Oil drilling rig chain quality evaluation method and system based on lubrication consumption analysis

Abstract

This application provides a method and system for quality assessment of oil drilling rig chains based on lubrication consumption analysis, relating to the field of lubrication oil detection technology. The method includes: acquiring lubrication oil consumption detection devices; acquiring lubrication oil consumption detection data of the oil drilling rig chain; determining the real-time operating mode of the oil drilling rig chain; constructing a lubrication oil consumption anomaly detection model; inputting the real-time operating mode and lubrication oil consumption detection data into the lubrication oil consumption anomaly detection model to detect lubrication oil consumption anomalies; and converting lubrication oil consumption anomaly indicators through a consumption anomaly-quality conversion module. This application addresses the technical problem in existing technologies that lack correlation analysis between lubrication oil consumption anomalies and equipment quality issues, further affecting the accuracy of maintenance decisions and the operational reliability of equipment. It achieves the technical goal of correlation analysis between lubrication oil consumption and equipment health status, and enables real-time monitoring of lubrication oil consumption anomalies and accurate judgment of equipment wear and other problems.

Description

Technical Field

[0001] This application relates to the field of lubricating oil testing technology, and in particular to a method and system for quality assessment of oil drilling rig chains based on lubrication consumption analysis. Background Technology

[0002] As a crucial component of drilling rigs, drilling rig chains operate in complex and variable environments, enduring high-intensity tensile, torsional, and impact loads. Therefore, maintaining proper lubrication of the drilling rig chain is essential for its performance and lifespan. Lubricating oil plays a key role in reducing friction, minimizing wear, preventing overheating, and maintaining chain sealing. Chain wear, fatigue, and seal failure are often the main causes of abnormal lubricating oil consumption. Current technologies primarily rely on directly measuring the chain's physical wear and fatigue strength, or visually inspecting for cracks, to assess the quality of oil drilling rig chains.

[0003] In summary, existing technologies lack effective correlation analysis between abnormal lubricant consumption and equipment quality problems. Direct measurement methods require shutdown for testing, making it impossible to continuously and accurately determine the quality problems of oil drilling rig chain equipment in real time, which further affects the operational reliability and efficiency of the equipment. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for quality assessment of oil drilling rig chains based on lubrication consumption analysis, in order to solve the technical problem that the existing technology lacks an effective correlation analysis between abnormal lubricating oil consumption and equipment quality problems. Direct measurement methods require shutdown for testing, which makes it impossible to continuously and accurately judge the quality problems of oil drilling rig chain equipment in real time, and further affects the operational reliability and efficiency of the equipment.

[0005] In view of the above problems, this application provides a method and system for evaluating the quality of oil drilling rig chains based on lubrication consumption analysis.

[0006] Firstly, this application provides a quality assessment method for oil drilling rig chains based on lubrication consumption analysis, implemented through an oil drilling rig chain quality assessment system based on lubrication consumption analysis. The method includes: acquiring a lubrication oil consumption detection device, which is used to detect lubrication oil consumption in the oil drilling rig chain. The lubrication oil consumption detection device includes an oil quantity sensor and a flow meter, wherein the oil quantity sensor is installed in the lubrication oil supply system, and the flow meter is installed on the lubrication oil pipeline; acquiring lubrication oil consumption detection data of the oil drilling rig chain based on the lubrication oil consumption detection device, the lubrication oil consumption detection data including lubrication oil consumption amount and lubrication oil flow rate; determining the real-time operating mode of the oil drilling rig chain; constructing a lubrication oil consumption anomaly detection model, inputting the real-time operating mode and the lubrication oil consumption detection data into the lubrication oil consumption anomaly detection model to detect lubrication oil consumption anomalies, and outputting a lubrication oil consumption anomaly index; and converting the lubrication oil consumption anomaly index through a consumption anomaly-quality conversion module to output the quality anomaly detection result of the oil drilling rig chain.

[0007] Secondly, this application also provides a quality assessment system for an oil drilling rig chain based on lubrication consumption analysis, used to execute the oil drilling rig chain quality assessment method based on lubrication consumption analysis as described in the first aspect, comprising: a lubricating oil consumption detection device acquisition module, used to acquire a lubricating oil consumption detection device, wherein the lubricating oil consumption detection device is used to detect the consumption of lubricating oil in the oil drilling rig chain, the lubricating oil consumption detection device including an oil quantity sensor and a flow meter, wherein the oil quantity sensor is installed in the lubricating oil supply system, and the flow meter is installed on the lubricating oil pipeline; and a lubricating oil consumption detection data acquisition module, used to acquire the oil consumption data based on the lubricating oil consumption detection device. The system includes: a lubricating oil consumption detection data for the drilling rig chain, comprising lubricating oil consumption amount and lubricating oil flow rate; a real-time operating condition mode determination module for determining the real-time operating condition mode of the oil drilling rig chain; a lubricating oil consumption anomaly output module for constructing a lubricating oil consumption anomaly detection model, inputting the real-time operating condition mode and the lubricating oil consumption detection data into the model to detect lubricating oil consumption anomalies, and outputting a lubricating oil consumption anomaly index; and a quality anomaly detection result output module for converting the lubricating oil consumption anomaly index through a consumption anomaly-quality conversion module, and outputting the quality anomaly detection result of the oil drilling rig chain.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: By acquiring a lubricating oil consumption detection device, which is used to detect the lubricating oil consumption of an oil drilling rig chain, the device includes an oil quantity sensor and a flow meter. The oil quantity sensor is installed in the lubricating oil supply system, and the flow meter is installed on the lubricating oil pipeline. Based on the lubricating oil consumption detection device, lubricating oil consumption detection data of the oil drilling rig chain is acquired, including lubricating oil consumption amount and lubricating oil flow rate. The real-time operating mode of the oil drilling rig chain is determined. An abnormal lubricating oil consumption detection model is constructed, and the real-time operating mode and the lubricating oil consumption detection data are input into the lubricating oil supply system. The lubricating oil consumption anomaly detection model detects lubricating oil consumption anomalies and outputs lubricating oil consumption anomaly indicators. The consumption anomaly-quality conversion module converts these indicators to output the quality anomaly detection results for the oil drilling rig chain. Ultimately, this achieves the technical goal of intelligent correlation analysis between lubricating oil consumption and equipment health status. This enables continuous, real-time, and accurate monitoring of lubricating oil consumption anomalies to reflect the quality of the oil drilling rig chain without requiring downtime for complex inspections. This not only improves the timeliness and accuracy of equipment maintenance but also effectively extends equipment lifespan and reduces downtime due to failure to address potential problems in a timely manner.

[0009] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in this application 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 merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating the oil drilling rig chain quality assessment method based on lubrication consumption analysis proposed in this application. Figure 2 This is a schematic diagram of the structure of the oil drilling rig chain quality assessment system based on lubrication consumption analysis proposed in this application.

[0012] Explanation of reference numerals in the attached figures: The system includes a lubricating oil consumption detection device acquisition module 11, a lubricating oil consumption detection data acquisition module 12, a real-time operating condition mode determination module 13, a lubricating oil consumption abnormality index output module 14, and a quality abnormality detection result output module 15. Detailed Implementation

[0013] This application provides a method and system for quality assessment of oil drilling rig chains based on lubrication consumption analysis. It addresses the shortcomings of existing technologies, such as the lack of effective correlation analysis between abnormal lubricant consumption and equipment quality problems. Direct measurement methods require downtime for inspection, hindering continuous, real-time, and accurate assessment of oil drilling rig chain equipment quality, thus impacting equipment reliability and efficiency. The application achieves the technical goal of correlation analysis between lubricant consumption and equipment health status, enabling continuous, real-time, and accurate monitoring of abnormal lubricant consumption to reflect the quality of the oil drilling rig chain. This eliminates the need for complex downtime inspections, improving the timeliness and accuracy of equipment maintenance, effectively extending equipment lifespan, and reducing downtime due to untimely handling of potential problems.

[0014] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0015] Example 1, please refer to the appendix. Figure 1 This application provides a method for evaluating the quality of an oil drilling rig chain based on lubrication consumption analysis, which is applied to an oil drilling rig chain quality evaluation system based on lubrication consumption analysis. The method specifically includes the following steps: Step 1: Obtain the lubricating oil consumption detection device. The lubricating oil consumption detection device is used to detect the consumption of lubricating oil in the oil drilling rig chain. The lubricating oil consumption detection device includes an oil quantity sensor and a flow meter. The oil quantity sensor is installed in the lubricating oil supply system, and the flow meter is installed on the lubricating oil pipeline.

[0016] Specifically, the lubricating oil consumption detection device is used to monitor the lubricating oil consumption of oil drilling rig chains. The core components of this device include an oil level sensor and a flow meter. First, the oil level sensor is primarily installed in the lubricating oil supply system to monitor the lubricating oil inventory in real time. By detecting changes in the oil level in the tank, it indirectly reflects the lubricating oil consumption. For example, when the oil level sensor detects a drop in the lubricating oil level from 200 liters to 150 liters, it can be determined that 50 liters of lubricating oil have been consumed. Next, the flow meter is installed on the lubricating oil pipeline. By recording the volume of lubricating oil flowing through it per unit time, it measures the actual amount of lubricating oil flowing through the pipeline. For example, it can measure that 10 liters of lubricating oil flow through the pipeline to the drilling rig chain within one hour. By using the oil level sensor and flow meter to accurately detect lubricating oil consumption, the device ensures the normal operation of the lubrication system, monitors lubricating oil consumption in real time, and promptly detects problems when consumption is abnormal, thereby protecting the normal operation of the equipment.

[0017] Step 2: Obtain lubricating oil consumption detection data of the oil drilling rig chain using the lubricating oil consumption detection device. The lubricating oil consumption detection data includes lubricating oil consumption and lubricating oil flow rate.

[0018] Specifically, lubricant consumption monitoring devices are used to acquire lubricant consumption data for the oil drilling rig chain, monitoring lubricant usage. This data includes lubricant consumption amount and flow rate. Lubricant consumption amount refers to the total amount of lubricant consumed over a period of time. For example, the drilling rig chain might consume 50 liters of lubricant in 8 hours of operation. Lubricant flow rate, on the other hand, represents the rate at which lubricant flows through the pipeline per unit time. For example, the flow rate might be 5 liters per minute. By obtaining lubricant consumption trends, excessive or insufficient consumption can be prevented, and potential leaks or equipment malfunctions can be detected early, ensuring the normal operation of the equipment.

[0019] Step 3: Determine the real-time operating mode of the oil drilling rig chain.

[0020] Specifically, determining the real-time operating mode of an oil drilling rig chain refers to identifying the specific working state or mode by monitoring and analyzing the current operating status of the equipment. The operating mode is related to various factors such as the load, speed, and lubrication requirements of the drilling rig chain. Real-time acquisition of operating load indicators for the oil drilling rig chain, including tensile load, operating speed, impact load, and continuous working time, as well as environmental indicators, including ambient temperature and humidity, corrosive gas concentration, and ambient liquid medium, is performed. These multidimensional indicators with different dimensions are then normalized and converted to dimensionless values ​​in the range [0,1]. = Among them, x i Let x be the real-time collected value of the i-th operating condition indicator, min(x) i ) and max(xi These are the historical minimum and maximum values, respectively. Then, based on prior knowledge of the impact of each operating condition index on lubricating oil consumption, such as the Pearson correlation coefficient or expert experience, corresponding weighting coefficients w are assigned. i ,satisfy =1, multiply the normalized values ​​of each indicator by their corresponding weight coefficients and sum them to calculate the comprehensive working condition score S, thus achieving the fusion of multi-dimensional indicators into a unified mode category. The calculation formula is: S= · Finally, the threshold ranges for pre-defined operating conditions are defined, such as S>0.7 for high load mode, 0.3≤S≤0.7 for medium load mode, and S<0.3 for low load mode. The threshold range into which the comprehensive operating condition score S falls is mapped to a specific operating condition label. For example, when the drilling rig chain is operating in high load mode, the chain speed might be detected as 300 rpm, and lubrication demand would increase; in this case, the operating condition mode would be identified as high load mode. Conversely, if the speed decreases to 100 rpm and lubrication demand decreases, it would be identified as low load mode. The system would then automatically adjust operating parameters based on the real-time operating condition mode to optimize lubrication and ensure the performance and lifespan of the equipment under different operating conditions.

[0021] Step 4: Construct a lubricating oil consumption anomaly detection model. Input the real-time operating mode and the lubricating oil consumption detection data into the lubricating oil consumption anomaly detection model to detect lubricating oil consumption anomalies and output lubricating oil consumption anomaly indicators.

[0022] Specifically, a lubricating oil consumption anomaly detection model is constructed to identify potential anomalies during lubricating oil consumption. First, real-time operating conditions and lubricating oil consumption detection data are input into the model. The model then determines whether abnormal lubricating oil consumption exists. If the consumption exceeds a predetermined normal range, an anomaly is detected, and an abnormal lubricating oil consumption index is output. Specifically, the lubricating oil consumption anomaly detection model is a prediction model constructed using a backpropagation (BP) neural network. Its network structure includes an input layer, three hidden layers, and an output layer. The number of nodes in the input layer is the same as the feature dimensions of the real-time operating conditions and lubricating oil consumption detection data. The output layer uses a sigmoid activation function to output a normalized value of the abnormal lubricating oil consumption index between 0 and 1. The hidden layers use a ReLU activation function. The network weights are iteratively updated using backpropagation and gradient descent until the loss function converges.

[0023] Step 5: Convert the abnormal lubricating oil consumption index using the consumption anomaly-quality conversion module, and output the quality anomaly detection result of the oil drilling rig chain.

[0024] Specifically, the consumption anomaly-quality conversion module converts abnormal lubricating oil consumption indicators, linking detected anomalies to equipment quality issues. Anomalies in lubricating oil consumption reflect the equipment's operating status; for example, a sudden increase in the consumption rate indicates accelerated wear or decreased sealing. Next, the consumption anomaly-quality conversion module outputs the quality anomaly detection results for the oil drilling rig chain, assessing the chain's overall health. For instance, if the lubricating oil consumption rate increases from 5 liters per hour to 10 liters per hour, it indicates severe chain wear or sealing problems, prompting relevant maintenance requests. By monitoring the lubricating oil consumption rate, the module assesses chain wear, sealing, and lubrication effectiveness, ultimately reflecting the chain's overall quality and providing accurate maintenance data for equipment managers.

[0025] The aforementioned lubrication consumption analysis-based oil drilling rig chain quality assessment method is applied to an oil drilling rig chain quality assessment system based on lubrication consumption analysis. It can achieve the technical goal of correlation analysis between lubricating oil consumption and equipment health status, enabling continuous, real-time, and accurate monitoring of abnormal lubricating oil consumption to reflect the quality status of the oil drilling rig chain. This eliminates the need for downtime for complex inspections, improving the timeliness and accuracy of equipment maintenance, effectively extending equipment lifespan, and reducing downtime due to failure to address potential problems in a timely manner.

[0026] Furthermore, this application also includes: The lubricating oil consumption detection device also includes a leak sensor, which is installed at the lubricating oil filling point. The device compares the sensing data of the leak sensor with the leak sensing data sample to determine whether there is a lubricating oil leak at the lubricating oil filling point. If a lubricating oil leak is found, a leak warning message is generated. The leak sensing data sample is obtained by analyzing data samples of lubricating oil leak events.

[0027] Specifically, the lubricating oil consumption detection device also includes a leak sensor. The main function of the leak sensor is to monitor whether there is excessive leakage of lubricating oil during the filling process, ensuring that the consumption is normal and not caused by leakage. Since the filling point is the inlet for lubricating oil to flow into the system, the leak sensor is installed at the lubricating oil filling point. For example, when adding lubricating oil, the leak sensor can detect whether abnormal lubricating oil leakage has occurred by detecting oil traces or changes in liquid concentration at the filling point.

[0028] Next, by comparing the leakage sensor data with previously collected leakage sensor data samples, identifying characteristics such as sudden pressure drops and abnormal lubricating oil flow rates, it can be determined whether a leak exists at the current lubricating oil filling point. The leakage sensor data samples collected include changes in liquid concentration and pressure in the environment. For example, if the liquid concentration or pressure changes exceed normal ranges, a leak can be identified.

[0029] When a leak does occur, a corresponding leak alert message is generated. This message not only alerts the operator to the current problem but also transmits it to relevant maintenance personnel so that timely measures can be taken to prevent further losses.

[0030] By installing leak sensors at the filling point, the leak situation is monitored in real time, and the real-time data is compared with historical leak samples to determine whether a leak has occurred. If a leak is confirmed, an alert message is generated, and accurate monitoring and early warning are carried out according to the standards set by the leak sensor data samples.

[0031] Furthermore, this application also includes: Sample data is collected for the operating conditions of the oil drilling rig chain to determine multi-condition sample data. This multi-condition sample data includes operating load indicators and operating environment indicators for the oil drilling rig chain. The operating load indicators include the tensile load, operating speed, impact load, and continuous working time of the drilling rig chain. The operating environment indicators include ambient temperature and humidity, corrosive gas concentration, and ambient liquid medium. Lubricating oil health consumption data samples are obtained corresponding to the multi-condition sample data, including lubricating oil health consumption amount and lubricating oil health consumption rate. Based on the multi-condition sample data and the lubricating oil health consumption data samples under the multi-condition sample data, a model is trained to output a lubricating oil consumption anomaly detection model.

[0032] Specifically, sample data is collected for the operating conditions of the oil drilling rig chain to ensure coverage of all possible operating modes. Operating modes refer not only to the equipment's performance under specific loads but also to the influence of environmental factors. Collecting sample data allows for a more comprehensive understanding of the operating status of the oil drilling rig chain under various loads and environmental conditions.

[0033] Next, the multi-condition sample data mainly consists of operating load indicators and operating environment indicators. Operating load indicators include the tensile load, operating speed, impact load, and continuous working time of the drilling rig chain. For example, the drilling rig chain operated continuously for 6 hours under a tensile load of 1000 Newtons, an operating speed of 200 revolutions per minute, and an impact load of 500 Newtons. On the other hand, operating environment indicators include ambient temperature and humidity, corrosive gas concentration, and ambient liquid medium. For example, the temperature was 35 degrees Celsius, the humidity was 80%, and the concentration of corrosive gases in the air was 0.3%.

[0034] Then, obtain the corresponding lubricating oil health consumption data samples under the multi-operating-condition sample data, that is, the historical lubricating oil consumption. The lubricating oil health consumption data samples include the amount of lubricating oil consumed and the consumption rate. For example, the healthy consumption of lubricating oil is 40 liters, and its consumption rate is 5 liters per hour.

[0035] Finally, based on multi-condition mode sample data and corresponding lubricating oil health consumption data samples, a model is trained to generate a lubricating oil consumption anomaly detection model, which predicts whether lubricating oil consumption will be normal under similar operating conditions in the future. The lubricating oil consumption anomaly detection model outputs warnings of abnormal consumption conditions. For example, when the lubricating oil consumption suddenly increases to 60 liters under a certain operating condition, exceeding the normal range, it indicates that there may be a leak or other equipment problems.

[0036] Based on the equipment load and environmental conditions, the abnormal lubricant consumption detection model can predict and identify abnormal situations in lubricant consumption, thus helping to maintain the normal operation of the equipment.

[0037] Furthermore, this application also includes: The abnormal lubricating oil consumption detection model includes a lubricating oil deterioration feedback layer; the lubricating oil deterioration feedback layer receives particulate matter content change data and color change data of the lubricating oil; based on the particulate matter content change data and the color change data, it obtains lubricating oil deterioration indicators; and uses the lubricating oil deterioration indicators to feed back to the abnormal lubricating oil consumption detection model, thereby adjusting the output abnormal lubricating oil consumption indicators.

[0038] Specifically, the lubricating oil consumption anomaly detection model includes a lubricating oil degradation feedback layer, which focuses on whether the lubricating oil has deteriorated during use. The lubricating oil degradation feedback layer helps determine whether the lubricating oil has already failed or is about to fail by detecting its condition. For example, if the lubricating oil consumption rate increases and the oil quality deteriorates, such as an increase in particulate matter or a darkening of the oil color, the degree of oil degradation is obtained.

[0039] Next, the lubricating oil deterioration feedback layer receives data on changes in particulate matter content and color of the lubricating oil, i.e., it receives important indicators reflecting the quality of the lubricating oil. Particulate matter content change data is acquired in real time through an online particulate counter installed on the lubricating oil pipeline. Specifically, the absolute particulate matter content (unit: mg / L) of the lubricating oil is collected in real time as P. real The corresponding baseline value is P base The real-time acquired color absorbance value is C real The corresponding baseline value is C base First, calculate the rate of change in particulate matter content ΔP and the rate of change in color ΔC: ΔP = ,ΔC= Subsequently, a correction matrix and weighting coefficients are introduced to calculate the normalized lubricant degradation index D. index :D index =α·ln(1+ΔP)+β·ΔC. Where α and β are preset dynamic feature weight factors, and satisfy α+β=1. In this embodiment, α=0.6, β=0.4, and D... index The value range is limited to [0,1]. If the calculated result is greater than 1, it is truncated to 1. Deterioration index D index The consumption anomaly index output by the model will be multiplied as a penalty coefficient to achieve feedback adjustment. For example, taking actual monitoring data after 100 hours of continuous operation by an oil drilling rig, the initial baseline value includes the baseline value P of particulate matter content in the new oil measured during new oil injection. base =15.0mg / L, color absorbance reference value C base =0.20; Real-time data collection includes the current particulate matter content P of the lubricating oil. real =45.0mg / L, color absorbance C real =0.50; The calculation of the change rate includes the particulate matter change rate ΔP=(45.0-15.0) / 15.0=2.0, which means it increased by 2 times; the color change rate ΔC=(0.50-0.20) / 0.20=1.5, which means it deepened by 1.5 times; By substituting the data into the formula, D index =0.6×ln(1+2.0)+0.4×1.5=0.6×1.0986+0.6=0.6592 to calculate the deterioration index. Since the calculation result 0.6592<10.6592<1, the final output lubricating oil deterioration index D is... indexA value of 0.6592 indicates that the lubricating oil has deteriorated, requiring an anomaly alert. The lubricating oil deterioration index is used to feed back into the lubricating oil consumption anomaly detection model, adjusting the output of the anomaly index. Particulate matter content change data refers to the increase in solid particles in the lubricating oil. During long-term use, lubricating oil accumulates particulate matter due to equipment wear or external contamination. For example, if the particulate matter content in the lubricating oil increases from 0.05% to 0.2%, it indicates that the oil may be contaminated. Color change data is obtained in real-time by an online colorimeter installed on the lubricating oil pipeline. The online colorimeter compares the lubricating oil color with a preset color standard level and outputs the color level value as color change data. This refers to the change in the lubricating oil's color. Under normal circumstances, lubricating oil is transparent or pale yellow. If the color turns dark brown or black, it may indicate that the lubricating oil has oxidized or is severely contaminated.

[0040] Then, based on the data on changes in particulate matter content and color change, the deterioration index of the lubricating oil is calculated. The lubricating oil deterioration index is used to quantify the degree of lubricating oil deterioration. Assuming the thresholds for particulate matter content and color change are 0.1% and color grade 3, respectively, if the actual particulate matter content is 0.2% and the color grade is 4, a higher deterioration index is generated, indicating that the lubricating oil needs to be replaced. Specifically, the calculation method for the lubricating oil deterioration index is as follows: The difference between the actual particulate matter content and the baseline particulate matter content value is divided by the baseline particulate matter content value to obtain the particulate matter content change rate; the difference between the actual color change grade value and the baseline color change grade value is divided by the baseline color change grade value to obtain the color change rate; the particulate matter content change rate is multiplied by a preset weighting coefficient for particulate matter content, and the color change rate is multiplied by a preset weighting coefficient for color change; these two products are added together to obtain the lubricating oil deterioration index, where the sum of the preset weighting coefficients for particulate matter content and color change equals 1.

[0041] Finally, the lubricating oil degradation index is fed back to the lubricating oil consumption anomaly detection model to adjust the output lubricating oil consumption anomaly index. Specifically, the calculated lubricating oil degradation index is multiplied by a preset penalty coefficient and then added to the lubricating oil consumption anomaly index value in the output layer of the BP neural network model. If the final value after addition exceeds a preset anomaly threshold, a final anomaly alarm is triggered. If the lubricating oil degradation is severe, the lubricating oil consumption anomaly detection model will adjust the lubricating oil consumption anomaly alarm accordingly. For example, if the lubricating oil degradation index is high, even if the consumption appears normal, an anomaly warning will be issued because the degraded lubricating oil cannot provide effective lubrication.

[0042] Through the lubricating oil degradation feedback layer, data on particulate matter content and color changes are received, lubricating oil degradation indicators are calculated, and these indicators are fed back into the model to adjust the output of abnormal consumption alarms, ensuring the quality of lubricating oil and providing more comprehensive monitoring and early warning functions.

[0043] Furthermore, this application also includes: Obtain the variable factors for each operating condition mode; construct a correlation matrix based on the correlation between the variable factors for each operating condition mode and lubricating oil consumption, wherein the correlation of each element in the correlation matrix is ​​obtained by calculating the Pearson correlation coefficient; introduce the correlation matrix for model training and output a lubricating oil consumption anomaly detection model.

[0044] Specifically, acquiring the variable factors for each operating mode refers to collecting factors affecting lubricant consumption under different working conditions, which are then used to analyze the correlation between each variable factor and lubricant consumption. Variable factors include equipment operating speed, load conditions, and ambient temperature. For example, under high load conditions, the equipment speed reaches 300 revolutions per minute, while the ambient temperature rises to 40 degrees Celsius, affecting lubricant consumption.

[0045] Next, a correlation matrix is ​​constructed based on the correlation between the variable factors and lubricating oil consumption for each operating mode. That is, the correlation matrix is ​​built using the relationship between the variable factors and lubricating oil consumption, with each element representing the strength of the correlation between a certain variable and lubricating oil consumption. The correlation magnitude is calculated using the Pearson correlation coefficient. The correlation matrix can be represented as follows: ; r is the correlation coefficient. As variable factors, This relates to lubricating oil consumption. The correlation coefficient ranges from -1 to 1, with values ​​close to 1 indicating a strong positive correlation, close to -1 indicating a strong negative correlation, and close to 0 indicating no significant correlation. For example, assuming a correlation coefficient of 0.85 between engine speed and lubricating oil consumption, it means that the higher the engine speed, the greater the lubricating oil consumption.

[0046] Then, the constructed correlation matrix is ​​used for model training, outputting a lubricating oil consumption anomaly detection model. During training, the correlation matrix learns the relationship between each variable factor and lubricating oil consumption, adjusts the weights, and learns to detect abnormal lubricating oil consumption. For example, when a specific combination of variables is detected, the lubricating oil consumption anomaly detection model predicts whether the lubricating oil consumption is abnormal and outputs a corresponding alarm. Specifically, during model training, the absolute values ​​of the Pearson correlation coefficients corresponding to each variable factor in the correlation matrix are normalized and used as the initial weight matrix connecting the input layer nodes to the first hidden layer nodes in the BP neural network model. Subsequently, supervised learning is performed using labeled sample data, and the mean squared error is used as the loss function to calculate the error between the predicted consumption and the actual healthy consumption. The initial weights are continuously corrected through the backpropagation algorithm until the loss function converges, thereby outputting the trained lubricating oil consumption anomaly detection model.

[0047] By acquiring variable factors under various operating conditions, a correlation matrix is ​​constructed using the correlation between the variable factors and lubricating oil consumption. The model is then trained, and a model capable of detecting abnormal lubricating oil consumption is output.

[0048] Furthermore, this application also includes: Collect samples of abnormal lubricating oil consumption indicators, as well as actual quality inspection data of the oil drilling rig chain, including wear detection data, fatigue detection data, and crack detection data; record the abnormal chain quality magnitude of the actual quality inspection data as training labels, and output quality anomaly labeling labels; establish a consumption anomaly-quality conversion module according to the mapping relationship between the abnormal lubricating oil consumption indicator samples and the quality anomaly labeling labels.

[0049] Specifically, collecting samples of abnormal lubricating oil consumption indicators refers to obtaining sample data related to abnormal lubricating oil consumption through data acquisition during equipment operation. Actual quality inspection data of the oil drilling rig chain refers to obtaining the actual quality status of the drilling rig chain. Actual quality inspection data includes information such as wear degree, fatigue condition, and crack detection. For example, if the chain wear degree is detected to be 30%, the fatigue service time has reached 500 hours, and microcracks have appeared.

[0050] Next, anomalies in the actual quality inspection data are recorded as labels for training the anomaly-quality conversion module. The degree of equipment quality anomaly is represented by chain wear detection data, fatigue detection data, and crack detection data. For example, if the chain wear reaches 40% or more, it is marked as "severe anomaly," while fatigue time exceeding 600 hours is marked as "moderate anomaly."

[0051] Then, based on the mapping relationship between the abnormal lubricating oil consumption index samples and the quality anomaly labels, the relationship between the degree of abnormal lubricating oil consumption and the actual quality problems of the equipment is analyzed. A consumption anomaly-quality conversion module is constructed to convert the lubricating oil consumption into a prediction of the equipment's quality health status. For example, if the abnormal lubricating oil consumption samples show a sudden increase in consumption, while the corresponding chain wear detection shows severe wear, the conversion module can derive the connection between lubricating oil consumption and equipment quality problems, and provide an early warning of potential quality risks. Specifically, the establishment process of the consumption anomaly-quality conversion module includes: using the abnormal lubricating oil consumption index samples as independent variables and the quality anomaly labels as dependent variables as output, performing function fitting training using a multiple linear regression algorithm; solving the regression coefficients using the least squares method to obtain the conversion function relationship that maps the abnormal lubricating oil consumption index to a specific numerical value of the chain quality anomaly: the chain quality anomaly degree equals a constant regression coefficient plus the first anomaly index multiplied by the first regression coefficient, plus the second anomaly index multiplied by the second regression coefficient, and so on, until the last anomaly index multiplied by its corresponding last regression coefficient is added. This conversion function relationship is then solidified as the consumption anomaly-quality conversion module.

[0052] By collecting samples of abnormal lubricant consumption and actual equipment quality data, equipment quality anomalies are identified. A conversion model between consumption anomalies and equipment quality is established through mapping relationships to predict the health status of the equipment and prevent further damage based on lubricant consumption.

[0053] Furthermore, this application also includes: The structure of the oil drilling rig chain is analyzed to obtain multiple sections of the oil drilling rig chain; based on the multiple sections of the oil drilling rig chain, the number of oil quantity sensors and flow meters of the lubricating oil consumption detection device are configured; the lubricating oil consumption of the multiple sections of the oil drilling rig chain is detected section by section using the configured lubricating oil consumption detection device.

[0054] Specifically, the structure of the oil drilling rig chain is analyzed to understand its design and components, determine the segmentation of the chain, and obtain data on multiple sections of the oil drilling rig chain. For example, a drilling rig chain may consist of 10 sections, each with different lengths and stress distributions, leading to an understanding of lubricant consumption in different parts of the chain.

[0055] Next, based on the number of sections of the oil drilling rig chain, the number of oil quantity sensors and flow meters for lubricating oil consumption detection devices is configured to ensure accurate monitoring of each section of the oil drilling rig chain. For example, if the drilling rig chain has 5 sections, then an oil quantity sensor and flow meter are installed in each section to monitor the supply and consumption of lubricating oil in real time. The number of oil quantity sensors and flow meters is matched to the number of chain sections and the complexity of the structure to ensure comprehensive and accurate monitoring.

[0056] Finally, using the configured lubricant consumption detection device, the lubricant consumption of multiple sections of the oil drilling rig chain is detected segment by segment. Lubricant consumption is monitored independently for each segment of the chain, and the consumption of each segment is recorded and analyzed separately. If the first segment of the chain consumes 2 liters of lubricant and the second segment consumes 3 liters, it can be determined that the chain with higher lubricant demand or abnormal consumption exists, thus providing a reference for equipment maintenance.

[0057] By analyzing the structure of the drilling rig chain and determining the segmentation, the number of sensors for the lubricating oil consumption detection device is configured according to the segmentation. Finally, the consumption of each segment is monitored to more precisely monitor the lubricating oil consumption of each chain segment, enabling timely detection of equipment problems and maintenance optimization.

[0058] In summary, the oil drilling rig chain quality assessment method based on lubrication consumption analysis provided in this application has the following technical advantages: By acquiring a lubricating oil consumption detection device, which is used to detect the lubricating oil consumption of an oil drilling rig chain, the device includes an oil quantity sensor and a flow meter. The oil quantity sensor is installed in the lubricating oil supply system, and the flow meter is installed on the lubricating oil pipeline. Based on the lubricating oil consumption detection device, lubricating oil consumption detection data of the oil drilling rig chain is acquired, including lubricating oil consumption amount and lubricating oil flow rate. The real-time operating mode of the oil drilling rig chain is determined. An abnormal lubricating oil consumption detection model is constructed, and the real-time operating mode and the lubricating oil consumption detection data are input into the system. The lubricating oil consumption anomaly detection model detects lubricating oil consumption anomalies and outputs lubricating oil consumption anomaly indicators. The lubricating oil consumption anomaly indicators are then converted using a consumption anomaly-quality conversion module to output the quality anomaly detection results for the oil drilling rig chain. Ultimately, this achieves the technical goal of correlation analysis between lubricating oil consumption and equipment health status. This enables continuous, real-time, and accurate monitoring of lubricating oil consumption anomalies to reflect the quality status of the oil drilling rig chain without requiring downtime for complex inspections. This not only improves the timeliness and accuracy of equipment maintenance but also effectively extends equipment lifespan and reduces downtime due to failure to address potential problems in a timely manner.

[0059] Example 2: Based on the same inventive concept as the oil drilling rig chain quality assessment method based on lubrication consumption analysis in the previous examples, this application also provides an oil drilling rig chain quality assessment system based on lubrication consumption analysis. Please refer to the appendix. Figure 2 ,include: The system includes a lubricating oil consumption detection device acquisition module 11, used to acquire information about a lubricating oil consumption detection device. This device is used to detect the lubricating oil consumption of the oil drilling rig chain. The lubricating oil consumption detection device includes an oil quantity sensor and a flow meter, wherein the oil quantity sensor is installed in the lubricating oil supply system, and the flow meter is installed on the lubricating oil pipeline. A lubricating oil consumption detection data acquisition module 12 is used to acquire lubricating oil consumption detection data of the oil drilling rig chain based on the lubricating oil consumption detection device. This data includes lubricating oil consumption amount and lubricating oil flow rate. A real-time operating condition mode determination module 13 is used to determine the real-time operating condition mode of the oil drilling rig chain. A lubricating oil consumption anomaly index output module 14 is used to construct a lubricating oil consumption anomaly detection model. The real-time operating condition mode and the lubricating oil consumption detection data are input into the model to detect lubricating oil consumption anomalies, and the model outputs a lubricating oil consumption anomaly index. A quality anomaly detection result output module 15 is used to convert the lubricating oil consumption anomaly index through a consumption anomaly-quality conversion module, and output the quality anomaly detection result of the oil drilling rig chain.

[0060] Furthermore, the oil drilling rig chain quality assessment system based on lubrication consumption analysis is also used for: The lubricating oil consumption detection device also includes a leak sensor, which is installed at the lubricating oil filling point. The device compares the sensing data of the leak sensor with the leak sensing data sample to determine whether there is a lubricating oil leak at the lubricating oil filling point. If a lubricating oil leak is found, a leak warning message is generated. The leak sensing data sample is obtained by analyzing data samples of lubricating oil leak events.

[0061] Furthermore, the oil drilling rig chain quality assessment system based on lubrication consumption analysis is also used for: Sample data is collected for the operating conditions of the oil drilling rig chain to determine multi-condition sample data. This multi-condition sample data includes operating load indicators and operating environment indicators for the oil drilling rig chain. The operating load indicators include the tensile load, operating speed, impact load, and continuous working time of the drilling rig chain. The operating environment indicators include ambient temperature and humidity, corrosive gas concentration, and ambient liquid medium. Lubricating oil health consumption data samples are obtained corresponding to the multi-condition sample data, including lubricating oil health consumption amount and lubricating oil health consumption rate. Based on the multi-condition sample data and the lubricating oil health consumption data samples under the multi-condition sample data, a model is trained to output a lubricating oil consumption anomaly detection model.

[0062] Furthermore, the oil drilling rig chain quality assessment system based on lubrication consumption analysis is also used for: The abnormal lubricating oil consumption detection model includes a lubricating oil deterioration feedback layer; the lubricating oil deterioration feedback layer receives particulate matter content change data and color change data of the lubricating oil; based on the particulate matter content change data and the color change data, it obtains lubricating oil deterioration indicators; and uses the lubricating oil deterioration indicators to feed back to the abnormal lubricating oil consumption detection model, thereby adjusting the output abnormal lubricating oil consumption indicators.

[0063] Furthermore, the oil drilling rig chain quality assessment system based on lubrication consumption analysis is also used for: Obtain the variable factors for each operating condition mode; construct a correlation matrix based on the correlation between the variable factors for each operating condition mode and lubricating oil consumption, wherein the correlation of each element in the correlation matrix is ​​obtained by calculating the Pearson correlation coefficient; introduce the correlation matrix for model training and output a lubricating oil consumption anomaly detection model.

[0064] Furthermore, the oil drilling rig chain quality assessment system based on lubrication consumption analysis is also used for: Collect samples of abnormal lubricating oil consumption indicators, as well as actual quality inspection data of the oil drilling rig chain, including wear detection data, fatigue detection data, and crack detection data; record the abnormal chain quality magnitude of the actual quality inspection data as training labels, and output quality anomaly labeling labels; establish a consumption anomaly-quality conversion module according to the mapping relationship between the abnormal lubricating oil consumption indicator samples and the quality anomaly labeling labels.

[0065] Furthermore, the oil drilling rig chain quality assessment system based on lubrication consumption analysis is also used for: The structure of the oil drilling rig chain is analyzed to obtain multiple sections of the oil drilling rig chain; based on the multiple sections of the oil drilling rig chain, the number of oil quantity sensors and flow meters of the lubricating oil consumption detection device are configured; the lubricating oil consumption of the multiple sections of the oil drilling rig chain is detected section by section using the configured lubricating oil consumption detection device.

[0066] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. The oil rig chain quality assessment method and specific examples based on lubrication consumption analysis in Embodiment 1 are also applicable to the oil rig chain quality assessment system based on lubrication consumption analysis in this embodiment. Through the foregoing detailed description of the oil rig chain quality assessment method based on lubrication consumption analysis, those skilled in the art can clearly understand the oil rig chain quality assessment system based on lubrication consumption analysis in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and relevant parts can be referred to in the method section.

[0067] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0068] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for evaluating the quality of oil drilling rig chains based on lubrication consumption analysis, characterized in that, The methods include: A lubricating oil consumption detection device is provided, which is used to detect the consumption of lubricating oil in an oil drilling rig chain. The lubricating oil consumption detection device includes an oil quantity sensor and a flow meter, wherein the oil quantity sensor is installed in the lubricating oil supply system and the flow meter is installed on the lubricating oil pipeline. According to the lubricating oil consumption detection device, the lubricating oil consumption detection data of the oil drilling rig chain is obtained, and the lubricating oil consumption detection data includes the lubricating oil consumption and the lubricating oil flow rate; Determine the real-time operating mode of the oil drilling rig chain; A lubricating oil consumption anomaly detection model is constructed. The real-time operating condition mode and the lubricating oil consumption detection data are input into the lubricating oil consumption anomaly detection model to detect lubricating oil consumption anomalies and output lubricating oil consumption anomaly indicators. The abnormal lubricating oil consumption detection model includes a lubricating oil deterioration feedback layer. The lubricating oil degradation feedback layer receives data on changes in particulate matter content and color of the lubricating oil. Based on the particulate matter content change data and the color change data, the lubricating oil deterioration index is obtained; The lubricating oil deterioration index is used to feed back the lubricating oil consumption anomaly detection model, and the output lubricating oil consumption anomaly index is adjusted accordingly. The lubricating oil consumption anomaly index is converted by the consumption anomaly-quality conversion module, and the quality anomaly detection result of the oil drilling rig chain is output. Collect samples of abnormal lubricating oil consumption indicators, as well as actual quality inspection data of the oil drilling rig chain, including wear detection data, fatigue detection data, and crack detection data; Record the chain anomaly quality magnitude from the actual quality detection data as training labels, and output quality anomaly annotation labels; Based on the mapping relationship between the lubricating oil consumption anomaly index samples and the quality anomaly labeling, a consumption anomaly-quality conversion module is established.

2. The method as described in claim 1, characterized in that, The lubricating oil consumption detection device also includes a leakage sensor, wherein the leakage sensor is installed at the lubricating oil filling point; The system compares the data from the leak sensor with the leak sensor data sample to determine whether there is a lubricating oil leak at the lubricating oil filling point. If a lubricating oil leak is found, a leak warning message is generated. The leak sensor data sample is obtained by analyzing data samples from lubricating oil leak events.

3. The method as described in claim 1, characterized in that, The method for constructing an abnormal lubricating oil consumption detection model includes: Sample data were collected for the working conditions of the oil drilling rig chain to determine multi-condition sample data. The multi-condition sample data includes the working load index and working environment index of the oil drilling rig chain. The working load index includes the tensile load, operating speed, impact load and continuous working time of the drilling rig chain. The working environment index includes ambient temperature and humidity, corrosive gas concentration and ambient liquid medium. Obtain lubricating oil health consumption data samples corresponding to the multi-operating-condition mode sample data respectively, wherein the lubricating oil health consumption data samples include lubricating oil health consumption amount and lubricating oil health consumption rate; The model is trained based on the multi-condition mode sample data and the lubricating oil health consumption data sample under the multi-condition mode sample data, and the output lubricating oil consumption anomaly detection model is generated.

4. The method as described in claim 3, characterized in that, Model training is performed based on the multi-operating-condition sample data and the lubricating oil health consumption data samples under the multi-operating-condition sample data. The method includes: Obtain the variable factors for each operating condition mode; A correlation matrix is ​​constructed based on the correlation between the variable factors of each operating mode and the lubricating oil consumption. The correlation of each element in the correlation matrix is ​​obtained by calculating the Pearson correlation coefficient. The correlation matrix is ​​used for model training, and an abnormal lubricating oil consumption detection model is output.

5. The method as described in claim 1, characterized in that, The lubricating oil consumption detection device is used to detect the consumption of lubricating oil in an oil drilling rig chain, and the method further includes: The structure of the oil drilling rig chain was analyzed to obtain multiple sections of the oil drilling rig chain; Based on the multi-section oil drilling rig chain, configure the number of oil quantity sensors and flow meters of the lubricating oil consumption detection device; The lubricating oil consumption is detected section by section using the configured lubricating oil consumption detection device of the multi-section oil drilling rig chain.

6. A quality assessment system for oil drilling rig chains based on lubrication consumption analysis, characterized in that, The steps for implementing the oil drilling rig chain quality assessment method based on lubrication consumption analysis as described in any one of claims 1 to 5 include: A lubricating oil consumption detection device acquisition module is used to acquire a lubricating oil consumption detection device. The lubricating oil consumption detection device is used to detect the consumption of lubricating oil in an oil drilling rig chain. The lubricating oil consumption detection device includes an oil quantity sensor and a flow meter. The oil quantity sensor is installed in the lubricating oil supply system, and the flow meter is installed on the lubricating oil pipeline. The lubricating oil consumption detection data acquisition module is used to acquire the lubricating oil consumption detection data of the oil drilling rig chain according to the lubricating oil consumption detection device. The lubricating oil consumption detection data includes the lubricating oil consumption amount and the lubricating oil flow rate. A real-time operating condition mode determination module is used to determine the real-time operating condition mode of the oil drilling rig chain. The lubricating oil consumption anomaly output module is used to construct a lubricating oil consumption anomaly detection model. The real-time operating mode and the lubricating oil consumption detection data are input into the lubricating oil consumption anomaly detection model to detect lubricating oil consumption anomalies and output lubricating oil consumption anomaly indicators. The quality anomaly detection result output module is used to convert the lubricating oil consumption anomaly index through the consumption anomaly-quality conversion module and output the quality anomaly detection result of the oil drilling rig chain.

Images