Intelligent lubricating system based on mine red-pot

Abstract

The invention relates to the technical field of mining equipment maintenance, in particular to an intelligent lubrication system based on a mine red, and the system comprises a data acquisition unit which is used for acquiring real-time data of an oil product and an operation condition of mining equipment; the prediction unit is used for calculating an oil film safety margin coefficient according to the real-time data, and predicting a minimum prediction value of the oil film safety margin coefficient in a prediction window based on a short-time prediction model; and the lubrication unit is used for generating an advanced lubrication instruction when the minimum prediction value is smaller than or equal to a preset safety lower limit in the prediction window. When the prediction result shows that the oil film safety margin coefficient is about to be lower than the preset safety lower limit, the system can generate and issue a lubrication instruction in advance, so that the lubrication operation is timely intervened before the oil film fails, and the phenomenon of friction pair boundary lubrication or dry friction caused by lubrication opportunity lag in a traditional fixed period lubrication mode is avoided; therefore, the wear rate is reduced, the service life of equipment is prolonged, and non-planned shutdown is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mine equipment maintenance, and in particular relates to a mine-hong-based intelligent lubrication system. BACKGROUND

[0002] The mine-hong-based intelligent lubrication system refers to intelligent management and control of the lubrication process of mine equipment by using the data acquisition, edge computing and device linkage capabilities of the mine-hong platform. The mine-hong platform is an industrial Internet of Things operating system for the mining field, and has the capabilities of multi-device access, real-time data transmission, and cloud-edge collaborative computing. With the help of the mine-hong platform, the intelligent lubrication system can integrate on-site sensors, control units and actuators into a unified management architecture, and support centralized monitoring and policy issuance of lubrication data.

[0003] In the existing lubrication management of mine equipment, the related technologies face the following problems:

[0004] Lubrication opportunity lags behind: traditional lubrication relies on automatic refueling within a fixed period set by the system, and lacks real-time assessment of oil film state, which can easily lead to equipment friction surfaces being in boundary lubrication or even dry friction state due to untimely lubrication, thereby accelerating wear.

[0005] Blockage risk cannot be handled in advance: most existing systems can only alarm after blockage causes lubrication failure, and cannot take measures before blockage occurs. Once the lubrication pipeline or nozzle is blocked, the lubrication process will be interrupted, causing the equipment that should be lubricated to lack oil for a short period of time, increasing the risk of failure.

[0006] Therefore, the present application proposes a mine-hong-based intelligent lubrication system to solve the above problems. SUMMARY

[0007] To achieve the above purpose, the present application provides the following technical solutions:

[0008] A mine-hong-based intelligent lubrication system, comprising:

[0009] A data acquisition unit for acquiring real-time data of mine equipment oil and operating conditions;

[0010] A prediction unit for calculating an oil film safety margin coefficient based on real-time data, and predicting the minimum predicted value of the oil film safety margin coefficient within a prediction window based on a short-term prediction model;

[0011] A lubrication unit for generating an advance lubrication instruction when the minimum predicted value is less than or equal to a preset safety lower limit within the prediction window;

[0012] A curve construction unit is used to obtain the metering pump outlet pressure and flow data generated during the execution of the advance lubrication instruction to construct a first flow curve; obtain the metering pump outlet pressure and flow data under historical normal working conditions to construct a second flow curve;

[0013] a comparison unit, configured to compare the first flow curve with the second flow curve to determine whether the nozzle has a clogging trend during the execution of the current lubrication instruction;

[0014] Backwash unit, used to send and execute backwash instructions immediately when there is a tendency of clogging, and to check the nozzle status again after backwashing;

[0015] If the fault unit still has a clogging trend after backwashing, the current lubrication instruction will be stopped and a fault alarm will be triggered to notify the operation and maintenance personnel.

[0016] An intelligent lubrication system based on Kuanghong also includes: an instruction execution unit, which is used to receive and execute the advance lubrication instruction sent by the lubrication unit; the instruction execution unit will synchronously collect the operating data of the lubricated equipment during the execution of the advance lubrication instruction, and the operating data will provide a data acquisition benchmark for the curve construction unit.

[0017] Preferably, real-time data on the oil quality and operating conditions of mining equipment is obtained, specifically including:

[0018] The real-time data includes oil temperature, oil pressure, lubricating oil level, equipment load, spindle speed and surface roughness parameters related to the friction surface; the real-time data is obtained through oil temperature sensors, oil pressure sensors and oil level sensors arranged in the equipment lubrication oil circuit, as well as load sensors, speed sensors and surface roughness meters installed on the equipment transmission components.

[0019] Preferably, the oil film safety margin coefficient is calculated based on real-time data, and the minimum predicted value of the oil film safety margin coefficient within the prediction window is predicted based on the short-term prediction model, specifically including:

[0020] The calculation formula of the oil film safety margin coefficient is:

[0021]

[0022] Where, is the oil film safety margin coefficient; is the surface roughness parameter, is the minimum oil film thickness calculated based on equivalent viscosity, equipment load and spindle speed, The calculation formula is:

[0023]

[0024] Where, Represents the empirical constant related to the equipment type and lubrication oil circuit structure; is the equivalent viscosity, which is calculated after correction according to oil temperature and oil pressure; is the spindle speed; The equipment load.

[0025] The short-term prediction model is constructed through a time series prediction method trained with historical equipment operation data. The short-term prediction model takes the multi-point time series data of the oil film safety margin coefficient currently calculated as input, outputs a prediction value sequence within the corresponding prediction window, and takes the minimum value in the prediction value sequence as the minimum prediction value.

[0026] Preferably, when the minimum predicted value is less than or equal to a preset safety lower limit within the prediction window, an advance lubrication instruction is generated, specifically including:

[0027] The preset safety lower limit is determined by collecting three months of historical oil film safety margin coefficients when the equipment is in normal and good operating condition, and taking the 5th percentile value of the statistical distribution of the historical oil film safety margin coefficients as the initial threshold reference. Based on the initial threshold reference, the initial safety lower limit is set, and the initial safety lower limit is corrected according to the load factor of the equipment location. If there is a high load at the equipment location, the safety lower limit of the corresponding location will be increased by 5% to 10% based on the initial value, and the low-load location will remain unchanged. The preset safety lower limit of each part of the equipment is obtained based on the correction.

[0028] When the minimum predicted value output by the prediction unit is less than or equal to the preset safety lower limit within the prediction window, the lubrication unit will immediately generate an advance lubrication instruction based on the prediction result; the lubrication instruction includes: target lubrication point identification, lubricant type, single injection amount, injection duration, metering pump target working pressure execution parameters, and send the advance lubrication instruction to the instruction execution unit.

[0029] Preferably, obtaining the metering pump outlet pressure and flow data generated during the execution of the advance lubrication instruction to construct a first flow curve; obtaining the metering pump outlet pressure and flow data under historical normal working conditions to construct a second flow curve, specifically including:

[0030] The first flow curve refers to the characteristic relationship curve of pressure and flow between the outlet pressure and flow data of the metering pump in real time; the second flow curve refers to the characteristic relationship curve of pressure and flow between the outlet pressure and flow data of the metering pump under historical normal working conditions.

[0031] The first flow curve is obtained by collecting real-time pressure data and real-time flow data of the outlet of the metering pump during execution of the lubrication instruction in advance, pairing the collected real-time pressure data and real-time flow data according to time stamps, arranging the paired real-time pressure data and real-time flow data in chronological order, and drawing a characteristic curve of pressure and flow with pressure values as abscissa and flow values as ordinate to obtain the first flow curve.

[0032] The second flow curve is obtained by calling pressure data and flow data of the outlet of the metering pump under normal working conditions during execution of historical lubrication instructions, pairing the called historical pressure data and historical flow data according to time stamps, arranging the paired historical pressure data and historical flow data in chronological order, and drawing a characteristic curve of pressure and flow with pressure values as abscissa and flow values as ordinate to obtain the second flow curve.

[0033] Preferably, the first flow curve is compared with the second flow curve to determine whether the nozzle has a clogging trend during execution of the current lubrication instruction, and the comparison specifically includes:

[0034] The corresponding real-time pressure data and flow data in the first flow curve are obtained and aligned in chronological order.

[0035] The pressure data and flow data under the historical normal working condition in the second flow curve are obtained, and a reference base value of pressure and flow under the historical normal working condition and a base curve slope are established.

[0036] The real-time flow data is compared with the reference base value point by point, and in the comparison process, a flow difference value between the real-time flow data and the reference base value at each time point is calculated to obtain the flow difference value, which represents the difference between the real-time flow and the reference base flow; a preset time window is set, and a median of the flow difference value and a low flow proportion in the current time window are counted; a change trend of pressure and flow in the preset time window is calculated, and the change trend is specifically a curve slope; the calculated real-time curve slope is compared with the base curve slope to obtain a slope comparison result.

[0037] The nozzle clogging trend in the preset time window is comprehensively determined in combination with the flow difference value judgment, the low flow proportion, and the slope comparison result, and the judgment condition is:

[0038] If the median of the flow difference value is greater than or equal to a set residual threshold value and the low flow proportion exceeds a set low flow proportion threshold value in the preset time window, it is considered that the current time window has a clogging trend.

[0039] Alternatively, if the flow change trend gradually slows down in the slope comparison result and the average pressure continuously rises and exceeds a set pressure increment threshold value in the preset time window, it is also considered that the current time window has a clogging sign.

[0040] When it is determined that there is a clogging trend within three consecutive preset time windows, a notification of the nozzle clogging trend is output to the backwash unit. When it is not determined that there is a clogging trend within three consecutive preset time windows, it is determined that there is no clogging trend in the current lubrication instruction execution process, the current lubrication instruction is maintained and continues to run, and the backwash unit is not triggered.

[0041] Preferably, when there is a clogging trend, a backwash instruction is immediately sent and executed, and the nozzle status is checked again after backwashing, specifically including:

[0042] The backwash instruction is an execution command sent to the solenoid valve control of the lubrication branch where the nozzle is located. The execution command content includes switching to the backwash circuit, starting the metering pump to reversely transport lubricating oil or cleaning medium, setting the number of pulses and pulse duration, and automatically stopping when the set number of times is reached or the nozzle outlet pressure is detected to have returned to the normal range.

[0043] The second inspection is to restore the equipment to the normal lubrication circuit after the backwash is completed, collect real-time pressure data and flow data at the nozzle outlet, reconstruct the first curve and perform blockage trend judgment. When the judgment result meets the normal working condition judgment conditions, it is determined that the nozzle status has returned to normal, otherwise the backwash is determined to be invalid and the fault unit is triggered.

[0044] Preferably, if there is still a clogging trend after backwashing, the current lubrication instruction is stopped and a fault alarm is triggered to notify the operation and maintenance personnel, specifically including:

[0045] The fault alarm content includes the comparison conclusion of the first flow curve and the second flow curve, including the median of the flow difference, the low flow ratio, the slope comparison result and the average pressure in the time window; the record of three consecutive preset time windows being judged as a blockage trend; the number of pulses executed, the duration of each pulse and the pulse interval, the re-test results after backwashing; and the minimum predicted value of the most recent oil film safety margin coefficient.

[0046] The beneficial effects of this application are:

[0047] 1. This application collects the oil status and operating condition parameters of mining equipment in real time with the data support of the Kuanghong platform, calculates the oil film safety margin coefficient, and predicts its minimum value in the future prediction window based on the short-term prediction model; when the prediction result shows that the oil film safety margin coefficient is about to fall below the preset safety lower limit, the system can generate and issue lubrication instructions in advance, so that the lubrication operation can be intervened in time before the oil film fails, avoiding the boundary lubrication or dry friction of the friction pair caused by the delay in lubrication timing in the traditional fixed-cycle lubrication method, thereby reducing the wear rate, extending the service life of the equipment and reducing unplanned downtime.

[0048] 2. In the process of lubrication, the application collects the pressure and flow data of the metering pump outlet in real time to form a first flow curve, and compares it with a second flow curve formed under normal historical working conditions, and uses the comprehensive analysis of flow difference, low flow ratio and curve slope change to judge whether the nozzle has a blocking trend. Once the blocking trend is detected, the system immediately issues a backwash command to pulse the nozzle for reverse flushing, and detects the nozzle state again after flushing is completed. If the blocking risk still exists, the current lubrication command is stopped immediately and a fault alarm is triggered to notify the operation and maintenance personnel. Thus, nozzle blockage can be identified and handled before complete blockage, avoiding lubrication interruption and the resulting equipment damage and safety risks.

[0049] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the following preferred embodiments are described in detail below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0051] Figure 1 A whole framework diagram of a mine intelligent lubrication system is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present application will be described below in combination with the drawings in the embodiments of the present application.

[0053] Please refer to Figure 1 , Figure 1 A framework diagram of a mine intelligent lubrication system is provided for the embodiments of the present application.

[0054] In the present embodiment, a mine intelligent lubrication system comprises the following:

[0055] The data acquisition unit is used to acquire real-time data of oil and running conditions of the mine equipment, specifically including: real-time data including oil temperature, oil pressure, lubricating oil level, equipment load, main shaft speed and surface roughness parameters related to friction surface; Real-time data is acquired through oil temperature sensor, oil pressure sensor and oil level sensor arranged in the equipment lubricating oil circuit, and load sensor, speed sensor and surface roughness measuring device installed in the equipment transmission component.

[0056] The prediction unit is configured to calculate an oil film safety margin coefficient according to real-time data, and predict a minimum prediction value of the oil film safety margin coefficient within a prediction window based on a short-term prediction model, and specifically includes:

[0057] The calculation formula of the oil film safety margin coefficient is:

[0058]

[0059] In the formula, is the oil film safety margin coefficient; is a surface roughness parameter, is a minimum oil film thickness calculated according to an equivalent viscosity, a device load, and a main shaft rotating speed, The calculation formula of the minimum oil film thickness is:

[0060]

[0061] In the formula, represents an empirical constant related to the type of the device and the structure of the lubricating oil circuit; is an equivalent viscosity obtained after correction calculation according to the oil temperature and the oil pressure; is the main shaft rotating speed; is the device load.

[0062] The short-term prediction model is constructed by a time series prediction method trained by historical operation data of the device. The short-term prediction model takes the multi-point time series data of the oil film safety margin coefficient calculated at present as input, outputs a prediction value sequence within the corresponding prediction window, and takes the minimum value in the prediction value sequence as the minimum prediction value.

[0063] It should be noted that the time series prediction method selects a long short-term memory neural network to construct model parameters.

[0064] The lubrication unit is configured to generate an advance lubrication instruction when the minimum prediction value is less than or equal to a preset safety lower limit within the prediction window, and specifically includes:

[0065] The preset safety lower limit is obtained by collecting historical oil film safety margin coefficients for three months under the condition that the device is in a normal state and has a good running state, taking the 5th percentile value of the statistical distribution of the historical oil film safety margin coefficients as an initial threshold reference, setting an initial safety lower limit according to the initial threshold reference, correcting the initial safety lower limit according to the load coefficient of the part where the device is located, increasing the safety lower limit of the corresponding part by 5% to 10% based on the initial value if there is a high load in the part where the device is located, and keeping the low load part unchanged, and obtaining the preset safety lower limit of each part of the device according to the correction.

[0066] When the minimum prediction value output by the prediction unit is less than or equal to the preset safety lower limit within the prediction window, the lubrication unit generates an advance lubrication instruction according to the prediction result; the lubrication instruction includes: target lubrication point identification, lubricant type, single injection amount, injection duration, metering pump target working pressure execution parameter, and sends the advance lubrication instruction to the instruction execution unit.

[0067] It should be noted that the oil film thickness involved in the preset safety lower limit must be higher than 1.2 times the critical failure thickness.

[0068] It should be noted that the high load part and the low load part of the equipment are collectively referred to as different parts of the working condition in the equipment; the high load part refers to the part that bears larger load, higher speed or frequent impact during the operation of the equipment, such as main bearing, gear meshing surface, etc.; the low load part refers to the part that bears smaller load, lower speed and less impact during the operation of the equipment, such as auxiliary bearing, guide rail, etc.

[0069] The curve construction unit is configured to obtain the metering pump outlet pressure and flow data generated in the advance lubrication instruction execution process, and construct a first flow curve; obtain the metering pump outlet pressure and flow data under the historical normal working condition, and construct a second flow curve, specifically including:

[0070] The first flow curve refers to the pressure-flow characteristic relationship curve between the metering pump outlet pressure and flow data in real-time state; the second flow curve refers to the pressure-flow characteristic relationship curve between the metering pump outlet pressure and flow data under the historical normal working condition.

[0071] The first flow curve is obtained by collecting real-time pressure data and real-time flow data of the metering pump outlet in the advance lubrication instruction execution process; and pairing the collected real-time pressure data and real-time flow data according to the time stamp; arranging the paired real-time pressure data and real-time flow data in time sequence, and drawing the pressure-flow characteristic relationship curve with pressure value as abscissa and flow value as ordinate, to obtain the first flow curve.

[0072] The second flow curve is obtained by calling the metering pump outlet pressure data and flow data under the normal working condition in the historical lubrication instruction execution process; pairing the called historical pressure data and historical flow data according to the time stamp; arranging the paired historical pressure data and historical flow data in time sequence, and drawing the pressure-flow characteristic relationship curve with pressure value as abscissa and flow value as ordinate, to obtain the second flow curve.

[0073] It should be noted that the normal working condition refers to the running state of the metering pump and the corresponding lubricating pipeline without nozzle blockage, without leakage, the lubricating oil temperature being in the set working range and the oil pressure being stable in the rated range, and the device load and the main shaft speed being in the rated working interval specified by the current device type, and the lubricating oil viscosity meeting the recommended value of the manufacturer.

[0074] The comparison unit compares the first flow curve with the second flow curve to determine whether there is a nozzle blockage trend in the current lubrication instruction execution process, specifically including:

[0075] The corresponding real-time pressure data and flow data in the first flow curve are obtained and aligned in time sequence.

[0076] The pressure data and flow data under the historical normal working condition in the second flow curve are obtained, and the reference base value of pressure and flow under the historical normal working condition and the base curve slope are established.

[0077] The real-time flow data is compared with the reference base value point by point, and in the comparison process, the flow difference value between the real-time flow data and the reference base value at each time point is calculated to obtain the flow difference value, which represents the difference between the real-time flow and the reference flow. A preset time window is set, and the median of the flow difference value and the low flow ratio in the current time window are counted. The change trend of pressure and flow in the preset time window is calculated, and the change trend is specifically the curve slope. The calculated real-time curve slope is compared with the base curve slope to obtain the slope comparison result.

[0078] Combining the flow difference value judgment, the low flow ratio and the slope comparison result, it is comprehensively judged whether there is a nozzle blockage trend in the preset time window, and the judgment condition is:

[0079] If the median of the flow difference value is greater than or equal to the set residual threshold value, and the low flow ratio exceeds the set low flow ratio threshold value in the preset time window, it is considered that the current time window has a blockage trend.

[0080] Or, in the preset time window, the flow change trend gradually slows down in the slope comparison result, and the average pressure continuously rises and exceeds the set pressure increment threshold value, which is also considered as a blockage sign of the current time window.

[0081] When the continuous three preset time windows are all judged to have a blockage trend, a notification of the existence of a nozzle blockage trend is output to the backwashing unit. When the continuous three preset time windows are not judged to have a blockage trend, it is determined that the current lubrication instruction execution process does not have a blockage trend, and the current lubrication instruction continues to run without triggering the backwashing unit.

[0082] It should be noted that the calculation formula of the flow difference value is:

[0083]

[0084] In the formula, represents the flow difference value of the i-th sampling point, represents real-time flow data, represents a reference flow value. It should be noted that the preset time window length is 3 to 5 seconds.

[0085] It should be noted that the low flow ratio is obtained by counting the proportion of the total number of sampling points that meet the condition that the flow difference value is greater than 0 in the preset time window. The low flow ratio represents the proportion of time when the real-time flow is lower than the reference flow.

[0086] It should be noted that the calculation formula of the real-time curve slope is:

[0087]

[0088] In the formula,

[0089] represents the real-time curve slope, represents real-time flow, represents real-time pressure, and represent the starting sampling point and the ending sampling point of the preset time window, respectively.

[0090] It should be noted that the reference curve slope is constructed by the reference flow and the reference pressure. The calculation formula is referenced from the real-time curve slope. The real-time flow and the real-time pressure in the real-time curve slope calculation formula are replaced by the reference flow and the reference pressure to complete the calculation.

[0091] It should be noted that the slope comparison result includes the flow change trend and the average pressure in the preset time window.

[0092] It should be noted that the residual threshold is set to 0.15; the low flow ratio threshold is set to 0.70; and the pressure increment threshold is set to 0.1 Mpa.

[0093] The backwashing unit is used to send a backwashing instruction and execute it immediately when there is a clogging trend, and detect the nozzle state again after backwashing, and specifically includes:

[0094] The backwashing instruction is an execution command sent to the electromagnetic valve control of the lubrication branch where the nozzle is located. The execution command content includes switching to the backwashing circuit, starting the metering pump to deliver lubricating oil or cleaning medium in reverse, setting the pulse number and pulse duration, and automatically stopping when the set number is reached or the nozzle outlet pressure is restored to the normal range;

[0095] ​​It should be noted that the pulse number is set to 3 by default, each lasting 0.6 seconds, and the pulse interval is 0.5 seconds.

[0096] The retest is performed after the backwashing is completed, the device is restored to the normal lubrication circuit, the real-time pressure data and flow data of the nozzle outlet are collected, the first curve is reconstructed and the blockage trend judgment is performed, when the judgment result meets the normal working condition judgment condition, it is determined that the nozzle state returns to normal, otherwise it is determined that the backwashing is invalid and the fault unit is triggered.

[0097] The fault unit is used to stop executing the current lubrication instruction when the blockage trend still exists after backwashing, and trigger a fault alarm to inform the operation and maintenance personnel, which specifically includes:

[0098] The fault alarm includes the comparison conclusion of the first flow curve and the second flow curve, the median of the flow difference, the low flow ratio, the slope comparison result and the average pressure in the time window; the record of the three consecutive preset time windows are determined as the blockage trend; the number of pulses executed, the duration of each pulse and the pulse interval, and the retest result after backwashing; the minimum predicted value of the oil film safety margin coefficient of the last time.

[0099] It should be noted that the mine is an existing mine industrial internet of things operating system platform developed and provided by a related manufacturer, which has functions such as multi-device access, real-time data acquisition and transmission, edge computing, cloud collaboration, and can realize centralized monitoring and management of mine equipment; the present application obtains data, issues instructions and monitors the state based on the mine platform, and the hardware structure, software architecture and implementation principle of the mine platform itself are prior art, therefore, this specification will not be repeated.

[0100] At this point, a mine-based intelligent lubrication system is completed.

[0101] It should be understood that the order of the units or modules of the above processes in various embodiments of the present application does not mean the order of execution, the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0102] Those of ordinary skill in the art can realize that the algorithms, steps, units or modules described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0103] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A Kuanghong intelligent lubrication system, characterized in that: include: Data acquisition unit, used to obtain real-time data on mining equipment oil quality and operating conditions; A prediction unit is used to calculate the oil film safety margin coefficient based on real-time data, and predict the minimum predicted value of the oil film safety margin coefficient within the prediction window based on a short-term prediction model; A lubrication unit is used to generate an advance lubrication instruction when the minimum predicted value is less than or equal to a preset safety lower limit within the prediction window; A curve construction unit is used to obtain the metering pump outlet pressure and flow data generated during the execution of the advance lubrication instruction to construct a first flow curve; obtain the metering pump outlet pressure and flow data under historical normal working conditions to construct a second flow curve; a comparison unit, configured to compare the first flow curve with the second flow curve to determine whether the nozzle has a clogging trend during the execution of the current lubrication instruction; Backwash unit, used to send and execute backwash instructions immediately when there is a tendency of clogging, and to check the nozzle status again after backwashing; If the fault unit still has a clogging trend after backwashing, the current lubrication instruction will be stopped and a fault alarm will be triggered to notify the operation and maintenance personnel.

2. The intelligent lubrication system based on Kuanghong according to claim 1, characterized in that: Also includes: An instruction execution unit, configured to receive and execute an advance lubrication instruction sent by the lubrication unit; The instruction execution unit will synchronously collect the operating data of the lubricated equipment during the process of executing the advance lubrication instruction. The operating data will provide a data acquisition benchmark for the curve construction unit.

3. The intelligent lubrication system based on Kuanghong according to claim 1, characterized in that: Obtain real-time data on mining equipment oil quality and operating conditions, including: The real-time data includes oil temperature, oil pressure, lubricating oil level, equipment load, spindle speed and surface roughness parameters related to the friction surface; the real-time data is obtained through oil temperature sensors, oil pressure sensors and oil level sensors arranged in the equipment lubrication oil circuit, as well as load sensors, speed sensors and surface roughness meters installed on the equipment transmission components.

4. The intelligent lubrication system based on Kuanghong according to claim 1, characterized in that: Calculate the oil film safety margin coefficient based on real-time data, and predict the minimum predicted value of the oil film safety margin coefficient within the prediction window based on the short-term prediction model, including: The calculation formula of the oil film safety margin coefficient is: ； Where, is the oil film safety margin coefficient; is the surface roughness parameter, is the minimum oil film thickness calculated based on equivalent viscosity, equipment load and spindle speed, The calculation formula is: ； Where, Represents the empirical constant related to the equipment type and lubrication oil circuit structure; is the equivalent viscosity, which is calculated after correction according to oil temperature and oil pressure; is the spindle speed; is the equipment load; The short-term prediction model is constructed through a time series prediction method trained with historical equipment operation data. The short-term prediction model takes the multi-point time series data of the oil film safety margin coefficient currently calculated as input, outputs a prediction value sequence within the corresponding prediction window, and takes the minimum value in the prediction value sequence as the minimum prediction value.

5. The intelligent lubrication system based on Kuanghong according to claim 1, characterized in that: When the minimum predicted value is less than or equal to the preset safety lower limit within the prediction window, an advance lubrication instruction is generated, including: The preset lower safety limit is determined by continuously collecting three months of historical oil film safety margin coefficients when the equipment is in normal and good operating condition, and taking the 5th percentile value of the statistical distribution of the historical oil film safety margin coefficients as the initial threshold reference. Based on the initial threshold reference, the initial lower safety limit is set, and the initial lower safety limit is corrected according to the load factor of the equipment location. If there is a high load at a location where the equipment is located, the lower safety limit of the corresponding location is increased by 5% to 10% based on the initial value, while the low-load location remains unchanged. The preset lower safety limit of each location of the equipment is obtained based on the correction; When the minimum predicted value output by the prediction unit is less than or equal to the preset safety lower limit within the prediction window, the lubrication unit will immediately generate an advance lubrication instruction based on the prediction result; the lubrication instruction includes: target lubrication point identification, lubricant type, single injection amount, injection duration, metering pump target working pressure execution parameters, and send the advance lubrication instruction to the instruction execution unit.

6. The intelligent lubrication system based on Kuanghong according to claim 5, characterized in that: The outlet pressure and flow data of the metering pump generated during the execution of the advance lubrication instruction are obtained to construct a first flow curve; the outlet pressure and flow data of the metering pump under historical normal working conditions are obtained to construct a second flow curve, specifically including: The first flow curve refers to a characteristic relationship curve between the pressure and flow rate of the metering pump outlet pressure and flow rate data in real time; the second flow curve refers to a characteristic relationship curve between the pressure and flow rate of the metering pump outlet pressure and flow rate data under historical normal working conditions; The first flow curve is obtained by collecting real-time pressure data and real-time flow data at the metering pump outlet during the execution of the advance lubrication instruction; pairing the collected real-time pressure data and real-time flow data according to timestamps; arranging the paired real-time pressure data and real-time flow data in chronological order, and plotting a characteristic relationship curve between pressure and flow with pressure as the horizontal axis and flow value as the vertical axis, thereby obtaining the first flow curve; The second flow curve is obtained by calling the metering pump outlet pressure data and flow data under normal working conditions during the execution of historical lubrication instructions; pairing the called historical pressure data and historical flow data according to timestamps; arranging the paired historical pressure data and historical flow data in chronological order, and drawing a characteristic relationship curve between pressure and flow with pressure value as the horizontal axis and flow value as the vertical axis to obtain the second flow curve.

7. The intelligent lubrication system based on Kuanghong according to claim 6, characterized in that: Comparing the first flow curve with the second flow curve to determine whether the nozzle has a tendency to become clogged during the execution of the current lubrication instruction, specifically including: Obtaining the real-time pressure data and flow data corresponding to the first flow curve and aligning them in chronological order; Obtaining pressure data and flow data under historical normal operating conditions in the second flow curve, and establishing reference baseline values ​​of pressure and flow under historical normal operating conditions and a baseline curve slope; The real-time flow data is compared with the benchmark reference value point by point. During the comparison process, the flow difference between the real-time flow data and the benchmark reference value at each time point is calculated to obtain a flow difference value, which represents the difference between the real-time flow and the benchmark reference flow; a time window is preset, and the median of the flow difference value and the low flow ratio in the current time window are calculated; the change trend of the pressure and flow in the preset time window is calculated, and the change trend is specifically the slope of the curve. The calculated real-time curve slope is compared with the slope of the benchmark curve to obtain a slope comparison result; Combined with the flow difference judgment, low flow ratio and slope comparison results, a comprehensive judgment is made on whether there is a nozzle clogging trend within the preset time window. The judgment conditions are: If the median of the flow difference within the preset time window is greater than or equal to the set residual threshold, and the low flow ratio exceeds the set low flow ratio threshold, it is considered that there is a congestion trend in the current time window; Alternatively, if, within a preset time window, the flow rate change trend in the slope comparison result gradually slows down, and the average pressure continues to rise and exceeds the set pressure increment threshold, it is also considered that there is a sign of blockage in the current time window; When it is determined that there is a clogging trend within three consecutive preset time windows, a notification of the nozzle clogging trend is output to the backwash unit. When it is not determined that there is a clogging trend within three consecutive preset time windows, it is determined that there is no clogging trend in the current lubrication instruction execution process, the current lubrication instruction is maintained and continues to run, and the backwash unit is not triggered.

8. The intelligent lubrication system based on Kuanghong according to claim 7, characterized in that: When there is a tendency for clogging, a backwash command is immediately sent and executed, and the nozzle status is checked again after backwashing, including: The backwash instruction is an execution command sent to the solenoid valve control of the lubrication branch where the nozzle is located. The execution command content includes switching to the backwash circuit, starting the metering pump to reversely deliver lubricating oil or cleaning medium, setting the number of pulses and pulse duration, and automatically stopping when the set number of pulses is reached or the nozzle outlet pressure is detected to have returned to the normal range; The second inspection is to restore the equipment to the normal lubrication circuit after the backwash is completed, collect real-time pressure data and flow data at the nozzle outlet, reconstruct the first curve and perform blockage trend judgment. When the judgment result meets the normal working condition judgment conditions, it is determined that the nozzle status has returned to normal, otherwise the backwash is determined to be invalid and the fault unit is triggered.

9. The intelligent lubrication system based on Kuanghong according to claim 1, characterized in that: If there is still a tendency of clogging after backwashing, the current lubrication instruction will be stopped and a fault alarm will be triggered to notify the operation and maintenance personnel, including: The fault alarm content includes the comparison conclusion of the first flow curve and the second flow curve, including the median of the flow difference, the low flow ratio, the slope comparison result and the average pressure in the time window; the record of three consecutive preset time windows being judged as a blockage trend; the number of pulses executed, the duration of each pulse and the pulse interval, the re-test results after backwashing; and the minimum predicted value of the most recent oil film safety margin coefficient.

Images