Pump station intelligent production management system based on big data decision

Abstract

The invention discloses a pump station intelligent production management system based on big data decision, and belongs to the technical field of pump station production management, in the pump station intelligent production management system, a data mining sub-module, a data visualization sub-module and a decision support sub-module jointly form a powerful analysis platform, and the data mining sub-module uses a big data analysis technology to carry out big data analysis on the data visualization sub-module and the decision support sub-module. Valuable information and modes can be extracted from a large amount of data. And the decision support sub-module provides decision suggestions for operation, maintenance, transformation and the like of the pump station according to data mining and visualization results. Comprising the aspects of optimization suggestion, prediction maintenance, risk assessment, cost-benefit analysis and the like. And through the decision support sub-module, a manager can obtain a comprehensive data analysis result so as to make a more intelligent decision. For example, through cost-benefit analysis, managers can calculate costs and benefits of different decision-making schemes, a basis is provided for investment decision-making, and long-term stable operation of the pump station is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of pump station production management, and specifically is an intelligent production management system for pump stations based on big data decision-making. Background Art

[0002] The pump station management system is an intelligent management system that integrates computer technology, communication technology, automatic control technology, and sensor technology. It is mainly used in urban drainage, sewage treatment, farmland irrigation, water conservancy projects, and other fields. Through remote monitoring, automatic adjustment, and intelligent management of pump stations, efficient, stable, and safe operation of pump stations can be achieved. The pump station management system mainly consists of the following parts: Data acquisition and transmission: Through sensors installed on water pumps, valves, water levels, flow rates, and other equipment, the working status and operation data of the equipment are collected in real time, and the data is transmitted to the monitoring center through wired or wireless networks. Monitoring center: The monitoring center is the core part of the system, responsible for receiving, processing, and storing data from various pump stations, and displaying it to operators through a human-machine interface. Operators can understand the operation of the pump station in real time through the monitoring center, and perform remote control and adjustment. Pump station equipment control: According to the instructions of the monitoring center or the preset operation strategy, the start, stop, and adjustment of water pumps, valves, and other equipment are automatically controlled to realize the automatic operation of the pump station. In short, the pump station management system is an efficient, intelligent and reliable pump station management tool, which is of great significance in improving the operating efficiency of pump stations, ensuring the safe and stable operation of pump stations, reducing the intensity of manual labor, and saving operating costs. With the advancement of science and technology and the continuous development of urban construction, the pump station management system will play an increasingly important role in the field of pump station management.

[0003] However, existing pump station monitoring systems often rely on manual monitoring and analysis and are unable to process large amounts of data in real time. At the same time, traditional pump station monitoring systems are insufficient in decision support and are unable to provide managers with comprehensive data analysis and decision-making recommendations. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent production management system for pump stations based on big data decision-making in order to solve the above-mentioned problems.

[0005] The technical solution adopted by the present invention is as follows: a pump station intelligent production management system based on big data decision-making, characterized in that: the system includes: a data acquisition and transmission module, a data storage and management module, a big data analysis and decision-making module, an intelligent control module, an equipment management module, a safe production management module and a comprehensive information management module;

[0006] The data acquisition and transmission module is the front end of the system, collecting real-time data from sensors and monitoring equipment, and transmitting these data to the data storage and management module; the data storage and management module is responsible for receiving, storing and managing data from the data acquisition module. The big data analysis and decision-making module uses the data stored in the data storage module to mine and analyze, and generate decision support information. This information is used to guide the operation of the intelligent control module. The intelligent control module automatically adjusts the operating status of the pump station based on the decision support provided by the big data analysis module;

[0007] The equipment management module relies on the equipment files and operation data in the data storage module and the feedback from the intelligent control module to maintain and manage the equipment.

[0008] The production safety management module utilizes the potential safety hazard information provided by the big data analysis module and combines it with the actual situation of the equipment management module to perform safety management and accident prevention.

[0009] The comprehensive information management module provides information support for other modules, including publishing notices, managing documents and personnel information, etc., and can also receive feedback information from other modules;

[0010] The big data analysis and decision-making module is internally provided with a data mining submodule, a data visualization submodule and a decision support submodule. The data mining submodule processes and analyzes data, passes the results to the data visualization submodule for display, and finally the decision support submodule uses this information to provide decision suggestions for managers.

[0011] In a preferred embodiment, the data acquisition and transmission module is the front end of the system, responsible for collecting real-time data from sensors and monitoring equipment and transmitting the data to the data center. Sensor data acquisition includes parameters such as liquid level, flow, pressure, temperature, etc., while video monitoring data acquisition uses high-definition cameras to monitor the internal and external environment of the pump station in real time. Data transmission is achieved using Internet of Things technology and wireless communication technology to ensure the real-time and accuracy of data.

[0012] In a preferred embodiment, the data storage and management module is responsible for receiving, storing and managing data from the data acquisition module. A pump station operation database is established to store real-time data, historical data, equipment parameters, etc. The data is cleaned, sorted and archived to ensure data quality. Data storage and management provide data support for subsequent big data analysis.

[0013] In a preferred embodiment, the data mining submodule extracts valuable information from a large amount of data through the DBSCAN algorithm and model.

[0014] The calculation process of the data mining submodule is as follows:

[0015] S1: Initialization: Select an unvisited point as a seed point, mark all points as unvisited, and for each point in the dataset, calculate all points in its neighborhood. This is usually done by calculating the Euclidean distance. For two points p and q, their distance d(p,q) is calculated by the following formula:

[0016]

[0017] Where px, py and qx, qy are the coordinates of points p and q in two-dimensional space respectively. For high-dimensional space, this formula can be extended to include more dimensions;

[0018] S2: Find core points: For a seed point, calculate the number of points in its neighborhood. If the number of points in the neighborhood is greater than or equal to the threshold MinPts, mark it as a core point.

[0019] S3: Expand the cluster: For each core point, find all density-reachable points to form a cluster, remove these points from the unvisited set, and mark them as visited.

[0020] S4: Repeat steps S2 and S3: Select a new point from the unvisited points as the seed point, and repeat steps S2 and S3 until all points are visited.

[0021] S5: End: All core points and boundary points are assigned to a cluster, and noise points are marked as unassigned.

[0022] In a preferred embodiment, the data visualization submodule is provided with:

[0023] Bar chart display module: used to display data comparisons of different categories, including the number of failures of each device.

[0024] Line chart display module: used to display the trend of data changes over time, including the change of pump station flow over time.

[0025] Scatter plot display module: used to display the relationship between two variables, including the relationship between pressure and flow.

[0026] Heat map display module: used to display the distribution of data, including the frequency of device usage in different time periods.

[0027] Dashboard display module: used to comprehensively display multiple key indicators and provide an overview perspective.

[0028] In a preferred embodiment, the decision support submodule provides decision suggestions for the operation, maintenance, and transformation of the pump station based on the results of data mining and visualization.

[0029] Optimization suggestions: Based on the data analysis results, optimization suggestions for pump station operating parameters are put forward, such as adjusting the start and stop time of the pump, changing the scheduling strategy, etc.

[0030] Predictive maintenance: Based on the equipment’s operating data and failure history, predict future maintenance needs and schedule maintenance work in advance.

[0031] Risk assessment: By analyzing historical accident data, the risks of pump station operation are assessed and improvement measures are proposed.

[0032] Cost-benefit analysis: Calculate the costs and benefits of different decision-making options to provide a basis for investment decisions;

[0033] The calculation formula of the decision support submodule using the ARIMA model is:

[0034] (1-φ1B-φ2B 2 -…-φpBp)(1-B) d X t =c+θ1BX t-1 +θ2B 2 X t-2 +…+θqB q ∈t;

[0035] Where: X t is the value of the time series at time t.

[0036] B is the lag operator, B k Xt=X t-k .

[0037] φ1,φ2,…,φp are the coefficients of the autoregressive term.

[0038] θ1,θ2,…,θq are the coefficients of the moving average term.

[0039] d is the number of differences.

[0040] ∈t is the white noise error term.

[0041] c is a constant term;

[0042] In the intelligent production management system of pumping stations, the ARIMA model can be used to predict the operating parameters of pumping stations, such as flow, pressure, temperature, etc., as well as the status of equipment, such as the time when a fault occurs. By predicting future operating parameters and equipment status, the system can prepare in advance, such as adjusting the start and stop time of the pump, changing the scheduling strategy, or arranging maintenance work, thereby improving the operating efficiency and safety of the pumping station.

[0043] In a preferred embodiment, the intelligent control module automatically adjusts the pump station operation parameters according to the real-time data and big data analysis results to achieve high efficiency and energy saving. It includes three aspects: pump station operation optimization, equipment failure prediction and emergency plan. Pump station operation optimization achieves high efficiency and energy saving by adjusting the start and stop of the pump, changing the scheduling strategy, etc.; equipment failure prediction predicts possible equipment failures through the analysis of equipment operation data, and performs maintenance in advance; emergency plan automatically starts the emergency plan for emergencies to ensure the safe and stable operation of the pump station.

[0044] In a preferred embodiment, the equipment management module is responsible for equipment management, including equipment file management, equipment inspection management and spare parts management. Equipment file management establishes equipment files, including equipment parameters, maintenance records, replacement records, etc.; equipment inspection management formulates inspection plans, records inspection results, and ensures the normal operation of equipment; spare parts management manages the inventory of spare parts to ensure sufficient spare equipment.

[0045] In a preferred embodiment, the safety production management module is responsible for the management of safety production, including safety hazard investigation, safety training and assessment, and accident emergency management. The safety hazard investigation submodule discovers safety hazards through data analysis and makes timely rectifications. The safety training and assessment submodule organizes safety training, enhances employee safety awareness, and conducts safety assessments regularly. The accident emergency management submodule formulates accident emergency plans, organizes emergency drills, and improves the ability to respond to emergencies.

[0046] In a preferred embodiment, the comprehensive information management module is responsible for issuing notices and announcements on the operation, maintenance, and transformation of the pump station, and classifying and archiving various documents for easy query and retrieval. At the same time, the information of the pump station personnel is managed, including positions, responsibilities, contact information, etc. Through the comprehensive information management module, information sharing and efficient transmission are achieved, and the management level of the pump station is improved. The module also supports the generation of various reports and statements to provide a basis for decision-making.

[0047] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0048] 1. In the present invention, the data mining submodule, the data visualization submodule and the decision support submodule together constitute a powerful analysis platform. The data mining submodule can extract valuable information and patterns from a large amount of data by using big data analysis technology. This information can provide important decision-making basis for the operation, maintenance and transformation of the pump station. For example, by analyzing the equipment operation data, the data mining submodule can predict possible failures of the equipment, so as to perform maintenance in advance, reduce downtime, and increase the service life of the equipment. In addition, the data mining submodule can also help optimize the operating parameters of the pump station, such as adjusting the start and stop time of the pump and changing the scheduling strategy to achieve high efficiency and energy saving.

[0049] 2. In the present invention, the data visualization submodule intuitively displays the results of data mining in the form of charts, reports, etc., helping managers to better understand the meaning behind the data. Through visualization technology, managers can quickly identify key information, such as the number of failures, equipment operation trends, pressure and flow relationship, etc. This helps to improve the accuracy and efficiency of decision-making. For example, through a line chart, managers can intuitively observe the change trend of the pump station flow over time, so as to adjust the operating parameters in time to ensure the stable operation of the pump station.

[0050] 3. In the present invention, the decision support submodule provides decision suggestions for the operation, maintenance, and transformation of the pump station based on the results of data mining and visualization. It includes optimization suggestions, predictive maintenance, risk assessment, and cost-benefit analysis. Through the decision support submodule, managers can obtain comprehensive data analysis results and make more informed decisions. For example, through cost-benefit analysis, managers can calculate the costs and benefits of different decision-making plans, provide a basis for investment decisions, and ensure the long-term stable operation of the pump station. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is the overall system block diagram of the present invention;

[0052] Figure 2 This is a system block diagram of the big data analysis and decision-making module in the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0054] Reference Figure 1-2 ,

[0055] Example:

[0056] A pump station intelligent production management system based on big data decision-making, the system includes: data acquisition and transmission module, data storage and management module, big data analysis and decision-making module, intelligent control module, equipment management module, production safety management module and comprehensive information management module;

[0057] The data acquisition and transmission module is the front end of the system, collecting real-time data from sensors and monitoring equipment, and transmitting this data to the data storage and management module; the data storage and management module is responsible for receiving, storing and managing data from the data acquisition module. The big data analysis and decision-making module uses the data stored in the data storage module for mining and analysis to generate decision support information, which is used to guide the operation of the intelligent control module. The intelligent control module automatically adjusts the operating status of the pump station based on the decision support provided by the big data analysis module;

[0058] The equipment management module relies on the equipment files and operation data in the data storage module and the feedback from the intelligent control module to maintain and manage the equipment.

[0059] The production safety management module uses the safety hazard information provided by the big data analysis module and combines it with the actual situation of the equipment management module to carry out safety management and accident prevention.

[0060] The comprehensive information management module provides information support for other modules, including publishing notices, managing documents and personnel information, etc. It can also receive feedback information from other modules;

[0061] The big data analysis and decision-making module is internally configured with a data mining submodule, a data visualization submodule, and a decision support submodule. The data mining submodule processes and analyzes data, and passes the results to the data visualization submodule for display. Finally, the decision support submodule uses this information to provide decision recommendations to managers.

[0062] The data acquisition and transmission module is the front end of the system, responsible for collecting real-time data from sensors and monitoring equipment and transmitting this data to the data center. Sensor data collection includes parameters such as liquid level, flow, pressure, temperature, etc., while video monitoring data collection uses high-definition cameras to monitor the internal and external environment of the pump station in real time. Data transmission is achieved using Internet of Things technology and wireless communication technology to ensure the real-time and accuracy of data.

[0063] The data storage and management module is responsible for receiving, storing and managing data from the data acquisition module. A pump station operation database is established to store real-time data, historical data, equipment parameters, etc. The data is cleaned, sorted and archived to ensure data quality. Data storage and management provide data support for subsequent big data analysis.

[0064] The data mining submodule extracts valuable information from a large amount of data through the DBSCAN algorithm and model. The calculation process of the data mining submodule is as follows:

[0065] S1: Initialization: Select an unvisited point as a seed point, mark all points as unvisited, and for each point in the dataset, calculate all points in its neighborhood. This is usually done by calculating the Euclidean distance. For two points p and q, their distance d(p,q) is calculated by the following formula:

[0066]

[0067] Where px, py and qx, qy are the coordinates of points p and q in two-dimensional space respectively. For high-dimensional space, this formula can be extended to include more dimensions;

[0068] S2: Find core points: For a seed point, calculate the number of points in its neighborhood. If the number of points in the neighborhood is greater than or equal to the threshold MinPts, mark it as a core point.

[0069] S3: Expand the cluster: For each core point, find all density-reachable points to form a cluster, remove these points from the unvisited set, and mark them as visited.

[0070] S4: Repeat steps S2 and S3: Select a new point from the unvisited points as the seed point, and repeat steps S2 and S3 until all points are visited.

[0071] S5: End: All core points and boundary points are assigned to a cluster, and noise points are marked as unassigned.

[0072] The data visualization submodule settings are:

[0073] Bar chart display module: used to display data comparisons of different categories, including the number of failures of each device.

[0074] Line chart display module: used to display the trend of data changes over time, including the change of pump station flow over time.

[0075] Scatter plot display module: used to display the relationship between two variables, including the relationship between pressure and flow.

[0076] Heat map display module: used to display the distribution of data, including the frequency of device usage in different time periods.

[0077] Dashboard display module: used to comprehensively display multiple key indicators and provide an overview perspective.

[0078] The decision support submodule provides decision suggestions for the operation, maintenance, and transformation of pumping stations based on the results of data mining and visualization. It includes:

[0079] Optimization suggestions: Based on the data analysis results, optimization suggestions for pump station operating parameters are put forward, such as adjusting the start and stop time of the pump, changing the scheduling strategy, etc.

[0080] Predictive maintenance: Based on the equipment’s operating data and failure history, predict future maintenance needs and schedule maintenance work in advance.

[0081] Risk assessment: By analyzing historical accident data, the risks of pump station operation are assessed and improvement measures are proposed.

[0082] Cost-benefit analysis: Calculate the costs and benefits of different decision-making options to provide a basis for investment decisions;

[0083] The decision support submodule uses the ARIMA model as follows:

[0084] (1-φ1B-φ2B 2 -…-φpBp)(1-B) d X t =c+θ1BX t-1 +θ2B 2 X t-2 +…+θqB q ∈t;

[0085] Where: X t is the value of the time series at time t.

[0086] B is the lag operator, B k Xt=X t-k .

[0087] φ1,φ2,…,φp are the coefficients of the autoregressive term.

[0088] θ1,θ2,…,θq are the coefficients of the moving average term.

[0089] d is the number of differences.

[0090] ∈t is the white noise error term.

[0091] c is a constant term;

[0092] In the intelligent production management system of pumping stations, the ARIMA model can be used to predict the operating parameters of pumping stations, such as flow, pressure, temperature, etc., as well as the status of equipment, such as the time when a fault occurs. By predicting future operating parameters and equipment status, the system can prepare in advance, such as adjusting the start and stop time of the pump, changing the scheduling strategy, or arranging maintenance work, thereby improving the operating efficiency and safety of the pumping station.

[0093] The intelligent control module automatically adjusts the pump station operation parameters according to the real-time data and big data analysis results to achieve high efficiency and energy saving. It includes three aspects: pump station operation optimization, equipment failure prediction and emergency plan. Pump station operation optimization achieves high efficiency and energy saving by adjusting the start and stop of the pump and changing the scheduling strategy; equipment failure prediction predicts possible equipment failures through the analysis of equipment operation data and performs maintenance in advance; emergency plan automatically starts the emergency plan for emergencies to ensure the safe and stable operation of the pump station.

[0094] The equipment management module is responsible for equipment management, including equipment file management, equipment inspection management and spare parts management. Equipment file management establishes equipment files, including equipment parameters, maintenance records, replacement records, etc.; equipment inspection management formulates inspection plans, records inspection results, and ensures the normal operation of equipment; spare parts management manages the inventory of spare parts to ensure sufficient spare equipment.

[0095] The safety production management module is responsible for the management of safety production, including safety hazard investigation, safety training and assessment, and accident emergency management. The safety hazard investigation submodule discovers safety hazards through data analysis and makes timely rectifications. The safety training and assessment submodule organizes safety training, enhances employees' safety awareness, and conducts safety assessments regularly. The accident emergency management submodule formulates accident emergency plans, organizes emergency drills, and improves the ability to respond to emergencies.

[0096] The comprehensive information management module is responsible for issuing notices and announcements on pump station operation, maintenance, and renovation, and for classifying and archiving various documents for easy query and access. At the same time, it manages the information of pump station personnel, including positions, responsibilities, contact information, etc. Through the comprehensive information management module, information sharing and efficient transmission are achieved, and the management level of the pump station is improved. The module also supports the generation of various reports and statements to provide a basis for decision-making.

[0097] In the present invention, the data mining submodule, the data visualization submodule and the decision support submodule together constitute a powerful analysis platform. The data mining submodule can extract valuable information and patterns from a large amount of data by using big data analysis technology. This information can provide important decision-making basis for the operation, maintenance and transformation of the pump station. For example, by analyzing the equipment operation data, the data mining submodule can predict possible failures of the equipment, so as to perform maintenance in advance, reduce downtime, and increase the service life of the equipment. In addition, the data mining submodule can also help optimize the operating parameters of the pump station, such as adjusting the start and stop time of the pump and changing the scheduling strategy to achieve high efficiency and energy saving.

[0098] In the present invention, the data visualization submodule intuitively displays the results of data mining in the form of charts, reports, etc., helping managers to better understand the meaning behind the data. Through visualization technology, managers can quickly identify key information, such as the number of failures, equipment operation trends, pressure and flow relationship, etc. This helps to improve the accuracy and efficiency of decision-making. For example, through a line chart, managers can intuitively observe the change trend of the pump station flow over time, so as to adjust the operating parameters in time to ensure the stable operation of the pump station.

[0099] In the present invention, the decision support submodule provides decision suggestions for the operation, maintenance, and transformation of the pump station based on the results of data mining and visualization. It includes optimization suggestions, predictive maintenance, risk assessment, and cost-benefit analysis. Through the decision support submodule, managers can obtain comprehensive data analysis results and make more informed decisions. For example, through cost-benefit analysis, managers can calculate the costs and benefits of different decision-making plans, provide a basis for investment decisions, and ensure the long-term stable operation of the pump station.

[0100] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0101] The above description enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A pump station intelligent production management system based on big data decision-making, characterized by: The system includes: data collection and transmission module, data storage and management module, big data analysis and decision-making module, intelligent control module, equipment management module, production safety management module and comprehensive information management module; The data acquisition and transmission module is the front end of the system, collecting real-time data from sensors and monitoring equipment, and transmitting these data to the data storage and management module; the data storage and management module is responsible for receiving, storing and managing data from the data acquisition module; the big data analysis and decision-making module uses the data stored in the data storage module to mine and analyze, and generates decision support information, which is used to guide the operation of the intelligent control module. The intelligent control module automatically adjusts the operating status of the pump station according to the decision support provided by the big data analysis module; The equipment management module relies on the equipment files and operation data in the data storage module and the feedback from the intelligent control module to maintain and manage the equipment; The production safety management module uses the potential safety information provided by the big data analysis module and combines it with the actual situation of the equipment management module to perform safety management and accident prevention; The comprehensive information management module provides information support for other modules, including publishing notices, managing documents and personnel information, and also receives feedback information from other modules; The big data analysis and decision-making module is internally provided with a data mining submodule, a data visualization submodule and a decision support submodule. The data mining submodule processes and analyzes data, passes the results to the data visualization submodule for display, and finally the decision support submodule uses this information to provide decision suggestions for managers.

2. The intelligent production management system for pump stations based on big data decision-making according to claim 1, characterized in that: The data acquisition and transmission module is the front end of the system, responsible for collecting real-time data from sensors and monitoring equipment and transmitting this data to the data center; sensor data collection includes liquid level, flow, pressure, and temperature parameters, while video monitoring data collection uses high-definition cameras to monitor the internal and external environment of the pump station in real time; data transmission is achieved using Internet of Things technology and wireless communication technology to ensure the real-time and accuracy of the data.

3. The intelligent production management system for pump stations based on big data decision-making according to claim 1, characterized in that: The data storage and management module is responsible for receiving, storing and managing the data from the data acquisition module; Establish a pump station operation database to store real-time data, historical data, and equipment parameters; clean, organize, and archive data to ensure data quality; data storage and management provide data support for subsequent big data analysis.

4. The intelligent production management system for pump stations based on big data decision-making according to claim 1, characterized in that: The data mining submodule extracts valuable information from large amounts of data through the DBSCAN algorithm and model. The calculation process of the data mining submodule is as follows: S1: Initialization: Select an unvisited point as a seed point, mark all points as unvisited, and for each point in the dataset, calculate all points in its neighborhood; this is usually done by calculating the Euclidean distance. For two points p and q, their distance d(p,q) is calculated by the following formula: Where px, py and qx, qy are the coordinates of points p and q in two-dimensional space respectively; for high-dimensional space, this formula is extended to include more dimensions; S2: Find the core point: For the seed point, calculate the number of points in its neighborhood. If the number of points in the neighborhood is greater than or equal to the threshold MinPts, mark it as a core point. S3: Expand clusters: For each core point, find all density-reachable points to form a cluster, remove these points from the unvisited set, and mark them as visited; S4: Repeat steps S2 and S3: Select a new point from the unvisited points as the seed point, and repeat steps S2 and S3 until all points are visited; S5: End: All core points and boundary points are assigned to a cluster, and noise points are marked as unassigned.

5. The intelligent production management system for pump stations based on big data decision-making according to claim 1, characterized in that: The data visualization submodule is provided with: Bar chart display module: used to display data comparisons of different categories, including the number of failures of each device; Line chart display module: used to display the trend of data changes over time, including the change of pump station flow over time; Scatter plot display module: used to display the relationship between two variables, including the relationship between pressure and flow; Heat map display module: used to display the distribution of data, including the frequency of equipment use in different time periods; Dashboard display module: used to comprehensively display multiple key indicators and provide an overview perspective.

6. The intelligent production management system for pump stations based on big data decision-making according to claim 1, characterized in that: The decision support submodule provides decision suggestions for the operation, maintenance and transformation of the pump station based on the results of data mining and visualization; including: Optimization suggestions: Based on the data analysis results, optimization suggestions for pump station operation parameters are put forward; Predictive maintenance: predict future maintenance needs based on the equipment’s operating data and failure history, and schedule maintenance work in advance; Risk assessment: By analyzing historical accident data, assess the risks of pump station operation and propose improvement measures; Cost-benefit analysis: Calculate the costs and benefits of different decision-making options to provide a basis for investment decisions; The calculation formula of the decision support submodule using the ARIMA model is: (1-φ1B-φ2B 2 -…-φpBp)(1-B) d X t =c+θ1BX t-1 +θ2B 2 X t-2 +…+θqB q ∈t; Where: X t is the value of the time series at time t; B is the lag operator, B k Xt=X t-k ; φ1, φ2,…, φp are the coefficients of the autoregressive term; θ1,θ2,…,θq are the coefficients of the moving average term; d is the number of differences; ∈t is the white noise error term; c is a constant term.

7. The intelligent production management system for pump stations based on big data decision-making according to claim 1, characterized in that: The intelligent control module automatically adjusts the pump station operation parameters according to the real-time data and big data analysis results to achieve high efficiency and energy saving. It includes three aspects: pump station operation optimization, equipment failure prediction and emergency plan. Pump station operation optimization achieves high efficiency and energy saving by adjusting the start and stop of the pump and changing the scheduling strategy. Equipment failure prediction predicts possible equipment failures through analysis of equipment operation data and performs maintenance in advance. The emergency plan automatically starts the emergency plan for emergencies to ensure safe and stable operation of the pump station.

8. The intelligent production management system for pump stations based on big data decision-making according to claim 1, characterized in that: The equipment management module is responsible for equipment management, including equipment file management, equipment inspection management and spare parts management; equipment file management establishes equipment files, including equipment parameters, maintenance records, and replacement records; equipment inspection management formulates inspection plans, records inspection results, and ensures the normal operation of equipment; spare parts management manages the inventory of spare parts to ensure sufficient spare equipment.

9. The intelligent production management system for pump stations based on big data decision-making according to claim 1, characterized in that: The safety production management module is responsible for the management of safety production, including safety hazard investigation, safety training and assessment, and accident emergency management; the safety hazard investigation submodule discovers safety hazards through data analysis and makes timely rectifications; the safety training and assessment submodule organizes safety training, enhances employees' safety awareness, and conducts safety assessments regularly; The accident emergency management submodule formulates accident emergency plans, organizes emergency drills, and improves the ability to respond to emergencies.

10. The intelligent production management system for pump stations based on big data decision-making according to claim 1, characterized in that: The comprehensive information management module is responsible for issuing notices and announcements regarding the operation, maintenance, and renovation of the pump station, and for classifying and archiving various documents for easy query and retrieval; at the same time, it manages the information of the pump station personnel, including their positions, responsibilities, and contact information.

Images