Intelligent pipe network data acquisition method

Abstract

The invention discloses a pipe network data intelligent acquisition method, and relates to the technical field of pipe network intelligent monitoring, and the method comprises the steps: S1, deploying sensing equipment, including a flow monitor, a pressure sensor and a temperature sensor, at each monitoring node in a heat supply pipe network system to monitor pipeline operation data in real time; s2, realizing remote data acquisition and transmission of the online monitoring equipment by utilizing NB-IoT communication, and transmitting the data to a cloud server to wait for being processed and called; and S3, storing the collected data in a cloud or a local database, and the like. The sensing devices are deployed in the monitoring nodes in the heat supply pipe network system to monitor the pipeline operation data in real time, comprehensive and automatic collection of pipe network data is achieved, problems can be found in time, corresponding measures are taken, the operation efficiency and stability of the pipe network system are improved, remote data collection and transmission are achieved through NB-IoT communication, and the system is convenient to use. The efficiency and convenience of data acquisition are improved, and the waste of human resources is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring of pipe networks, and specifically to an intelligent data acquisition method for pipe networks. Background Art

[0002] Urban pipe networks refer to the various infrastructure pipe networks in cities, such as water supply pipe networks, drainage pipe networks, natural gas pipe networks, etc. These pipe networks are crucial infrastructure in the operation of cities, ensuring the normal life and operation of residents and enterprises. Among them, the heating pipe network is a pipe network system for centralized heating and cooling in cities. It transports heat energy or cold energy to each user unit through a heat energy center, including residential buildings, commercial buildings, and industrial land. The heating pipe network provides heating services in winter and cooling services in summer, and is an important part of the modern urban energy infrastructure.

[0003] At present, the length of urban heating pipe networks is huge and the distribution is complex. Traditional manual acquisition methods are difficult to cover all areas, resulting in low data acquisition efficiency. Moreover, there are a large amount of data involved in the pipe networks. Traditional pipe network data acquisition relies on methods such as manual inspections and fixed monitoring stations, which require a large amount of human and material resources, and there are problems such as missed inspections and misjudgments, and comprehensive and real-time data acquisition cannot be achieved, thus affecting the decision-making and operation effects of pipe network management. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent data acquisition method for pipe networks to solve the problems raised in the above background art, that is, for urban heating pipe network data acquisition, the efficiency is low and there are a large amount of data involved in the pipe networks. Traditional pipe network data acquisition relies on methods such as manual inspections and fixed monitoring stations, which require a large amount of human and material resources, and there are problems such as missed inspections and misjudgments, and comprehensive and real-time data acquisition cannot be achieved, thus affecting the decision-making and operation effects of pipe network management.

[0005] To achieve the above purpose, the present invention provides the following technical solution: An intelligent data acquisition method for pipe networks, including the following steps: S1. Deploy sensing devices at each monitoring node in the heating pipe network system, including flow monitors, pressure sensors, and temperature sensors to monitor the pipeline operation data in real time; S2. Use NB-IoT communication to realize remote data acquisition and transmission of on-line monitoring devices, and transmit the data to the cloud server for waiting to be processed and called; S3. Store the acquired data in the cloud or a local database, and use big data technology to process and analyze the data; S4. Use artificial intelligence algorithms to analyze the processed acquired data to discover the correlation, trend, and anomalies between the data, and help optimize the operation and management of the pipe network; S5. Develop intelligent decision-making strategies based on the data analysis results, including pipeline network maintenance, pipeline network inspection, and optimization measures, to improve the operation efficiency of the pipeline network and reduce maintenance costs; S6. Use data visualization tools and combine with GIS maps to visually display the analysis results, help users understand the data and trends, generate reports regularly, and provide the data analysis results and suggestions to relevant personnel, so as to visually display the data analysis results, help users better understand the pipeline network data and trends, and promote the accuracy and efficiency of decision-making and pipeline network management.

[0006] Preferably, in step S1, the deployment of sensing devices at each monitoring node in the heat pipeline network system includes the following steps: S11. Determine the positions of monitoring nodes in the heat pipeline network system and deploy monitoring devices. The device layout positions are based on the following principles: Representativeness principle: In order to reflect the flow and pressure conditions in different sections of the pipeline, the selection of installation points and monitoring points should give priority to representative points on the main line; Convenience principle: The workplace should be as convenient as possible for workers to enter and exit; the working space should be as open as possible to facilitate the installation, maintenance, and other operations of the equipment. Safety principle: The structure of the inspection chamber should be sound to prevent collapse during the installation and operation of the equipment; the cover of the inspection chamber should be intact to prevent falling and damage to the equipment below. S12. After installing the sensing devices, connect and network the sensing devices to ensure that the sensing devices can be connected to the data acquisition system or communication network of the pipeline network system; S13. The sensing devices start to monitor the pipeline status data.

[0007] Preferably, in step S2, the transmission of data to the cloud server includes the following steps: S21. Configure the communication parameters of the device, connect the monitoring device and the cloud server through the NB-IoT network, and establish a communication channel; S22. The monitoring device starts to collect data and transmits the data to the cloud server through the NB-IoT network. The NB-IoT communication technology can be used to achieve remote data collection and transmission of online monitoring devices and transmit the data to the cloud server for processing and storage, helping to improve the monitoring efficiency and operation safety of the pipeline network system; S23. Set up a data storage and management system on the cloud server to store and organize the received data; S24. Transmit the data to the required system or application program through the API interface for further call and processing.

[0008] Preferably, in step S3, the database uses a MySQL database, and also supports relational databases such as Oracle and SQLServer, which are used to analyze, filter, and classify and store each data source in real time, helping to achieve the storage, management, analysis, and report generation of monitoring data, and improving the efficiency and reliability of the monitoring system.

[0009] Preferably, in step S3, the use of big data technology to process and analyze data includes the following steps: S31. Use an ETL tool or a big data technology streaming processing engine to collect data; S32. Clean and preprocess the collected data, including removing duplicate data and handling missing values; S33. Store the cleaned and preprocessed data in a database; S34. Integrate and aggregate data from different data sources to establish a comprehensive data set; S35. Use a clustering algorithm to analyze the data to obtain information and trends of pipeline network nodes.

[0010] Preferably, in step S35, the use of the clustering algorithm to analyze the data includes the following steps: ① Initialize the clustering center points: ; In the formula: represents the center point of the k-th cluster, represents the number of data points in the k-th cluster, represents the n-th data point in the k-th cluster; ② Calculate the distance from the data point to the clustering center point: ; In the formula: represents the Euclidean distance; ③ Update the clustering center points: ; where t represents the number of iterations; ④ Repeat steps ② and ③ until the convergence condition is met.

[0011] Preferably, in step S4, the use of artificial intelligence algorithms to analyze the processed collected data includes the following steps: S41. Build a model for the processed data through the BP neural network algorithm; S42. Train the model using the training set data and verify it using the validation set data; S43. Analyze the processed collected data through the trained model to explore the correlation, trend, and anomalies between the data; S44. Output the analysis results.

[0012] Preferably, in step S5, formulating an intelligent decision-making strategy based on the data analysis results includes the following steps: S51. Formulate corresponding intelligent decision-making strategies according to the data analysis results and goals; S52. Use machine learning algorithms to establish a prediction model for predicting possible problems and risks in the pipeline network; S53. Based on the results of the prediction model, optimize the pipeline network maintenance strategy, including regular maintenance, emergency repair, and preventive maintenance; S54. According to the data analysis results and the prediction model, formulate an intelligent inspection plan, focusing on areas where problems may exist, and improve the inspection efficiency and accuracy; S55. According to the data analysis results and the optimized maintenance strategy, formulate pipeline network optimization measures to ensure the stable operation of the pipeline network; S56. Implement the formulated intelligent decision-making strategy, monitor the operation status and effects of the pipeline network, and adjust the strategy in a timely manner to cope with changing situations.

[0013] Preferably, in step S6, visually presenting the analysis results includes the following steps: S61. Organize the processed and analyzed pipeline network data into the format required for visualization, including geographical coordinates, attribute information, etc.; S62. Use data visualization tools such as PowerBI / matplotlib to create GIS map visualizations, project the pipeline network data on the map, and display the pipeline network structure, pipeline positions, and facility information; S63. According to the data analysis results, add different layers to display different attributes, trends, and abnormal data; S64. Provide necessary explanations and descriptions in the visual display to help users understand the meaning behind the data and decision-making suggestions; S65. According to the data analysis and user feedback, regularly update the map visualization to reflect the latest situation of the pipeline network data and trends, and help users understand the pipeline network status at any time.

[0014] Compared with the prior art, the beneficial effects of the present invention are: 1. In this method, by deploying sensing devices at each monitoring node in the heat pipeline network system to monitor the pipeline operation data in real time, comprehensive and automatic collection of pipeline network data is achieved, which helps to promptly discover problems and take corresponding measures, improve the operation efficiency and stability of the pipeline network system. Using NB-IoT communication to achieve remote data collection and transmission improves the efficiency and convenience of data collection, enhances the monitoring efficiency of the pipeline network system, and reduces the waste of human resources.

[0015] 2. In this method, analyzing data through a clustering algorithm can efficiently process and analyze massive data, extract hidden useful information, and further analyze the heat pipe network data by combining with the BP neural network algorithm to discover the correlation, trend, and anomalies among the data, providing support for intelligent decision-making.

[0016] 3. In this method, formulating an intelligent decision-making strategy helps optimize pipe network maintenance, inspection, and optimization measures, improving the overall operation level of the pipe network system. The combination of data visualization tools and GIS maps intuitively displays the analysis results, helping users better understand the pipe network data and trends, and promoting the accuracy and efficiency of decision-making and pipe network management. Brief Description of the Drawings

[0017] Figure 1 It is a flowchart of the intelligent data acquisition method for the pipe network of the present invention. Detailed Embodiments

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0019] Please refer to Figure 1 , the present invention provides a technical solution: an intelligent data acquisition method for pipe network data, including the following steps: Step 1: Deploy sensing devices at each monitoring node in the heat pipe network system, including flow monitors, pressure sensors, and temperature sensors to monitor the pipeline operation data in real time, which can realize the deployment of sensing devices in the heat pipe network system to monitor the pipeline operation data in real time, improve the operation efficiency and safety of the pipe network system, and reduce potential problems and risks; Among them, deploying sensing devices at each monitoring node in the heat pipe network system includes the following steps: 11) Determine the positions of monitoring nodes in the heat pipe network system and deploy monitoring devices. The equipment layout positions are based on the following principles: Representativeness principle: To reflect the flow and pressure conditions in different sections of the pipeline, the selection of installation points and monitoring points should give priority to representative points on the main line; Convenience principle: The workplace should be as convenient as possible for workers to enter and exit; the working space should be as open as possible to facilitate the installation, maintenance, and other operations of the equipment Safety principle: The structure of the inspection chamber should be sound to prevent collapse during equipment installation and operation; the cover of the inspection chamber should be intact to prevent falling and damage to the equipment below; 12) After installing the sensing device, connect and network the sensing device to ensure that the sensing device can be connected to the data acquisition system or communication network of the pipeline network system; 13) The sensing device starts to monitor the pipeline status data; Step 2: Use NB-IoT communication to achieve remote data acquisition and transmission of the online monitoring device, and transmit the data to the cloud server, waiting to be processed and called. Using NB-IoT communication technology can achieve remote data acquisition and transmission of the online monitoring device, and transmit the data to the cloud server for processing and storage, helping to improve the monitoring efficiency and operation safety of the pipeline network system; Among them, the process of transmitting the data to the cloud server is as follows: First, configure the communication parameters of the device, connect the monitoring device and the cloud server through the NB-IoT network, and establish a communication channel; then the monitoring device starts to collect data and transmit the data to the cloud server through the NB-IoT network; finally, set up a data storage and management system on the cloud server to store and sort the received data; and the data can be transmitted to the required system or application program through the API interface for further calling and processing; Step 3: Store the collected data in the cloud or local database, and use big data technology to process and analyze the data; Among them, the database uses the MySQL database, and at the same time supports relational databases such as Oracle and SQLServer, which are used for real-time analysis, filtering, and classified storage of each data source, helping to realize the storage, management, analysis, and report generation of monitoring data, and improving the efficiency and reliability of the monitoring system; Among them, using big data technology to process and analyze the data includes the following steps: 31) Use ETL tools or big data technology streaming processing engines for data acquisition; 32) Clean and preprocess the collected data, including removing duplicate data and handling missing values; 33) Store the cleaned and preprocessed data in the database; 34) Integrate and aggregate the data from different data sources to establish a comprehensive data set; 35) Use clustering algorithms to analyze the data to obtain information and trends of pipeline network nodes; Among them, the clustering algorithm for analyzing the data includes the following steps: ① Initialize the clustering center points: ; In the formula: represents the center point of the kth cluster, represents the number of data points in the kth cluster, Represents the nth data point in the kth cluster; ② Calculate the distance from the data point to the cluster center point: ; In the formula: Represents the Euclidean distance; ③ Update the cluster center point: ; where t represents the number of iterations; ④ Repeat steps ② and ③ until the convergence condition is met.

[0020] Step Four: Use artificial intelligence algorithms to analyze the processed collected data, discover the correlations, trends, and anomalies among the data, use artificial intelligence algorithms to comprehensively analyze the processed collected data, and mine valuable information in the data to help optimize the operation and management of the pipe network; Among them, the process of using artificial intelligence algorithms to analyze the processed collected data is as follows: Build a model for the processed data through the BP neural network algorithm; Train the model using the training set data and verify it through the validation set data; Through the trained model, analyze the processed collected data to explore the correlations, trends, and anomalies among the data; Output the analysis results; Step Five: Develop intelligent decision-making strategies based on the data analysis results, including pipe network maintenance, pipe network inspection, and optimization measures. Developing intelligent decision-making strategies based on data analysis can help improve the operation efficiency of the pipe network, reduce maintenance costs, and achieve more efficient, safe, and sustainable pipe network management; Among them, developing intelligent decision-making strategies based on the data analysis results includes the following steps: 51) Develop corresponding intelligent decision-making strategies based on the data analysis results and goals; 52) Use machine learning algorithms to build a prediction model for predicting possible problems and risks in the pipe network; Among them, the machine learning algorithm adopts the algorithm, and the specific steps are as follows: Use the cross-validation method to divide the data set into a training set and a test set, use the training set data to train the machine learning model, use the test set data to evaluate the performance of the model, adjust the model parameters to improve the performance, apply the trained model to the actual data for prediction, and monitor the operation status and possible problems and risks of the pipe network.

[0021] 53) Based on the results of the prediction model, optimize the pipe network maintenance strategy, including regular maintenance, emergency repair, and preventive maintenance; 54) Develop an intelligent inspection plan based on the data analysis results and the prediction model, focusing on areas where problems may exist to improve the inspection efficiency and accuracy; 55) Develop pipeline network optimization measures based on data analysis results and optimized maintenance strategies to ensure the stable operation of the pipeline network; 56) Implement the formulated intelligent decision-making strategy, monitor the operation status and effects of the pipeline network, and adjust the strategy in a timely manner to cope with changing situations; Step 6: Use data visualization tools and combine with GIS maps to visually display the analysis results, help users understand the data and trends, regularly generate reports, and provide data analysis results and suggestions to relevant personnel. By combining data visualization tools with GIS maps, the data analysis results can be visually displayed, helping users better understand the pipeline network data and trends, and promoting the accuracy and efficiency of decision-making and pipeline network management; Among them, visually displaying the analysis results includes the following steps: 61) Organize the processed and analyzed pipeline network data into the format required for visualization, including geographical coordinates, attribute information, etc.; 62) Use PowerBI / matplotlib data visualization tools to create GIS map visualizations, project the pipeline network data onto the map, and display the pipeline network structure, pipeline locations, and facility information; 63) Add different layers according to the data analysis results to display different attributes, trends, and abnormal data; 64) Provide necessary explanations and instructions in the visual display to help users understand the meaning behind the data and decision-making suggestions; 65) Regularly update the map visualization according to data analysis and user feedback to reflect the latest situation of the pipeline network data and trends, and help users understand the pipeline network status at any time.

[0022] In this method, by deploying sensing devices at each monitoring node in the heat pipe network system to monitor the pipeline operation data in real time, comprehensive and automatic collection of pipe network data is achieved, which helps to timely detect problems and take corresponding measures, improve the operation efficiency and stability of the pipe network system, reduce potential problems and risks. Using NB-IoT communication to achieve remote data collection and transmission improves the efficiency and convenience of data collection and reduces the waste of human resources. Using NB-IoT communication technology can achieve remote data collection and transmission of online monitoring devices and transmit the data to the cloud server for processing and storage, helping to improve the monitoring efficiency and operation safety of the pipe network system. By using the clustering algorithm to analyze the data, efficient processing and analysis of massive data can be carried out to dig out the useful information hidden therein. The BP neural network algorithm can model the processed data to more deeply analyze the heat pipe network data, discover the correlation, trend and anomalies between the data, and provide support for intelligent decision-making. By formulating intelligent decision-making strategies, it helps to optimize pipe network maintenance, pipe network inspection and optimization measures. Based on data analysis, formulating intelligent decision-making strategies can help improve the operation efficiency of the pipe network, reduce maintenance costs, and achieve more efficient, safe and sustainable pipe network management. By combining data visualization tools with GIS maps, the analysis results of data can be intuitively displayed, helping users better understand the pipe network data and trends, and promoting the accuracy and efficiency of decision-making and pipe network management.

[0023] Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent acquisition method for pipeline network data, characterized in that, It includes the following steps: S1. Deploy sensing devices at each monitoring node in the thermal pipeline network system, including flow monitors, pressure sensors, and temperature sensors to monitor the pipeline operation data in real time; S2. Use NB-IoT communication to realize remote data collection and transmission of the online monitoring devices, and transmit the data to the cloud server, waiting to be processed and called; S3. Store the collected data in the cloud or local database, and use big data technology to process and analyze the data; S4. Use artificial intelligence algorithms to analyze the processed collected data to discover the correlation, trend, and anomalies between the data; S5. Develop intelligent decision-making strategies based on the data analysis results, including pipeline maintenance, pipeline inspection, and optimization measures; S6. Use data visualization tools and combine with GIS maps to visually display the analysis results, help users understand the data and trends, generate reports regularly, and provide the data analysis results and suggestions to relevant personnel.

2. The intelligent acquisition method of pipe network data according to claim 1, characterized in that, In step S1, the deployment of sensing devices at each monitoring node in the thermal pipeline network system includes the following steps: S11. Determine the positions of the monitoring nodes in the thermal pipeline network system, deploy the monitoring devices, and the device layout positions are based on the principles: representativeness principle, convenience principle, and safety principle; S12. After installing the sensing devices, connect and network the sensing devices to ensure that the sensing devices can be connected to the data acquisition system or communication network of the pipeline network system; S13. The sensing devices start to monitor the pipeline status data.

3. The intelligent acquisition method of pipe network data according to claim 1, characterized in that, In step S2, the transmission of the data to the cloud server includes the following steps: S21. Configure the communication parameters of the device, connect the monitoring device and the cloud server through the NB-IoT network, and establish a communication channel; S22. The monitoring device starts to collect data and transmits the data to the cloud server through the NB-IoT network; S23. Set up a data storage and management system on the cloud server to store and organize the received data; S24. Transmit the data to the required system or application program through the API interface for further calling and processing.

4. The intelligent acquisition method of pipeline network data according to claim 1, wherein In step S3, the database uses the MySQL database, and at the same time, it also supports relational databases such as Oracle and SQLServer for real-time analysis, filtering, and classified storage of each data source.

5. The intelligent acquisition method of pipeline network data according to claim 1, wherein In step S3, the use of big data technology to process and analyze the data includes the following steps: S31. Use ETL tools or big data technology streaming processing engines for data collection; S32. Clean and preprocess the collected data, including removing duplicate data and processing missing values; S33. Store the cleaned and preprocessed data in the database; S34. Integrate and aggregate the data from different data sources to establish a comprehensive data set; S35. Use clustering algorithms to analyze the data to obtain information and trends of the pipeline network nodes.

6. The intelligent acquisition method of pipe network data according to claim 5, wherein In step S35, the analysis of the data by the clustering algorithm includes the following steps: ① Initialize the clustering center points: ; Wherein: represents the center point of the k-th cluster, represents the number of data points in the k-th cluster, represents the n-th data point in the k-th cluster; ② Calculate the distance from the data point to the cluster center point: ; In the formula: represents the Euclidean distance; ③ Update the cluster center points: ; where t represents the number of iterations; ④ Repeat steps ② and ③ until the convergence condition is met.

7. The intelligent acquisition method of pipe network data according to claim 1, characterized in that In step S4, the analysis of the processed collected data using artificial intelligence algorithms includes the following steps: S41. Model the processed data through the BP neural network algorithm; S42. Train the model using the training set data and verify it using the validation set data; S43. Analyze the processed collected data through the trained model to explore the correlations, trends, and anomalies among the data; S44. Output the analysis results.

8. The intelligent acquisition method of pipe network data according to claim 1, wherein, In step S5, formulating an intelligent decision-making strategy based on the data analysis results includes the following steps: S51. Formulate corresponding intelligent decision-making strategies according to the data analysis results and objectives; S52. Use machine learning algorithms to establish a prediction model for predicting possible problems and risks in the pipe network; S53. Optimize the pipe network maintenance strategy based on the results of the prediction model, including regular maintenance, emergency repair, and preventive maintenance; S54. Formulate an intelligent inspection plan according to the data analysis results and the prediction model, focusing on areas where problems may exist; S55. Formulate pipe network optimization measures according to the data analysis results and the optimized maintenance strategy; S56. Implement the formulated intelligent decision-making strategy, monitor the operation status and effects of the pipe network, and adjust the strategy in a timely manner to cope with changing situations.

9. The intelligent acquisition method of pipeline network data according to claim 1, characterized in that In step S6, the intuitive display of the analysis results includes the following steps: S61. Organize the processed and analyzed pipe network data into the format required for visualization; S62. Use data visualization tools such as PowerBI / matplotlib to create GIS map visualizations, project the pipe network data onto the map, and display the pipe network structure, pipeline locations, and facility information; S63. Add different layers according to the data analysis results to display different attributes, trends, and anomaly data; S64. Provide necessary explanations and descriptions in the visual display to help users understand the meaning behind the data and decision-making suggestions; S65. Regularly update the map visualization according to the data analysis and user feedback to reflect the latest situation of the pipe network data and trends.

Images