Multi-point coordinated early warning system for emulsion pumping stations

Abstract

The present invention discloses a multi-point collaborative early warning system for an emulsion pump station, which relates to the field of collaborative early warning technology. The system includes: a main-branch pipeline determination module, which is used to determine the main pipeline and multiple branch pipelines in the emulsion pump station; a monitoring module configuration module, which is used to configure the main pipeline monitoring module and the branch pipeline monitoring module; a pipeline monitoring module, which is used to connect the main pipeline monitoring data set and the branch pipeline monitoring data set; a collaborative abnormality analysis module, which is used to perform collaborative abnormality analysis; an abnormality alarm module, which is used to generate and mark collaborative abnormal pipeline sources, and generate abnormal early warning signals for alarm. The present invention solves the technical problems in the prior art of incomplete monitoring of the emulsion status of the main and branch pipelines of the emulsion pump station, inability to effectively analyze the collaborative abnormality of the main and branch pipelines, and difficulty in timely discovering and warning potential faults, and achieves the technical effect of realizing comprehensive monitoring of the emulsion status of the main and branch pipelines of the emulsion pump station and ensuring the safe and stable operation of the pump station.

Description

Technical Field

[0001] The present invention relates to the technical field of coordinated early warning, and in particular to a multi-point coordinated early warning system for an emulsion pump station. Background Art

[0002] In industrial production, emulsion pumping stations are widely used in various processes, such as metal cutting and press forming. They provide cooling, lubrication, and chip removal for equipment, playing a critical role in ensuring the smooth operation of the production process. However, existing technologies for monitoring the main and branch pipelines of emulsion pumping stations present numerous challenges. Firstly, most monitoring systems monitor only the main or branch pipelines individually, lacking a coordinated analysis of the emulsion status in both the main and branch pipelines, making it impossible to fully understand the operational status of the entire pipeline system. For example, focusing solely on the flow rate of the main pipeline while ignoring the impact of abnormal branch flow rates on overall emulsion distribution makes it difficult to detect potential failures caused by coordination issues between the main and branch pipelines. Secondly, traditional monitoring methods often focus on determining the threshold of a single parameter and lack in-depth analysis of the complex relationships between multiple parameters. For example, simply determining an anomaly based on whether the emulsion temperature exceeds the specified value ignores the interrelationships between temperature and other parameters such as pressure and flow. This prevents the timely detection of anomalies hidden in the complex changes in parameters.

[0003] The existing technology has technical problems such as incomplete monitoring of the emulsion status of the main and branch pipelines of the emulsion pump station, inability to effectively analyze abnormal coordination conditions of the main and branch pipelines, and difficulty in timely detection and early warning of potential faults. Summary of the Invention

[0004] The present application provides a multi-point coordinated early warning system for an emulsion pump station, which is used to solve the technical problems in the existing technology of incomplete monitoring of the emulsion status of the main and branch pipelines of the emulsion pump station, inability to effectively analyze abnormal conditions of the coordination of the main and branch pipelines, and difficulty in timely detection and early warning of potential faults.

[0005] In view of the above problems, the present application provides a multi-point collaborative early warning system for emulsion pumping stations.

[0006] The present application provides a multi-point coordinated early warning system for an emulsion pump station, the system comprising:

[0007] A main-branch pipeline determination module is used to determine the main pipeline and multiple branch pipelines in the emulsion pump station; a monitoring module configuration module is used to configure a main pipeline monitoring module and multiple branch pipeline monitoring modules for the main pipeline and the multiple branch pipelines respectively; a pipeline monitoring module is used to connect the main pipeline monitoring module to obtain the main pipeline monitoring data set of the main pipeline, and connect the multiple branch pipeline monitoring modules to obtain the multiple branch pipeline monitoring data sets of the multiple branch pipelines; a collaborative abnormality analysis module is used to perform collaborative abnormality analysis of the emulsion state of the main and branch pipelines based on the main pipeline monitoring data set and the multiple branch pipeline monitoring data sets, and generate independent abnormality data of the main pipeline and independent abnormality data of any branch pipeline; an abnormality alarm module is used to perform collaborative abnormality impact analysis on the main pipeline and the multiple branch pipelines based on the independent abnormality data of the main pipeline and the independent abnormality data of any branch pipeline, generate a collaborative abnormal pipeline source and mark it, and generate an abnormal warning signal for the marked pipeline to alarm.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The main and branch pipeline determination module is used to determine the main pipeline and multiple branch pipelines in the emulsion pump station; the monitoring module configuration module is used to configure the main pipeline monitoring module and multiple branch pipeline monitoring modules for the main pipeline and the multiple branch pipelines respectively; the pipeline monitoring module is used to connect the main pipeline monitoring data set and the branch pipeline monitoring data set; the collaborative abnormality analysis module is used to perform collaborative abnormality analysis of the emulsion status of the main and branch pipelines, generating independent abnormality data for the main pipeline and independent abnormality data for any branch pipeline; the abnormality alarm module is used to perform collaborative abnormality impact analysis, generate and mark collaborative abnormal pipeline sources, and generate abnormal warning signals for the marked pipelines to alarm. The technical effect of achieving comprehensive monitoring of the emulsion status of the main and branch pipelines of the emulsion pump station and ensuring the safe and stable operation of the pump station is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of the structure of a multi-point coordinated early warning system for an emulsion pump station is provided for an embodiment of the present application;

[0012] Figure 2 A structural execution diagram of a collaborative anomaly analysis module of a multi-point collaborative early warning system for an emulsion pump station is provided for an embodiment of the present application.

[0013] Description of the accompanying drawings: main and branch pipeline determination module 10, monitoring module configuration module 20, pipeline monitoring module 30, collaborative abnormality analysis module 40, abnormality alarm module 50. DETAILED DESCRIPTION

[0014] This application provides a multi-point collaborative early warning system for an emulsion pump station, which is used to solve the technical problems in the existing technology of incomplete monitoring of the emulsion status of the main and branch pipelines of the emulsion pump station, inability to effectively analyze abnormal conditions of the coordination of the main and branch pipelines, and difficulty in timely detection and early warning of potential faults.

[0015] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making any creative work are within the scope of protection of this application.

[0016] Examples, such as Figure 1 As shown, the present application provides a multi-point coordinated early warning system for an emulsion pump station, the system comprising:

[0017] The main and branch pipeline determining module 10 is used to determine the main pipeline and multiple branch pipelines in the emulsion pumping station.

[0018] Specifically, the main and branch pipeline determination module 10 determines the main pipeline and multiple branch pipelines through detailed surveys and precise analysis of the complex pipeline layout inside the pump station. In the pump station facilities, the configuration of multiple pipelines uses distribution valves and switching valve devices to flexibly switch the pipelines or adjust the flow according to actual production needs. For example, under certain working conditions, when the demand for emulsion suddenly increases, the switching valve is used to direct more emulsion in the main pipeline to the branch pipeline connected to it to ensure the normal operation of the equipment. The main pipeline undertakes the initial transportation task of the emulsion, and stably transports the emulsion from the source of the pump station to each key node. The branch pipeline accurately distributes the emulsion according to the diverse needs of different equipment in different production links, ensuring that each equipment that needs emulsion can obtain appropriate supply, thereby maintaining the smooth progress of the entire production process, and providing an indispensable prerequisite for the efficient and stable operation of the emulsion pump station.

[0019] The monitoring module configuration module 20 is used to configure a main line monitoring module and multiple branch line monitoring modules for the main line and the multiple branch lines respectively.

[0020] Specifically, the monitoring module configuration module 20 installs a series of adaptive monitoring equipment for the main line to form a main line monitoring module. For example, temperature sensors are arranged at the key nodes and problem-prone parts of the main line. These sensors can sense the temperature changes of the emulsion when it flows in the main line in real time. Once the temperature exceeds the normal range, it indicates that the performance of the emulsion is abnormal or there is a potential fault in the pipeline. At the same time, the flow sensor will accurately measure the flow rate of the emulsion in the main line to ensure that the flow rate is stable in a reasonable range. If the flow rate changes suddenly, it means that there is a leak or blockage in the pipeline. The flow rate sensor is responsible for monitoring the flow rate of the emulsion, and its data helps to analyze the smoothness of the pipeline and the operating efficiency of the pump station.

[0021] For multiple branch lines, a branch monitoring module is customized for each branch line based on its specific characteristics and the needs of the connected equipment. Because the equipment served by different branch lines has different emulsion requirements, the configuration of the branch monitoring module will also vary. For example, for branch lines that transport emulsion to high-precision processing equipment, the sensors in its monitoring module will be more accurate, allowing them to more sensitively capture subtle changes in the emulsion's state, thereby promptly identifying potential risks that may affect the normal operation of the equipment, ensuring the stable and safe operation of the entire emulsion pump station system, and providing a reliable data source for subsequent data analysis and abnormality judgment.

[0022] The pipeline monitoring module 30 is used to connect to the main pipeline monitoring module to obtain the main pipeline monitoring data set of the main pipeline, and connect to the multiple branch pipeline monitoring modules to obtain the multiple branch pipeline monitoring data sets of the multiple branch pipelines.

[0023] Specifically, the pipeline monitoring module 30 establishes a close communication link with the main line monitoring module via connecting lines. These connecting lines use highly reliable industrial-grade cables with excellent anti-interference capabilities and signal transmission stability, ensuring that it can continuously and accurately receive various types of data from the main line monitoring module. The temperature sensors, flow sensors, and flow velocity sensors in the main line monitoring module collect data at a set frequency. This data covers key indicators such as the temperature changes of the emulsion in the main line, the real-time value of the flow rate, and dynamic information on the flow rate. This data is received and integrated with extremely high efficiency to form a comprehensive and detailed main line monitoring data set, providing a solid data foundation for subsequent analysis of the main line's operating status.

[0024] At the same time, the pipeline monitoring module 30 is efficiently connected with multiple branch pipeline monitoring modules. In view of the unique layout and operating characteristics of different branch pipelines, a well-adaptable connection technology is adopted to ensure that the data collected by each branch pipeline monitoring module can be stably obtained. Each branch pipeline monitoring module is also equipped with sensors such as temperature, flow and flow velocity. The data they collect reflects the specific status of the emulsion in each branch pipeline. The pipeline monitoring module 30 will classify, organize and summarize the monitoring data from each branch pipeline to form multiple branch pipeline monitoring data sets. These data sets fully record the operating conditions of different branch pipelines, providing indispensable data support for a comprehensive understanding of the working status of the entire emulsion pump station, so as to promptly detect potential anomalies and problems and ensure the safe and stable operation of the pump station.

[0025] The collaborative abnormality analysis module 40 is used to perform collaborative abnormality analysis on the emulsion state of the main and branch pipelines based on the main pipeline monitoring data set and the multiple branch pipeline monitoring data sets, and generate independent abnormality data of the main pipeline and independent abnormality data of any branch pipeline.

[0026] Specifically, the collaborative anomaly analysis module 40 conducts a comprehensive and in-depth collaborative anomaly analysis of the emulsion state of the main and branch pipelines based on the main pipeline monitoring data set and multiple branch pipeline monitoring data sets. The main pipeline monitoring data set contains rich data collected by temperature sensors, flow sensors and flow velocity sensors at various points on the main pipeline. These data reflect key information such as the temperature, flow rate and flow velocity of the emulsion in the main pipeline at different times. The multiple branch pipeline monitoring data sets are similar, and each records the data of the corresponding sensors on each branch pipeline. During the analysis process, the main pipeline monitoring data is carefully sorted out, and data mining technology and statistical methods are used to analyze the changing trends of parameters such as temperature, flow rate, flow velocity, etc. over time, as well as the relationship between the various parameters. For example, under normal circumstances, the flow rate and flow velocity should show a certain proportional relationship. If, within a certain period of time, the flow rate suddenly drops sharply, but the flow velocity does not decrease accordingly, or even abnormal fluctuations occur, and the temperature deviates from the normal range, these abnormal conditions will be identified and extracted, and organized to form independent abnormal data for the main pipeline. For multiple branch pipeline monitoring data sets, we conduct in-depth analysis to analyze the functional characteristics of each branch pipeline, the connection method with the main pipeline, and the differences in the specific equipment or areas served, and analyze the data of each branch pipeline separately. For example, a branch pipeline provides emulsion to a specific processing equipment, and its flow rate and temperature must meet the specific process requirements of the equipment. If the flow rate of the branch pipeline is continuously lower than the flow rate required for normal operation of the equipment for a certain period of time, and the temperature also exceeds the range that the equipment can withstand, this will be recorded as an abnormality of the branch pipeline, forming independent abnormal data for any branch pipeline. Through this collaborative analysis of the main and branch pipeline data, the abnormality of the emulsion status of the main and branch pipelines can be accurately identified, and independent abnormal data for the main pipeline and any branch pipeline can be generated separately, providing important data support for subsequent abnormality tracing and fault handling.

[0027] The abnormality alarm module 50 is used to perform collaborative abnormality impact analysis on the main line and the multiple branch lines based on the independent abnormality data of the main line and the independent abnormality data of any branch line, generate collaborative abnormal line sources and mark them, and generate abnormality warning signals for the marked lines to alarm.

[0028] Specifically, after the abnormal alarm module 50 obtains the independent abnormal data of the main pipeline and the independent abnormal data of any branch pipeline generated by the collaborative abnormal analysis module, it quickly starts the workflow. First, these abnormal data are deeply mined and correlated through the built-in data analysis engine. For the independent abnormal data of the main pipeline, it will comprehensively sort out all parameter changes related to the abnormality, such as the flow fluctuation range that may be caused by sudden temperature changes, the impact of flow rate reduction on system pressure, etc., and combine the experience of handling similar abnormal situations in historical data to establish a preliminary impact model. For the independent abnormal data of the branch pipeline, its potential impact on the connected equipment and the part of the main pipeline that may be affected will also be analyzed in detail. For example, if the flow of a branch pipeline increases abnormally, track the impact of this change on the operating stability of the downstream equipment, and whether it will interfere with the normal transportation of the main pipeline due to factors such as back pressure. When comprehensively considering the complex interactive relationship between the main and branch pipelines, the system dynamics method is used to construct a collaborative impact network model of the main and branch pipelines. In this model, the relationships between energy transfer, flow distribution, and pressure coupling between pipelines are precisely quantified. By simulating the system response under different abnormal conditions, the root cause and propagation path of the abnormality are accurately located, thereby generating a collaborative abnormal pipeline source. Once the collaborative abnormal pipeline source is determined, it is immediately marked. The marking information covers key content such as the abnormality type, severity, and possible impact range. Subsequently, according to the preset alarm rules and priority system, corresponding abnormal warning signals are generated for the marked pipelines. These signals can be used through various means such as sound and light alarms, pop-up windows of the station monitoring system, and text messages or push notifications to relevant maintenance personnel to ensure that relevant personnel are notified in a timely manner so that they can quickly take measures to deal with abnormal situations, minimize the impact on the operation of the emulsion pump station, and ensure production safety.

[0029] In one possible implementation, Figure 2 As shown, the collaborative anomaly analysis module 40 also includes:

[0030] The demand parameter receiving unit is used to receive preset operation demand parameters of the emulsion pump station, wherein the preset operation scenario includes the emulsion demand parameters of the emulsion supply targets connected to the multiple branch pipelines.

[0031] The operating parameter generating unit is used to call the main-branch pipeline dispatching center to analyze the emulsion demand parameters and generate the main pipeline emulsion operating parameters of the main pipeline and the multiple branch pipeline emulsion operating parameters of the multiple branch pipelines.

[0032] The twin main-branch pipeline operation model establishing unit is used to perform modeling based on the main pipeline emulsion operation parameters and the multiple branch pipeline emulsion operation parameters to establish a twin main-branch pipeline operation model.

[0033] An independent abnormal data generation unit is used to train a main-branch pipeline collaborative abnormality recognition model with the twin main-branch pipeline operation model, call the main-branch pipeline collaborative abnormality recognition model to collaboratively analyze the main pipeline monitoring data set and the multiple branch pipeline monitoring data sets, and generate the main pipeline independent abnormality data and any branch pipeline independent abnormality data.

[0034] Specifically, the demand parameter receiving unit has a specially designed data receiving interface and communication protocol, which can establish a stable connection with the pump station's control system, production process planning system, and related equipment management databases. Through these connection channels, it continuously collects and filters the preset operation demand parameters of the emulsion pump station. In particular, for emulsion supply targets connected by multiple branch pipes, it can accurately obtain its key demand parameters for the emulsion, such as flow rate, flow rate, and temperature. For example, in some high-precision machining operation scenarios, the processing equipment connected to the branch pipes requires the emulsion to have a specific temperature range to ensure machining accuracy, and at the same time requires a stable flow rate and an appropriate amount of flow to achieve good lubrication and cooling effects. The demand parameter receiving unit will update these parameter information in a timely manner according to the predetermined time interval or event trigger mechanism, and transmit it to the subsequent processing module, providing indispensable basic data support for the generation of operating parameters and abnormality analysis of the entire pump station, ensuring that the pump station can operate efficiently and stably according to actual production needs.

[0035] The operating parameter generation unit is closely connected to the main and branch pipeline dispatch center. Once it receives the emulsion demand parameters, including flow rate, flow rate, and temperature, from the demand parameter receiving unit, it quickly initiates the analysis process. For the main pipeline, based on the basic principles of fluid mechanics and the actual equipment performance parameters of the pump station, by comprehensively considering factors such as the main pipeline diameter, the roughness of the pipeline material, the output power of the pump station power equipment, and the pressure loss of the entire system, the Bernoulli equation and the continuity equation are used for precise calculations to determine the optimal operating parameters of the main pipeline emulsion. For example, based on the power output of the pump station and the physical characteristics of the main pipeline, the flow rate range that can ensure stable emulsion transportation with minimal energy consumption is calculated, as well as the flow rate value that meets the needs of the entire pump station. The appropriate temperature range is determined in combination with environmental factors and the physical and chemical properties of the emulsion itself. For multiple branch pipelines, the unique process requirements of the emulsion supply target connected to each branch pipeline are analyzed. If a branch line connects to high-precision processing equipment that is extremely sensitive to temperature, then when generating the branch line's emulsion operating parameters, the focus is on adjusting the flow rate and flow velocity to ensure that the temperature of the emulsion delivered to the equipment remains within the minimal fluctuation range allowed by the equipment. Through this personalized analysis and calculation of different branch lines, the operating parameter generation unit generates precisely matched emulsion operating parameters for each branch line, providing a critical data foundation for subsequent model establishment and system operation, ensuring the efficient and safe operation of the emulsion pump station under various operating conditions.

[0036] The twin main and branch pipeline operation modeling unit first establishes a detailed mathematical description of the emulsion flow process in the main and branch pipelines, based on fundamental scientific principles such as fluid mechanics and thermodynamics. For the main pipeline, geometric characteristics such as pipe diameter, length, and roughness, as well as its connection to the pump station power source, are considered to construct a mathematical model that reflects the variations in emulsion velocity, flow rate, and pressure along the main pipeline. For the branch pipelines, local flow models are established based on their respective pipe diameters, directions, and specific operating conditions of connected equipment. These models are then coupled to the main pipeline model through boundary conditions. Secondly, in terms of data-driven modeling, a large amount of historical operating data is utilized to supplement and optimize the aforementioned physical model. Actual operating parameters of the emulsion in the main and branch pipelines under various operating conditions, such as flow rate and pressure under varying flow demands and temperature conditions, are collected. Using the neural network within a machine learning algorithm, the underlying patterns and characteristics within the data are explored to modify and refine the parameters in the physical model, improving the model's accuracy and adaptability. Through a deep integration of physical and data-driven modeling, coupled with repeated iterative optimization, a twin main and branch pipeline operation model was successfully established. This model closely simulates the operating state of emulsions in actual pump station main and branch pipelines. It not only accurately predicts changes in operating parameters under normal operating conditions but also simulates and analyzes various abnormal operating conditions and potential faults, providing a powerful virtual testing platform and decision-making support tool for subsequent anomaly identification and system optimization.

[0037] The independent abnormal data generation unit divides the rich and representative normal operating data and simulated abnormal data obtained from the twin main-branch pipeline operation model into training, validation, and test sets according to specific ratios. The training set is used to train the main-branch pipeline collaborative abnormality recognition model. During the training process, the model continuously learns and adjusts its parameters based on a neural network algorithm to establish a discrimination mechanism that can accurately distinguish between normal and abnormal conditions. The validation set is used to evaluate and optimize the model during training to ensure that the model does not suffer from overfitting and achieves a good balance between generalization and accuracy. After thorough training and optimization, the main-branch pipeline collaborative abnormality recognition model possesses powerful analytical capabilities. Upon receiving the main pipeline monitoring dataset and multiple branch pipeline monitoring datasets from the pipeline monitoring module, the model rapidly analyzes the changing trends, fluctuation ranges, and interrelationships of parameters such as temperature, flow rate, and flow velocity in the main pipeline data, and compares these with the corresponding parameters predicted under normal conditions by the twin main-branch pipeline operation model. If it is found that the main pipeline data deviates significantly from the normal range and cannot be explained by changes in normal operating conditions, and at the same time, through correlation analysis, it is determined that the anomaly has no direct correlation with the branch pipeline or has little impact, independent abnormal data for the main pipeline will be generated. Similarly, for multiple branch pipeline monitoring data sets, the model will analyze the parameters of each branch pipeline one by one, considering the interactions between the branches and between the branches and the main pipeline. Once the parameters of a branch pipeline are abnormal, and further analysis determines that the anomaly is not caused by conduction from the main pipeline or indirectly caused by other branches, but is caused by problems in the branch pipeline itself, such as local blockage, sensor failure, etc., the corresponding independent abnormal data for any branch pipeline will be generated, providing a key basis for subsequent troubleshooting and processing, and ensuring the safe and stable operation of the emulsion pump station.

[0038] In one possible implementation, the independent abnormal data generating unit further includes:

[0039] The pipeline collaborative abnormality data generating unit is used to debug the twin main and branch pipeline operation model and generate pipeline collaborative abnormality data.

[0040] The synergistic effect training unit is used to perform synergistic effect training when the main and branch pipelines are abnormal based on the pipeline synergistic abnormality data, and generate the main and branch pipeline synergistic abnormality recognition model.

[0041] Specifically, the pipeline collaborative anomaly data generation unit generates the first pipeline collaborative anomaly data, based on an analysis of the pump station's operating principles and historical fault data, for the main pipeline. This unit then sets specific abnormal operating conditions for the main pipeline in the twin main-branch pipeline operation model, such as simulating a flow control valve failure in the main pipeline, which could result in a sudden and significant drop in main pipeline flow or abnormal flow rate fluctuations. During operation, the model simulates the impact of the main pipeline anomaly on the entire system based on the principles of fluid mechanics and the physical properties of the pipeline system. At this point, the model monitors and records changes in key parameters of the main pipeline itself and each branch pipeline in real time, such as sudden changes in main pipeline pressure and the chain reactions of flow, pressure, and temperature in each branch pipeline caused by changes in main pipeline flow. This data constitutes the first pipeline collaborative anomaly data, which clearly reflects the coordinated changes in the system caused by the main pipeline anomaly. When generating the second pipeline collaborative anomaly data, based on any branch pipeline as the anomaly source, a specific branch pipeline is selected. For example, a failure scenario, such as a partial blockage or valve damage in a branch pipeline due to long-term use, is assumed, and these anomalies are input into the twin main-branch pipeline operation model. After the model runs, it displays the impact of the branch anomaly on the main line and other branches. It records adjustments made by the main line to balance system pressure or flow, as well as changes in other branch parameters due to factors such as flow redistribution and pressure changes, such as flow rate adjustments and temperature fluctuations. These detailed data together constitute the second-line coordinated anomaly data, providing a basis for analyzing the coordinated impact of a single branch anomaly on the entire system. For the third-line coordinated anomaly data, which uses the main line and any branch as parallel anomaly sources, more complex anomaly scenarios are designed. For example, the model simultaneously models unstable flow in the main line due to aging equipment and a sudden leak in a branch. When simulating this complex anomaly, the unit comprehensively monitors the dynamic changes in the main line, the abnormal branch line, and other branches after the anomaly occurs, including complex pressure transmission and fluctuations, flow redistribution, and nonlinear temperature changes. The unit records the changes in these parameters at different time points, forming the third-line coordinated anomaly data covering the entire system under the condition of parallel anomalies in the main line and branches. This provides rich data support for in-depth research on the coordinated effects of systems under complex anomaly conditions.

[0042] The synergy training unit utilizes this pipeline coordination anomaly data and employs the deep learning framework of recurrent neural networks (RNNs) and their variant, long short-term memory networks (LSTMs), to train for synergy when main and branch pipelines exhibit anomalies. RNNs effectively process time series data, while LSTMs address the vanishing gradient problem in RNNs and are suitable for capturing dependencies within long sequences. Pipeline coordination anomaly data is input into the LSTM network in time series. The network weights are adjusted using a backpropagation algorithm, enabling the network to learn the coordinated parameter changes associated with main and branch pipeline anomalies, such as the response of branch pipeline flow to a sudden change in main pipeline pressure. This ultimately generates a main-branch coordination anomaly recognition model that accurately identifies main-branch coordination anomalies.

[0043] In one possible implementation, the pipeline collaborative abnormality data generating unit further includes:

[0044] The pipeline collaborative abnormality data includes first pipeline collaborative abnormality data with the main pipeline as the abnormality source, second pipeline collaborative abnormality data with any branch pipeline as the abnormality source, and third pipeline collaborative abnormality data with the main pipeline and any branch pipeline as parallel abnormality sources.

[0045] Specifically, pipeline collaborative anomaly data is a data set generated by a comprehensive simulation and analysis of abnormal conditions in the main and branch pipelines of an emulsion pumping station. It includes three types. The first type of pipeline collaborative anomaly data is generated with the main pipeline as the anomaly source. When debugging the twin main and branch pipeline models, by setting abnormal changes in specific parameters of the main pipeline, such as a sudden and significant decrease in the main pipeline flow rate or a sharp increase in temperature, the chain reaction of other parameters of each branch pipeline and the main pipeline itself is observed and recorded. For example, the pressure fluctuations and flow rate changes in the branch pipeline caused by the main pipeline flow change are observed and recorded. These data constitute the first type of pipeline collaborative anomaly data and reflect the impact of the main pipeline anomaly on the entire system. The second type of pipeline collaborative anomaly data is generated with any branch pipeline as the anomaly source. In the model, an anomaly is set in a branch pipeline, such as a valve failure in a branch pipeline causing a blockage. The responses of the main pipeline and other branches are then analyzed, including the flow adjustment made by the main pipeline to balance pressure and the changes in other branches caused by flow redistribution. These recorded data are the second type of pipeline collaborative anomaly data, reflecting the coordinated changes in the system when a single branch pipeline anomaly occurs. The third-line collaborative anomaly data simulates the situation in the model where the main line and any branch line are simultaneously parallel anomaly sources. For example, a failure of the main line flow control valve and a local leakage in a branch line occur simultaneously. At this time, the changes in various parameters of the main line, the abnormal branch line and other branch lines in this complex anomaly situation are collected, such as the dynamic changes in pressure, flow, temperature and other data. These data form the third-line collaborative anomaly data, showing the more complex collaborative anomaly situation of the entire system when the main line and branch line are abnormal in parallel.

[0046] In one possible implementation, the abnormality alarm module 50 further includes:

[0047] An abnormal source backtracking model establishing unit is used to establish an abnormal source backtracking model for the main pipeline and multiple branch pipelines, wherein the abnormal source backtracking model is used to be obtained by training with any device of the flow control valve and cooling device of the main and branch pipelines independently or in combination as the tracing target.

[0048] The adaptation analysis unit is used to call the abnormal source backtracking model to collect the operation data of any main and branch pipelines corresponding to any traceability target, perform adaptation analysis on the independent abnormal data of the main pipeline and the independent abnormal data of any branch pipeline, generate the collaborative abnormal pipeline source and mark it.

[0049] Specifically, a massive amount of operational data for main and branch pipelines under different operating conditions is first collected. This data includes flow and pressure values at different flow control valve openings, temperature data at different cooling efficiency levels for cooling units, and parameters such as flow velocity, flow rate, and temperature for the main and branch pipelines. Furthermore, the corresponding operating status of this data is labeled as normal or abnormal. Abnormalities require a clear description of the abnormality type and possible cause. During the training phase, a decision tree algorithm is used to analyze the training data. When considering the flow control valve as a single traceability target, the decision tree classifies the impact of changes in the flow control valve opening on parameters such as flow and pressure in the main and branch pipelines. If a small change in the flow control valve opening causes a significant fluctuation in the main pipeline flow, and this fluctuation is highly correlated with a known abnormality, then this node will become a key branch in the decision tree. For cooling units, the impact of changes in cooling efficiency on temperature parameters is similarly analyzed, as well as how these changes relate to abnormal conditions in the piping system. When considering a combination of a flow control valve and a cooling unit, a comprehensive analysis is performed to determine the patterns of change in parameters in the main and branch pipelines when both change simultaneously. For example, if the flow control valve opening increases and the cooling unit's efficiency decreases, the main line temperature continues to rise and exceeds the normal range, and the branch line flow distribution also exhibits anomalies, the decision tree will combine these conditions to form a composite branch node. By continuously splitting the data and growing the decision tree, a backtracking model for the anomaly source is constructed that can accurately determine, based on the operating data of the main and branch lines, whether the anomaly is caused by the flow control valve, the cooling unit alone, or a combination of the two. This model is presented in a tree structure, with each internal node representing a test on an attribute (such as flow control valve opening, cooling unit efficiency, etc.), branches representing the test outputs, and leaf nodes representing the category (i.e., the type of anomaly source).

[0050] The adaptation analysis unit works based on the abnormal source backtracking model, calls the established abnormal source backtracking model, and collects the corresponding main and branch pipeline operation data for each traceability target. These data cover key parameters such as flow, pressure, and temperature. At the same time, combined with the independent abnormal data of the main pipeline and any branch pipeline generated by the collaborative abnormality analysis module, a comprehensive and detailed analysis is performed using the correlation analysis algorithm. During the analysis process, the actual abnormal data is compared with the expected abnormal pattern based on the traceability target in the model to determine the degree of match between the abnormal data and each traceability target. If it is found that the adaptation index of a certain traceability target and the current abnormal data exceeds the preset threshold, the traceability target is determined to be a collaborative abnormal pipeline source and is marked. The marking content includes the specific information of the traceability target, the possible time of the abnormality, the degree of impact of the abnormality on the pipeline system, etc., so that subsequent maintenance personnel can quickly locate and handle abnormal situations to ensure the stable operation of the emulsion pump station.

[0051] In one possible implementation, the adaptation analysis unit further includes:

[0052] Any adaptation index generating unit is used to fuse the independent abnormal data of the main pipeline and the independent abnormal data of any branch pipeline, and then perform an adaptation comparison of the abnormal data with the operation data of any main and branch pipeline to generate any adaptation index.

[0053] The traceability target adding unit is used to add any traceability target into the collaborative abnormal pipeline source if any adaptation index is greater than a preset adaptation index.

[0054] Specifically, when performing abnormal data adaptation and comparison, any adaptation indicator generation unit fuses the independent abnormal data of the main pipeline with the independent abnormal data of any branch pipeline. This integration combines various aspects of the main pipeline's abnormal data, such as abnormal flow values, abnormal pressure fluctuation ranges, and abnormal temperature fluctuation amplitudes, with the corresponding abnormal data of flow, pressure, and temperature for any branch pipeline. For example, if the main pipeline flow suddenly decreases by a certain value while the branch pipeline pressure increases by a specific percentage, these abnormal data are aggregated to form a new comprehensive abnormal data set. The abnormal source tracing model obtains the operating data of any main and branch pipelines. This data contains various parameters during normal operation of the main and branch pipelines, including flow, pressure, and temperature. A correlation analysis is performed between the fused abnormal data and the main and branch pipeline operating data. For example, using flow parameters as an example, the correlation between abnormal flow changes in the fused abnormal data and normal flow changes in the main and branch pipeline operating data is examined. If the flow rate in the main and branch pipeline operating data typically fluctuates within a certain range, but the flow rate in the fused abnormal data fluctuates significantly, the correlation between this fluctuation and the normal flow changes in the main and branch pipelines is analyzed. Similarly, other parameters such as pressure and temperature are analyzed one by one. During the analysis process, the correlation between the abnormal changes of each parameter and the changes in the normal operating parameters of the main and branch pipelines is comprehensively considered, and different weights are assigned to each parameter according to its importance in the pipeline operation. For example, for some key equipment, the importance of the flow parameter may be higher than the temperature parameter, so the weight corresponding to the flow parameter will be greater. Finally, through weighted calculation of the results of the correlation analysis of all parameters, a comprehensive value is obtained as any adaptation index. This indicator can reflect the overall correlation between the fused abnormal data and the main and branch pipeline operation data, that is, the adaptation of the abnormal data. The higher the index value, the stronger the correlation between the abnormal data and the main and branch pipeline operation data, and the higher the adaptability; conversely, the lower the index value, the lower the adaptability.

[0055] When any adaptation indicator generation unit generates any adaptation indicator, the traceability target adding unit will immediately compare the indicator with the preset adaptation indicator. The preset adaptation indicator is determined based on a large amount of historical data, equipment operation standards, industry experience and other factors, and is an important threshold for judging whether the abnormal source matches. If any adaptation indicator is greater than the preset adaptation indicator, this indicates that there is a high degree of match between the currently analyzed abnormal data and the corresponding main and branch pipeline operation data, which means that the traceability target is the source of the pipeline collaborative abnormality. At this time, the traceability target adding unit will add any traceability target to the collaborative abnormal pipeline source. This operation enables the collaborative abnormal pipeline source to be continuously improved, provides a clear and precise direction for subsequent troubleshooting and repair work, and greatly improves the efficiency and accuracy of fault handling.

[0056] In one possible implementation, the pipeline monitoring module 30 further includes:

[0057] The main pipeline monitoring module includes a temperature sensor, a flow sensor and a flow velocity sensor arranged at various points on the main pipeline, and the multiple branch pipeline monitoring modules respectively include a temperature sensor, a flow sensor and a flow velocity sensor located at different points on each branch pipeline.

[0058] Specifically, in the emulsion pump station monitoring system, the main line monitoring module consists of multiple precise sensors deployed at key points along the main line. The temperature sensor is responsible for capturing real-time temperature information of the emulsion at different locations within the main line, accurately measuring temperature changes, and providing an important basis for determining the thermal stability of the emulsion and the heat dissipation during equipment operation. The flow sensor is used to measure the flow rate of the emulsion in the main line. By monitoring the flow rate at different points, it is possible to determine whether the emulsion is being delivered stably throughout the main line and whether there are sudden changes or abnormal fluctuations in the flow rate. This is crucial for ensuring the normal supply of the pump station and the stable operation of subsequent production processes. The flow rate sensor can accurately sense the flow rate of the emulsion in the main line. By monitoring changes in flow rate, it can not only assist in determining whether there are problems such as blockages or leaks in the pipeline, but also provide more accurate parameters for precise flow calculation. At the same time, multiple branch line monitoring modules correspond to each branch line. Their structure is similar to that of the main line monitoring module, consisting of a temperature sensor, a flow sensor, and a flow rate sensor. The difference is that these sensors are installed at different points on each branch pipeline. The selection of these points fully considers the equipment layout, process requirements, and risk points of possible failure on the branch pipeline. For example, a temperature sensor will be installed near a specific processing equipment on the branch pipeline to promptly understand whether the temperature of the emulsion entering the equipment meets the equipment operating requirements; a flow sensor will be arranged near the flow regulating valve on the branch pipeline to monitor whether the flow rate after valve adjustment reaches the expected value; and a flow velocity sensor will be set in a narrow part of the pipeline or an area prone to turbulence to accurately measure the flow velocity changes and analyze whether the flow state of the emulsion in the pipeline is normal. Through these branch pipeline monitoring modules, the real-time operating parameters of the emulsion in each branch pipeline can be fully and meticulously grasped, providing solid data support for the stable and efficient operation of the entire emulsion pump station system.

[0059] In one possible implementation, the abnormality alarm module 50 further includes:

[0060] The main line particle sensor data monitoring unit is used to set a particle sensor on the main line to monitor the main line particle sensor data.

[0061] The pipeline damage index establishing unit is used to perform pipeline damage analysis based on the main pipeline particle sensing data and establish a pipeline damage index.

[0062] The abnormal warning signal issuing unit is used to issue a first emulsion particle abnormal warning signal if the pipeline damage index is greater than or equal to a preset damage index.

[0063] The operation damage index generating unit is used to perform operation damage analysis on the emulsion supply targets connected to the multiple branch pipelines based on the particle sensing data of the main pipeline if the pipeline damage index is less than the preset damage index, and generate multiple operation damage indicators.

[0064] The damage threshold judgment unit is used to issue a second emulsion particle abnormality warning signal when the multiple operation damage indicators are greater than or equal to their respective damage thresholds.

[0065] Specifically, in the operation monitoring system of the emulsion pump station, the main line particle sensor data monitoring unit is responsible for acquiring data related to the emulsion particles in the main line. Given that the emulsion in the branch line originates from the transportation of the main line, as long as there are particles in the emulsion in the main line, the branch line will inevitably have the same situation, so particle sensors are only installed on the main line. These particle sensors are deployed at specific locations in the main line and can keenly sense various information about the particles in the emulsion, such as particle concentration, particle size, and material composition of the particles. Through continuous and real-time monitoring, the sensor accurately collects this data, converts it into electrical signals or digital signals, and then transmits it to the subsequent data processing module. These main line particle sensor data play a vital basic supporting role in fully understanding the cleanliness of the emulsion and evaluating its possible impact on the pipeline system and related equipment.

[0066] In-depth analysis of particle sensor data from the main pipeline reveals detailed information such as particle concentration, size distribution, hardness, and chemical composition within the emulsion. Based on materials science principles, the wear effects of particles of varying sizes and hardness on pipeline materials are considered. For example, when large, hard particles in a high-speed emulsion collide with the inner wall of a pipeline, they produce an effect similar to abrasive wear, gradually reducing the pipe wall thickness over time. Furthermore, the chemical composition of the particles can cause corrosion in the pipeline. For example, certain corrosive particle components can react chemically with the pipeline material, weakening its structural strength. These influencing factors are comprehensively considered using mathematical models and statistical analysis. A multivariate linear regression model is employed, using particle concentration, size, and hardness as independent variables and actual pipeline wear or corrosion as the dependent variable. The model parameters are calibrated using extensive historical data to establish a pipeline damage index that accurately reflects the extent of pipeline damage. This index is not a simple numerical value, but rather a quantitative representation of the impact of multiple particle factors on pipeline damage, providing a key basis for subsequent anomaly diagnosis and equipment maintenance.

[0067] The abnormality warning signal issuing unit monitors changes in the pipeline damage index in real time. Once the pipeline damage index establishment unit generates a pipeline damage index, it immediately and accurately compares it with a pre-set damage index. This pre-set damage index is determined based on a combination of factors, including the pump station pipeline's material properties, design service life, safe operation standards, and past operating experience. It serves as a critical threshold for determining whether the pipeline is operating safely. If the abnormality warning signal issuing unit determines that the pipeline damage index is greater than or equal to the pre-set damage index, it means that the pipeline has been damaged to a level exceeding the safe range due to the particles in the emulsion. Continued operation could cause failures such as leakage, blockage, or even rupture, seriously impacting the normal operation of the pump station. At this point, the abnormality warning signal issuing unit quickly and accurately issues a first emulsion particle abnormality warning signal. This warning signal may be displayed in the form of an audible and visual alarm at the pump station's monitoring center. Simultaneously, the relevant alarm information is also instantly pushed to the mobile devices of pump station managers, ensuring that they are immediately notified of the abnormality and can take appropriate measures, such as arranging for maintenance personnel to conduct a comprehensive inspection and repair of the pipeline, to ensure the safe and stable operation of the pump station.

[0068] When the pipeline damage index is less than the preset damage index, the operational damage index generation unit focuses on the main pipeline particle sensor data and conducts a comprehensive operational damage analysis for various emulsion supply targets connected by multiple branch pipelines, such as processing equipment for different production processes and reactors for specific chemical reactions. For each supply target, the unit screens particle characteristic parameters closely related to operational damage, such as particle concentration, particle size distribution, particle shape coefficient, and hardness, based on its operating principle, performance parameters, and emulsion cleanliness requirements. For example, for precision machining equipment, particle size distribution and particle hardness significantly influence machining accuracy; for chemical reaction equipment, particle concentration and chemical properties may play a key role in the reaction process. Next, a large amount of historical data is collected, covering the operational performance of each supply target under different particle characteristic parameters. Using this data, a quantitative relationship between particle characteristic parameters and operational damage is established through statistical analysis. Association rule mining is used to identify the correlation between specific particle size ranges and product quality defect types. Finally, the current main pipeline particle sensor data is substituted into the established relationship model to calculate the operational damage index for each emulsion supply target. These indicators quantify the potential damage to each operation caused by emulsion particles, providing a strong basis for assessing operational risks and taking targeted measures in advance. By performing the above operations on the supply targets connected to all branch pipelines, multiple operational damage indicators are generated.

[0069] After generating multiple operational damage indicators, the damage threshold determination unit meticulously compares each one with its own pre-set damage threshold. These thresholds are determined based on a comprehensive set of factors, including the equipment characteristics, process standards, safe operation requirements, and long-term practical experience of the target emulsion supply. They serve as critical thresholds for determining whether an operation faces unacceptable risk. Once the damage threshold determination unit confirms that one or more of the multiple operational damage indicators is greater than or equal to its corresponding damage threshold, it indicates that particles in the emulsion have posed a significant potential risk to the corresponding operation. If not addressed promptly, this could lead to adverse consequences such as reduced production efficiency, decreased product quality, and equipment failure. At this point, the damage threshold determination unit immediately issues a second emulsion particle anomaly warning signal. This warning signal may be displayed in a prominent audio and visual format at the monitoring center, and can be rapidly communicated to relevant operators and management personnel via text messages, in-station notifications, and other means. This ensures that the anomaly is immediately detected and effective measures, such as adjusting the emulsion filtration system or replacing equipment components, can be taken to mitigate the risk and ensure stable and safe production operations.

[0070] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the foregoing descriptions of specific embodiments of this specification are provided. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0071] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. This specification and the drawings are merely exemplary illustrations of the present application and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application intends to include these modifications and variations.

Claims

1. The multi-point coordinated early warning system of the emulsion pump station is characterized by: include: A main and branch pipeline determination module is used to determine the main pipeline and multiple branch pipelines in the emulsion pump station; A monitoring module configuration module, configured to configure a main line monitoring module and multiple branch line monitoring modules for the main line and the multiple branch lines respectively; a pipeline monitoring module, configured to connect to the main pipeline monitoring module to obtain a main pipeline monitoring data set of the main pipeline, and connect to the multiple branch pipeline monitoring modules to obtain multiple branch pipeline monitoring data sets of the multiple branch pipelines; a collaborative abnormality analysis module, configured to perform collaborative abnormality analysis of the emulsion state of the main and branch pipelines based on the main pipeline monitoring data set and the plurality of branch pipeline monitoring data sets, and generate independent abnormality data of the main pipeline and independent abnormality data of any branch pipeline; An abnormality alarm module, configured to perform a collaborative abnormality impact analysis on the main pipeline and the multiple branch pipelines based on the independent abnormality data of the main pipeline and the independent abnormality data of any branch pipeline, generate and mark the collaborative abnormal pipeline source, and generate an abnormality warning signal for the marked pipeline to alarm; The collaborative anomaly analysis module also includes: a demand parameter receiving unit, configured to receive preset operation demand parameters of the emulsion pump station, wherein the preset operation scenario includes emulsion demand parameters of emulsion supply targets connected to the plurality of branch pipelines; an operating parameter generating unit, configured to call a main-branch pipeline dispatching center to analyze the emulsion demand parameter, and generate a main pipeline emulsion operating parameter of the main pipeline and multiple branch pipeline emulsion operating parameters of the multiple branch pipelines; a twin main-branch pipeline operation model establishing unit, configured to establish a twin main-branch pipeline operation model by modeling the main pipeline emulsion operation parameters and the plurality of branch pipeline emulsion operation parameters; An independent abnormal data generation unit is used to train a main-branch pipeline collaborative abnormality recognition model with the twin main-branch pipeline operation model, call the main-branch pipeline collaborative abnormality recognition model to collaboratively analyze the main pipeline monitoring data set and the multiple branch pipeline monitoring data sets, and generate the main pipeline independent abnormality data and any branch pipeline independent abnormality data.

2. The multi-point coordinated early warning system for an emulsion pump station according to claim 1, characterized in that: The independent abnormal data generating unit further includes: A pipeline coordination abnormality data generating unit, configured to debug the twin main and branch pipeline operation model and generate pipeline coordination abnormality data; The synergistic effect training unit is used to perform synergistic effect training when the main and branch pipelines are abnormal based on the pipeline synergistic abnormality data, and generate the main and branch pipeline synergistic abnormality recognition model.

3. The multi-point coordinated early warning system for an emulsion pump station according to claim 2, characterized in that: The pipeline collaborative abnormality data includes first pipeline collaborative abnormality data with the main pipeline as the abnormality source, second pipeline collaborative abnormality data with any branch pipeline as the abnormality source, and third pipeline collaborative abnormality data with the main pipeline and any branch pipeline as parallel abnormality sources.

4. The multi-point coordinated early warning system for an emulsion pump station according to claim 1, characterized in that: The abnormal alarm module also includes: An abnormal source backtracking model establishing unit is used to establish an abnormal source backtracking model for the main pipeline and multiple branch pipelines, wherein the abnormal source backtracking model is used to be trained by using any device among the flow control valve and the cooling device of the main and branch pipelines independently or in combination as the tracing target; The adaptation analysis unit is used to call the abnormal source backtracking model to collect the operation data of any main and branch pipelines corresponding to any traceability target, perform adaptation analysis on the independent abnormal data of the main pipeline and the independent abnormal data of any branch pipeline, generate the collaborative abnormal pipeline source and mark it.

5. The multi-point coordinated early warning system for an emulsion pump station according to claim 4, characterized in that: The adaptation analysis unit also includes: Any adaptation index generating unit is used to fuse the independent abnormal data of the main pipeline and the independent abnormal data of any branch pipeline, and then perform an adaptation comparison of the abnormal data with the operation data of any main and branch pipeline to generate any adaptation index; The traceability target adding unit is used to add any traceability target into the collaborative abnormal pipeline source if any adaptation index is greater than a preset adaptation index.

6. The multi-point coordinated early warning system for an emulsion pump station according to claim 1, characterized in that: The main pipeline monitoring module includes a temperature sensor, a flow sensor and a flow velocity sensor arranged at various points on the main pipeline, and the multiple branch pipeline monitoring modules respectively include a temperature sensor, a flow sensor and a flow velocity sensor located at different points on each branch pipeline.

7. The multi-point coordinated early warning system for an emulsion pump station according to claim 1, characterized in that: It also includes an emulsion abnormality warning module: a main line particle sensor data monitoring unit, configured to set a particle sensor on the main line and monitor the main line particle sensor data; a pipeline damage index establishing unit, configured to perform pipeline damage analysis based on the main pipeline particle sensing data and establish a pipeline damage index; an abnormal warning signal issuing unit, configured to issue a first emulsion particle abnormality warning signal if the pipeline damage index is greater than or equal to a preset damage index; an operation damage index generating unit, configured to perform an operation damage analysis on emulsion supply targets connected to a plurality of branch pipelines using the particle sensing data of the main pipeline to generate a plurality of operation damage indices if the pipeline damage index is less than a preset damage index; The damage threshold judgment unit is used to issue a second emulsion particle abnormality warning signal when the multiple operation damage indicators are greater than or equal to their respective damage thresholds.

Images