the actual load borne by mechanical equipment during operation using force sensors;

[0017] Lubricating oil pressure monitoring: The pressure of lubricating oil in the lubrication path is monitored in real time through pressure sensors. The monitoring of lubricating oil pressure also serves to detect whether the lubricating oil passage is unobstructed and whether there are any leaks.

[0018] Furthermore, the evaluation of lubrication performance in S2 includes:

[0019] Applications of the Arrhenius model: The Arrhenius model is used to calculate and predict the viscosity of lubricating oils under different temperature conditions, helping to evaluate the flow properties of lubricating oils. The calculation formula is as follows:

[0020] ;

[0021] in, Represents temperature The viscosity of the lubricating oil below, It is the viscosity at the reference temperature. It is activation energy. It is the gas constant. It is the temperature of the lubricating oil. ;

[0022] Application of the Barus model: The Barus model evaluates the viscosity change of lubricating oil under different pressures, thereby determining the lubricating performance of the lubricating oil under high load conditions. The calculation formula is as follows:

[0023] ;

[0024] in, It's pressure The viscosity of the lubricating oil below, It is the viscosity at standard atmospheric pressure. It is the pressure coefficient of the lubricating oil. It is the pressure of the lubricating oil. ;

[0025] Performance evaluation: Combining the calculation results of the Arrhenius and Barus models, the flow properties and lubrication performance of the lubricating oil are comprehensively evaluated. The relationship between the viscosity of the lubricating oil and the changes in temperature and pressure is considered to determine whether the lubricating oil can maintain the lubrication of equipment components under working conditions, prevent wear, and reduce the risk of overheating.

[0026] Furthermore, the dynamic lubricating film thickness monitoring and adjustment in S3 includes:

[0027] Lubricating film thickness monitoring: A film thickness sensor is installed in the lubrication contact area of ​​the mechanical equipment. The film thickness sensor monitors the thickness of the lubricating film in real time. The film thickness sensor includes optical sensors, capacitive sensors or ultrasonic sensors.

[0028] Data analysis and processing: The collected lubricating film thickness data is analyzed, and the improved strategy gradient method is used to evaluate whether the thickness of the lubricating film is within the ideal range. The improved strategy gradient method determines the optimal thickness of the lubricating film based on the operating parameters of the mechanical equipment and the physical properties of the lubricating oil.

[0029] Automatic adjustment of lubricating oil supply: The lubricating oil supply is automatically adjusted based on data analysis results.

[0030] Furthermore, the improved policy gradient method includes:

[0031] Model definition: Strategy Indicates the state given Select action The probability, These are policy parameters and states. This includes the operating parameters of the mechanical equipment (such as load and speed) and the physical properties of the lubricating oil (such as temperature and pressure), and the action. It is the adjusted lubricant supply, reward function. Used to evaluate the state Take action below The effect of this is the ability to maintain an ideal lubricating film thickness;

[0032] Improved policy gradient formula: The improved policy gradient method applies the policy parameters... The update is performed using the following formula:

[0033] ;

[0034] in, It is a performance function. This indicates the expectation under the strategy;

[0035] Reward Function Design: The reward function is designed to encourage the strategy to reduce the gap between the actual lubricating film thickness and the ideal thickness. The calculation formula is as follows:

[0036] ;

[0037] in, Taking action The thickness of the lubricating film was measured later. It is the ideal thickness of the lubricating film;

[0038] Parameter update: In each iteration, the policy parameters are updated. The update is performed using the gradient ascent method, and the calculation formula is:

[0039] ;

[0040] in, It is the learning rate, a pre-set positive number that controls the step size for updating parameters.

[0041] Furthermore, the automatic adjustment of the lubricating oil supply is achieved by controlling the speed of the lubricating oil pump or adjusting the opening of the oil supply valve. If the lubricating film thickness is detected to be below the optimal range, the lubricating oil supply will be increased; conversely, if the lubricating film thickness is above the optimal range, the lubricating oil supply will be reduced.

[0042] Furthermore, the evaluation of lubrication effectiveness in S4 includes:

[0043] Real-time data acquisition: Collect parameters of mechanical equipment in real time, including load, speed, temperature and pressure, and continuously monitor the real-time thickness of the lubricating film;

[0044] Data analysis: Based on the collected operating parameters and lubricant film thickness data, an improved graph attention network (GAT) algorithm is used to predict the quality of lubrication effect, and the model is continuously updated based on newly collected data;

[0045] Comprehensive evaluation of lubrication effect: Based on the prediction results and real-time monitoring data of lubrication film thickness, the current lubrication status is comprehensively evaluated to determine whether the ideal lubrication effect has been achieved. Attention is paid to whether the lubrication film prevents direct contact between metal parts and the wear risk under the current lubrication status.

[0046] Furthermore, the improved Graph Attention Network (GAT) algorithm includes:

[0047] Calculate the attention coefficient: for each pair of nodes and The attention coefficient is determined at the update node. The representation of the node The importance is calculated using the following formula:

[0048] ;

[0049] in, It is a node and The unnormalized attention coefficients between them It is a non-linear activation function. These are parameters related to the attention mechanism. It is a weight matrix. These are nodes and The input feature vector, It is a join operation that connects the feature vectors of two nodes together.

[0050] Normalized attention weights: for all nodes To the node The attention coefficient is normalized and calculated using the following formula:

[0051] ;

[0052] in, These are normalized attention weights, representing the attention weights used in updating nodes. When representing features, nodes Contribution It is a node The set of neighboring nodes;

[0053] Node feature update: The feature representation of each node is updated by weighting the feature vectors of its neighboring nodes. The calculation formula is as follows:

[0054] ;

[0055] in, It is a node Based on the updated feature representation according to the attention weights It is an activation function.

[0056] Furthermore, determining the reliability level in S5 includes:

[0057] Determine reliability indicators: Calculate the reliability indicators of the lubricating oil based on the lubrication performance evaluation results. The reliability index of lubricating oil is a comprehensive score that reflects its performance in maintaining lubricating film thickness, preventing wear, and maintaining chemical stability. The calculation formula is as follows:

[0058] ;

[0059] in, These are weighting coefficients, which respectively reflect the contribution of lubricating film thickness, temperature stability, pressure stability, and anti-wear performance to the overall reliability index. It is an indicator of lubricating film thickness. It is an indicator of the stability of lubricating oil temperature. It is an indicator of the stability of lubricating oil pressure. It is an indicator of wear resistance. It is a normalization function;

[0060] Preset reliability level standards: Set preset reliability level standards, with each level standard corresponding to a different range of lubricant performance;

[0061] Comparison and determination of the level: The calculated reliability index of the lubricating oil is compared with the preset reliability level standard to determine the current reliability level of the lubricating oil;

[0062] Assess the overall reliability of lubrication in mechanical equipment: Based on the reliability grade of the lubricating oil, assess the overall reliability of lubrication in the mechanical equipment. If the reliability grade of the lubricating oil used in all components meets or exceeds the preset minimum requirements, then the overall lubrication of the mechanical equipment is reliable.

[0063] A mechanical equipment lubrication reliability assessment system, used to implement the above-mentioned industrial equipment lubrication reliability assessment method, includes the following modules:

[0064] Data collection module: Equipped with sensors and recording devices, used to collect data on the mechanical equipment's operating time, temperature, load, and lubricating oil pressure;

[0065] Lubrication performance evaluation module: Integrates the computational capabilities of the Arrhenius and Barus models to analyze the viscosity of lubricating oil as a function of temperature and pressure, and evaluate the flow properties and lubrication performance of the lubricating oil.

[0066] Dynamic monitoring and adjustment module: used to monitor the thickness of the lubricating film in real time and dynamically adjust the supply of lubricating oil according to the equipment operating conditions;

[0067] Lubrication performance evaluation module: Based on real-time monitoring data and lubrication performance evaluation results, it comprehensively judges the actual lubrication effect of the lubricating oil, including whether the lubricating film prevents metal-to-metal contact and reduces wear;

[0068] Reliability level determination module: compares the lubrication effect with the preset reliability level standard, determines the reliability level of the lubricating oil, and evaluates the overall reliability of the lubrication of mechanical equipment;

[0069] Feedback and Improvement Module: Based on the reliability assessment results, if the lubrication reliability of the mechanical equipment does not meet the preset standard, the feedback and improvement module will propose specific lubrication improvement measures, including replacing the lubricating oil, adjusting the lubrication parameters, or improving the lubrication scheme design.

[0070] The beneficial effects of this invention are:

[0071] This invention, through precise collection and analysis of equipment operating data, including key parameters such as operating time, temperature, load, and lubricating oil pressure, provides a solid foundation for lubricating oil performance evaluation. This makes the evaluation of lubrication effect more accurate and comprehensive. By real-time monitoring and utilizing Arrhenius and Barus models to predict the flow properties and lubrication performance of lubricating oil, it not only improves the scientific nature of the evaluation but also makes the monitoring and adjustment of lubrication status more intelligent and adaptive. This ensures that mechanical equipment always maintains optimal lubrication under constantly changing working conditions, reducing the risk of wear caused by improper lubrication.

[0072] This invention effectively adapts to changes in equipment operating conditions by dynamically monitoring the thickness of the lubricating film and adjusting the lubricating oil supply in a timely manner. This dynamic adjustment mechanism not only ensures that the thickness of the lubricating film is always in an ideal state, preventing direct contact and wear between metal parts, but also optimizes the efficiency of lubricating oil use, avoiding waste of resources. In the process of evaluating the lubrication effect, special attention is paid to whether the lubricating film can prevent direct contact between metal parts and the wear risk under the current lubrication condition, thereby ensuring the reliability and long-term stable operation of mechanical equipment.

[0073] This invention provides a quantitative standard for assessing the overall reliability of lubrication in mechanical equipment by determining the reliability level of lubricating oil and comparing it with preset standards. This allows maintenance personnel to clearly understand the performance of the lubricating oil and make timely adjustments or replacements, thereby preventing potential failures in advance. Furthermore, if the reliability of the lubricating oil does not meet the preset standards, improvement measures are provided, further enhancing the maintenance strategy for mechanical equipment and providing an effective solution for extending equipment life and improving equipment performance. Attached Figure Description

[0074] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0075] Figure 1 This is a schematic diagram of the evaluation method flow according to an embodiment of the present invention;

[0076] Figure 2 This is a schematic diagram of the system functional modules according to an embodiment of the present invention. Detailed Implementation

[0077] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0078] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0079] like Figure 1 As shown, a method for evaluating the lubrication reliability of industrial equipment includes the following steps:

[0080] S1, Collect operating data: Collect operating data of mechanical equipment, including equipment operating time, temperature, load, and lubricating oil pressure;

[0081] S2, Evaluate lubrication performance: Based on the collected data, the flow properties and lubrication performance of the lubricating oil are calculated using the Arrhenius model and the Barus model. The Arrhenius model and the Barus model respectively consider the relationship between the viscosity of the lubricating oil and the changes in temperature and pressure.

[0082] S3, Dynamic Lubricating Film Thickness Monitoring and Adjustment: Implements technology for dynamically monitoring the thickness of the lubricating film, monitoring and adjusting the thickness of the lubricating film in real time to adapt to changes in equipment operating conditions. It uses sensor technology to monitor the film thickness in the lubrication contact area and automatically adjusts the supply of lubricating oil to ensure optimal lubrication effect.

[0083] S4, Evaluate lubrication effect: Based on the flow performance, lubrication performance and real-time monitoring results of the lubricating film, evaluate the lubrication effect of the lubricating oil under the current working conditions, including evaluating whether the lubricating film formed by the lubricating oil prevents metal contact and reduces wear;

[0084] S5, Determine the reliability level: Based on the lubrication effect, determine the reliability level of the lubricating oil and compare it with the preset reliability level standard to evaluate the overall reliability of the lubrication of mechanical equipment.

[0085] S6, propose improvement measures: If the reliability of lubrication of mechanical equipment does not meet the preset standard, propose improvement measures for the lubrication scheme, including replacing the lubricating oil, adjusting the working parameters of the lubrication scheme, or improving the design of the lubrication scheme;

[0086] The above methods can accurately assess and optimize the lubrication status of mechanical equipment, thereby improving lubrication reliability, reducing equipment failures, and extending equipment service life.

[0087] The collected runtime data in S1 includes:

[0088] Equipment running time recording: By installing a time recorder on the mechanical equipment, the start-up, running and shutdown times of the equipment are automatically recorded. The time recorder provides data on the cumulative running time of the equipment, providing basic information for assessing lubrication needs and equipment wear conditions;

[0089] Temperature monitoring: Using temperature sensors, temperature changes are monitored and recorded in real time on moving parts and lubrication points of mechanical equipment. By monitoring the temperature of the equipment body and lubricating oil, the thermal stability of the lubricating oil and the thermal load of the equipment under different working conditions can be analyzed. In this way, the optimal performance of the equipment and its lubrication system can be ensured in various operating environments, and potential problems caused by abnormal temperatures can be detected in a timely manner.

[0090] Load monitoring: The actual load borne by mechanical equipment during operation is measured and recorded by force sensors. Load data is crucial for understanding the working status of the equipment and assessing the lubricating oil's load-bearing capacity.

[0091] Lubricating oil pressure monitoring: Through pressure sensors, the pressure of lubricating oil in the lubrication path is monitored in real time. The monitoring of lubricating oil pressure can not only ensure the normal operation of the lubrication counterweight, but also serve as an important basis for detecting whether the lubricating oil passage is unobstructed and whether there are any leaks.

[0092] By integrating these monitoring tools and methods, this assessment method can comprehensively and accurately collect key data on mechanical equipment during actual operation, providing solid data support for lubrication reliability assessment, thereby making the assessment results more accurate and reliable.

[0093] The evaluation of lubrication performance in S2 includes:

[0094] Applications of the Arrhenius model: The Arrhenius model is used to calculate and predict the viscosity of lubricating oils under different temperature conditions, helping to evaluate the flow properties of lubricating oils. The calculation formula is as follows:

[0095] ;

[0096] in, Represents temperature The viscosity of the lubricating oil below, It is the viscosity at the reference temperature. It is activation energy. It is the gas constant. It is the temperature of the lubricating oil. ;

[0097] Application of the Barus model: The Barus model evaluates the viscosity change of lubricating oil under different pressures, thereby determining the lubricating performance of the lubricating oil under high load conditions. The calculation formula is as follows:

[0098] ;

[0099] in, It's pressure The viscosity of the lubricating oil below, It is the viscosity at standard atmospheric pressure. It is the pressure coefficient of the lubricating oil. It is the pressure of the lubricating oil. ;

[0100] Performance evaluation: Combining the calculation results of the Arrhenius model and the Barus model, the flow properties and lubrication performance of the lubricating oil are comprehensively evaluated. The relationship between the viscosity of the lubricating oil and the changes in temperature and pressure is considered to determine whether the lubricating oil can maintain the lubrication of equipment parts, prevent wear and reduce the risk of overheating under specific working conditions.

[0101] By using the above methods and specific physical models and actual collected data, lubrication configurations can be accurately evaluated and optimized, thereby improving the operating efficiency and reliability of mechanical equipment.

[0102] Dynamic lubrication film thickness monitoring and adjustment in S3 includes:

[0103] Lubricating film thickness monitoring: A film thickness sensor is installed in the lubrication contact area of ​​the mechanical equipment. The film thickness sensor monitors the thickness of the lubricating film in real time. The film thickness sensor includes optical sensors, capacitive sensors or ultrasonic sensors. The film thickness sensor has high sensitivity and accuracy and can accurately measure the thickness of the lubricating film under different working conditions.

[0104] Data analysis and processing: The collected lubricating film thickness data is analyzed, and the improved strategy gradient method is used to evaluate whether the thickness of the lubricating film is within the ideal range. The improved strategy gradient method determines the optimal thickness of the lubricating film based on the operating parameters of the mechanical equipment and the physical properties of the lubricating oil.

[0105] Automatic adjustment of lubricating oil supply: The lubricating oil supply is automatically adjusted based on data analysis results;

[0106] By using the above methods, we can ensure that mechanical equipment achieves optimal lubrication under various operating conditions, reduce the risk of wear, improve the operating efficiency of the equipment, and extend its service life.

[0107] Improved policy gradient methods include:

[0108] Model definition: Strategy Indicates the state given Select action The probability, These are policy parameters and states. This includes the operating parameters of the mechanical equipment (such as load and speed) and the physical properties of the lubricating oil (such as temperature and pressure), and the action. It is the adjusted lubricant supply, reward function. Used to evaluate the state Take action below The effect, namely the ability to maintain the ideal lubricating film thickness, is rewarded based on the difference between the lubricating film thickness and the ideal thickness;

[0109] Improved policy gradient formula: The improved policy gradient method applies the policy parameters... The update is performed using the following formula:

[0110] ;

[0111] in, It is a performance function that represents the expected value of long-term rewards. This indicates the expectation under the strategy;

[0112] Reward Function Design: The reward function is designed to encourage the strategy to reduce the gap between the actual lubricating film thickness and the ideal thickness. The calculation formula is as follows:

[0113] ;

[0114] in, Taking action The thickness of the lubricating film was measured later. It is the ideal thickness of the lubricating film;

[0115] Parameter update: In each iteration, the policy parameters are updated. The update is performed using the gradient ascent method, and the calculation formula is:

[0116] ;

[0117] in, It is the learning rate, a pre-set positive number that controls the step size of parameter updates;

[0118] The improved strategy gradient method can be applied to adjust the lubricant supply in real time to respond to changes in the operating status of mechanical equipment and changes in the physical properties of lubricant, thereby dynamically maintaining the lubricating film within the ideal thickness range. By continuously learning and updating strategy parameters, this method can adapt to complex working conditions, optimize equipment lubrication maintenance, and ensure long-term equipment efficiency and reliability. This method optimizes the lubrication process through real-time monitoring and adaptive adjustment, reduces wear or damage caused by improper lubrication, thereby extending equipment service life and improving its performance.

[0119] The automatic adjustment of lubricating oil supply is achieved by controlling the speed of the lubricating oil pump or adjusting the opening of the oil supply valve. If the lubricating film thickness is detected to be below the optimal range, the lubricating oil supply will be increased; conversely, if the lubricating film thickness is above the optimal range, the lubricating oil supply will be reduced, ensuring that the dynamic adjustment of the lubricating oil supply matches the actual needs of the equipment.

[0120] The evaluation of lubrication effectiveness in S4 includes:

[0121] Real-time data acquisition: Collect parameters of mechanical equipment in real time, including load, speed, temperature and pressure, and continuously monitor the real-time thickness of the lubricating film;

[0122] Data analysis: Based on the collected operating parameters and lubricating film thickness data, an improved graph attention network (GAT) algorithm is used to predict the quality of lubrication effect. The model is continuously updated based on newly collected data to improve the accuracy and adaptability of the prediction.

[0123] Comprehensive evaluation of lubrication effect: Based on the prediction results and real-time monitoring data of lubrication film thickness, comprehensively evaluate the current lubrication status, determine whether the ideal lubrication effect has been achieved, pay attention to whether the lubrication film prevents direct contact between metal parts, and the wear risk under the current lubrication status;

[0124] In this invention, the method for evaluating lubrication effect makes the monitoring and adjustment of lubrication status more intelligent and adaptive. Through real-time data acquisition and data analysis, this method can accurately evaluate the lubrication effect and promptly detect problems of insufficient or excessive lubrication. This not only ensures the efficient operation of mechanical equipment but also extends the service life of the equipment and reduces maintenance costs.

[0125] Improved Graph Attention Network (GAT) algorithms include:

[0126] Calculate the attention coefficient: for each pair of nodes and The attention coefficient is determined at the update node. The representation of the node The importance is calculated using the following formula:

[0127] ;

[0128] in, It is a node and The unnormalized attention coefficients between them It is a non-linear activation function that allows small gradients to pass through when the input is negative, thus avoiding the "dead neuron" problem. These are parameters related to the attention mechanism. It is a weight matrix used for linear transformation of node features. These are nodes and The input feature vector, It is a join operation that connects the feature vectors of two nodes together.

[0129] Normalized attention weights: for all nodes To the node The attention coefficient is normalized and calculated using the following formula:

[0130] ;

[0131] in, These are normalized attention weights, representing the attention weights used in updating nodes. When representing features, nodes Contribution It is a node The set of neighboring nodes;

[0132] Node feature update: The feature representation of each node is updated by weighting the feature vectors of its neighboring nodes. The calculation formula is as follows:

[0133] ;

[0134] in, It is a node Based on the updated feature representation according to the attention weights It is an activation function used to introduce nonlinearity and increase the expressive power of the model;

[0135] Gaussian Attention (GAT) can automatically learn and emphasize the interrelationships and influences between different lubrication points within mechanical equipment through its attention mechanism. It can identify the most critical parts for maintaining the ideal lubrication film thickness, thus providing a precise basis for the formulation and adjustment of lubrication strategies. During the operation of mechanical equipment, working conditions (such as temperature and load) and environmental factors (such as humidity and temperature changes) will continuously change. The GAT model can dynamically adjust its learned attention weights based on real-time data, thereby achieving a rapid response to these changes. By using GAT for comprehensive analysis of the lubrication system, the trend of lubrication film thickness changes and the quality of lubrication can be predicted more accurately. Accurate lubrication effect prediction and timely adjustment of lubrication strategies can significantly reduce the risks and costs caused by over-lubrication or under-lubrication.

[0136] The reliability levels defined in S5 include:

[0137] Determine reliability indicators: Calculate the reliability indicators of the lubricating oil based on the lubrication performance evaluation results. The reliability index of lubricating oil is a comprehensive score that reflects its performance in maintaining lubricating film thickness, preventing wear, and maintaining chemical stability. The calculation formula is as follows:

[0138] ;

[0139] in, These are weighting coefficients, which respectively reflect the contribution of lubricating film thickness, temperature stability, pressure stability, and anti-wear performance to the overall reliability index. It is an indicator of lubricating film thickness. It is an indicator of the stability of lubricating oil temperature. It is an indicator of the stability of lubricating oil pressure. It is an indicator of wear resistance. It is a normalization function that ensures that each indicator contributes to the total score on the same order of magnitude.

[0140] The calculation is performed by comparing the measured thickness of the lubricating film with the ideal thickness. The formula is as follows:

[0141] ,in, This refers to the flow rate of the lubricating oil (usually expressed in liters per minute). It refers to the area covered by the lubricating film (usually expressed in square meters). It is the time it takes for the lubricating oil to flow (usually expressed in minutes);

[0142] The calculation is derived by measuring the temperature fluctuation range of the lubricating oil. The calculation formula is as follows:

[0143] ,in, It is in time Temperature measurement value, It is the average temperature. It refers to the number of temperature measurements.

[0144] The assessment is based on the range of lubricating oil pressure fluctuations, and the calculation formula is as follows:

[0145] ,in, It is in time Pressure measurement value, It is the average pressure. It refers to the number of pressure measurements;

[0146] The degree of wear on mechanical parts is determined by comparing the changes in wear before and after lubrication. The calculation formula is as follows:

[0147] ,in, It is the depth of the worn part. It is the depth of the component before wear;

[0148] Preset reliability level standards: Set preset reliability level standards. Each level standard corresponds to a different range of lubricant performance. For example, the level can be set from "A" to "E", where "A" represents the highest reliability and "E" represents the lowest.

[0149] Comparison and determination of grade: The calculated reliability index of the lubricating oil is compared with the preset reliability grade standard to determine the current reliability grade of the lubricating oil. If the reliability index of the lubricating oil meets or exceeds the requirements of a certain preset grade, the lubricating oil is classified into that grade.

[0150] Assess the overall reliability of lubrication in mechanical equipment: Based on the reliability grade of the lubricating oil, assess the overall reliability of lubrication in the mechanical equipment. If the reliability grade of the lubricating oil used in all components meets or exceeds the preset minimum requirements, then the overall lubrication of the mechanical equipment is reliable.

[0151] The above methods can be used to systematically assess the reliability level of lubricating oil and evaluate the overall reliability of the lubrication system of mechanical equipment. This method helps to identify potential risk points in the lubrication system, guide maintenance personnel to make targeted lubricant selections and adjustments, thereby optimizing the operating performance of the equipment and extending its service life.

[0152] like Figure 2 As shown, a mechanical equipment lubrication reliability assessment system, used to implement the above-mentioned industrial equipment lubrication reliability assessment method, includes the following modules:

[0153] Data collection module: Equipped with sensors and recording devices, used to collect data on the mechanical equipment's operating time, temperature, load, and lubricating oil pressure;

[0154] Lubrication performance evaluation module: Integrates the computational capabilities of the Arrhenius and Barus models to analyze the viscosity of lubricating oil as a function of temperature and pressure, and evaluate the flow properties and lubrication performance of the lubricating oil.

[0155] Dynamic monitoring and adjustment module: used to monitor the thickness of the lubricating film in real time and dynamically adjust the supply of lubricating oil according to the equipment operating conditions;

[0156] Lubrication effect evaluation module: Based on real-time monitoring data and lubrication performance evaluation results, it comprehensively judges the actual lubrication effect of the lubricating oil, including whether the lubricating film can prevent metal contact and reduce wear;

[0157] Reliability level determination module: compares the lubrication effect with the preset reliability level standard, determines the reliability level of the lubricating oil, and evaluates the overall reliability of the lubrication of mechanical equipment;

[0158] Feedback and Improvement Module: Based on the reliability assessment results, if the lubrication reliability of the mechanical equipment does not meet the preset standard, the feedback and improvement module will propose specific lubrication improvement measures, including replacing the lubricating oil, adjusting the lubrication parameters, or improving the lubrication scheme design.

[0159] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention is limited to these examples; within the framework of the invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.

[0160] This invention is intended to cover all such substitutions, modifications, and variations falling within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An industrial equipment lubrication reliability evaluation method, characterized by, The method comprises the following steps: S1, collecting operation data: collecting operation data of the mechanical equipment, including the operation time, temperature, load and lubricating oil pressure of the equipment; S2, evaluating lubrication performance: based on the collected data, the flow performance and lubrication performance of the lubricating oil are calculated using the Arrhenius model and the Barus model, which respectively consider the relationship between the viscosity of the lubricating oil and the change of temperature and pressure; S3, dynamic lubrication film thickness monitoring and adjustment: a technology for dynamically monitoring the thickness of the lubrication film is implemented, the thickness of the lubrication film is monitored and adjusted in real time to adapt to the changes of the operation conditions of the equipment, the film thickness in the lubrication contact area is monitored by using sensor technology, and the supply amount of the lubricating oil is automatically adjusted to ensure the optimal lubrication effect; S4, evaluating lubrication effect: according to the flow performance, lubrication performance and real-time monitoring results of the lubrication film, the lubrication effect of the lubricating oil under the current working conditions is evaluated, including whether the lubrication film formed by the lubricating oil prevents metal contact and reduces wear; S5, determining reliability level: according to the lubrication effect, the reliability level of the lubricating oil is determined and compared with the preset reliability level standard to evaluate the overall reliability of the lubrication of the mechanical equipment; S6, proposing improvement measures: if the reliability of the lubrication of the mechanical equipment does not meet the preset standard, improvement measures for the lubrication scheme are proposed, including replacing the lubricating oil, adjusting the working parameters of the lubrication scheme or improving the design of the lubrication scheme; The evaluation of the lubrication effect in S4 includes: Real-time data collection: real-time collection of parameters during the operation of the mechanical equipment, including load, speed, temperature and pressure, continuous monitoring of the real-time thickness of the lubrication film; Data analysis: according to the collected operation parameters and lubrication film thickness data, an improved graph attention network algorithm is used to predict the pros and cons of the lubrication effect, and the model is continuously updated according to the newly collected data; Comprehensive evaluation of lubrication effect: based on the prediction results and real-time monitoring data of the lubrication film thickness, the current lubrication state is comprehensively evaluated to determine whether the ideal lubrication effect is achieved, whether the lubrication film prevents direct contact between metal parts, and the wear risk under the current lubrication state; The improved graph attention network algorithm automatically learns and emphasizes the mutual relationship and influence between different lubrication points in the mechanical equipment through the attention mechanism, which can identify the most critical parts for maintaining the ideal lubrication film thickness, thereby providing accurate basis for the formulation and adjustment of the lubrication strategy.

2. The method of claim 1, wherein The evaluation of the lubrication performance in S2 includes: Application of Arrhenius model: the Arrhenius model is used to calculate and predict the viscosity of the lubricating oil under different temperature conditions, which helps to evaluate the flow performance of the lubricating oil, and the calculation formula is: ； wherein represents the viscosity of the lubricating oil at a temperature is the viscosity at a reference temperature, is the activation energy, is the gas constant, is the temperature of the lubricating oil;​ Application of Barus model: the Barus model is used to evaluate the change of viscosity of the lubricating oil under different pressures, so as to judge the lubrication performance of the lubricating oil under high load conditions, and the calculation formula is: ； wherein is the viscosity of the lubricating oil at a pressure of P, is the viscosity at standard atmospheric pressure, is the pressure coefficient of the lubricating oil, is the pressure of the lubricating oil; Performance evaluation: Based on the calculation results of the Arrhenius model and the Barus model, the flow performance and lubrication performance of the lubricating oil are comprehensively evaluated, considering the relationship between the viscosity of the lubricating oil and the temperature and pressure changes, to determine whether the lubricating oil can maintain the lubrication of the equipment components, prevent wear and reduce the risk of overheating under working conditions.

3. The method of claim 2, wherein The dynamic lubrication film thickness monitoring and adjustment in S3 includes: Lubrication film thickness monitoring: installing a film thickness sensor in the lubrication contact area of the mechanical equipment, the film thickness sensor monitors the thickness of the lubrication film in real time, the film thickness sensor includes an optical sensor, a capacitive sensor or an ultrasonic sensor; Data analysis and processing: analyzing the collected lubrication film thickness data, using an improved policy gradient method to evaluate whether the thickness of the lubrication film is within the ideal range, the improved policy gradient method determines the optimal thickness of the lubrication film based on the operating parameters of the mechanical equipment and the physical properties of the lubricating oil; Automatic adjustment of lubricating oil supply: automatically adjusting the supply of lubricating oil according to the results of data analysis.

4. The method of claim 3, wherein The improved policy gradient method includes: Model definition: policy represents the probability of selecting action in a given state , is a policy parameter, state includes operating parameters of the mechanical equipment and physical properties of the lubricating oil, action is the adjusted lubricating oil supply amount, reward function is used to evaluate the effect of taking action in state , i.e. the ability to maintain the ideal lubricating film thickness; Improved policy gradient formula: the improved policy gradient method for policy parameters is updated, and the calculation formula is ； wherein, is a performance function, denotes the expected value under the policy; Reward function design: the reward function is designed to encourage the policy to reduce the gap between the actual lubrication film thickness and the ideal thickness, the calculation formula is: ； in, Taking action The thickness of the lubricating film was measured later. It is the ideal thickness of the lubricating film; Parameter update: At each iteration, the policy parameters are updated by a gradient ascent method, computed as: ； wherein is a learning rate, a positive number predetermined in advance, which controls the step size of the parameter update.

5. The method of claim 4, wherein the step of determining the reliability of the industrial equipment lubrication system comprises the step of: The automatic adjustment of the supply of lubricating oil is realized by controlling the speed of the lubricating oil pump or adjusting the opening of the oil supply valve, if the lubrication film thickness is lower than the optimal range, the supply of lubricating oil will be increased, otherwise, if the lubrication film thickness is higher than the optimal range, the supply of lubricating oil will be reduced. ​ 6. The method of claim 5, wherein the step of determining the reliability of the industrial equipment lubrication system comprises the step of: The improved graph attention network algorithm includes: ​ Compute attention coefficients: for each pair of nodes and , the attention coefficient determines the importance of node when updating the representation of node , computed as: ； wherein, is an unnormalized attention coefficient between nodes and , is a nonlinear activation function, is an attention mechanism parameter, is a weight matrix, are input feature vectors of nodes and , respectively, is a concatenation operation that concatenates the feature vectors of two nodes together; Normalized attention weights: over all nodes to node The attention coefficients are normalized, calculated as follows: ； wherein, is a normalized attention weight representing the contribution of node when updating the feature representation of node , is a set of neighbor nodes of node . Node feature update: update the feature representation of each node by weighting the feature vectors of neighboring nodes, the calculation formula is: ； wherein, is a node according to the attention weight updated feature representation, is an activation function.

7. The method of claim 6, wherein the step of determining the reliability of the industrial equipment lubrication system comprises the step of: The determination of reliability level in S5 includes: ​ determining a reliability index: based on the evaluation result of the lubrication effect, calculating a reliability index of the lubricating oil The reliability index of the lubricating oil is a comprehensive score, reflecting the performance of the lubricating oil in maintaining the lubricating film thickness, preventing wear and keeping chemical stability, and the calculation formula is: ； wherein, are weight coefficients, respectively reflecting the contribution degree of the lubricating film thickness, the temperature stability, the pressure stability and the anti-wear performance to the total reliability index, is the lubricating film thickness index, is the stability index of the lubricating oil temperature, is the stability index of the lubricating oil pressure, is the anti-wear performance index, is a normalization function; Pre-set reliability level standard: set a pre-set reliability level standard, each level standard corresponds to a different range of lubricating oil performance; Comparison and determination of level: compare the calculated lubricating oil reliability index with the pre-set reliability level standard to determine the reliability level of the current lubricating oil; Evaluate the overall reliability of the lubrication of the mechanical equipment: according to the reliability level of the lubricating oil, evaluate the overall reliability of the lubrication of the mechanical equipment, if the reliability level of the lubricating oil used by all components meets or exceeds the pre-set minimum requirement, the overall lubrication reliability of the mechanical equipment is achieved.

Images