Mechanical lubrication equipment fault intelligent monitoring method based on industrial big data

Abstract

The invention relates to the technical field of mechanical lubricating equipment, in particular to a mechanical lubricating equipment fault intelligent monitoring method based on industrial big data, which comprises the following steps: S1, lubricating equipment parameters and lubricating oil parameters are acquired, and the acquired lubricating equipment parameters comprise lubricating equipment shell temperature WDsb and lubricating equipment vibration amplitude ZFDsb; the collected lubricating oil parameters comprise the lubricating oil temperature WDrhy, the lubricating oil viscosity NDrhy and the lubricating oil flow rate LDLrhy; s2, analyzing and processing the shell temperature WDsb of the lubricating equipment and the vibration amplitude ZFDsb of the lubricating equipment to generate a stability coefficient XSsb of the lubricating equipment, and analyzing and processing the temperature WDrhy of the lubricating oil, the viscosity NDrhy of the lubricating oil and the flow rate LDLrhy of the lubricating oil to generate a quality coefficient XSrhy of the lubricating oil. According to the method, the shell temperature WDsb, the vibration amplitude ZFDsb, the lubricating oil temperature WDrhy, the lubricating oil viscosity NDrhy and the lubricating oil flow rate LDLrhy of the lubricating equipment are collected, and related parameters are comprehensively analyzed and processed, so that the fault judgment precision of the mechanical lubricating equipment is improved.

Description

Technical Field

[0001] This invention relates to the field of mechanical lubrication equipment technology, specifically to an intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data. Background Technology

[0002] Mechanical lubrication equipment refers to devices used to lubricate mechanical equipment, and there is a close relationship between them. Specifically, mechanical lubrication equipment has a significant impact on the normal operation and lifespan of mechanical equipment, while the performance and reliability of mechanical equipment depend on the effective operation of mechanical lubrication equipment. The main task of mechanical lubrication equipment is to provide the correct lubricant (such as lubricating oil or grease) to reduce friction and wear between mechanical parts. Lubrication equipment reduces friction, wear, and heat generation by forming a lubricating film between mechanical parts, thereby extending the service life of mechanical equipment. Mechanical lubrication equipment can play multiple roles in mechanical equipment, such as controlling friction and wear, controlling heat and energy, sealing and protecting, and fault detection and prediction. Therefore, mechanical lubrication equipment plays a vital role in the operation of mechanical equipment. By providing lubrication, sealing, and protection functions, it can reduce friction and wear, control heat and energy, extend the life of mechanical equipment, and improve the reliability and performance of the equipment.

[0003] In the prior art, the intelligent monitoring method for lubrication equipment faults based on industrial big data, with application number CN114941796A, includes: real-time acquisition of filter data, oil pump data, and oil data of the lubrication equipment under test; obtaining the degree of sedimentation in the filter through the filter data, and obtaining real-time quality indicators of the oil based on oil temperature, sedimentation degree, and cleanliness; obtaining the working status of the lubrication equipment through changes in oil height, quality indicators, pressure data, and oil pump temperature within a preset time; obtaining standard data and standard working status of standard equipment of the same model in the database within a preset time, obtaining the working difference between the lubrication equipment under test and the standard equipment, and issuing a fault warning when the working difference exceeds a difference threshold.

[0004] However, the following shortcomings still exist: As can be seen from the above statement, when monitoring mechanical lubrication equipment, only the parameters of the filter and oil inside the mechanical lubrication equipment are monitored. The failure of the mechanical lubrication equipment is judged based on the changes in the filter and oil parameters, but the influence of the outer shell temperature and vibration amplitude of the lubrication equipment on the mechanical lubrication equipment is not considered, which leads to a decrease in the accuracy of the judgment of lubrication equipment failure. Summary of the Invention

[0005] In view of this, the purpose of this invention is to propose an intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data. This method addresses the problem that existing technologies only monitor the parameters of the filters and oil inside the mechanical lubrication equipment and determine whether the equipment is faulty based on changes in these parameters. However, the methods do not consider the influence of the equipment's casing temperature and vibration amplitude. Relying solely on changes in the parameters of the filters and oil inside the equipment leads to decreased accuracy in determining faults.

[0006] To achieve the above objectives, this invention provides an intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data, comprising the following steps:

[0007] S1. Collect lubrication equipment parameters and lubricating oil parameters. The collected lubrication equipment parameters include the lubrication equipment housing temperature WDsb and the lubrication equipment vibration amplitude ZFDsb. The collected lubricating oil parameters include the lubricating oil temperature WDrhy, the lubricating oil viscosity NDrhy, and the lubricating oil flow rate LDLrhy.

[0008] S2. Analyze and process the housing temperature WDsb and vibration amplitude ZFDsb of the lubrication equipment to generate the stability coefficient XSsb of the lubrication equipment. Analyze and process the lubricating oil temperature WDrhy, lubricating oil viscosity NDrhy, and lubricating oil flow rate LDLrhy to generate the quality coefficient XSrhy of the lubricating oil.

[0009] S3. Analyze the stability coefficient XSsb of the lubrication equipment and the quality coefficient XSrhy of the lubricating oil to generate a fault risk level model for evaluating the fault risk level of the lubrication equipment. Then, use data from industrial big data to verify the parameters of the fault risk level model and generate a fault risk level evaluation model.

[0010] S4. Analyze the stability coefficient XSsb and the lubricating oil quality coefficient XSrhy using the fault risk level evaluation model to generate a fault risk level coefficient. Compare the fault risk level coefficient with different level evaluation thresholds to determine the fault level of the lubrication equipment and issue different warning signals according to the fault level.

[0011] Furthermore, the temperature of the lubrication equipment housing WDsb is measured by an infrared thermometer, and the vibration amplitude ZFDsb of the lubrication equipment is measured by a displacement sensor.

[0012] Furthermore, the lubricating oil temperature WDrhy is measured by an infrared thermometer, the lubricating oil viscosity NDrhy is measured by a temperature method, and the lubricating oil flow rate LDLrhy is measured by a pressure difference measurement method.

[0013] Furthermore, the parameters of the lubrication equipment and the lubricating oil are analyzed and processed to generate the stability coefficient of the lubrication equipment and the quality coefficient of the lubricating oil, respectively. The process of generating the stability coefficient of the lubrication equipment is as follows: Take N identical lubrication devices, where N is an integer greater than 1, and obtain the shell temperature and vibration amplitude of the lubrication equipment.

[0014] WDsb = [WDsb1, WDsb2, ..., WDsb] i …WDsb N ]

[0015] ZFDsb=[ZFDsb1, ZFDsb2…ZFDsb i …ZFDsb N ]

[0016] Among them, WDsb i Let ZFDsb be the temperature value of the i-th lubrication device. i Let i be the amplitude value of the i-th lubrication device;

[0017] The average values ​​of the casing temperature wd and vibration amplitude zfd of N lubrication devices are labeled as PJWDsb and PJZFDsb, respectively, and are obtained by the following formula:

[0018]

[0019]

[0020] The collected PJWDsb and PJZFDsb values ​​were dimensionless, and the parameters were correlated to generate the stability coefficient XSsb of the lubrication equipment, based on the following formula:

[0021]

[0022] Wherein, the parameters are: α is the weighting factor coefficient of the average temperature of the lubrication equipment casing, 0.2≤α≤0.5; β is the weighting factor coefficient of the average vibration amplitude of the lubrication equipment, 0.1≤β≤0.3; δ is the exponential factor of the average temperature of the lubrication equipment casing, 2≤δ≤4; ε is the exponential factor of the average vibration amplitude of the lubrication equipment, 2≤ε≤4; and C1 is the constant correction coefficient.

[0023] Furthermore, the lubricating oil temperature (WDrhy), lubricating oil viscosity (NDrhy), and lubricating oil flow rate (LDLrhy) are obtained. These parameters are then dimensionless, and the quality coefficient of the lubricating oil (XSrhy) is generated based on the following formula:

[0024]

[0025] Wherein, the parameters are: θ is the weighting factor coefficient of lubricating oil temperature, 0.3≤θ≤0.5, e is the base of the natural logarithm (approximately equal to 2.718), σ is the parameter of lubricating oil temperature, 2≤σ≤4, μ is the weighting factor coefficient of lubricating oil viscosity, 0.2≤μ≤0.4, ω is the parameter of lubricating oil viscosity, 2≤ω≤4, τ is the weighting factor coefficient of lubricating oil flow rate, 0.2≤τ≤0.5, λ is the parameter of lubricating oil flow rate, 2≤λ≤4, and C2 is a constant correction coefficient.

[0026] Furthermore, by analyzing the stability coefficient XSsb of the lubrication equipment and the quality coefficient XSrhy of the lubricating oil, the resulting failure risk level model is as follows:

[0027] The aforementioned fault risk level model: γ is an unknown.

[0028]

[0029] Wherein, the parameter ρ represents the weighting factor coefficient of the stability coefficient of the lubrication equipment, 0.2≤ρ≤0.5. The weighting factor coefficient for the quality coefficient of lubricating oil. FDJsb is the fault risk level coefficient, γ is the unknown regression coefficient, also known as the constant term or offset, and C3 is the constant correction coefficient.

[0030] The fault risk level evaluation model is constructed by using data from industrial big data to verify the parameter γ in the fault risk level model:

[0031]

[0032] Where γ1 is the verified value of γ.

[0033] Furthermore, the specific steps for validating the parameters in the fault risk level model using data from industrial big data include:

[0034] The reference lubrication equipment parameters and reference lubricating oil parameters are obtained from industrial big data. The reference lubrication equipment parameters include the reference lubrication equipment housing temperature WDsc, the reference lubrication equipment vibration amplitude ZFDsc, and the reference fault risk level coefficient FDJc. The lubricating oil parameters include the reference lubricating oil temperature WDrc, the reference lubricating oil viscosity NDrc, and the reference lubricating oil flow rate LDLrc.

[0035] Analysis and processing will be carried out based on the reference lubricating equipment housing temperature WDsc and the reference lubricating equipment vibration amplitude ZFDsc to generate the reference stability coefficient XSbc of the lubricating equipment. Analysis and processing will be carried out on the reference lubricating oil temperature WDrc, the reference lubricating oil viscosity NDrc, and the reference lubricating oil flow rate LDLrc to generate the reference quality coefficient XSrc of the lubricating oil;

[0036] The reference stability coefficient XSbc, the reference quality coefficient XSrc, and the reference failure risk level coefficient FDJc will be brought into the failure risk level model to calculate the regression coefficient γ. The formula based on is:

[0037]

[0038] Furthermore, the specific parameters of the obtained reference failure risk level coefficient FDJc are manually calibrated according to the reference lubricating equipment housing temperature WDsc, the reference lubricating equipment vibration amplitude ZFDsc, and in combination with the failure conditions of the lubricating equipment in the industrial big data.

[0039] Furthermore, the failure level of the mechanical lubricating equipment is judged according to the calculated failure risk level model of the lubricating equipment; when the failure risk level model of the lubricating equipment is low risk, 0.3FDB < FDJsb ≤ 0.5FDB (FDB is the failure risk level calibration threshold), a first-level alarm is issued. The first-level alarm includes that the lubricating equipment housing temperature WDsb is relatively high or the lubricating equipment vibration amplitude ZFDsb is relatively high, the lubricating oil temperature WDrhy or the lubricating oil viscosity NDrhy is relatively low, and the lubricating oil flow rate LDLrhy is relatively high;

[0040] When the failure risk level model of the lubricating equipment is medium risk, 0.1FDB < FDJsb ≤ 0.3FDB, a second-level alarm is issued. The second-level alarm includes that the lubricating equipment housing temperature WDsb is high or the lubricating equipment vibration amplitude ZFDsb is high, the lubricating oil temperature WDrhy or the lubricating oil viscosity NDrhy is low, and the lubricating oil flow rate LDLrhy is high;

[0041] When the failure risk level model of the lubricating equipment is high risk, 0 < FDJsb ≤ 0.1FDB, a third-level alarm is issued. The third-level alarm includes that the lubricating equipment housing temperature WDsb is very high or the lubricating equipment vibration amplitude ZFDsb is very high, the lubricating oil temperature WDrhy or the lubricating oil viscosity NDrhy is very low, and the lubricating oil flow rate LDLrhy is very high.

[0042] The beneficial effects of the present invention:

[0043] This invention generates a stability coefficient XSsb for the lubrication equipment by collecting the equipment's casing temperature WDsb and vibration amplitude ZFDsb. It also generates a quality coefficient XSrhy for the lubricating oil by collecting the lubricating oil temperature WDrhy, lubricating oil viscosity NDrhy, and lubricating oil flow rate LDLrhy. Furthermore, it analyzes the correlation between the stability coefficient XSsb and the quality coefficient XSrhy to generate a fault risk level model for evaluating the fault risk level of the lubrication equipment. The parameters in the fault risk level model are validated using industrial big data, resulting in a fault risk level evaluation model. Based on this model, the fault level of the mechanical lubrication equipment is determined. Therefore, by collecting and comprehensively analyzing the relevant parameters—including the lubricating equipment casing temperature WDsb, vibration amplitude ZFDsb, lubricating oil temperature WDrhy, lubricating oil viscosity NDrhy, and lubricating oil flow rate LDLrhy—the accuracy of diagnosing mechanical lubrication equipment faults is improved. Attached Figure Description

[0044] 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.

[0045] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0046] 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.

[0047] 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.

[0048] Example 1

[0049] like Figure 1 As shown, this invention provides an embodiment of an intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data, comprising:

[0050] S1. Collect lubrication equipment parameters and lubricating oil parameters. The collected lubrication equipment parameters include the lubrication equipment housing temperature WDsb and the lubrication equipment vibration amplitude ZFDsb. The collected lubricating oil parameters include the lubricating oil temperature WDrhy, the lubricating oil viscosity NDrhy, and the lubricating oil flow rate LDLrhy.

[0051] S2. Analyze and process the housing temperature WDsb and vibration amplitude ZFDsb of the lubrication equipment to generate the stability coefficient XSsb of the lubrication equipment. Analyze and process the lubricating oil temperature WDrhy, lubricating oil viscosity NDrhy, and lubricating oil flow rate LDLrhy to generate the quality coefficient XSrhy of the lubricating oil.

[0052] S3. Analyze the stability coefficient XSsb of the lubrication equipment and the quality coefficient XSrhy of the lubricating oil to generate a fault risk level model for evaluating the fault risk level of the lubrication equipment. Then, use data from industrial big data to verify the parameters of the fault risk level model and generate a fault risk level evaluation model.

[0053] S4. Analyze the stability coefficient XSsb and the lubricating oil quality coefficient XSrhy using the fault risk level evaluation model to generate a fault risk level coefficient. Compare the fault risk level coefficient with different level evaluation thresholds to determine the fault level of the lubrication equipment and issue different warning signals according to the fault level.

[0054] Among them, the higher the temperature of the lubrication equipment casing WDsb and the greater the vibration amplitude ZFDsb of the lubrication equipment, the worse the stability of the lubrication equipment, and vice versa.

[0055] Among them, the higher the lubricating oil temperature (WDrhyUI), the greater the lubricating oil viscosity (NDrhy), and the lower the lubricating oil flow rate (LDLrhy), the higher the quality of the lubricating oil, and vice versa.

[0056] An increase in the WDsb of the lubricated equipment casing temperature usually indicates poor lubrication, meaning the oil film cannot effectively prevent direct contact and friction between metal surfaces. This leads to increased friction and wear, which in turn exacerbates heat generation and temperature rise in the equipment. Lubricating oil at the appropriate temperature can effectively remove the heat generated by the equipment during circulation and cooling, keeping the equipment operating temperature within the normal range. If the cooling effect of the lubricating oil is poor or there are problems with the lubrication system, the casing temperature will rise. Therefore, assuming other performance parameters of the lubricated equipment are the same, the higher the casing temperature, the lower the equipment's safety performance and stability; WDsb and the stability of the lubricated equipment are negatively correlated.

[0057] Methods for measuring the WDsb temperature of lubricated equipment housings:

[0058] Thermocouples or temperature sensors: When measuring the housing temperature of lubrication equipment, thermocouples or temperature sensors can be directly installed on or near the housing surface of the lubrication equipment and output the temperature reading of the equipment through an electrical signal.

[0059] Infrared thermometer: It measures temperature by detecting the infrared radiation emitted by the housing of the lubrication equipment. Using an infrared thermometer, the temperature of different locations on the lubrication equipment can be obtained quickly and conveniently without direct contact with the equipment surface.

[0060] In summary, different measurement methods are suitable for different application scenarios and requirements. In practical applications, the most suitable method can be selected based on the convenience and accuracy of the data. Here, an infrared thermometer is preferred for measuring the WDsb temperature of the lubrication equipment casing.

[0061] The vibration amplitude (ZFDsb) of lubrication equipment can be used to assess the quality of lubrication. Excessively high vibration amplitude may indicate insufficient or uneven lubrication, leading to rupture of the lubrication film or excessive gaps, increasing friction and wear, and reducing equipment lifespan. By monitoring and analyzing vibration amplitude, the quality of lubrication can be evaluated, and corresponding measures can be taken to improve lubrication. Therefore, assuming other performance parameters of the lubrication equipment are consistent, a higher vibration amplitude is negatively correlated with lower equipment safety and stability.

[0062] Method for measuring the vibration amplitude ZFDsb of lubrication equipment:

[0063] Accelerometer: An accelerometer is fixed on or near the vibrating surface of the lubrication equipment. The sensor measures the vibration amplitude by converting the vibration into an electrical signal. Single-axis or multi-axis accelerometers can be used to monitor and record vibration data in real time.

[0064] Speed ​​sensor: The vibration amplitude is calculated by measuring the speed change of the vibrating surface of the lubrication equipment. The speed sensor is usually placed on the vibrating surface of the lubrication equipment and generates an electrical signal that is proportional to the vibration amplitude.

[0065] Displacement sensors: Displacement sensors typically employ a non-contact measurement principle. By measuring the displacement change of a vibrating surface, the amplitude of the vibration can be determined. Examples include laser displacement sensors or capacitive displacement sensors.

[0066] In summary, different measurement methods are suitable for different application scenarios and requirements. In practical applications, the most suitable method can be selected based on the convenience and accuracy of the data. Here, a displacement sensor is preferred for measuring the vibration amplitude ZFDsb of lubrication equipment.

[0067] When measuring the vibration amplitude of lubrication equipment, the following precautions should also be considered:

[0068] The sensor should be installed in a location that represents the vibration state of the equipment; the accuracy and sensitivity of the sensor should be calibrated and verified regularly to ensure that the sensor measurement results are reliable and accurate; appropriate sensors and measuring equipment should be selected according to the frequency range of interest, as vibrations in different frequency ranges may require different types or specifications of sensors for measurement.

[0069] Lubricating oil temperature (WDrhy) can be used to assess insufficient lubrication. A high lubricating oil temperature indicates inadequate lubrication, meaning the lubricating oil cannot effectively reduce friction and wear, leading to overheating of the equipment's friction surfaces. This can be caused by factors such as oil pump failure, insufficient oil supply from the pump, oil passage blockage, or pump pressure regulation failure in the lubrication system. Therefore, assuming other lubricating oil performance parameters are the same, a higher lubricating oil temperature generally indicates poorer lubricating oil quality, showing a negative correlation.

[0070] Methods for measuring lubricating oil temperature (WDrhy):

[0071] Thermometer measurement: Various types of thermometers can be used, such as glass thermometers, electronic thermometers, or infrared thermometers. Place the thermometer in lubricating oil, ensuring the sensor part is completely immersed in the oil, wait for a period of time for the temperature to stabilize, and then read the temperature value.

[0072] Temperature sensor: A specialized temperature sensor (such as a thermocouple, resistance temperature detector, or thermistor) is used to measure the temperature of the lubricating oil by connecting it to the lubrication system. The sensor can be directly mounted on the equipment or connected to the location where the lubricating oil flows through a pipeline. The electrical signal output by the sensor can be converted into a temperature value by an instrument or control system for monitoring and recording.

[0073] Infrared thermometer: An infrared thermometer can directly measure the temperature of lubricating oil by aiming at the surface of the equipment. Before measurement, it is necessary to ensure that there are no obstructions or reflective objects between the thermometer and the lubricating oil to obtain an accurate temperature reading.

[0074] In summary, different measurement methods are suitable for different application scenarios and requirements. In practical applications, the most suitable method can be selected based on the convenience and accuracy of the data. Here, an infrared thermometer is preferred for measuring lubricating oil temperature (WDrhy).

[0075] An increase in lubricating oil viscosity (NDrhy) means that the friction surfaces of equipment cannot be effectively lubricated. High-viscosity lubricating oil is difficult to form a film on the contact surface and cannot effectively reduce friction and wear, leading to increased equipment friction and wear, which may cause equipment failure. It also affects the forced circulation effect of the lubrication system, as the oil pump in the lubrication system cannot effectively deliver high-viscosity lubricating oil to the parts that need lubrication, affecting the normal operation of the lubrication system. Therefore, when other performance parameters of the lubricating oil are the same, the higher the lubricating oil viscosity, the worse the quality of the lubricating oil, showing a negative correlation.

[0076] Methods for measuring the viscosity (NDrhy) of lubricating oil:

[0077] Temperature method: This method utilizes the effect of temperature on the viscosity of lubricating oil for measurement. For example, a viscometer, such as a commonly used kinematic viscometer, provides readings based on the viscosity-temperature relationship curve of the lubricating oil.

[0078] Absolute viscosity method: This method uses an absolute viscosity measuring instrument to measure the resistance of a lubricating oil sample. It employs equipment such as a rotational viscometer and a vibratory viscometer to determine the resistance of the lubricating oil under given flow conditions.

[0079] Indirect measurement method: This method infers the viscosity of a lubricating oil based on the measurement results of other lubricating oil performance parameters. For example, it uses flash point or pour point tests, combined with empirical formulas or tables, to calculate the viscosity value of the lubricating oil.

[0080] Optical method: This method uses optical sensors to measure the viscosity of lubricating oil. It obtains viscosity data by measuring the flow rate or deformation of the lubricating oil within an optical device.

[0081] In summary, different measurement methods are suitable for different application scenarios and requirements. In practical applications, the most suitable method can be selected based on the convenience and accuracy of the data. Here, the temperature method for measuring lubricating oil viscosity (NDrhy) is preferred.

[0082] Low lubricating oil flow rate means that the friction surfaces of equipment cannot be adequately lubricated. When the flow rate is low, the lubricating oil cannot effectively form a lubricating film on the contact surface, leading to blockages in the lubrication system. This affects the flow and delivery of the lubricating oil, and the blockage in the oil passages results in insufficient lubrication of equipment components, increasing friction and wear, and causing equipment failure. Therefore, assuming other performance parameters of the lubricating oil are the same, a lower flow rate indicates a lower quality lubricating oil, showing a positive correlation.

[0083] Methods for measuring the flow rate (LDLrhy) of lubricating oil:

[0084] Flow meter measurement: Flow meters can be used to directly measure the flow rate of lubricating oil. Common liquid flow meters include turbine flow meters, vortex flow meters, electromagnetic flow meters, and positive AC flow meters. These flow meters are usually installed on the pipelines of lubrication system equipment, and measure the flow rate by sensing the flow of lubricating oil through sensors or instruments, displaying or recording the results in the form of volume or mass.

[0085] Differential pressure measurement method: When lubricating oil flows through pipelines, a certain pressure loss occurs. By measuring the pressure difference at different locations in the lubrication system equipment, the flow rate of the lubricating oil can be indirectly inferred. Common differential pressure measurement methods include pressure sensors and differential pressure gauges. By calculating the flow rate of lubricating oil measured through the pressure difference, the flow rate of the lubricating oil can be estimated.

[0086] In summary, different measurement methods are suitable for different application scenarios and requirements. In practical applications, the most suitable method can be selected based on the convenience and accuracy of the data. Here, the pressure difference measurement method is preferred for measuring the lubricating oil flow rate (LDLrhy).

[0087] The parameters of the lubrication equipment and the lubricating oil are analyzed and processed to generate the stability coefficient of the lubrication equipment and the quality coefficient of the lubricating oil, respectively.

[0088] The preprocessing procedure for the stability coefficient of lubrication equipment is as follows: Take N identical lubrication devices, where N is an integer greater than 1, and obtain the shell temperature and vibration amplitude of the lubrication devices:

[0089] WDsb = [WDsb1, WDsb2, ..., WDsb] i …WDsb N ]

[0090] ZFDsb=[ZFDsb1, ZFDsb2…ZFDsb i …ZFDsb N ]

[0091] Among them, WDsb i Let ZFDsb be the temperature value of the i-th lubrication device. iLet i be the amplitude value of the i-th lubrication device;

[0092] The average values ​​of the casing temperature wd and vibration amplitude zfd of N lubrication devices are labeled as PJWDsb and PJZFDsb, respectively, and are obtained by the following formula:

[0093]

[0094]

[0095] The collected PJWDsb and PJZFDsb values ​​were dimensionless, and the parameters were correlated to generate the stability coefficient XSsb of the lubrication equipment, based on the following formula:

[0096]

[0097] Wherein, the parameters are: α is the weighting factor coefficient of the average temperature of the lubrication equipment casing, 0.2≤α≤0.5; β is the weighting factor coefficient of the average vibration amplitude of the lubrication equipment, 0.1≤β≤0.3; δ is the exponential factor of the average temperature of the lubrication equipment casing, 2≤δ≤4; ε is the exponential factor of the average vibration amplitude of the lubrication equipment, 2≤ε≤4; and C1 is the constant correction coefficient.

[0098] As can be seen from the above formula, when PJWDsb and PJZFDsb are higher, the stability coefficient XSsb of the lubrication equipment is lower, indicating that PJWDsb, PJZFDsb and XSsb are negatively correlated. The weight factor coefficient in the formula is used to balance the proportion of each data in the formula, thereby promoting the accuracy of the calculation results.

[0099] The lubricating oil temperature (WDrhy), lubricating oil viscosity (NDrhy), and lubricating oil flow rate (LDLrhy) are obtained. These parameters are then dimensionless, and the quality coefficient (XSrhy) of the lubricating oil is generated based on the following formula:

[0100]

[0101] Wherein, the parameters are: θ is the weighting factor coefficient of lubricating oil temperature, 0.3≤θ≤0.5, e is the base of the natural logarithm (approximately equal to 2.718), σ is the parameter of lubricating oil temperature, 2≤σ≤4, μ is the weighting factor coefficient of lubricating oil viscosity, 0.2≤μ≤0.4, ω is the parameter of lubricating oil viscosity, 2≤ω≤4, τ is the weighting factor coefficient of lubricating oil flow rate, 0.2≤τ≤0.5, λ is the parameter of lubricating oil flow rate, 2≤λ≤4, and C2 is a constant correction coefficient.

[0102] From the above formula, we can see that within a certain range, when WDrhy is higher and NDrhy and LDLrhy are constant, the lubricating oil quality coefficient XSrhy is higher, indicating better lubricating oil quality, and vice versa. Similarly, when NDrhy is higher and WDrhy and LDLrhy are constant, the lubricating oil quality coefficient XSrhy is higher, indicating better lubricating oil quality, and vice versa. Conversely, when LDLrhy is higher and WDrhy and NDrhy are constant, the lubricating oil quality coefficient XSrhy is lower, indicating worse lubricating oil quality, and vice versa. Therefore, WDrhy, NDrhy, and XSrhy are positively correlated, while LDLrhy and XSrhy are negatively correlated.

[0103] By analyzing the stability coefficient XSsb of the lubrication equipment and the quality coefficient XSrhy of the lubricating oil, the resulting fault risk level model is as follows:

[0104] The aforementioned fault risk level model:

[0105]

[0106] Wherein, the parameter ρ represents the weighting factor coefficient of the stability coefficient of the lubrication equipment, 0.2≤ρ≤0.5. The weighting factor coefficient for the quality coefficient of lubricating oil. FDJsb is the failure risk level coefficient, γ is an unknown regression coefficient, also known as a constant term or offset. γ reflects the basic level of the failure risk level itself when the stability coefficient of the lubrication equipment and the quality coefficient of the lubricating oil have no effect. C3 is a constant correction coefficient.

[0107] The fault risk level evaluation model is constructed by using data from industrial big data to verify the parameter γ in the fault risk level model:

[0108]

[0109] Where γ1 is the verified value of γ.

[0110] The data includes known lubrication equipment housing temperature WDsb, vibration amplitude ZFDsb, lubricating oil temperature WDrhy, lubricating oil viscosity NDrhy, lubricating oil flow rate LDLrhy, and the content disclosed in this embodiment. The known lubrication equipment stability coefficient XSsb, lubricating oil quality coefficient XSrhy, and failure risk level FDJsb can be determined. Substituting these into the failure risk level model can verify γ = γ1. The data for verifying γ may be inconsistent for each group. The average value of γ for multiple groups can be calculated using the formula for the average.

[0111] The specific steps for validating the parameters in the fault risk level model using data from industrial big data include:

[0112] Obtain the reference lubrication equipment parameters and reference lubricant parameters in industrial big data. The obtained reference lubrication equipment parameters include the reference lubrication equipment shell temperature WDsc, the reference lubrication equipment vibration amplitude ZFDsc, and the reference fault risk level coefficient FDJc. The collected lubricant parameters include the reference lubricant temperature WDrc, the reference lubricant viscosity NDrc, and the reference lubricant flow rate LDLrc;

[0113] Analyze and process the reference lubrication equipment shell temperature WDsc and the reference lubrication equipment vibration amplitude ZFDsc to generate the reference stability coefficient XSbc of the lubrication equipment. Analyze and process the reference lubricant temperature WDrc, the reference lubricant viscosity NDrc, and the reference lubricant flow rate LDLrc to generate the reference quality coefficient XSrc of the lubricant;

[0114] Substitute the reference stability coefficient XSbc, the reference quality coefficient XSrc, and the reference fault risk level coefficient FDJc into the fault risk level model to calculate the regression coefficient γ. The formula is:

[0115]

[0116] Judge the level of mechanical lubrication equipment failure according to the fault risk level model of the lubrication equipment after calculation and processing;

[0117] When the fault risk level model of the lubrication equipment is low risk, 0.3FDB < FDJsb ≤ 0.5FDB (FDB is the fault risk level calibration threshold), issue a first-level alarm. The first-level alarm includes that the lubrication equipment shell temperature WDsb is relatively high or the lubrication equipment vibration amplitude ZFDsb is relatively high, the lubricant temperature WDrhy or the lubricant viscosity NDrhy is relatively low, and the lubricant flow rate LDLrhy is relatively high;

[0118] When the fault risk level model of the lubrication equipment is medium risk, 0.1FDB < FDJsb ≤ 0.3FDB, issue a second-level alarm. The second-level alarm includes that the lubrication equipment shell temperature WDsb is high or the lubrication equipment vibration amplitude ZFDsb is high, the lubricant temperature WDrhy or the lubricant viscosity NDrhy is low, and the lubricant flow rate LDLrhy is high;

[0119] When the fault risk level model of the lubrication equipment is high risk, 0 < FDJsb ≤ 0.1FDB, issue a third-level alarm. The third-level alarm includes that the lubrication equipment shell temperature WDsb is very high or the lubrication equipment vibration amplitude ZFDsb is very high, the lubricant temperature WDrhy or the lubricant viscosity NDrhy is very low, and the lubricant flow rate LDLrhy is very high.

[0120] It should be noted that high risk is higher than medium risk, and medium risk is higher than low risk. That is, the probability of lubrication equipment failure is greater for high-risk equipment than for medium-risk equipment, and greater for medium-risk equipment than for low-risk equipment.

[0121] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents. The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center containing one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive (SSD).

[0122] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0123] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0124] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division of a waterway underwater topography change analysis system and method. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0125] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0126] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0127] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0128] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0129] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for intelligent fault monitoring of mechanical lubrication equipment based on industrial big data, characterized in that, Includes the following steps: S1. Collect lubrication equipment parameters and lubricating oil parameters. The collected lubrication equipment parameters include the lubrication equipment housing temperature WDsb and the lubrication equipment vibration amplitude ZFDsb. The collected lubricating oil parameters include the lubricating oil temperature WDrhy, the lubricating oil viscosity NDrhy, and the lubricating oil flow rate LDLrhy. S2. Analyze and process the housing temperature WDsb and vibration amplitude ZFDsb of the lubrication equipment to generate the stability coefficient XSsb of the lubrication equipment. Analyze and process the lubricating oil temperature WDrhy, lubricating oil viscosity NDrhy, and lubricating oil flow rate LDLrhy to generate the quality coefficient XSrhy of the lubricating oil. S3. Analyze the stability coefficient XSsb of the lubrication equipment and the quality coefficient XSrhy of the lubricating oil to generate a fault risk level model for evaluating the fault risk level of the lubrication equipment. Then, use data from industrial big data to verify the parameters of the fault risk level model and generate a fault risk level evaluation model. S4. Analyze the stability coefficient XSsb and the lubricating oil quality coefficient XSrhy using the fault risk level evaluation model to generate a fault risk level coefficient. Compare the fault risk level coefficient with different level evaluation thresholds to determine the fault level of the lubrication equipment and issue different warning signals according to the fault level.

2. The intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data according to claim 1, characterized in that: The temperature of the lubrication equipment housing WDsb is measured by an infrared thermometer, and the vibration amplitude ZFDsb of the lubrication equipment is measured by a displacement sensor.

3. The intelligent monitoring method for mechanical lubrication equipment faults based on industrial big data according to claim 1, wherein the lubricating oil temperature WDrhy is measured by an infrared thermometer, the lubricating oil viscosity NDrhy is measured by a temperature method, and the lubricating oil flow rate LDLrhy is measured by a pressure difference measurement method.

4. The intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data according to claim 1, characterized in that: The parameters of the lubrication equipment and lubricating oil are analyzed and processed to generate the stability coefficient of the lubrication equipment and the quality coefficient of the lubricating oil, respectively. The process of generating the stability coefficient of the lubrication equipment is as follows: Take N identical lubrication devices, where N is an integer greater than 1, and obtain the shell temperature and vibration amplitude of the lubrication equipment. WDsb=[WDsb1、WDsb2…WDsb i …WDsb N ] ZFDsb=[ZFDsb1、ZFDsb2…ZFDsb i …ZFDsb N ] Among them, WDsb i Let ZFDsb be the temperature value of the i-th lubrication device. i Let i be the amplitude value of the i-th lubrication device; The average values ​​of the casing temperature wd and vibration amplitude zfd of N lubrication devices are labeled as PJWDsb and PJZFDsb, respectively, and are obtained by the following formula: The collected PJWDsb and PJZFDsb values ​​were dimensionless, and the parameters were correlated to generate the stability coefficient XSsb of the lubrication equipment, based on the following formula: Wherein, the parameters are: α is the weighting factor coefficient of the average temperature of the lubrication equipment casing, 0.2≤α≤0.5; β is the weighting factor coefficient of the average vibration amplitude of the lubrication equipment, 0.1≤β≤0.3; δ is the exponential factor of the average temperature of the lubrication equipment casing, 2≤δ≤4; ε is the exponential factor of the average vibration amplitude of the lubrication equipment, 2≤ε≤4; and C1 is the constant correction coefficient.

5. The intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data according to claim 4, characterized in that: The lubricating oil temperature (WDrhy), lubricating oil viscosity (NDrhy), and lubricating oil flow rate (LDLrhy) are obtained. These parameters are then dimensionless, and the quality coefficient (XSrhy) of the lubricating oil is generated based on the following formula: Wherein, the parameters are: θ is the weighting factor coefficient of lubricating oil temperature, 0.3≤θ≤0.5, e is the base of the natural logarithm (approximately equal to 2.718), σ is the parameter of lubricating oil temperature, 2≤σ≤4, μ is the weighting factor coefficient of lubricating oil viscosity, 0.2≤μ≤0.4, ω is the parameter of lubricating oil viscosity, 2≤ω≤4, τ is the weighting factor coefficient of lubricating oil flow rate, 0.2≤τ≤0.5, λ is the parameter of lubricating oil flow rate, 2≤λ≤4, and C2 is a constant correction coefficient.

6. The intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data according to claim 5, characterized in that: By analyzing the stability coefficient XSsb of the lubrication equipment and the quality coefficient XSrhy of the lubricating oil, the resulting fault risk level model is as follows: The aforementioned fault risk level model: Wherein, the parameter ρ represents the weighting factor coefficient of the stability coefficient of the lubrication equipment, 0.2≤ρ≤0.

5. The weighting factor coefficient for the quality coefficient of lubricating oil. FDJsb is the fault risk level coefficient, γ is the unknown regression coefficient, also known as the constant term or offset, and C3 is the constant correction coefficient. The fault risk level evaluation model is constructed by using data from industrial big data to verify the parameter γ in the fault risk level model: Where γ1 is the verified value of γ.

7. The intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data according to claim 6, characterized in that: The specific steps for validating the parameters in the fault risk level model using data from industrial big data include: The reference lubrication equipment parameters and reference lubricating oil parameters are obtained from industrial big data. The reference lubrication equipment parameters include the reference lubrication equipment housing temperature WDsc, the reference lubrication equipment vibration amplitude ZFDsc, and the reference fault risk level coefficient FDJc. The lubricating oil parameters include the reference lubricating oil temperature WDrc, the reference lubricating oil viscosity NDrc, and the reference lubricating oil flow rate LDLrc. The reference lubrication equipment housing temperature WDsc and the reference lubrication equipment vibration amplitude ZFDsc are analyzed and processed to generate the reference stability coefficient XSbc of the lubrication equipment. The reference lubricating oil temperature WDrc, the reference lubricating oil viscosity NDrc, and the reference lubricating oil flow rate LDLrc are analyzed and processed to generate the reference quality coefficient XSrc of the lubricating oil. The reference stability coefficient XSbc, reference quality coefficient XSrc, and reference failure risk level coefficient FDJc are substituted into the failure risk level model to calculate the regression coefficient γ. The formula used is as follows:

8. The intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data according to claim 7, characterized in that: The specific parameters of the obtained reference fault risk level coefficient FDJc are manually calibrated based on the reference lubrication equipment shell temperature WDsc, the reference lubrication equipment vibration amplitude ZFDsc, and the fault status of lubrication equipment in industrial big data.

9. The intelligent fault monitoring method for mechanical lubrication equipment based on industrial big data according to claim 6, characterized in that: The level of mechanical lubrication equipment failure is determined based on the calculated failure risk level model of the lubrication equipment. When the failure risk level model of the lubrication equipment is a low risk, 0.3FDB < FDJsb ≤ 0.5FDB (FDB is the calibration threshold of the failure risk level), a first-level alarm is issued. The first-level alarm includes that the temperature WDsb of the lubrication equipment shell is relatively high or the vibration amplitude ZFDsb of the lubrication equipment is relatively high, the temperature WDrhy of the lubricating oil or the viscosity NDrhy of the lubricating oil is relatively low, and the flow rate LDLrhy of the lubricating oil is relatively high; When the failure risk level model of the lubrication equipment is a medium risk, 0.1FDB < FDJsb ≤ 0.3FDB, a second-level alarm is issued. The second-level alarm includes that the temperature WDsb of the lubrication equipment shell is high or the vibration amplitude ZFDsb of the lubrication equipment is high, the temperature WDrhy of the lubricating oil or the viscosity NDrhy of the lubricating oil is low, and the flow rate LDLrhy of the lubricating oil is high; When the failure risk level model of the lubrication equipment is a high risk, 0 < FDJsb ≤ 0.1FDB, a third-level alarm is issued. The third-level alarm includes that the temperature WDsb of the lubrication equipment shell is very high or the vibration amplitude ZFDsb of the lubrication equipment is very high, the temperature WDrhy of the lubricating oil or the viscosity NDrhy of the lubricating oil is very low, and the flow rate LDLrhy of the lubricating oil is very high.

Images