Process production alarm optimization system and method based on artificial intelligence

Abstract

The invention discloses a method for a process production alarm optimization system based on artificial intelligence, and the method comprises the following steps: A, a data collection module which collects key parameter data in the production process of various types of equipment, B, a preprocessing module which carries out the cleaning, denoising, normalization and other processing of the collected data, and C, an artificial intelligence analysis module which carries out the analysis of the collected data. And identifying and analyzing the preprocessed data. Through cooperative use of the above steps, deep analysis is performed on production data through an intelligent algorithm, an alarm threshold value is dynamically adjusted, false alarm and missing alarm are reduced, alarm accuracy is improved, a production state is monitored in real time, an alarm is immediately given once an abnormity is found, response time is shortened, response speed is improved, and causal analysis is performed on alarm data. The method has the advantages that bottleneck and problems in the production process are identified, optimization suggestions are provided, the production process is optimized, the burden of manually processing alarm information is reduced, and the working efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of process production, and in particular to an artificial intelligence-based process production alarm optimization system and method thereof. Background Art

[0002] Process production refers to the process of processing raw materials or semi-finished products into marketable finished products that meet market demand through certain technologies and processing techniques. The purpose of production is to meet human production and life needs, transform raw materials into useful products, and increase the added value of raw materials.

[0003] Most of the existing process production alarm systems rely on fixed threshold settings and simple logical judgments. When the parameters in the production process exceed the preset threshold, the system will trigger an alarm. However, the disadvantage of this method is that it cannot adapt to the dynamic changes and complex environment in the production process, and it is easy to cause false alarms and missed alarms. At the same time, in an emergency, the existing system may take a long time to respond and process the alarm, affecting production safety, and it is impossible to conduct in-depth analysis of production data, unable to warn of potential risks in advance, and unable to provide data support for production optimization. Therefore, it is necessary to invent an artificial intelligence-based process production alarm optimization system and method to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide a process production alarm optimization system and method based on artificial intelligence, which has the advantages of improving alarm accuracy, reducing false alarms and missed alarms, improving response speed, shortening response time, optimizing production processes, reducing the burden of manual processing of alarm information, and improving work efficiency, and solves the problems of false alarms and missed alarms that are prone to occur, interfering with normal production operations, slow response speed that affects production safety, and lack of intelligent analysis capabilities.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for a process production alarm optimization system based on artificial intelligence, comprising the following steps: A: Data acquisition module, which collects key parameter data of various equipment during production; B: Preprocessing module, which performs cleaning, denoising, and normalization on the collected data; C: Artificial intelligence analysis module, which identifies and analyzes the pre-processed data; D: Alarm optimization module, based on the results of data analysis, optimizes the alarm information; E: User interface module, providing a friendly interactive interface to display optimized alarm information.

[0006] Preferably, in step A, the data acquisition module collects key parameter data in the process of process production in real time through the data acquisition gateway, DCS system, sensor, mobile terminal and MES system; the data acquisition gateway collects key data in the production process in real time by connecting to various sensors and actuators, including temperature, pressure, flow, liquid level, voltage, etc. The DCS system monitors and controls the real-time collection of various data of the production site, such as temperature, pressure, flow, liquid level and other physical quantities, as well as the operating status and fault information of the equipment, and generates reports, trend charts, etc. to help operators understand the status and change trend of the process. The sensor can detect various information produced by the equipment and convert it into electrical signals or other forms of information according to certain rules and output it to the data acquisition gateway. By collecting data in the production process in real time, the MES system can promptly respond to the production situation and reduce production waste and delays.

[0007] Preferably, in step B, the preprocessing module includes data aggregation, data cleaning, data governance, data standards and data storage to process various types of collected data, delete duplicate information, correct errors, solve missing values, delete outliers and other operations from the collected original data and store the data, so as to make subsequent data analysis and data mining more accurate and effective, ensure data quality, and avoid misleading conclusions caused by data quality problems.

[0008] Preferably, in step C, the artificial intelligence analysis module processes and analyzes a large amount of collected data through an algorithm engine. The algorithm engine is a specially designed software system for processing and analyzing a large amount of data. It mines, organizes and interprets data through complex algorithms to provide users with valuable information. The pre-processed data is then analyzed through a deep learning framework and a machine learning framework to identify normal and abnormal modes in the production process and dynamically adjust alarm thresholds. Finally, the algorithm warehouse stores and manages large-scale data sets, and applies machine learning algorithms for data analysis and mining.

[0009] Preferably, in step D, the alarm optimization module optimizes the alarm information according to the results of the artificial intelligence analysis module through jitter analysis, causal analysis, flooding analysis and timing analysis, so as to reduce false alarms and missed alarms and improve the accuracy and response speed of the alarm; jitter analysis refers to the process of analyzing and evaluating various jitter phenomena generated by data signals during transmission, causal analysis is to analyze whether a certain factor is the "cause" of other variables by observing the changes in it, so as to find the key factors that really affect the business and formulate corresponding response strategies, and timing analysis refers to a method of analyzing data arranged in chronological order.

[0010] Preferably, in step E, the user interface module includes alarm push, alarm history, alarm processing, alarm analysis and alarm KPI, which can display optimized alarm information, alarm history, production status monitoring, etc. and interact with personnel, wherein the alarm KPI refers to the data alarm KPI, which is a series of quantitative indicators used to measure and evaluate system performance and problem handling efficiency in the data management and monitoring system. These indicators generally include the average number of alarms per hour, timely confirmation rate, timely handling rate, 24-hour continuous alarm number and 10-minute peak alarm number, etc. Through these indicators, the alarm management function of the system can be optimized and the risk perception and emergency response capabilities of on-site personnel can be improved.

[0011] Compared with the prior art, the present invention has the following beneficial effects: The present invention, through the coordinated use of the above steps, conducts in-depth analysis of production data through intelligent algorithms, dynamically adjusts alarm thresholds, reduces false alarms and missed alarms, improves alarm accuracy, monitors production status in real time, and immediately issues an alarm once an abnormality is found, thereby shortening response time, improving response speed, conducting causal analysis on alarm data, identifying bottlenecks and problems in the production process, making optimization suggestions, optimizing the production process, reducing the burden of manual processing of alarm information, and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 This is a diagram of the process production alarm optimization system of the present invention. DETAILED DESCRIPTION

[0013] A method for a process production alarm optimization system based on artificial intelligence comprises the following steps: A: Data acquisition module, which collects key parameter data of various equipment during production; B: Preprocessing module, which performs cleaning, denoising, and normalization on the collected data; C: Artificial intelligence analysis module, which identifies and analyzes the pre-processed data; D: Alarm optimization module, based on the results of data analysis, optimizes the alarm information; E: User interface module, providing a friendly interactive interface to display optimized alarm information.

[0014] In step A, the data acquisition module collects key parameter data in the process of process production in real time through the data acquisition gateway, DCS system, sensor, mobile terminal and MES system; the data acquisition gateway collects key data in the production process in real time by connecting to various sensors and actuators, including temperature, pressure, flow, liquid level, voltage, etc. The DCS system monitors and controls various data collected in real time at the production site, such as temperature, pressure, flow, liquid level and other physical quantities, as well as the operating status and fault information of the equipment, and generates reports, trend charts, etc. to help operators understand the status and change trend of the process. The sensor can detect various information produced by the equipment and convert it into electrical signals or other forms of information according to certain rules and output it to the data acquisition gateway. By collecting data in the production process in real time, the MES system can respond to the production situation in a timely manner and reduce production waste and delays; In step B, the preprocessing module includes data aggregation, data cleaning, data governance, data standards and data storage to process various types of collected data, delete duplicate information, correct errors, solve missing values, delete outliers and other operations from the collected original data, and store the data to make subsequent data analysis and data mining more accurate and effective, ensure data quality, and avoid misleading conclusions caused by data quality problems; In step C, the artificial intelligence analysis module processes and analyzes a large amount of collected data through an algorithm engine. The algorithm engine is a specially designed software system for processing and analyzing large amounts of data. It mines, organizes and interprets data through complex algorithms to provide valuable information to users. Then, the pre-processed data is analyzed through a deep learning framework and a machine learning framework to identify normal and abnormal patterns in the production process and dynamically adjust alarm thresholds. Finally, the algorithm warehouse stores and manages large-scale data sets, and applies machine learning algorithms for data analysis and mining. In step D, the alarm optimization module optimizes the alarm information based on the results of the artificial intelligence analysis module through jitter analysis, causal analysis, flooding analysis, and timing analysis, so as to reduce false alarms and missed alarms and improve the accuracy and response speed of alarms. Jitter analysis is the process of analyzing and evaluating various jitter phenomena generated during the transmission of data signals. Causal analysis is to analyze whether a certain factor is the "cause" of other variables by observing the changes in it, so as to find the key factors that really affect the business and formulate corresponding response strategies. Timing analysis is a method of analyzing data arranged in chronological order. In step E, the user interface module includes alarm push, alarm history, alarm processing, alarm analysis and alarm KPI, which can display optimized alarm information, alarm history, production status monitoring, etc. and interact with personnel. Among them, alarm KPI refers to data alarm KPI, which is a series of quantitative indicators used to measure and evaluate system performance and problem handling efficiency in data management and monitoring systems. These indicators usually include the average number of alarms per hour, timely confirmation rate, timely handling rate, 24-hour continuous alarm number and 10-minute peak alarm number, etc. Through these indicators, the alarm management function of the system can be optimized and the risk perception and emergency response capabilities of on-site personnel can be improved. Embodiment 1:

[0015] A method for a process production alarm optimization system based on artificial intelligence comprises the following steps: A: Data acquisition module, which collects key parameter data of various equipment during production; B: Preprocessing module, which performs cleaning, denoising, and normalization on the collected data; C: Artificial intelligence analysis module, which identifies and analyzes the pre-processed data; D: Alarm optimization module, based on the results of data analysis, optimizes the alarm information; E: User interface module, providing a friendly interactive interface to display optimized alarm information.

[0016] In step A, the data acquisition module collects key parameter data in the process of process production in real time through the data acquisition gateway, DCS system, sensor, mobile terminal and MES system; the data acquisition gateway collects key data in the production process in real time by connecting to various sensors and actuators, including temperature, pressure, flow, liquid level, voltage, etc. The DCS system monitors and controls various data collected in real time at the production site, such as temperature, pressure, flow, liquid level and other physical quantities, as well as the operating status and fault information of the equipment, and generates reports, trend charts, etc. to help operators understand the status and change trend of the process. The sensor can detect various information produced by the equipment and convert it into electrical signals or other forms of information according to certain rules and output it to the data acquisition gateway. By collecting data in the production process in real time, the MES system can respond to the production situation in a timely manner and reduce production waste and delays; In step B, the preprocessing module includes data aggregation, data cleaning, data governance, data standards and data storage to process various types of collected data, delete duplicate information, correct errors, solve missing values, delete outliers, and store the data to make subsequent data analysis and data mining more accurate and effective, ensure data quality, and avoid misleading conclusions caused by data quality issues. Embodiment 2:

[0017] A method for a process production alarm optimization system based on artificial intelligence comprises the following steps: A: Data acquisition module, which collects key parameter data of various equipment during production; B: Preprocessing module, which performs cleaning, denoising, and normalization on the collected data; C: Artificial intelligence analysis module, which identifies and analyzes the pre-processed data; D: Alarm optimization module, based on the results of data analysis, optimizes the alarm information; E: User interface module, providing a friendly interactive interface to display optimized alarm information.

[0018] In step A, the data acquisition module collects key parameter data in the process of process production in real time through the data acquisition gateway, DCS system, sensor, mobile terminal and MES system; the data acquisition gateway collects key data in the production process in real time by connecting to various sensors and actuators, including temperature, pressure, flow, liquid level, voltage, etc. The DCS system monitors and controls various data collected in real time at the production site, such as temperature, pressure, flow, liquid level and other physical quantities, as well as the operating status and fault information of the equipment, and generates reports, trend charts, etc. to help operators understand the status and change trend of the process. The sensor can detect various information produced by the equipment and convert it into electrical signals or other forms of information according to certain rules and output it to the data acquisition gateway. By collecting data in the production process in real time, the MES system can respond to the production situation in a timely manner and reduce production waste and delays; In step B, the preprocessing module includes data aggregation, data cleaning, data governance, data standards and data storage to process various types of collected data, delete duplicate information, correct errors, solve missing values, delete outliers and other operations from the collected original data, and store the data to make subsequent data analysis and data mining more accurate and effective, ensure data quality, and avoid misleading conclusions caused by data quality problems; In step C, the artificial intelligence analysis module processes and analyzes a large amount of collected data through an algorithm engine. The algorithm engine is a specially designed software system used to process and analyze large amounts of data. It mines, organizes and interprets data through complex algorithms to provide users with valuable information. The pre-processed data is then analyzed through a deep learning framework and a machine learning framework to identify normal and abnormal patterns in the production process and dynamically adjust alarm thresholds. Finally, the algorithm warehouse stores and manages large-scale data sets, and applies machine learning algorithms for data analysis and mining.

[0019] To sum up: the artificial intelligence-based process production alarm optimization system and method, through the coordinated use of the above steps, solves the problem of being unable to adapt to the dynamic changes and complex environment in the production process, easily leading to false alarms and missed alarms, and interfering with the normal operation of production. In an emergency, the existing system may take a long time to respond and process alarms, affecting production safety, and unable to conduct in-depth analysis of production data, unable to warn of potential risks in advance, and unable to provide data support for production optimization.

Claims

1. A method for a process production alarm optimization system based on artificial intelligence, characterized in that: The following steps are involved: A: Data acquisition module, which collects key parameter data of various equipment during production; B: Preprocessing module, which performs cleaning, denoising, and normalization on the collected data; C: Artificial intelligence analysis module, which identifies and analyzes the pre-processed data; D: Alarm optimization module, based on the results of data analysis, optimizes the alarm information; E: User interface module, providing a friendly interactive interface to display optimized alarm information.

2. The method of a process production alarm optimization system based on artificial intelligence according to claim 1, characterized in that: In step A, the data acquisition module collects key parameter data in the process of process production in real time through the data acquisition gateway, DCS system, sensor, mobile terminal and MES system; the data acquisition gateway collects key data in the production process in real time by connecting to various sensors and actuators, including temperature, pressure, flow, liquid level, voltage, etc. The DCS system monitors and controls various data collected in real time at the production site, such as temperature, pressure, flow, liquid level and other physical quantities, as well as the operating status and fault information of the equipment, and generates reports, trend charts, etc. to help operators understand the status and change trend of the process. The sensor can detect various information produced by the equipment and convert it into electrical signals or other forms of information according to certain rules and output it to the data acquisition gateway. By collecting data in the production process in real time, the MES system can respond to the production situation in a timely manner and reduce production waste and delays.

3. The method of a process production alarm optimization system based on artificial intelligence according to claim 1, characterized in that: In step B, the preprocessing module includes data aggregation, data cleaning, data governance, data standards and data storage to process various types of collected data, delete duplicate information, correct errors, solve missing values, delete outliers and other operations from the collected original data, and store the data to make subsequent data analysis and data mining more accurate and effective, ensure data quality, and avoid misleading conclusions caused by data quality issues.

4. The method of a process production alarm optimization system based on artificial intelligence according to claim 1, characterized in that: In step C, the artificial intelligence analysis module processes and analyzes a large amount of collected data through an algorithm engine. The algorithm engine is a specially designed software system for processing and analyzing large amounts of data. It mines, organizes and interprets data through complex algorithms to provide users with valuable information. The pre-processed data is then analyzed through a deep learning framework and a machine learning framework to identify normal and abnormal patterns in the production process and dynamically adjust alarm thresholds. Finally, the algorithm warehouse stores and manages large-scale data sets, and applies machine learning algorithms for data analysis and mining.

5. The method of a process production alarm optimization system based on artificial intelligence according to claim 1, characterized in that: In step D, the alarm optimization module optimizes the alarm information according to the results of the artificial intelligence analysis module through jitter analysis, causal analysis, flooding analysis and timing analysis, so as to reduce false alarms and missed alarms and improve the accuracy and response speed of the alarm. Jitter analysis refers to the process of analyzing and evaluating various jitter phenomena generated by data signals during transmission. Causal analysis is to analyze whether a certain factor is the "cause" of other variables by observing the changes in it, so as to find the key factors that really affect the business and formulate corresponding response strategies. Timing analysis refers to a method of analyzing data arranged in chronological order.

6. The method of a process production alarm optimization system based on artificial intelligence according to claim 1, characterized in that: In step E, the user interface module includes alarm push, alarm history, alarm processing, alarm analysis and alarm KPI, which can display optimized alarm information, alarm history, production status monitoring, etc. and interact with personnel, wherein the alarm KPI refers to the data alarm KPI, which is a series of quantitative indicators used to measure and evaluate system performance and problem handling efficiency in the data management and monitoring system. These indicators usually include the average number of alarms per hour, timely confirmation rate, timely handling rate, 24-hour continuous alarm number and 10-minute peak alarm number, etc. Through these indicators, the alarm management function of the system can be optimized and the risk perception and emergency response capabilities of on-site personnel can be improved.

Images