Anti-blocking lubricating grease supply system based on self-cleaning structure

Abstract

The invention discloses an anti-blocking lubricating grease supply system based on a self-cleaning structure. The system comprises a multi-mode sensing and data acquisition unit, a graph neural network feature extraction and processing unit and the like. The multi-modal sensing unit collects multi-dimensional data such as pressure and flow in real time, the multi-dimensional data is converted into node features through the graph neural network unit, a graph data model is constructed, the features are deeply extracted, and the improved Gaussian mixture model unit analyzes the running state of the system in a clustering mode according to the features. The intelligent decision-making unit matches a control instruction according to an analysis result, the self-cleaning execution unit is driven to achieve impurity interception and pipeline cleaning through the rotatable interception net and the high-pressure pulse cleaning device, and meanwhile the grease supply adjusting unit accurately regulates and controls the rotating speed of a grease pump, the opening degree of a throttling valve and pressure compensation. Through combination of multi-unit cooperation and an innovative model, intelligent monitoring of the running state of the lubricating grease supply system, blockage risk identification and active anti-blockage treatment are achieved, and stable running of the system is guaranteed.

Description

Technical Field

[0001] The invention relates to the field of lubricating grease management in oil production, and in particular to an anti-clogging lubricating grease supply system based on a self-cleaning structure. Background Art

[0002] In the field of oil extraction, drilling equipment and oil extraction machinery need to operate continuously in a complex environment of high temperature, high pressure and high dust for a long time. The lubricating grease supply system is a key link to ensure the normal operation of the equipment, and its performance directly affects the production efficiency and equipment life. As the mining operation expands to complex areas such as deep sea and shale formations, the traditional lubricating grease supply system can no longer meet the stringent requirements of modern oil extraction, and innovation is imperative.

[0003] Existing lubricating grease supply systems have significant defects in data processing. Most systems are only equipped with basic sensors and cannot fully obtain multi-dimensional data such as pressure distribution and grease flow in the pipeline. In addition, traditional systems lack deep analysis architectures such as graph neural network feature extraction and processing units. They cannot convert data into node features to build graph data models, and it is difficult to mine the spatial correlation between data based on the pipeline topology structure. It is even more impossible to use the improved Gaussian mixture model analysis unit to perform cluster analysis on the system operation status, resulting in potential blockage risks that are difficult to identify in a timely manner.

[0004] In terms of anti-clogging and self-cleaning functions, traditional systems usually rely only on simple filters to filter impurities, which makes it difficult to dynamically intercept impurities such as sand and metal debris mixed in under complex working conditions, which can easily cause pipeline blockage. At the same time, it is impossible to automatically start the cleaning program according to the system operating status, and manual maintenance is not only inefficient and costly, but also has the problem of incomplete cleaning, making it difficult to maintain the performance of the lubricant and the smooth flow of the pipeline. Summary of the invention

[0005] In order to overcome the shortcomings and deficiencies of the prior art, the present invention provides an anti-clogging lubricating grease supply system based on a self-cleaning structure.

[0006] The technical solution adopted by the present invention is an anti-clogging lubricating grease supply system based on a self-cleaning structure, comprising: Multimodal sensing and data acquisition unit, which consists of a high-precision pressure sensor array, a flow monitoring module, a temperature sensing component and an impurity concentration detection probe. The high-precision pressure sensor array is used to obtain real-time pressure distribution data in the pipeline; the flow monitoring module uses ultrasonic flow measurement technology to measure the grease flow; the temperature sensing component is used to obtain temperature information during the grease transportation process; the impurity concentration detection probe uses the optical scattering principle to detect the impurity concentration in the grease; Graph neural network feature extraction and processing unit, which includes a multi-layer graph convolutional neural network architecture, receives data of pressure, flow rate, temperature and impurity concentration transmitted by the multi-modal perception and data acquisition unit, converts them into node features, and constructs a graph data model containing pipeline topological structure information; Improved Gaussian mixture model analysis unit, which introduces an adaptive weight adjustment mechanism and a dynamic covariance matrix update strategy, receives the feature vectors output by the graph neural network feature extraction and processing unit, and performs clustering analysis on the operating state of the grease supply system through the improved Gaussian mixture model to identify normal operating modes and potential blockage risk modes; Intelligent decision-making and control unit, which receives the analysis results of the improved Gaussian mixture model analysis unit, has a preset control strategy library built-in, and matches corresponding control instructions from the control strategy library according to the analysis results; Self-cleaning execution unit, which consists of a rotatable impurity interception net, a high-pressure pulse cleaning device and an impurity collection chamber. The rotatable impurity interception net is driven by a servo motor to rotate to dynamically intercept impurities in the grease; the high-pressure pulse cleaning device sprays high-pressure pulsed water flow into the pipeline after receiving the control instructions from the intelligent decision-making and control unit to clean the interception net and the inner wall of the pipeline; the impurities generated by the cleaning are drained to the impurity collection chamber through the pipeline; Grease supply regulation unit, which consists of a grease pump driven by frequency conversion, an adjustable throttle valve and a pressure compensation device. The grease pump driven by frequency conversion adjusts the rotation speed according to the control instructions of the intelligent decision-making and control unit to change the grease supply; the adjustable throttle valve is installed in the conveying pipeline and adjusts the opening through an electric actuator to control the grease flow; the pressure compensation device monitors the pipeline pressure in real time and adjusts the output pressure according to the control instructions to maintain the pipeline pressure stable.

[0007] The forward propagation process of the graph convolutional neural network architecture adopted in the graph neural network feature extraction and processing unit satisfies the following formula: Where, 、 represent the node feature matrices of the th layer and the th layer of the graph convolutional neural network, and each row represents the feature vector of a node; is the adjacency matrix with self-loops added, is the original adjacency matrix constructed according to the topological structure of the lubricating grease conveying pipeline, is the identity matrix; is the diagonal node degree matrix of , and the diagonal element is the weight matrix of the th layer, which is used to transform the node features; is the activation function.

[0008] Furthermore, for the improved Gaussian mixture model analysis unit, the probability density function of the improved Gaussian mixture model is as follows:

[0009] where, is the probability density function, is the feature vector output by the graph neural network feature extraction and processing unit, with the dimension of is the number of components of the Gaussian mixture model, which is preset according to the complexity of the operating state of the lubricating grease supply system; is the th weight of the Gaussian component, and satisfies , and its value is dynamically updated according to the system operation data through the adaptive weight adjustment mechanism; is the th mean vector of the Gaussian component; is the th covariance matrix of the Gaussian component, and adopts the dynamic covariance matrix update strategy, which is adjusted in real time according to the change of data distribution, is the inverse of the covariance matrix, is the index variable in the summation operation.

[0010] Furthermore, the graph neural network feature extraction and processing unit further includes an attention mechanism module, and the calculation process of this module satisfies the formula:

[0011] where, and respectively represent the feature vectors of nodes and node in the graph data, is the total number of nodes in the graph; represents the concatenation operation of the two feature vectors; is the activation function; is the weight matrix of the attention mechanism module; is the attention coefficient of node to node , which reflects the importance of the feature of node to node ; is the new feature vector of node after being processed by the attention mechanism, T represents the transpose operation of the matrix, , j are the index variables in the summation operation.

[0012] Furthermore, for the improved Gaussian mixture model analysis unit, the update formula of the adaptive weight adjustment mechanism is:

[0013]

[0014] wherein, represents the number of iterations; is the number of samples in the current batch; and are the weights of the -th and -th Gaussian components at the -th iteration; is the posterior probability that the sample at the -th iteration belongs to the -th Gaussian component; is the probability density value of the Gaussian distribution with as the mean vector and as the covariance matrix at ; where is the mean vector of the -th Gaussian component at the i -th iteration, and j and i are index variables in the summation operation.

[0015] Furthermore, when constructing the graph data model, the graph neural network feature extraction and processing unit considers the factor of pipe diameter change, and the construction formula of node features is: where is the feature vector of node ; is the pressure value at node , which is obtained by the pressure sensor in the multi-modal perception and data acquisition unit; is the grease flow rate value at node , which is measured by the flow monitoring module; is the temperature value at node , which is collected by the temperature sensing component; is the impurity concentration in the grease in the area corresponding to node , which is detected by the impurity concentration detection probe; is the pipe diameter value of the pipeline where node is located, which is preset according to the pipeline design parameters.

[0016] Furthermore, the dynamic covariance matrix update strategy of the improved Gaussian mixture model analysis unit satisfies the formula:

[0017] Among them, represents the number of iterations; is the number of samples in the current batch; is the posterior probability that the sample belongs to the th Gaussian component at the th iteration; is the sample feature vector; is the th mean vector of the th Gaussian component at the th iteration; is the regularization parameter used to prevent the covariance matrix from being singular;

[0018] Furthermore, the matching rule of the control strategy library in the intelligent decision-making and control unit is constructed by a graph neural network, and the matching process satisfies the formula:

[0019] Among them, is the analysis result vector output by the improved Gaussian mixture model analysis unit; represents processing the analysis result vector by a graph neural network to mine the correlation relationships among various factors in the analysis result; is the weight matrix of the matching rule; is the matching probability vector of each control strategy in the control strategy library. According to this vector, the control strategy with the highest probability is selected as the final control instruction,

[0020] Furthermore, for the grease supply adjustment unit, the speed adjustment formula of the variable-frequency driven grease pump is: , where is the adjusted speed of the grease pump; is the initial speed of the grease pump; is the speed adjustment step size; is the control instruction vector output by the intelligent decision-making and control unit; is the speed adjustment coefficient calculated according to the control instruction vector.

[0021] For the anti-blocking lubricating grease supply system based on a self-cleaning structure, the operation of this system includes the following steps: Step 1: The multi-modal perception and data acquisition unit collects the pressure data, grease flow data, temperature data in the lubricating grease delivery pipeline and the grease impurity concentration data at the oil outlet of the storage tank in real time according to the preset sampling frequency, and transmits the collected data to the graph neural network feature extraction and processing unit through the high-speed data transmission bus; Step 2: The graph neural network feature extraction and processing unit receives the data transmitted by the multi-modal perception and data acquisition unit, converts it into node features, constructs a graph data model based on the topological structure of the lubricating grease pipeline, extracts and fuses features from the graph data through a multi-layer graph convolutional neural network architecture, mines the spatial correlation relationships between the data, outputs the processed feature vectors, and transmits them to the improved Gaussian mixture model analysis unit; Step 3: The improved Gaussian mixture model analysis unit receives the feature vectors output by the graph neural network feature extraction and processing unit, uses the improved Gaussian mixture model, performs clustering analysis on the operating state of the grease supply system through an adaptive weight adjustment mechanism and a dynamic covariance matrix update strategy, identifies the normal operating mode and potential blockage risk mode of the system, outputs the analysis results and transmits them to the intelligent decision-making and control unit; Step 4: The intelligent decision-making and control unit receives the analysis results of the improved Gaussian mixture model analysis unit, based on the built-in control strategy library, selects the corresponding control instructions from the control strategy library through specific matching rules, and transmits the control instructions to the self-cleaning execution unit and the grease supply adjustment unit respectively; Step 5: After receiving the control instructions from the intelligent decision-making and control unit, the self-cleaning execution unit drives the rotatable impurity interception net to rotate by a servo motor to intercept impurities in the grease. At the same time, the high-pressure pulse cleaning device sprays high-pressure pulse water flow into the pipeline according to the control instructions to clean the interception net and the inner wall of the pipeline, and the impurities generated by the cleaning are drained to the impurity collection chamber; Step 6: After receiving the control instructions from the intelligent decision-making and control unit, the grease supply adjustment unit adjusts the rotation speed of the grease pump driven by frequency conversion according to the control instructions, the adjustable throttle valve adjusts the opening degree through an electric actuator, and the pressure compensation device monitors the pipeline pressure in real time and adjusts the output pressure according to the control instructions to complete the adjustment of the lubricating grease supply volume and the pipeline pressure.

[0022] Beneficial effects: The present invention proposes an anti-clogging lubricating grease supply system based on a self-cleaning structure. In terms of data processing and analysis, the multimodal perception and data acquisition unit uses high-precision pressure sensor arrays, flow monitoring modules and other components. Compared with the single and inefficient data acquisition method of the traditional system, it can comprehensively obtain multi-dimensional data such as pressure distribution, flow, temperature and impurity concentration in the lubricating grease delivery process. The graph neural network feature extraction and processing unit combines the pipeline topology structure to build a graph data model, and uses the graph convolutional neural network architecture and attention mechanism to deeply mine the spatial correlation between data, changing the situation where traditional systems cannot effectively process complex data; the improved Gaussian mixture model analysis unit accurately identifies the system operation mode through adaptive weight adjustment and dynamic covariance matrix update, which greatly improves the ability to identify potential blockage risks compared to the traditional fixed threshold judgment method. In terms of anti-clogging and self-cleaning functions, the rotatable impurity interception net and high-pressure pulse cleaning device of the self-cleaning execution unit replace the simple filter filtration of the traditional system, realize dynamic interception and active cleaning of impurities, and avoid impurities clogging the pipeline; the intelligent decision-making and control unit accurately matches instructions from the control strategy library based on the analysis results of the improved Gaussian mixture model, and links the self-cleaning execution unit and the grease supply adjustment unit to accurately adjust the grease pump speed, throttle valve opening and pressure compensation to ensure smooth pipeline operation and stable grease supply, solving the problem of the traditional system's lack of active cleaning mechanism and precise control capabilities, and significantly improving the reliability and stability of the lubricating grease supply system. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a diagram of the system unit composition of the present invention; Figure 2 The present invention is a flowchart of the system operation steps. DETAILED DESCRIPTION

[0024] like Figure 1 As shown, the anti-clogging lubricating grease supply system based on the self-cleaning structure includes: A multimodal sensing and data acquisition unit, which consists of a high-precision pressure sensor array, a flow monitoring module, a temperature sensing component, and an impurity concentration detection probe. The high-precision pressure sensor array is installed at each key node of the lubricating grease delivery pipeline in a distributed manner to obtain real-time pressure distribution data in the pipeline; the flow monitoring module is arranged on the main grease supply channel, and uses ultrasonic flow measurement technology to accurately measure the grease flow; the temperature sensing component is tightly attached to the outer wall of the delivery pipeline to obtain temperature information during grease delivery; the impurity concentration detection probe is arranged at the oil outlet of the oil storage tank, and uses the optical scattering principle to detect the impurity concentration in the grease. The multimodal sensing and data acquisition unit is connected to the subsequent unit through a high-speed data transmission bus; Specifically, the multi-modal perception and data acquisition unit is the basic module for the entire system to obtain operation information. It consists of a high-precision pressure sensor array, a flow monitoring module, a temperature sensing component, and an impurity concentration detection probe. In the lubricating grease delivery pipeline, the pressure distribution is crucial for the system operation. The high-precision pressure sensor array is installed at each key node in a distributed manner. These sensors can accurately sense the pressure values at different positions in the pipeline in real time. For example, at positions prone to pressure changes such as pipeline bends and near valves, they can precisely obtain pressure data, providing a basis for the system to judge the smoothness of grease delivery. The flow monitoring module is set on the main grease supply channel. Using ultrasonic flow measurement technology, it can accurately measure the grease flow rate passing through per unit time. This data directly reflects the grease supply efficiency. Once the flow rate shows abnormal fluctuations, it may indicate pipeline blockage or other faults.

[0025] The temperature sensing component is closely attached to the outer wall of the delivery pipeline to continuously monitor the temperature changes during grease delivery. Excessive temperature may cause the grease viscosity to decrease, affecting the lubrication effect; too low temperature may make the grease thicken, increasing the delivery resistance and even causing blockage. The impurity concentration detection probe is arranged at the oil outlet of the storage tank. Using the principle of optical scattering, it detects the impurity content in the grease about to enter the delivery pipeline. Impurities are an important factor causing pipeline blockage. By real-time monitoring the impurity concentration, the blockage problem caused by impurity accumulation can be prevented in advance. The data such as pressure, flow rate, temperature, and impurity concentration collected by this unit are quickly and stably transmitted to the subsequent unit through a high-speed data transmission bus, providing comprehensive and accurate raw data support for the system's analysis and decision-making.

[0026] The graph neural network feature extraction and processing unit, which contains a multi-layer graph convolutional neural network architecture, receives the pressure, flow rate, temperature, and impurity concentration data transmitted by the multi-modal perception and data acquisition unit, converts them into node features, constructs a graph data model containing pipeline topology structure information, extracts and fuses features from the graph data through graph convolutional operations, mines the spatial correlation relationships between data, outputs the processed feature vectors, and transmits them to the improved Gaussian mixture model analysis unit; Specifically, after receiving the data transmitted by the multi-modal perception and data acquisition unit, the graph neural network feature extraction and processing unit deeply processes these raw data. It contains a multi-layer graph convolutional neural network architecture. First, it converts the data such as pressure, flow rate, temperature, and impurity concentration into node features, and at the same time combines the topology structure information of the lubricating grease delivery pipeline to construct a graph data model. In this model, each node represents a monitoring point or a key part in the pipeline, and the connection relationship between nodes reflects the actual layout of the pipeline.

[0027] Through graph convolution operations, this unit can deeply explore the spatial correlation relationships between data based on the pipeline topological structure. For example, when the pressure at a certain node changes, the graph neural network can analyze the possible impacts on the pressure, flow rate, and other data of other nodes connected to this node, thereby identifying the patterns and potential trends of data changes. This kind of exploration of the spatial correlation relationships between data can, compared with traditional data processing methods, understand the operating state of the lubricating grease supply system more comprehensively and accurately, and extract more valuable feature information. After processing, this unit outputs the processed feature vectors and transmits them to the improved Gaussian mixture model analysis unit, providing key data for subsequent analysis of the system operating state.

[0028] The improved Gaussian mixture model analysis unit is based on the traditional Gaussian mixture model and is improved by introducing an adaptive weight adjustment mechanism and a dynamic covariance matrix update strategy. It receives the feature vectors output by the graph neural network feature extraction and processing unit, and conducts clustering analysis on the operating state of the grease supply system through the improved Gaussian mixture model, identifying the normal operating mode and the potential blockage risk mode, outputting the analysis results and transmitting them to the decision-making and control unit; Specifically, the improved Gaussian mixture model analysis unit has made innovative improvements based on the traditional Gaussian mixture model, introducing an adaptive weight adjustment mechanism and a dynamic covariance matrix update strategy. It receives the feature vectors output by the graph neural network feature extraction and processing unit, and these feature vectors contain the key information of the operating state of the lubricating grease supply system.

[0029] The improved Gaussian mixture model conducts clustering analysis on these feature vectors to divide the operating state of the system into different modes. Among them, the adaptive weight adjustment mechanism can dynamically adjust the weights of each Gaussian component according to the changes in the actual operating data of the system, enabling the model to better adapt to the diversity of the system operating state; the dynamic covariance matrix update strategy adjusts the covariance matrix in real time according to the changes in the data distribution, thereby more accurately describing the feature distribution of the system operating state. In this way, this unit can accurately identify the normal operating mode and the potential blockage risk mode of the system. Once the potential blockage risk mode is detected, it will promptly transmit the analysis results to the decision-making and control unit, providing a decision-making basis for the system to take corresponding anti-blockage measures.

[0030] The intelligent decision-making and control unit receives the analysis results of the improved Gaussian mixture model analysis unit, has a built-in preset control strategy library, matches the corresponding control instructions from the control strategy library according to the analysis results, and transmits the control instructions to the self-cleaning execution unit and the grease supply adjustment unit respectively; Specifically, the intelligent decision-making and control unit is the core decision-making module of the entire system. It receives the analysis results of the system operating state output by the improved Gaussian mixture model analysis unit. This unit has a built-in preset control strategy library, which stores a variety of control strategies for different operating states and blockage risk situations.

[0031] After receiving the analysis results, the intelligent decision-making and control unit will select the most suitable control instruction for the current system state from the control strategy library according to the preset matching rules. For example, if a potential blockage risk is detected in the system, it will select corresponding control instructions such as starting the self-cleaning program, adjusting the grease supply amount or pressure according to the degree and specific situation of the blockage risk. These control instructions are respectively transmitted to the self-cleaning execution unit and the grease supply adjustment unit to achieve precise control of the system. The intelligent decision-making and control unit ensures that the system can respond to various situations in a timely and effective manner, maintain the stable operation of the lubricating grease supply system, and avoid the occurrence of blockage problems through accurate judgment and reasonable decision-making on the system operating state.

[0032] The self-cleaning execution unit consists of a rotatable impurity interception net, a high-pressure pulse cleaning device, and an impurity collection chamber. The rotatable impurity interception net is installed in the conveying pipeline and is driven by a servo motor to rotate to achieve dynamic interception of impurities in the grease. The high-pressure pulse cleaning device is connected to the conveying pipeline and sprays high-pressure pulse water flow into the pipeline after receiving the control instruction from the intelligent decision-making and control unit to clean the interception net and the inner wall of the pipeline. The impurities generated by the cleaning are drained to the impurity collection chamber through the pipeline. The self-cleaning execution unit is connected to the intelligent decision-making and control unit through a control signal line. Specifically, the self-cleaning execution unit is an important execution module for the system to achieve the anti-blockage function. It consists of a rotatable impurity interception net, a high-pressure pulse cleaning device, and an impurity collection chamber. The rotatable impurity interception net is installed in the conveying pipeline and is driven by a servo motor to rotate. During the grease conveying process, it continuously intercepts impurities in the grease. The rotating design enables the interception net to contact the grease more comprehensively, improving the impurity interception efficiency and effectively preventing impurities from accumulating in the pipeline.

[0033] After the intelligent decision-making and control unit issues a control instruction, the high-pressure pulse cleaning device starts to work. It is connected to the conveying pipeline and sprays high-pressure pulse water flow into the pipeline. This high-pressure pulse water flow has a strong impact force and can wash off the impurities attached to the surface of the interception net and the inner wall of the pipeline. The impurities generated by the cleaning are drained to the impurity collection chamber through a specially designed pipeline, thus completing the removal of impurities. The self-cleaning execution unit keeps the pipeline clean and unobstructed by automatically intercepting impurities and regularly cleaning, fundamentally reducing the possibility of blockage and ensuring the normal transportation of lubricating grease.

[0034] The grease supply regulation unit consists of a frequency - converted driven grease pump, an adjustable throttle valve, and a pressure compensation device. The frequency - converted driven grease pump adjusts its rotational speed according to the control instructions of the intelligent decision - making and control unit, changing the grease supply amount. The adjustable throttle valve is installed in the conveying pipeline and adjusts the opening degree through an electric actuator to control the grease flow rate. The pressure compensation device monitors the pipeline pressure in real - time and adjusts the output pressure according to the control instructions to maintain the stability of the pipeline pressure. The grease supply regulation unit is connected to the intelligent decision - making and control unit through a control signal line.

[0035] Specifically, the grease supply regulation unit is responsible for precisely regulating the grease supply process. It consists of a frequency - converted driven grease pump, an adjustable throttle valve, and a pressure compensation device. The frequency - converted driven grease pump adjusts its rotational speed according to the control instructions of the intelligent decision - making and control unit, precisely controlling the grease supply amount by changing the rotational speed. When the system detects that a certain part requires more grease lubrication, the rotational speed of the grease pump increases to increase the grease supply; conversely, it decreases the rotational speed to reduce the supply, ensuring that the grease supply matches the actual needs of the equipment.

[0036] The adjustable throttle valve is installed in the conveying pipeline and adjusts the opening degree through an electric actuator to further precisely control the grease flow rate. Under different working conditions, the throttle valve can adjust the opening degree as needed to keep the grease flow rate stable within a suitable range. The pressure compensation device monitors the pipeline pressure in real - time. When the pipeline pressure changes due to various factors, the pressure compensation device adjusts the output pressure according to the control instructions to maintain the stability of the pipeline pressure. Stable pressure is crucial for the smooth conveyance of grease, which can avoid problems such as unsmooth grease conveyance or even blockage caused by pressure fluctuations. The grease supply regulation unit ensures the stable and efficient operation of the grease supply system under various working conditions through the coordinated regulation of the grease supply amount, flow rate, and pressure.

[0037] Preferably, in the graph neural network feature extraction and processing unit, the forward propagation process of the adopted graph convolutional neural network architecture satisfies the following formula:

[0038] where, represents the node feature matrix of the -th layer of the graph convolutional neural network, and each row represents the feature vector of a node; is the adjacency matrix with self - loops added, is the original adjacency matrix constructed according to the topological structure of the grease conveying pipeline, is the identity matrix; is the diagonal node degree matrix of , and its diagonal element is the weight matrix of the -th layer, which is used to transform the node features; As the activation function, the ReLU function is adopted; this formula realizes the feature extraction and fusion of the data of pressure, flow rate, temperature and impurity concentration in the lubricating grease supply system through convolutional operations on graph data, and mines the spatial correlation relationship between the data based on the pipeline topological structure.

[0039] Specifically, in the anti-blocking lubricating grease supply system, in order to deeply explore the potential connections between data such as pressure, flow rate, temperature and impurity concentration, a graph convolutional neural network architecture is used to process the data. This architecture constructs a graph data model based on the topological structure of the lubricating grease pipeline, takes each monitoring point of the pipeline as a node, and the connection relationship between the nodes reflects the pipeline layout. Through convolutional operations on graph data, the spatial correlation based on the pipeline topology between the data can be fully considered. For example, when the pressure at a certain node is abnormal, this architecture can quickly analyze the data change trend of the surrounding nodes, accurately extract data features, provide key basis for subsequent system operation state analysis, and effectively improve the system's ability to predict the blocking risk.

[0040] Preferably, in the improved Gaussian mixture model analysis unit, the probability density function of the improved Gaussian mixture model is:

[0041] where is the feature vector output by the graph neural network feature extraction and processing unit, and the dimension is is the number of components of the Gaussian mixture model, which is preset according to the complexity of the operating state of the lubricating grease supply system; is the weight of the th Gaussian component, and satisfies , and its value is dynamically updated according to the system operation data through an adaptive weight adjustment mechanism; is the th Gaussian component's mean vector; is the th Gaussian component's covariance matrix, and a dynamic covariance matrix update strategy is adopted to adjust it in real time according to the data distribution change; this formula is used to perform clustering analysis on the operating state of the lubricating grease supply system, and by calculating the probability that the feature vector belongs to different Gaussian components, the normal operating mode and potential blocking risk mode of the system are identified.

[0042] Specifically, to achieve precise analysis of the operating status of the lubricating grease supply system, the improved Gaussian mixture model plays a core role. This model receives the processed feature vectors and distinguishes the normal operating mode and the potential blockage risk mode by performing clustering analysis on the system operation data. The introduced adaptive weight adjustment and dynamic covariance matrix update mechanisms can optimize the model parameters in real time according to the changes in the system working conditions. During actual operation, when the equipment load changes, resulting in fluctuations in grease pressure and flow rate, the model can quickly adjust the weights of each Gaussian component and the covariance matrix, accurately identify the system operating status, provide reliable support for intelligent decision-making, and avoid equipment failures caused by blockages.

[0043] Preferably, the graph neural network feature extraction and processing unit further includes an attention mechanism module, and the calculation process of this module satisfies the formula:

[0044] where and respectively represent the feature vectors of nodes and node in the graph data, is the total number of nodes in the graph; represents the concatenation operation of the two feature vectors; is the weight matrix of the attention mechanism module; is the attention coefficient of node to node , reflecting the importance of the features of node to node ; is the new feature vector of node after being processed by the attention mechanism; this module enhances the ability to extract the key data features of the lubricating grease supply system by calculating the attention coefficients between nodes, and further optimizes the feature extraction effect of the graph neural network.

[0045] Specifically, when processing the data of the lubricating grease supply system, to enhance the extraction of key data features, an attention mechanism module is introduced. Among the massive data generated by the system operation, some data have higher value for judging the blockage risk. This module determines the importance of the features of each node by calculating the attention coefficients between nodes. When situations such as a sudden increase in impurity concentration or an abnormal decrease in flow rate that may indicate blockage occur, the attention mechanism module can highlight these key data features, optimize the feature extraction effect of the graph neural network, enable the system to more sensitively capture the changes in the operating status, and timely detect potential blockage hazards.

[0046] Preferably, in the improved Gaussian mixture model analysis unit, the update formula of the adaptive weight adjustment mechanism is:

[0047]

[0048] Among them, represents the number of iterations; is the number of samples in the current batch; is the weight of the th Gaussian component at the th iteration; is the posterior probability that the sample belongs to the th Gaussian component at the th iteration; is the probability density value of the Gaussian distribution with as the mean vector and as the covariance matrix at ; This formula dynamically adjusts the weights of each Gaussian component through the calculation of the posterior probability based on the sample data, enabling the improved Gaussian mixture model to better adapt to the changes in the operating state of the lubricating grease supply system and improving the ability to identify potential blockage risk patterns.

[0049] Specifically, for the characteristics of the continuously changing working conditions of the lubricating grease supply system, the adaptive weight adjustment mechanism in the improved Gaussian mixture model plays an important role. This mechanism calculates based on the posterior probability of sample data. When the system operation data changes due to equipment status, environmental factors, etc., such as changes in environmental temperature affecting the fluidity of the grease, resulting in fluctuations in pressure and flow data, the adaptive weight adjustment mechanism will recalculate the weights of each Gaussian component according to the new sample data. Through dynamic adjustment, the model can better fit the current operating state, improve the recognition accuracy of potential blockage risk patterns, and ensure the stable operation of the system.

[0050] Preferably, in the graph neural network feature extraction and processing unit, when constructing the graph data model, the factor of the pipe diameter change is considered, and the construction formula of the node features is: , where is the feature vector of node ; is the pressure value at node , which is obtained by the pressure sensor in the multi-modal perception and data acquisition unit; is the grease flow value at node , which is measured by the flow monitoring module; is the temperature value at node , which is collected by the temperature sensing component; is the impurity concentration in the grease in the area corresponding to node , which is detected by the impurity concentration detection probe; is the node The pipe diameter value of the pipeline in question is preset according to the pipeline design parameters. This formula incorporates the pipe diameter change factor into the node features, enabling the graph data model to more accurately reflect the actual physical structure of the lubricating grease supply system and enhancing the extraction effect of the graph neural network on the system data features.

[0051] Specifically, when constructing the graph data model, considering the significant impact of pipeline diameter changes on grease transportation, the pipe diameter factor is incorporated into the node features. During the actual transportation process, changes in the pipe diameter directly affect parameters such as grease pressure and flow rate. For example, the grease flow rate increases and the pressure changes at the narrowing of the pipe diameter. The pipe diameter value, together with data such as pressure, flow rate, temperature, and impurity concentration, constitutes the node features, making the graph data model more in line with the actual physical structure of the system. When the graph neural network analyzes data based on this model, it can more accurately grasp the data change rules, effectively extract features related to the blockage risk, and provide a comprehensive basis for blockage risk judgment.

[0052] Preferably, in the improved Gaussian mixture model analysis unit, the dynamic covariance matrix update strategy satisfies the formula:

[0053] where, represents the number of iterations; is the number of samples in the current batch; is the -th iteration when the sample belongs to the -th Gaussian component's posterior probability; is the sample feature vector; is the -th iteration when the -th Gaussian component's mean vector; is the regularization parameter used to prevent the covariance matrix from being singular; is the identity matrix. This formula updates the covariance matrix based on the sample data and posterior probability and introduces a regularization term, enabling the improved Gaussian mixture model to adjust the covariance matrix in real time according to the distribution changes of the lubricating grease supply system operation data, more accurately describe the characteristic distribution of the system operation state, and improve the recognition accuracy of the blockage risk pattern.

[0054] Specifically, since the data distribution during the operation of the lubricating grease supply system changes with the working conditions, it is crucial to improve the dynamic covariance matrix update strategy of the Gaussian mixture model. The traditional fixed covariance matrix cannot accurately describe the complex changes of the system, while this update strategy adjusts the covariance matrix in real time based on sample data and posterior probability, and introduces a regularization term to prevent the matrix from being singular. When the grease parameters fluctuate due to equipment wear, environmental temperature changes, etc. in the system, the update strategy can optimize the covariance matrix in a timely manner, more accurately describe the characteristic distribution of the system operation state, improve the recognition accuracy of the model for the blockage risk mode, and ensure the reliable operation of the system.

[0055] Preferably, in the intelligent decision-making and control unit, the matching rule of the control strategy library is constructed by a graph neural network, and its matching process satisfies the formula:

[0056] Where, is the analysis result vector output by the improved Gaussian mixture model analysis unit; represents the graph neural network processing of the analysis result vector to mine the correlation relationships between various factors in the analysis result; is the weight matrix of the matching rule; is the matching probability vector of each control strategy in the control strategy library, and the control strategy with the highest probability is selected as the final control instruction according to this vector; this formula further processes the analysis result of the improved Gaussian mixture model through a graph neural network, constructs a more accurate control strategy matching rule, enables the intelligent decision-making and control unit to more accurately select appropriate control instructions according to the system operation state, and realizes the effective control of the self-cleaning execution unit and the grease supply regulation unit.

[0057] Specifically, in order to accurately select control strategies, the intelligent decision-making and control unit constructs the matching rule of the control strategy library by a graph neural network. When the improved Gaussian mixture model analysis unit outputs the analysis result of the system operation state, the graph neural network deeply processes the result vector to mine the complex correlation relationships between various factors. When there are multiple potential blockage risk factors in the system, such as the simultaneous occurrence of impurity accumulation and abnormal pressure, this matching rule can accurately analyze the mutual influence between factors, enable the intelligent decision-making unit to more accurately select control instructions, effectively control the self-cleaning execution unit and the grease supply regulation unit, and respond to the blockage risk in a timely manner.

[0058] Preferably, in the grease supply regulation unit, the rotation speed adjustment formula of the variable-frequency driven grease pump is: , where, is the adjusted rotation speed of the grease pump; is the initial rotation speed of the grease pump; is the rotation speed adjustment step size; is the control instruction vector output by the intelligent decision-making and control unit; is the rotational speed adjustment coefficient calculated according to the control instruction vector, and its calculation process involves the analysis and operation of each parameter in the control instruction; this formula realizes the precise adjustment of the rotational speed of the variable-frequency driven grease pump by combining the control instructions of the intelligent decision-making and control unit, thereby controlling the supply amount of lubricating grease to meet the requirements under different operating states of the system and preventing pipeline blockage.

[0059] Specifically, in the grease supply adjustment unit, to achieve precise control of the rotational speed of the variable-frequency driven grease pump, a specific rotational speed adjustment method is adopted. This method combines the control instructions output by the intelligent decision-making and control unit and realizes precise adjustment of the rotational speed of the grease pump by calculating the rotational speed adjustment coefficient. During the operation of the system, when the lubrication demand in a certain area increases or there is a risk of blockage and the grease flow needs to be adjusted, the intelligent decision-making unit issues an instruction, and the grease pump adjusts its rotational speed according to the instruction. At the same time, it works in coordination with the adjustable throttle valve and the pressure compensation device to ensure that the grease supply amount, flow rate, and pressure are in the best state, effectively preventing pipeline blockage and meeting the requirements of different working conditions of the system.

[0060] As Figure 2 shown, for the anti-blocking lubricating grease supply system based on a self-cleaning structure, the operation of this system includes the following steps: Step 1: The multi-modal perception and data acquisition unit collects the pressure data, grease flow data, temperature data in the lubricating grease conveying pipeline, and the grease impurity concentration data at the oil outlet of the storage tank in real time according to the preset sampling frequency, and transmits the collected data to the graph neural network feature extraction and processing unit through the high-speed data transmission bus; Step 2: The graph neural network feature extraction and processing unit receives the data transmitted by the multi-modal perception and data acquisition unit, converts it into node features, constructs a graph data model based on the topological structure of the lubricating grease conveying pipeline, extracts and fuses the features of the graph data through a multi-layer graph convolutional neural network architecture, mines the spatial correlation relationship between the data, outputs the processed feature vector, and transmits it to the improved Gaussian mixture model analysis unit; Step 3: The improved Gaussian mixture model analysis unit receives the feature vector output by the graph neural network feature extraction and processing unit, uses the improved Gaussian mixture model, and performs clustering analysis on the operating state of the grease supply system through the adaptive weight adjustment mechanism and the dynamic covariance matrix update strategy, identifies the normal operating mode and potential blockage risk mode of the system, outputs the analysis result and transmits it to the intelligent decision-making and control unit; Step 4: The intelligent decision-making and control unit receives the analysis results of the improved Gaussian mixture model analysis unit. Based on the built-in control strategy library, it selects corresponding control instructions from the control strategy library through specific matching rules and transmits the control instructions to the self-cleaning execution unit and the grease supply adjustment unit respectively; Step 5: After receiving the control instructions from the intelligent decision-making and control unit, the self-cleaning execution unit drives the rotatable impurity interceptor to rotate by a servo motor to intercept impurities in the grease. At the same time, the high-pressure pulse cleaning device sprays high-pressure pulse water flow into the conveying pipeline according to the control instructions to clean the interceptor and the inner wall of the pipeline, and the impurities generated by the cleaning are drained into the impurity collection cavity; Step 6: After receiving the control instructions from the intelligent decision-making and control unit, the grease supply adjustment unit adjusts the rotation speed of the grease pump driven by frequency conversion according to the control instructions. The adjustable throttle valve adjusts the opening degree through an electric actuator. The pressure compensation device monitors the pipeline pressure in real time and adjusts the output pressure according to the control instructions to realize the adjustment of the lubricating grease supply amount and the pipeline pressure.

[0061] Aiming at the defect of the weak data processing ability of the traditional system, this system constructs a powerful data perception and analysis system. The multi-modal perception and data acquisition unit deploys high-precision pressure sensor arrays, flow monitoring modules and other devices. Compared with the traditional single-point monitoring, it can collect multi-dimensional data such as the pressure distribution at each key node of the pipeline and the grease flow with higher precision and more comprehensively, laying a solid data foundation for the system operation analysis. The graph neural network feature extraction and processing unit uses the graph convolutional neural network architecture to convert the data into node features to construct a graph data model, and deeply excavates the spatial correlation relationship based on the pipeline topology among the data; the improved Gaussian mixture model analysis unit accurately clusters and analyzes the system operation state through the adaptive weight adjustment and dynamic covariance matrix update strategy, realizes the early identification of potential blockage risks, and completely changes the situation that the traditional system relies on empirical judgment and the risk identification is lagging.

[0062] In terms of the anti-blocking and self-cleaning functions, this system has achieved a major breakthrough. The rotatable impurity interceptor and the high-pressure pulse cleaning device of the self-cleaning execution unit work together. Compared with the passive filtration of the traditional filter screen, the rotatable impurity interceptor can dynamically intercept impurities such as sand grains and metal debris mixed in oil extraction. The high-pressure pulse cleaning device regularly and powerfully cleans the interceptor and the inner wall of the pipeline under the instruction of the intelligent decision-making and control unit to ensure the pipeline is clean and unobstructed. The frequency-conversion driven grease pump, adjustable throttle valve and pressure compensation device of the grease supply adjustment unit accurately control the grease supply amount, flow rate and pressure according to the instructions of the intelligent decision-making unit, maintain the stable operation of the system, avoid blockage caused by abnormal grease transportation, fundamentally solve the problem of frequent blockages and difficult maintenance of the traditional system, and greatly improve the operation efficiency and reliability of oil extraction equipment.

[0063] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "arranged", "installed", "connected", "coupled", "fixed" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood through specific circumstances.

[0064] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various equivalent changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalent scope.

Claims

1. A clogging prevention lubricating grease supply system based on a self-cleaning structure, characterized in that, Including: A multi-modal perception and data acquisition unit, a graph neural network feature extraction and processing unit, an improved Gaussian mixture model analysis unit, an intelligent decision-making and control unit, a self-cleaning execution unit, and a grease supply regulation unit; The multi-modal perception and data acquisition unit consists of a high-precision pressure sensor array, a flow monitoring module, a temperature sensing component, and an impurity concentration detection probe. The high-precision pressure sensor array is used to obtain the pressure distribution data in the pipeline in real time; the flow monitoring module measures the grease flow using ultrasonic flow measurement technology; the temperature sensing component is used to obtain the temperature information during the grease transportation process; the impurity concentration detection probe detects the impurity concentration in the grease using the principle of optical scattering; The graph neural network feature extraction and processing unit contains a multi-layer graph convolutional neural network architecture, receives the pressure, flow, temperature, and impurity concentration data transmitted by the multi-modal perception and data acquisition unit, and converts them into node features to construct a graph data model containing pipeline topology structure information; The improved Gaussian mixture model analysis unit introduces an adaptive weight adjustment mechanism and a dynamic covariance matrix update strategy, receives the feature vectors output by the graph neural network feature extraction and processing unit, and performs clustering analysis on the operating state of the grease supply system through the improved Gaussian mixture model to identify normal operating modes and potential blockage risk modes.

2. The anti-blocking lubricating grease supply system based on a self-cleaning structure according to claim 1, characterized in that The intelligent decision-making and control unit receives the analysis results of the improved Gaussian mixture model analysis unit, has a preset control strategy library built-in, and matches corresponding control instructions from the control strategy library according to the analysis results; The self-cleaning execution unit consists of a rotatable impurity interception net, a high-pressure pulse cleaning device, and an impurity collection chamber. The rotatable impurity interception net is driven by a servo motor to rotate to dynamically intercept impurities in the grease; the high-pressure pulse cleaning device sprays high-pressure pulse water flow into the pipeline after receiving the control instructions from the intelligent decision-making and control unit to clean the interception net and the inner wall of the pipeline; the impurities generated by the cleaning are drained to the impurity collection chamber through the pipeline; The grease supply regulation unit consists of a frequency-converted driven grease pump, an adjustable throttle valve, and a pressure compensation device. The frequency-converted driven grease pump adjusts the rotation speed according to the control instructions of the intelligent decision-making and control unit to change the grease supply volume; the adjustable throttle valve is installed in the transportation pipeline and adjusts the opening degree through an electric actuator to control the grease flow; the pressure compensation device monitors the pipeline pressure in real time and adjusts the output pressure according to the control instructions to maintain the pipeline pressure stable; The forward propagation process of the graph convolutional neural network architecture adopted in the graph neural network feature extraction and processing unit satisfies the following formula: Wherein, , represents the node feature matrix of the -th and -th layers of the graph convolutional neural network, and each row represents the feature vector of a node; is the adjacency matrix with self-loops added, is the original adjacency matrix constructed according to the topological structure of the lubricating grease pipeline, is the identity matrix; is the diagonal node degree matrix of , and the diagonal element is the weight matrix of the -th layer, which is used to transform the node features; is the activation function.

3. The anti-clogging lubricating grease supply system based on the self-cleaning structure according to claim 1, characterized in that, The probability density function of the improved Gaussian mixture model in the improved Gaussian mixture model analysis unit is as follows: where is the feature vector output by the graph neural network feature extraction and processing unit, with a dimension of is the number of components of the Gaussian mixture model, which is preset according to the complexity of the operating state of the lubricating grease supply system; is the weight of the th Gaussian component, and satisfies , and its value is dynamically updated according to the system operation data through an adaptive weight adjustment mechanism; is the mean vector of the th Gaussian component; is the covariance matrix of the th Gaussian component. A dynamic covariance matrix update strategy is adopted to adjust it in real time according to the change of data distribution, is the inverse of the covariance matrix, is the index variable in the summation operation.

4. The anti-clogging lubricating grease supply system based on the self-cleaning structure according to claim 1, characterized in that, The graph neural network feature extraction and processing unit further includes an attention mechanism module, and the calculation process of this module satisfies the formula: Wherein, and respectively represent the feature vectors of nodes and node in the graph data; is the total number of nodes in the graph; represents the operation of concatenating two feature vectors; is an activation function; is the weight matrix of the attention mechanism module; is the attention coefficient of node to node , reflecting the importance of the features of node to node ; is the new feature vector of node after being processed by the attention mechanism, T represents the transpose operation of the matrix, , j are index variables in the summation operation.

5. The anti-clogging lubricating grease supply system based on the self-cleaning structure according to claim 1, characterized in that, The update formula for the adaptive weight adjustment mechanism in the improved Gaussian mixture model analysis unit is as follows: where represents the number of iterations; is the number of samples in the current batch; and are the weights of the -th and -th iterations for the -th Gaussian component; is the posterior probability that the sample belongs to the -th Gaussian component at the -th iteration; is the probability density value of the Gaussian distribution with as the mean vector and as the covariance matrix at at the -th iteration; is the mean vector of the -th Gaussian component at the i -th iteration, j and i are index variables in the summation operation.

6. The anti-clogging lubricating grease supply system based on the self-cleaning structure according to claim 1, characterized in that, When constructing the graph data model in the graph neural network feature extraction and processing unit, the factor of pipeline diameter change is considered, and the construction formula of node features is as follows: where, is the feature vector of node ; is the pressure value at node , which is obtained by the pressure sensor in the multi-modal perception and data acquisition unit; is the grease flow value at node , which is measured by the flow monitoring module; is the temperature value at node , which is collected by the temperature sensing component; is the impurity concentration in the grease in the corresponding area of node , which is detected by the impurity concentration detection probe; is the pipeline diameter value of the pipeline where node is located, which is preset according to the pipeline design parameters.

7. The anti-clogging lubricating grease supply system based on a self-cleaning structure according to claim 1, wherein The dynamic covariance matrix update strategy in the improved Gaussian mixture model analysis unit satisfies the formula: where represents the number of iterations; is the number of samples in the current batch; is the posterior probability that the sample at the -th iteration belongs to the -th Gaussian component; is the sample feature vector; is the mean vector of the -th iteration of the -th Gaussian component; is the regularization parameter used to prevent the covariance matrix from being singular; is the identity matrix; is the probability density value, and T represents the matrix transpose operation.

8. The anti-clogging lubricating grease supply system based on a self-cleaning structure according to claim 2, wherein, The matching rule of the control strategy library in the intelligent decision-making and control unit is constructed using a graph neural network, and the matching process satisfies the formula: Among them, is the analysis result vector output by the improved Gaussian mixture model analysis unit; represents performing graph neural network processing on the analysis result vector to mine the correlation relationships among various factors in the analysis result; is the weight matrix of the matching rule; is the matching probability vector of each control strategy in the control strategy library. According to this vector, the control strategy with the highest probability is selected as the final control instruction, is the activation function.

9. The anti-clogging lubricating grease supply system based on the self-cleaning structure according to claim 2, characterized in that, For the grease supply adjustment unit, the rotation speed adjustment formula of the frequency-converted grease pump is as follows: , where is the adjusted rotation speed of the grease pump; is the initial rotation speed of the grease pump; is the rotation speed adjustment step; is the control instruction vector output by the intelligent decision-making and control unit; is the rotation speed adjustment coefficient calculated according to the control instruction vector.

10. The anti-clogging lubricating grease supply system based on a self-cleaning structure according to any one of claims 1-9, characterized in that, The operation of this system includes the following steps: Step 1: The multi-modal perception and data acquisition unit collects the pressure data, grease flow data, temperature data in the lubricating grease transportation pipeline, and the grease impurity concentration data at the oil outlet of the storage tank in real time according to the preset sampling frequency, and transmits the collected data to the graph neural network feature extraction and processing unit through a high-speed data transmission bus; Step 2: The graph neural network feature extraction and processing unit receives the data transmitted by the multi-modal perception and data acquisition unit, converts it into node features, constructs a graph data model based on the topological structure of the lubricating grease delivery pipeline, extracts and fuses features from the graph data through a multi-layer graph convolutional neural network architecture, mines the spatial correlation relationships between data, outputs the processed feature vectors, and transmits them to the improved Gaussian mixture model analysis unit; Step 3: The improved Gaussian mixture model analysis unit receives the feature vectors output by the graph neural network feature extraction and processing unit, uses the improved Gaussian mixture model, performs clustering analysis on the operating state of the grease supply system through an adaptive weight adjustment mechanism and a dynamic covariance matrix update strategy, identifies the normal operating mode and potential blockage risk mode of the system, outputs the analysis results and transmits them to the intelligent decision-making and control unit; Step 4: The intelligent decision-making and control unit receives the analysis results of the improved Gaussian mixture model analysis unit, based on the built-in control strategy library, selects the corresponding control instructions from the control strategy library through specific matching rules, and transmits the control instructions to the self-cleaning execution unit and the grease supply regulation unit respectively; Step 5: After receiving the control instructions from the intelligent decision-making and control unit, the self-cleaning execution unit drives the rotatable impurity interception net to rotate by a servo motor to intercept impurities in the grease. At the same time, the high-pressure pulse cleaning device sprays high-pressure pulse water flow into the delivery pipeline according to the control instructions to clean the interception net and the inner wall of the pipeline, and the impurities generated by the cleaning are drained to the impurity collection cavity; Step 6: After receiving the control instructions from the intelligent decision-making and control unit, the grease supply regulation unit adjusts the rotation speed of the grease pump driven by frequency conversion according to the control instructions. The adjustable throttle valve adjusts the opening degree through an electric actuator. The pressure compensation device monitors the pipeline pressure in real time and adjusts the output pressure according to the control instructions to complete the adjustment of the lubricating grease supply volume and the pipeline pressure.

Images