AI-based integrated water purification plant operation system

Abstract

The present invention relates to an artificial intelligence-based integrated water purification plant operation system, comprising an integrated water purification plant operation unit comprising an autonomous operation unit that manages the operation of a plurality of regionally dispersed water purification plants and an artificial intelligence analysis unit equipped with an artificial intelligence model for autonomously operating a water purification process, and a regional water purification plant operation unit equipped with means for real-time data collection and control for a water purification process.

Description

Technology Field

[0001] The present invention relates to an artificial intelligence-based integrated operation system for water purification plants, and more specifically, to an artificial intelligence-based integrated operation system capable of providing a platform for autonomously controlling the water purification process of a regional water purification plant by comprising an integrated operation server that integrates and manages water supply operation data and a self-operating AI operation server that autonomously operates an artificial intelligence-based water purification process. Background Technology

[0002] Water supply facilities are a series of facilities that purify raw water supplied from water sources at geographically separated unit sites through a water purification process and then distribute it to the general public via water pipelines.

[0003] Until recently, water supply operating systems have relied on real-time remote monitoring and control of water facilities and equipment by operation managers in a central control room. However, due to the limited monitoring and control of equipment, there is a problem in that it is very difficult to apply new technologies such as artificial intelligence or big data.

[0004] Figure 1 is a diagram showing the structure of a conventional water supply operation system, which is configured as a system in which a manager in a central control room remotely controls the system through field monitoring control equipment and central monitoring control equipment, and collects real-time data from control equipment installed in dams, rivers, or regional water purification facilities and controls it while monitoring it.

[0005] In addition, with the recent rise of deep learning technology and the expansion of optimal state control technology by artificial intelligence, big data management, and the Internet of Things, efforts are also underway to rebuild water treatment plants into customized artificial intelligence platforms.

[0006] Patent Document 1 relates to a system for predicting the production and supply volumes of water supply using artificial intelligence. To this end, the system for predicting the production and supply volumes of water supply required for a water supply system is characterized by inferring daily production volumes and daily supply volumes using a neural network model based on date information, weather information, past performance information, and various measurement data information of a business unit. However, it does not disclose autonomous control means for detailed processes for water treatment.

[0007] Patent Document 2 relates to an IoT-based autonomous inspection and operation management system for water supply management facilities using an intelligent remote terminal device. It involves installing an intelligent remote terminal device at each water supply management facility to autonomously inspect the operating status of inspection targets, generating fault information for each inspection target based on the inspection results, and providing it to an intelligent central platform server via an IoT communication network. It is characterized by IoT-based remote monitoring but does not present an artificial intelligence-based platform for autonomous operation. Prior art literature

[0008] Korean Registered Patent Publication No. 10-2290980 Korean Registered Patent Publication No. 10-2346377 The problem to be solved

[0009] To solve the above-mentioned problems, the present invention aims to provide a machine learning-based artificial intelligence module for autonomously controlling the water treatment process of a water purification plant and to provide an artificial intelligence-based integrated water purification plant operation system having a structure of an integrated operation platform capable of visualizing the overall operation of the water treatment process. means of solving the problem

[0010] An artificial intelligence-based water purification plant integrated operation system according to the present invention for achieving the above-mentioned purpose is characterized by comprising: an autonomous operation unit (100) for managing the operation of a plurality of regionally dispersed water purification plants; an artificial intelligence analysis unit (200) equipped with an artificial intelligence model for autonomously operating a water purification process; a regional water purification plant operation unit (30) equipped with means for collecting and controlling real-time data for the water purification process; and a wired / wireless communication network (20) that interconnects the water purification plant integrated operation unit (10) and the regional water purification plant operation unit (30) via the Internet.

[0011] In addition, in the artificial intelligence-based water purification plant integrated operation system according to the present invention, the autonomous operation unit (100) is characterized by being linked with a visualization service unit (110) that displays the water purification process as an HMI-based graphic and a standard API interface (120) based on HTTP communication.

[0012] In addition, in the artificial intelligence-based water purification plant integrated operation system according to the present invention, the standard API interface (120) is characterized by being composed of a Spring framework, which is a Java platform, a REST API for reliably exchanging information over the internet, and a JNA and JWT authentication server to provide services through the visualization service unit (110).

[0013] In addition, in the artificial intelligence-based water purification plant integrated operation system according to the present invention, the artificial intelligence analysis unit (200) is characterized by including a data collection unit (210) that collects data for a water purification process from a regional water purification plant operation unit (30), a data management unit (220) that stores and manages data collected from the data collection unit (210), a configuration management unit (230) that manages the version and source code of software for integrated management of the water purification plant, and an artificial intelligence module unit (150) based on a deep learning neural network that autonomously operates the water purification process.

[0014] In addition, in the artificial intelligence-based water purification plant integrated operation system according to the present invention, the data management unit (220) is characterized by structuring the data collected from the data collection unit (210) into a Hive-based meta-information-based data storage, storing it in an Apache Hadoop File System (HDFS), and managing it as a database according to the analysis results.

[0015] In addition, in the artificial intelligence-based water purification plant integrated operation system according to the present invention, machine learning and testing for the water purification process in the artificial intelligence module (150) are performed in the integrated operation server (11), and real-time water purification is performed in the AI ​​operation server (12) using the learned artificial intelligence model.

[0016] In addition, in the artificial intelligence-based water purification plant integrated operation system according to the present invention, the data collection unit (210) is characterized by receiving data from the real-time data transmission unit (320) through the KAFKA module.

[0017] In addition, in the artificial intelligence-based water purification plant integrated operation system according to the present invention, the regional water purification plant operation unit (30) is characterized by including a real-time storage unit (310) that periodically collects data generated in the water purification process, preprocesses it into a form required by the visualization service unit (110), and stores it in the form of a CSV file, a real-time data transmission unit (320) that transmits the data stored in the real-time storage unit (310) to the water purification plant integrated operation unit (10), and an autonomous control unit (330) that autonomously controls the water purification process through control data received from the artificial intelligence module unit (240) that autonomously operates the water purification process.

[0018] In addition, in the artificial intelligence-based water purification plant integrated operation system according to the present invention, the regional water purification operation unit (30) is characterized by being operated by a SCADA server (31).

[0019] In addition, the water treatment process, which is autonomously operated in the artificial intelligence-based water purification plant integrated operation system according to the present invention, is characterized by being composed of seven stages: an initiation process, a chemical injection process, a mixing and coagulation process, a sedimentation process, a disinfection process, a filtration process, and an ozone process. Effects of the invention

[0020] As explained above, the artificial intelligence-based autonomous operation method for a water purification process according to the present invention has the advantage of being able to provide an artificial intelligence-based integrated platform capable of comprehensive management of a water purification plant, namely autonomous operation of the water purification process, energy management, facility management, and SW configuration management.

[0021] In addition, the artificial intelligence-based autonomous operation method for a water purification process according to the present invention has the advantage of enabling a stable water purification process, such as reducing human error, as well as reducing water supply operating costs and producing high-quality tap water by incorporating artificial intelligence technologies such as an artificial intelligence platform and autonomous operation of a water purification plant. Brief explanation of the drawing

[0022] Figure 1 is a diagram showing the structure of a water supply operating system according to the prior art. FIG. 2 is a diagram showing the configuration of an artificial intelligence-based water purification plant integrated operation system according to a preferred embodiment of the present invention. FIG. 3 is a functional block diagram showing the functions of the water purification plant integrated operation unit according to a preferred embodiment of the present invention. FIG. 4 is a diagram showing an example of a visualization screen for autonomous operation of a local water purification plant according to a preferred embodiment of the present invention. FIG. 5 is a drawing showing a screen that visualizes the overall status of a filtration process according to a preferred embodiment of the present invention. FIG. 6 is a functional block diagram showing the configuration of a regional water purification plant operation unit according to a preferred embodiment of the present invention. FIG. 7 is a diagram illustrating data linkage, collection, and flow between a regional water purification plant operation unit and a water purification plant integrated operation unit according to a preferred embodiment of the present invention. Specific details for implementing the invention

[0023] Embodiments that enable a person skilled in the art to easily implement the present invention are described in detail below with reference to the attached drawings. However, in describing the operating principles of preferred embodiments of the present invention in detail, if it is determined that a detailed description of related known functions or configurations may unnecessarily obscure the essence of the present invention, such detailed description is omitted.

[0024] In addition, the same reference numerals are used for parts having similar functions and operations throughout the drawings. Throughout the specification, when a part is described as being connected to another part, this includes not only cases where they are directly connected, but also cases where they are indirectly connected with other elements in between. Furthermore, unless specifically stated otherwise, the inclusion of a certain component does not exclude other components but implies that additional components may be included.

[0025] Hereinafter, an artificial intelligence-based water purification plant integrated operation system according to the present invention will be described in detail with reference to the attached drawings.

[0026] FIG. 2 is a diagram showing the configuration of an artificial intelligence-based water purification plant integrated operation system according to a preferred embodiment of the present invention.

[0027] As shown in FIG. 2, the artificial intelligence-based water purification plant integrated operation system according to the present invention is divided into a water purification plant integrated operation unit (10) and a regional water purification plant operation unit (30).

[0028] First, the water purification plant integrated operation unit (10) includes an integrated operation server (11), an AI operation server (12), and a big data storage server (13), and the regional water purification plant operation unit (30) includes a SCADA server (31) provided at the regional water purification plant and water purification equipment (32) for water purification treatment, and the water purification plant integrated operation unit (10) and a plurality of regional water purification plant operation units (30) are connected by a wired / wireless communication network (20) capable of transmitting and receiving data.

[0029] The integrated operation server (11) is a server that operates the water purification plant integrated operation unit (10), collects and stores various water purification status information data from the SCADA server (31) equipped in the local water purification plant operation unit (30), and performs functions for an administrator interface, visualization for integrated control, and artificial intelligence-based autonomous operation.

[0030] The AI ​​operating server (12) is equipped with an artificial intelligence model that autonomously operates the water purification process of a local water purification plant and performs the function of controlling the water purification equipment (32), such as valves and pumps, in real time.

[0031] The big data storage server (13) performs the function of collecting and storing real-time data related to water purification and big data for machine learning through artificial intelligence.

[0032] In addition, the regional water purification plant operation unit (30) operates multiple regional water purification plants with different water sources and is interconnected with the water purification plant integrated operation unit (10), and is equipped with a SCADA server (31) that collects and transmits status and control data of various water purification facilities (32) or receives data necessary for operation management and transmits it to various water purification facilities (32).

[0033] Although not clearly illustrated in FIG. 2, the AI ​​operation server (12) may be mapped to be directly linked to each regional water purification plant operation unit (30), but the AI ​​operation server (12) may operate multiple regional water purification plant operation units (30), so there is no limitation thereon. In addition, the AI ​​operation server (12) may be managed via cloud computing from an integrated operation server without physically separating it, so various changes can be made at the level of a typical technician.

[0034] FIG. 3 is a functional block diagram showing the functions of a water purification plant integrated operation system according to a preferred embodiment of the present invention, wherein the water purification plant integrated operation unit (10) consists of an autonomous operation unit (100) and an artificial intelligence analysis unit (200).

[0035] Referring to FIG. 3, the autonomous operation unit (100) includes a visualization service unit (110) that displays graphics based on HMI (Human-Machine Interface) and a standard API interface (120) based on HTTP communication. The visualization service unit (110) creates and provides a visualization service screen including an operation management menu so that the autonomous operation status of the local water purification plant, the Energy Management System (EMS), and the Power Management System (PMS) can be selectively monitored using commercially available visualization tools, such as Vuetify, Highcharts, FineReport, etc.

[0036] And, the visualization service department (110) provides a visualization service screen to the administrator, and the main menu of the service screen consists of a main dashboard, autonomous operation, smart EMS, smart PMS, and operation management menu, and detailed functions of autonomous operation and operation management can be provided by organizing sub-menus.

[0037] In addition, the standard API interface (120) aims to provide a standard interface to link state information data from the artificial intelligence analysis unit (200) with the visualization service unit (110) via API, and to provide a platform that facilitates the addition or deletion of new services.

[0038] Again in FIG. 3, the artificial intelligence analysis unit (200) is composed of a data collection unit (210) that collects data from a local water purification plant from a SCADA server (31), a data management unit (220) that stores the collected data, a configuration management unit (230) for managing various software source codes and versions, and an artificial intelligence module unit (240).

[0039] The data collection unit (210) includes an interface (Fleuntd -KAFKA) for collecting and loading original data in JSON or CSV file format from a SCADA server (31) and a Spark streaming interface for real-time streaming and data analysis.

[0040] The data management unit (220) structures the data collected from the data collection unit (210) based on Hive-based meta-information and stores it in the Apache Hadoop File System (HDFS), and manages it by building a separate database for each analysis result.

[0041] The configuration management department (230) manages the distribution of software and systematically updates the source code and versions of major software constituting the water purification plant platform. In particular, since control programs that operate based on artificial intelligence must be retrained and tested repeatedly due to surrounding environmental variables or replacement of equipment, their version management can be considered a very important configuration management.

[0042] The artificial intelligence module (240) performs learning for automatic control of various equipment for the water purification process of a water purification plant through a deep learning-based neural network. Since the input parameters related to the water purification process have a wide range of values, a preprocessing process is absolutely necessary, and it is necessary to build training data using big data stored in the data management unit (220) for supervised learning of expected control results according to the conditions of the input parameters.

[0043] In addition, the AI ​​model for each water purification process, generated through self-verification and retraining using training data, is transmitted to the AI ​​operating server (12) to calculate control values ​​for the autonomous water purification process in real time.

[0044] FIG. 4 is a diagram showing an example of a visualization screen for autonomous operation of a regional water purification plant according to a preferred embodiment of the present invention, graphically displaying the autonomous operation status of the water purification process of a water purification plant located in the Pyeongtaek and Songsan regions.

[0045] As shown in Fig. 4, when a starting process is selected during the water purification process, the turbidity of the raw water, the turbidity of the purified water, the inflow rate of the raw water, and the outflow rate of the purified water are displayed in real time, and the opening status of the inflow valves of the first series and the second series, which are controlled by an AI model, is displayed.

[0046] In addition, in addition to the initiation process, chemical, mixing coagulation, sedimentation, filtration, ozone, GAC filtration, disinfection, water transfer, and dehydration start processes can be selected, and the status of EMS and PMS can also be visualized and provided.

[0047] FIG. 5 is a graphic screen showing the overall status of a filtration process according to a preferred embodiment of the present invention.

[0048] As shown in Fig. 5, the inflow / outflow rate of the mixing tank, water level by filtration type, turbidity, current / predicted filtration duration, and backwash start time can be clearly and visually displayed. In addition, the operation schedule based on the prediction results from AI can be visually displayed hourly on a single screen.

[0049] FIG. 6 is a functional block diagram showing the configuration of a regional water purification plant operation unit (30) according to a preferred embodiment of the present invention, and FIG. 7 is a diagram illustrating data linkage, collection, and flow between the regional water purification plant operation unit (30) and the water purification plant integrated operation unit (10) according to a preferred embodiment of the present invention.

[0050] First, referring to FIG. 6, the local water purification plant operation unit (30) is composed of a real-time storage unit (310), a real-time data transmission unit (320), and an autonomous control unit (330).

[0051] The real-time storage unit (310) is a type of historian that stores operational data of integer processing collected in real-time from the SCADA server. This historian stores a large amount of data at a rapid rate (capable of processing tens of thousands of tags or more per second) and can read data quickly without complex queries using less space than a relational DB (RDB).

[0052] The real-time data transmission unit (320) performs the function of transmitting stored data to the data collection unit (210) of the water purification plant integrated operation unit (10) through the KAFKA module, and the KAFKA module is equipped with a data-specific queue management means and separates and stores the data by content in the data management unit (220) through the real-time analysis module. Preferably, it stores at 1-minute intervals, but there is no limitation thereon.

[0053] In particular, the real-time storage unit (310) periodically collects recent data to minimize the load on the SCADA server, preprocesses it into the format required by the visualization unit (110), and saves it to a CSV file.

[0054] The real-time data transmission unit (320) performs the function of collecting real-time data, converting the data into data for analysis in advance, and transmitting it to the water purification plant integrated operation unit (10).

[0055] Additionally, the autonomous control unit (330) stores input parameters and control values ​​of the water purification facility in real time in the real-time storage unit (310) to control each autonomous process within the water purification treatment, and performs the function of applying control values ​​from the artificial intelligence module unit (240) to the actual water purification facility.

[0056] Referring to FIG. 7, the real-time data transmission unit (320) represents data as a time stamp (time record) corresponding to the occurrence of an event and a fluent bit that constitutes a message, and a tag is assigned to every event that enters the fluent bit.

[0057] In particular, the data storage in the data management unit (220) can be divided into TAG data, external data, analysis data, distributed file system, metadata management, and parquet files stored in a columnar manner in Hadoop.

[0058] Additionally, the data collection unit (210) can transmit real-time TAG data and control data via HTTP communication through the standard API interface (120) of the autonomous operation unit (100).

[0059] Here, the standard API interface (120) is divided into three layers to provide services through the visualization unit (110): the Spring framework, which is a Java platform, the REST (Representation State Transfer) API for securely exchanging information over the internet, the JNA (Java Native Access), and the JWT (Json Web Token) authentication server.

[0060] The present invention has been described above with reference to specific embodiments. However, those skilled in the art will be able to make various applications and modifications within the scope of the present invention based on the above description. Explanation of the symbols

[0061] 10: Water Treatment Plant Integrated Operations Department 11: Integrated Operations Server 12: AI Operation Server 13: Big Data Storage Server 20: Wired and wireless communication networks 30: Regional Water Purification Plant Operations Department 31: SCADA Server 32: Local Water Purification Facilities 30: Regional Water Purification Plant Operations Department 100: Autonomous Operations Department 110: Visualization Service Department 120: Standard API Interface 200: Artificial Intelligence Analysis Department 210: Data Collection Unit 220: Data Management Department 230: Configuration Management Department 240: Artificial Intelligence Module 310: Real-time storage unit 320: Real-time data transmission unit 330: Autonomous Control Unit

Claims

Claim 1 An integrated operation server including an autonomous operation unit that manages the operation of multiple regionally dispersed water purification plants; An AI-based integrated water purification plant operation system comprising: an AI operation server including an AI analysis unit equipped with an AI model for autonomously operating a water purification process; a water purification plant integrated operation unit including a big data storage server that collects and stores real-time data related to the process and big data for machine learning from a plurality of regional water purification plants; and a regional water purification plant operation unit including a SCADA server equipped with means for collecting real-time data from the regional water purification plants and controlling water purification facilities, wherein the autonomous operation unit includes a visualization service unit that provides a control function by generating a graphically displayed HMI-based visualization screen including an operation management menu to selectively monitor the autonomous operation status of the regional water purification plant, an Energy Management System (EMS), and a Power Management System (PMS); and a standard API interface that collects and manages status information data through an HTTP communication-based API from the AI ​​analysis unit, wherein the AI ​​analysis unit includes: a data collection unit that collects data for the water purification process from the regional water purification plant operation unit through KAFKA and Spark streaming interfaces; a data management unit that stores and manages the data collected by the data collection unit in a Hadoop file system; and for integrated management of water purification plants It includes a configuration management unit that manages software versions and source code; and an artificial intelligence module unit based on a deep learning neural network that autonomously operates the water purification process, and the regional water purification plant operation unit comprises: a real-time storage unit that periodically collects data generated in the water purification process, preprocesses it into a format required by the visualization service unit, and saves it in the form of a CSV file; and a real-time data transmission unit that transmits data stored in the real-time storage unit at one-minute intervals to the water purification plant integrated operation unit.An artificial intelligence-based water purification plant integrated operation system characterized by including an autonomous control unit that autonomously controls a water purification process through control data received from an artificial intelligence module that autonomously operates the water purification process. Claim 2 delete Claim 3 An artificial intelligence-based water purification plant integrated operation system, wherein, in claim 1, the standard API interface comprises a Spring Framework, a Java platform, for providing services through a visualization service unit, a REST API for securely exchanging information over the Internet, and JNA and JWT authentication servers. Claim 4 delete Claim 5 delete Claim 6 An AI-based integrated water purification plant operation system according to claim 1, characterized in that machine learning and testing for the water purification process in the AI ​​module are performed on an integrated operation server, and real-time water purification is performed on an AI operation server using the learned AI model. Claim 7 delete Claim 8 delete Claim 9 delete Claim 10 An artificial intelligence-based water purification plant integrated operation system according to claim 1, characterized in that the autonomously operated water purification process consists of seven stages: an initiation process, a chemical injection process, a mixing and coagulation process, a sedimentation process, a disinfection process, a filtration process, and an ozone process.

Images