WO2021007871A1 - 一种基于云边协同的氧化铝生产运行优化系统及方法 - Google Patents

一种基于云边协同的氧化铝生产运行优化系统及方法 Download PDF

Info

Publication number
WO2021007871A1
WO2021007871A1 PCT/CN2019/096632 CN2019096632W WO2021007871A1 WO 2021007871 A1 WO2021007871 A1 WO 2021007871A1 CN 2019096632 W CN2019096632 W CN 2019096632W WO 2021007871 A1 WO2021007871 A1 WO 2021007871A1
Authority
WO
WIPO (PCT)
Prior art keywords
optimization
strategy
data
production operation
module
Prior art date
Application number
PCT/CN2019/096632
Other languages
English (en)
French (fr)
Inventor
丁进良
刘长鑫
徐德鹏
柴天佑
Original Assignee
东北大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 东北大学 filed Critical 东北大学
Priority to US17/625,690 priority Critical patent/US20220326667A1/en
Publication of WO2021007871A1 publication Critical patent/WO2021007871A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/047—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators the criterion being a time optimal performance criterion
    • C—CHEMISTRY; METALLURGY
    • C01—INORGANIC CHEMISTRY
    • C01F—COMPOUNDS OF THE METALS BERYLLIUM, MAGNESIUM, ALUMINIUM, CALCIUM, STRONTIUM, BARIUM, RADIUM, THORIUM, OR OF THE RARE-EARTH METALS
    • C01F7/00—Compounds of aluminium
    • C01F7/02—Aluminium oxide; Aluminium hydroxide; Aluminates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Definitions

  • the invention relates to the technical field of alumina production operation optimization, in particular to an alumina production operation optimization system and method based on cloud edge collaboration.
  • Aluminum and its alloys have many excellent properties. At the same time, aluminum is rich in resources, so the aluminum industry has developed rapidly since its inception. Large-scale equipment is conducive to the automatic detection and control of the process.
  • the production control and management system based on microcomputers and computers provides a huge potential for the alumina plant to improve labor productivity, reduce raw material consumption and save energy.
  • the technical problem to be solved by the present invention is to provide a cloud-side collaboration-based alumina production operation optimization system and method based on the above-mentioned shortcomings of the prior art, so as to realize the collaborative optimization of the alumina production operation process.
  • the present invention provides a cloud-side collaboration-based alumina production operation optimization system, including a process data collection unit, cloud storage and collaborative optimization computing unit, local Cooperative production operation optimization unit and data transmission unit;
  • the process data collection unit is used to collect the actual data of the whole process of the alumina production process, and transmit the collected data to the local coordinated production operation optimization unit at fixed time intervals through the data transmission unit;
  • the local coordinated production operation optimization control unit runs on a local computer terminal and is used for the control of the alumina production coordinated optimization system. It includes data preprocessing and analysis module, production operation optimization strategy operation module, optimization strategy remote correction module, and local working conditions Identification module, optimization strategy switching module, local model and strategy management module;
  • the optimization strategy remote correction module is used to receive the optimization strategy recommended by the cloud and save the received strategy to the local model and strategy management module;
  • the data preprocessing and analysis module performs uniform time stamp alignment and data preprocessing on the collected alumina production process data, and transmits the preprocessed data to the cloud storage and collaborative optimization calculation unit through the data transmission unit; Data preprocessing adopts different processing methods according to the different types of data in the alumina production process;
  • the local operating condition identification module performs local analysis of operating conditions based on the collected real-time data of the alumina production process, and provides the current operating conditions of the alumina production process;
  • the optimization strategy switching module automatically switches the optimization strategy that needs to be run currently according to the working condition information analyzed by the local working condition recognition module for real-time data;
  • the production operation optimization strategy operation module runs the strategy given by the optimization strategy switching module, and sends the actual production operation setting value obtained through the operation to the bottom control device in the alumina production process through the data transmission unit;
  • the local model and strategy management module stores all alumina production process models in the alumina production operation optimization system and the optimization strategies recommended by the cloud storage and collaborative optimization computing unit;
  • the data transmission unit transmits data through a public network or a dedicated line;
  • the cloud storage and collaborative optimization computing unit runs on a cloud server, and includes a production process historical data storage module, a big data intelligent working condition perception analysis module, a production process model establishment and testing module, a production operation optimization strategy configuration and testing module, and the cloud Model and strategy management module, production operation optimization strategy big data analysis and intelligent recommendation module, production process model and strategy issuing module.
  • the production process history data storage module is used for long-term reception and storage of the data generated during the production process transmitted by the local coordinated production operation optimization control unit to provide sufficient data support for big data analysis; at the same time, it stores the established alumina production process model and Production operation optimization strategy;
  • the big data intelligent working condition perception analysis module analyzes the collected alumina production process data and analyzes the working condition of the alumina production
  • the production process model establishment and testing module integrates the data received from the local coordinated production operation optimization control unit, models the data generated in the mass production process, and obtains the alumina production process model, which provides precision for the optimization decision process Model, and adjust the model in real time according to the accuracy of the model and the current production conditions;
  • the configuration and testing module of the production operation optimization strategy uses the existing alumina production process model and production operation optimization strategy in the cloud model and the strategy management module to configure the production operation optimization strategy during the alumina production process, and act as a local terminal When the computer crashes, restore it through cloud data;
  • the cloud model and strategy management module manages the model generated by the production process model establishment and testing module and the configuration of the production operation optimization strategy and the strategy generated by the test module;
  • the production operation optimization strategy big data analysis and intelligent recommendation module runs in the cloud in real time to optimize multiple strategies for the same index, and evaluates the strategy according to the actual index setting value of the historical underlying control device; and through the production process model and strategy
  • the sending module sends the strategy with the smallest evaluation result to the local coordinated production operation optimization control unit.
  • the present invention also provides a method for optimizing alumina production operation based on cloud-side collaboration, including the following steps:
  • Step 1 Collect the actual data of the entire alumina production process through the process data collection unit, and transmit the collected data to the local collaborative production operation optimization unit at fixed time intervals through the data transmission unit;
  • Step 2 Select the alumina production operation indicators and variables to be optimized, and judge whether there is an alumina production process model corresponding to the selected alumina production operation indicators and variables in the model and strategy management module of the local collaborative production operation optimization unit. If it exists, go to step 5 directly, otherwise, go to step 3;
  • Step 3 Optimize the model and strategy management module of the control unit through the local collaborative production operation to add the production indicators and variables that need to be modeled, and the time period for collecting production indicators and variable data, and select the production indicators and variables to be modeled.
  • Step 4 Input the modeling information into the cloud storage and collaborative optimization computing unit, use the production process model establishment and test module to perform data modeling and testing in the cloud, and adjust the model in real time according to the accuracy of the model and the current production conditions. And send the established model back to the model and strategy management module of the local coordinated production operation optimization control unit;
  • Step 5 The user configures the optimization strategy configuration of the production operation optimization strategy and the test module in the cloud storage and the collaborative optimization computing unit, and tests the configured optimization strategy;
  • the strategy configuration includes the target indicators, boundary conditions, Configuration of decision variables, production process models and optimization algorithms;
  • Step 6 Run multiple optimization strategies in the cloud in real time, evaluate the strategy results, select the strategy with the smallest deviation from the historical actual setting value, and transfer the selected strategy back to the local optimization strategy remote correction module;
  • Step 7 The local operating condition identification module performs operating condition identification based on real-time data, and passes the analysis result of the operating condition to the optimization strategy switching module, and the optimization strategy switching module adjusts the optimization strategy according to the analysis results of the operating conditions;
  • Step 8 The production operation optimization strategy operation module of the local collaborative production operation optimization control unit performs real-time operation calculation on the optimization strategy given by the optimization strategy switching module, and gives the calculation results;
  • Step 9 According to the calculation result given by the production operation optimization strategy operation module, the actual set value is sent to the bottom control device in the alumina production process through the data transmission unit.
  • the beneficial effects of using the above technical solutions are: the cloud-side collaboration-based alumina production operation optimization system and method provided by the present invention, for the large amount of data generated during the alumina production process, use machine learning and other methods to perform data Analyze and process to obtain an accurate alumina production process model, which provides a basis for accurate alumina production operation index optimization decision-making.
  • Local data integration and real-time data calculation reduce the cost and time delay of data transmission, provide real-time optimized calculation, and ensure the normal operation of the system when the network is disconnected. It can realize the real-time optimization of indicators in the alumina production process, reduce production energy consumption, improve production efficiency, reduce production waste, improve the rationality of production scheduling, and provide a solution for coordinating the entire production process.
  • FIG. 1 is a structural block diagram of an alumina production operation optimization system based on cloud-side collaboration provided by an embodiment of the present invention
  • Fig. 2 is a flowchart of alumina production operation optimization based on cloud-side collaboration provided by an embodiment of the present invention.
  • an alumina production operation optimization system based on cloud-side collaboration includes a process data collection unit, a cloud storage and collaborative optimization computing unit, a local collaborative production operation optimization unit, and a data transmission unit;
  • the process data collection unit is used to collect the actual data of the whole process of the alumina production process, and transmit the collected data to the local coordinated production operation optimization unit at fixed time intervals through the data transmission unit;
  • the local coordinated production operation optimization control unit runs on a local computer terminal and is used for the control of the alumina production coordinated optimization system. It includes data preprocessing and analysis module, production operation optimization strategy operation module, optimization strategy remote correction module, and local working conditions Identification module, optimization strategy switching module, local model and strategy management module;
  • the optimization strategy remote correction module is used to receive the optimization strategy recommended by the cloud and save the received strategy to the local model and strategy management module;
  • the data preprocessing and analysis module performs uniform time stamp alignment and data preprocessing on the collected alumina production process data, and transmits the preprocessed data to the cloud storage and collaborative optimization calculation unit through the data transmission unit; Data preprocessing adopts different processing methods according to the different types of data in the alumina production process;
  • the local operating condition identification module performs local analysis of operating conditions based on the collected real-time data of the alumina production process, and provides the current operating conditions of the alumina production process;
  • the optimization strategy switching module automatically switches the optimization strategy that needs to be run currently according to the working condition information analyzed by the local working condition identification module for real-time data;
  • the production operation optimization strategy operation module runs the strategy given by the optimization strategy switching module, and sends the actual production operation setting value obtained through the operation to the bottom control device in the alumina production process through the data transmission unit;
  • the local model and strategy management module stores all alumina production process models in the alumina production operation optimization system and the optimization strategies recommended by the cloud storage and collaborative optimization computing unit;
  • the data transmission unit transmits data through a public network or a dedicated line;
  • the cloud storage and collaborative optimization computing unit runs on a cloud server, and includes a production process historical data storage module, a big data intelligent working condition perception analysis module, a production process model establishment and testing module, a production operation optimization strategy configuration and testing module, and the cloud Model and strategy management module, production operation optimization strategy big data analysis and intelligent recommendation module, production process model and strategy issuing module;
  • the production process history data storage module is used for long-term reception and storage of the data generated during the production process transmitted by the local coordinated production operation optimization control unit to provide sufficient data support for big data analysis; at the same time, it stores the established alumina production process model and Production operation optimization strategy;
  • the big data intelligent working condition perception analysis module analyzes the collected alumina production process data and analyzes the working condition of the alumina production
  • the production process model establishment and testing module integrates the data received from the local coordinated production operation optimization control unit, models the data generated in the mass production process, and obtains the alumina production process model, which provides precision for the optimization decision process Model, and adjust the model in real time according to the accuracy of the model and the current production conditions;
  • the configuration and testing module of the production operation optimization strategy uses the existing alumina production process model and production operation optimization strategy in the cloud model and the strategy management module to configure the production operation optimization strategy during the alumina production process, and act as a local terminal When the computer crashes, restore it through cloud data;
  • the cloud model and strategy management module manages the model generated by the production process model establishment and testing module and the configuration of the production operation optimization strategy and the strategy generated by the test module;
  • the production operation optimization strategy big data analysis and intelligent recommendation module runs in the cloud in real time to optimize multiple strategies for the same index, and evaluates the strategy according to the actual index setting value of the historical underlying control device; and through the production process model and strategy
  • the sending module sends the strategy with the least deviation of the evaluation result to the local coordinated production operation optimization control unit.
  • a cloud-side collaboration-based alumina production operation optimization method includes the following steps:
  • Step 1 Collect the actual data of the entire alumina production process through the process data collection unit, and transmit the collected data to the local collaborative production operation optimization unit at fixed time intervals through the data transmission unit;
  • Step 2 Select the alumina production operation indicators and variables to be optimized, and judge whether there is an alumina production process model corresponding to the selected alumina production operation indicators and variables in the model and strategy management module of the local collaborative production operation optimization unit. If it exists, go to step 5 directly, otherwise, go to step 3;
  • Step 3 Optimize the model and strategy management module of the control unit through the local collaborative production operation to add the production indicators and variables that need to be modeled, and the time period for collecting production indicators and variable data, and select the production indicators and variables to be modeled.
  • Step 4 Input the modeling information into the cloud storage and collaborative optimization computing unit, use the production process model establishment and test module to perform data modeling and testing in the cloud, and adjust the model in real time according to the accuracy of the model and the current production conditions. And send the established model back to the model and strategy management module of the local coordinated production operation optimization control unit;
  • Step 5 The user configures the optimization strategy configuration of the production operation optimization strategy and the test module in the cloud storage and the collaborative optimization computing unit, and tests the configured optimization strategy;
  • the strategy configuration includes the target indicators, boundary conditions, Configuration of decision variables, production process models and optimization algorithms;
  • Step 6 Run multiple optimization strategies in the cloud in real time, evaluate the strategy results, select the strategy with the smallest deviation from the historical actual setting value, and transfer the selected strategy back to the local optimization strategy remote correction module;
  • Step 7 The local operating condition identification module performs operating condition identification based on real-time data, and passes the analysis result of the operating condition to the optimization strategy switching module, and the optimization strategy switching module adjusts the optimization strategy according to the analysis results of the operating conditions;
  • Step 8 The production operation optimization strategy operation module of the local collaborative production operation optimization control unit performs real-time operation calculation on the optimization strategy given by the optimization strategy switching module, and gives the calculation results;
  • Step 9 According to the calculation result given by the production operation optimization strategy operation module, the actual set value is sent to the bottom control device in the alumina production process through the data transmission unit.
  • the model and strategy management module of the local coordinated production operation optimization control unit is used to select the grinding A/S, ore adjustment NK, ore adjustment solid content, dissolution ak, and dissolution solid content of a certain period of time in the laboratory test results As a decision variable, the dissolution rate is used as an indicator for modeling.
  • Table 1 The selected data are shown in Table 1:
  • the sample division method selects the retention method
  • the data preprocessing method selects the normalized preprocessing method
  • the modeling method selects the support vector machine for modeling.
  • the genetic algorithm is selected to optimize the indicators in the alumina production and operation process, and the boundary conditions of the decision variables are given; the boundary conditions of the decision variables in this embodiment are shown in Table 2:
  • the production operation optimization strategy operation module of the local collaborative production operation optimization control unit is used to perform real-time operation calculation on the strategy given by the optimization strategy switching module, and the calculation result is given;
  • the dissolution rate was 98.85%.
  • the alumina production engineer Based on the calculation results given by the calculation and their own experience, the alumina production engineer gives the actual set values of the variables and indicators, and sends the actual set values to the bottom control device in the alumina production process through the data transmission unit.

Abstract

本发明提供一种基于云边协同的氧化铝生产运行优化系统及方法，涉及氧化铝生产运行优化技术领域。该系统及方法首先采集氧化铝生产过程的全流程数据，将数据进行预处理后传输到本地协同生产运行优化单元，本地协同生产运行优化单元首先判断当前氧化铝生产过程所处工况，根据工况自动切换当前需要运行的优化策略，本地运行优化策略得到氧化铝生产运行指标的实际设定值。对于本地协同生产运行优化单元不存在氧化铝生产过程模型的情况，本地协同生产运行优化控制单元将建模信息发送给云存储和协同优化计算单元，在云端进行建模和测试。云端搭建测试并运行多个优化策略，将与历史实际设定值偏差最小的策略推荐给本地协同生产运行优化单元。

Description

一种基于云边协同的氧化铝生产运行优化系统及方法 技术领域
本发明涉及氧化铝生产运行优化技术领域，尤其涉及一种基于云边协同的氧化铝生产运行优化系统及方法。
背景技术
铝及其合金具有许多优良的性能，同时，铝的资源很丰富，因此铝工业自问世以来发展十分迅速。大型化的设备有利于工艺过程的自动检测和控制，以微机和计算机为基础的生产控制和管理系统为氧化铝厂提高劳动生产率、降低原材料消耗和节能提供了巨大的潜力。
尽管相关企业在氧化铝冶炼技术方面进行了项目改良和升级，但是，依旧存在原料质量差、项目能耗高以及产品质量不足的问题，产品多数都是中间状态的氧化铝就会对整体技术应用管理造成影响，制约产品结构。
传统氧化铝生产过程中，很多控制指标主要依赖管理者、调度员、工程师等知识型工作者人工凭经验进行设定，生产系统不能运行在优化条件下。
同时，氧化铝生产的整个过程中，各个工序间的联系十分紧密，上一道工序的产品对于下一道工序的生产有十分大的影响，现有生产系统中，难以将各道工序中的数据整合提炼，取得全流程的最优生产指标设定。
发明概述
技术问题
问题的解决方案
技术解决方案
本发明要解决的技术问题是针对上述现有技术的不足，提供一种基于云边协同的氧化铝生产运行优化系统及方法，实现对氧化铝生产运行过程进行协同优化。
为解决上述技术问题，本发明所采取的技术方案是：一方面，本发明提供一种基于云边协同的氧化铝生产运行优化系统，包括过程数据采集单元、云存储和 协同优化计算单元、本地协同生产运行优化单元和数据传输单元；
所述过程数据采集单元用于采集氧化铝生产过程的全流程实际数据，并通过数据传输单元将采集到的数据以固定时间间隔传输到本地协同生产运行优化单元；
所述本地协同生产运行优化控制单元运行在本地计算机终端，用于氧化铝生产协同优化系统的控制，包括数据预处理和分析模块、生产运行优化策略运行模块、优化策略远程校正模块、本地工况识别模块、优化策略切换模块及本地模型和策略管理模块；
所述优化策略远程校正模块用于接收云端推荐的优化策略并将接收的策略保存到本地模型和策略管理模块；
所述数据预处理和分析模块将采集的氧化铝生产过程数据进行时间戳的统一对齐与数据预处理，并将预处理后的数据通过数据传输单元传输到云存储和协同优化计算单元；所述数据预处理根据氧化铝生产过程数据类型的不同，采用不同的处理方法；
所述本地工况识别模块针对采集的氧化铝生产过程实时数据进行工况的本地分析，给出当前氧化铝生产过程生产所处工况；
所述优化策略切换模块根据本地工况识别模块针对实时数据分析出的工况信息，自动切换当前需要运行的优化策略；
所述生产运行优化策略运行模块，运行优化策略切换模块给出的策略，并将运行得到的实际生产运行设定值通过数据传输单元下发给氧化铝生产过程中的底层控制装置；
所述本地模型和策略管理模块，存储氧化铝生产运行优化系统中所有的氧化铝生产过程模型和云存储和协同优化计算单元推荐的优化策略；
所述数据传输单元通过公网或专线进行数据的传输；
所述云存储和协同优化计算单元运行在云端服务器，包括生产过程历史数据存储模块，大数据智能工况感知分析模块，生产过程模型建立和测试模块，生产运行优化策略的配置和测试模块，云端模型和策略管理模块，生产运行优化策略大数据分析与智能推荐模块，生产过程模型和策略下发模块。
所述生产过程历史数据存储模块，用于长期接收存储本地协同生产运行优化控制单元传输的生产过程中产生的数据，为大数据分析提供充足数据支持；同时存储建立好的氧化铝生产过程模型以及生产运行优化策略；
所述大数据智能工况感知分析模块，对采集到的氧化铝生产过程数据进行分析，分析出氧化铝生产所处的工况；
所述生产过程模型建立和测试模块，将从本地协同生产运行优化控制单元接收到的数据进行整合，对大量生产过程产生的数据进行建模，得到氧化铝生产过程模型，为优化决策过程提供精确模型，同时根据模型精度及当前生产所处的工况，实时调整模型；
所述生产运行优化策略的配置和测试模块，利用云端模型和策略管理模块中已有的氧化铝生产过程模型和生产运行优化策略，配置氧化铝生产工艺过程中的生产运行优化策略，当本地终端计算机崩溃时，通过云端数据进行恢复；
所述云端模型和策略管理模块，对生产过程模型建立和测试模块产生的模型和生产运行优化策略的配置和测试模块产生的策略进行管理；
所述生产运行优化策略大数据分析与智能推荐模块，在云端实时运行优化同一指标的多个策略，根据历史底层控制装置的实际指标设定值对策略进行评价；并通过生产过程模型和策略下发模块将评价结果最小的策略下发给本地协同生产运行优化控制单元。
另一方面，本发明还提供一种基于云边协同的氧化铝生产运行优化方法，包括以下步骤：
步骤1、通过过程数据采集单元采集氧化铝生产过程的全流程实际数据，并通过数据传输单元将采集到的数据以固定时间间隔传输到本地协同生产运行优化单元；
步骤2：选择待优化的氧化铝生产运行指标和变量，判断本地协同生产运行优化单元的模型和策略管理模块中是否存在与选择的氧化铝生产运行指标和变量相对应的氧化铝生产过程模型，若存在，直接执行到步骤5，否则，执行步骤3；
步骤3：通过本地协同生产运行优化控制单元的模型和策略管理模块添加需要 建模的生产指标和变量，以及采集生产指标和变量数据的时间段，选择与待建模的生产指标和变量相对应的样本划分方法、数据预处理方式以及建模方法；
步骤4：将建模信息输入云存储和协同优化计算单元，在云端利用生产过程模型建立和测试模块进行数据建模和测试，同时根据模型精度及当前生产所处的工况，实时调整模型，并将建立好的模型传回本地协同生产运行优化控制单元的模型和策略管理模块；
步骤5：用户在云存储和协同优化计算单元的生产运行优化策略配置和测试模块配置要优化的指标的策略，并对配置好的优化策略进行测试；策略的配置包括对目标指标、边界条件、决策变量、生产过程模型以及优化算法的配置；
步骤6：云端实时运行多个优化策略，对策略结果进行评价，选出和历史实际设定值偏差最小的策略，将选出的策略传回到本地优化策略远程校正模块；
步骤7：本地工况识别模块根据实时数据进行工况识别，将工况分析结果传递给优化策略切换模块，优化策略切换模块根据工况分析结果调整优化策略；
步骤8：本地协同生产运行优化控制单元的生产运行优化策略运行模块对优化策略切换模块给出的优化策略进行实时运行计算，并给出计算结果；
步骤9：根据生产运行优化策略运行模块给出的计算结果，通过数据传输单元将实际设定值发送给氧化铝生产过程中的底层控制装置。
发明的有益效果
有益效果
采用上述技术方案所产生的有益效果在于：本发明提供的一种基于云边协同的氧化铝生产运行优化系统及方法，对于氧化铝生产过程产生的大量数据，在云端利用机器学习等方法进行数据分析处理，得到精确氧化铝生产过程模型，为进行精准的氧化铝生产运行指标优化决策提供基础。在本地进行数据整合和实时数据计算，减少了数据传输的成本和时间上的延迟，提供了实时的优化计算，同时保证断网情况下系统正常运行。能够实现氧化铝生产过程中指标的实时优化，降低生产能耗，提高生产效率，减少生产浪费，提高生产调度的合理性，提供一种协调整个生产过程的方案。
对附图的简要说明
附图说明
图1为本发明实施例提供的一种基于云边协同的氧化铝生产运行优化系统的结构框图；
图2为本发明实施例提供的一种基于云边协同的氧化铝生产运行优化的流程图。
发明实施例
本发明的实施方式
下面结合附图和实施例，对本发明的具体实施方式作进一步详细描述。以下实施例用于说明本发明，但不用来限制本发明的范围。
本实施例中，一种基于云边协同的氧化铝生产运行优化系统，如图1所示，包括过程数据采集单元、云存储和协同优化计算单元、本地协同生产运行优化单元和数据传输单元；
所述过程数据采集单元用于采集氧化铝生产过程的全流程实际数据，并通过数据传输单元将采集到的数据以固定时间间隔传输到本地协同生产运行优化单元；
所述本地协同生产运行优化控制单元运行在本地计算机终端，用于氧化铝生产协同优化系统的控制，包括数据预处理和分析模块、生产运行优化策略运行模块、优化策略远程校正模块、本地工况识别模块、优化策略切换模块及本地模型和策略管理模块；
所述优化策略远程校正模块用于接收云端推荐的优化策略并将接收的策略保存到本地模型和策略管理模块；
所述数据预处理和分析模块将采集的氧化铝生产过程数据进行时间戳的统一对齐与数据预处理，并将预处理后的数据通过数据传输单元传输到云存储和协同优化计算单元；所述数据预处理根据氧化铝生产过程数据类型的不同，采用不同的处理方法；
所述本地工况识别模块针对采集的氧化铝生产过程实时数据进行工况的本地分析，给出当前氧化铝生产过程生产所处工况；
所述优化策略切换模块根据本地工况识别模块针对实时数据分析出的工况信息 ，自动切换当前需要运行的优化策略；
所述生产运行优化策略运行模块，运行优化策略切换模块给出的策略，并将运行得到的实际生产运行设定值通过数据传输单元下发给氧化铝生产过程中的底层控制装置；
所述本地模型和策略管理模块，存储氧化铝生产运行优化系统中所有的氧化铝生产过程模型和云存储和协同优化计算单元推荐的优化策略；
所述数据传输单元通过公网或专线进行数据的传输；
所述云存储和协同优化计算单元运行在云端服务器，包括生产过程历史数据存储模块，大数据智能工况感知分析模块，生产过程模型建立和测试模块，生产运行优化策略的配置和测试模块，云端模型和策略管理模块，生产运行优化策略大数据分析与智能推荐模块，生产过程模型和策略下发模块；
所述生产过程历史数据存储模块，用于长期接收存储本地协同生产运行优化控制单元传输的生产过程中产生的数据，为大数据分析提供充足数据支持；同时存储建立好的氧化铝生产过程模型以及生产运行优化策略；
所述大数据智能工况感知分析模块，对采集到的氧化铝生产过程数据进行分析，分析出氧化铝生产所处的工况；
所述生产过程模型建立和测试模块，将从本地协同生产运行优化控制单元接收到的数据进行整合，对大量生产过程产生的数据进行建模，得到氧化铝生产过程模型，为优化决策过程提供精确模型，同时根据模型精度及当前生产所处的工况，实时调整模型；
所述生产运行优化策略的配置和测试模块，利用云端模型和策略管理模块中已有的氧化铝生产过程模型和生产运行优化策略，配置氧化铝生产工艺过程中的生产运行优化策略，当本地终端计算机崩溃时，通过云端数据进行恢复；
所述云端模型和策略管理模块，对生产过程模型建立和测试模块产生的模型和生产运行优化策略的配置和测试模块产生的策略进行管理；
所述生产运行优化策略大数据分析与智能推荐模块，在云端实时运行优化同一指标的多个策略，根据历史底层控制装置的实际指标设定值对策略进行评价；并通过生产过程模型和策略下发模块将评价结果偏差最小的策略下发给本地协 同生产运行优化控制单元。
一种基于云边协同的氧化铝生产运行优化方法，如图2所示，包括以下步骤：
步骤1、通过过程数据采集单元采集氧化铝生产过程的全流程实际数据，并通过数据传输单元将采集到的数据以固定时间间隔传输到本地协同生产运行优化单元；
步骤2：选择待优化的氧化铝生产运行指标和变量，判断本地协同生产运行优化单元的模型和策略管理模块中是否存在与选择的氧化铝生产运行指标和变量相对应的氧化铝生产过程模型，若存在，直接执行到步骤5，否则，执行步骤3；
步骤3：通过本地协同生产运行优化控制单元的模型和策略管理模块添加需要建模的生产指标和变量，以及采集生产指标和变量数据的时间段，选择与待建模的生产指标和变量相对应的样本划分方法、数据预处理方式以及建模方法；
步骤4：将建模信息输入云存储和协同优化计算单元，在云端利用生产过程模型建立和测试模块进行数据建模和测试，同时根据模型精度及当前生产所处的工况，实时调整模型，并将建立好的模型传回本地协同生产运行优化控制单元的模型和策略管理模块；
步骤5：用户在云存储和协同优化计算单元的生产运行优化策略配置和测试模块配置要优化的指标的策略，并对配置好的优化策略进行测试；策略的配置包括对目标指标、边界条件、决策变量、生产过程模型以及优化算法的配置；
步骤6：云端实时运行多个优化策略，对策略结果进行评价，选出和历史实际设定值偏差最小的策略，将选出的策略传回到本地优化策略远程校正模块；
步骤7：本地工况识别模块根据实时数据进行工况识别，将工况分析结果传递给优化策略切换模块，优化策略切换模块根据工况分析结果调整优化策略；
步骤8：本地协同生产运行优化控制单元的生产运行优化策略运行模块对优化策略切换模块给出的优化策略进行实时运行计算，并给出计算结果；
步骤9：根据生产运行优化策略运行模块给出的计算结果，通过数据传输单元将实际设定值发送给氧化铝生产过程中的底层控制装置。
本实施例中，通过本地协同生产运行优化控制单元的模型和策略管理模块选择 实验室化验结果中某段时间的入磨A/S、调矿NK、调矿固含、溶出ak、溶出固含作为决策变量，溶出率作为指标进行建模，所选择部分数据如表1所示：
表1氧化铝生产过程的变量和指标数据
Figure PCTCN2019096632-appb-000001
本例实施中，样本划分方法选择留出法、数据预处理方式选择归一化的预处理 方式、建模方法选择支持向量机进行建模。
本实施例中选择遗传算法对氧化铝生产运行过程中的指标进行优化，并给出决策变量的边界条件；本实施例中决策变量的边界条件如表2所示：
表2各变量的边界条件
[Table 1]
序号 变量名称 边界条件
1 入磨A/S ≥4.2
2 调矿NK 200-220
3 调矿固含 300-400
4 溶出ak 1.4-1.45
5 溶出固含 180-200
本实施例中，仅针对一种工况提供一种优化策略，故不涉及云端优化策略的智能推荐以及本地工况识别过程。
本实施例中，利用本地协同生产运行优化控制单元的生产运行优化策略运行模块对对优化策略切换模块给出的策略进行实时运行计算，并给出计算结果；
本实施例中，计算得到的决策变量结果如下：
[4.5373，208.3333，317.1667，1.4135，188.333]
溶出率为98.85％。
氧化铝生产的工程师根据计算给出的计算结果结合自身经验，给出变量和指标的实际设定值，通过数据传输单元将实际设定值发送给氧化铝生产过程中的底层控制装置。
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明权利要求所限定的范围。

Claims (4)

  1. 一种基于云边协同的氧化铝生产运行优化系统，其特征在于：包括过程数据采集单元、云存储和协同优化计算单元、本地协同生产运行优化单元和数据传输单元；
    所述过程数据采集单元用于采集氧化铝生产过程的全流程实际数据，并通过数据传输单元将采集到的数据以固定时间间隔传输到本地协同生产运行优化单元和云存储和协同优化计算单元；
    所述本地协同生产运行优化控制单元运行在本地计算机终端，用于氧化铝生产协同优化系统的控制，将接收到的氧化铝生产过程数据进行预处理后通过数据传输单元上传到云存储和协同优化计算单元，针对采集的氧化铝生产过程实时数据进行工况的本地分析，给出当前氧化铝生产过程生产所处工况，并根据工况自动切换当前需要运行的优化策略；在本地计算机终端运行优化策略，并将运行得到的实际生产运行设定值通过数据传输单元下发给氧化铝生产过程中的底层控制装置；所述云存储和协同优化计算单元运行在云端，用于接收存储本地协同生产运行优化控制单元传输的生产过程中产生的数据，并存储建立好的氧化铝生产过程模型以及生产运行优化策略；同时，将从本地协同生产运行优化控制单元接收到的数据进行整合，对大量生产过程产生的数据进行建模，得到氧化铝生产过程模型，并利用已有的氧化铝生产过程模型和生产运行优化策略配置氧化铝生产工艺过程中的生产运行优化策略，并将建立好的模型和配置的优化策略通过数据传输单元下传给本地协同生产运行优化控制单元。
  2. 根据权利要求1所述的一种基于云边协同的氧化铝生产运行优化系统，其特征在于：所述本地协同生产运行优化控制单元包括数据预处理和分析模块、生产运行优化策略运行模块、优化策略远程校正模块、本地工况识别模块、优化策略切换模块及本地模型和策略管理模块；
    所述优化策略远程校正模块用于接收云端推荐的优化策略并将接收的策略保存到本地模型和策略管理模块；
    所述数据预处理和分析模块将采集的氧化铝生产过程数据进行时间戳的统一对齐与数据预处理，并将预处理后的数据通过数据传输单元传输到云存储和协同优化计算单元；所述数据预处理根据氧化铝生产过程数据类型的不同，采用不同的处理方法；
    所述本地工况识别模块针对采集的氧化铝生产过程实时数据进行工况的本地分析，给出当前氧化铝生产过程生产所处工况；
    所述优化策略切换模块根据本地工况识别模块针对实时数据分析出的工况信息，自动切换当前需要运行的优化策略；
    所述生产运行优化策略运行模块，运行优化策略切换模块给出的策略，并将运行得到的实际生产运行设定值通过数据传输单元下发给氧化铝生产过程中的底层控制装置；
    所述本地模型和策略管理模块，存储氧化铝生产运行优化系统中所有的氧化铝生产过程模型和云存储和协同优化计算单元推荐的优化策略；
    所述数据传输单元通过公网或专线进行数据的传输。
  3. 根据权利要求2所述的一种基于云边协同的氧化铝生产运行优化系统，其特征在于：所述云存储和协同优化计算单元包括生产过程历史数据存储模块，大数据智能工况感知分析模块，生产过程模型建立和测试模块，生产运行优化策略的配置和测试模块，云端模型和策略管理模块，生产运行优化策略大数据分析与智能推荐模块，生产过程模型和策略下发模块；
    所述生产过程历史数据存储模块，用于长期接收存储本地协同生产运行优化控制单元传输的生产过程中产生的数据，为大数据分析提供充足数据支持；同时存储建立好的氧化铝生产过程模型以及生产运行优化策略；
    所述大数据智能工况感知分析模块，对采集到的氧化铝生产过程 数据进行分析，分析出氧化铝生产所处的工况；
    所述生产过程模型建立和测试模块，将从本地协同生产运行优化控制单元接收到的数据进行整合，对大量生产过程产生的数据进行建模，得到氧化铝生产过程模型，为优化决策过程提供精确模型，同时根据模型精度及当前生产所处的工况，实时调整模型；
    所述生产运行优化策略的配置和测试模块，利用云端模型和策略管理模块中已有的氧化铝生产过程模型和生产运行优化策略，配置氧化铝生产工艺过程中的生产运行优化策略，当本地终端计算机崩溃时，通过云端数据进行恢复；
    所述云端模型和策略管理模块，对生产过程模型建立和测试模块产生的模型和生产运行优化策略的配置和测试模块产生的策略进行管理；
    所述生产运行优化策略大数据分析与智能推荐模块，在云端实时运行优化同一指标的多个策略，根据历史底层控制装置的实际指标设定值对策略进行评价；并通过生产过程模型和策略下发模块将评价结果偏差最小的策略下发给本地协同生产运行优化控制单元。
  4. 一种基于云边协同的氧化铝生产运行优化方法，采用权利要求3所述的一种基于云边协同的氧化铝生产运行优化系统进行优化，其特征在于：包括以下步骤：
    步骤1、通过过程数据采集单元采集氧化铝生产过程的全流程实际数据，并通过数据传输单元将采集到的数据以固定时间间隔传输到本地协同生产运行优化单元；
    步骤2：选择待优化的氧化铝生产运行指标和变量，判断本地协同生产运行优化单元的模型和策略管理模块中是否存在与选择的氧化铝生产运行指标和变量相对应的氧化铝生产过程模型，若存在，直接执行到步骤5，否则，执行步骤3；
    步骤3：通过本地协同生产运行优化控制单元的模型和策略管理模 块添加需要建模的生产指标和变量，以及采集生产指标和变量数据的时间段，选择与待建模的生产指标和变量相对应的样本划分方法、数据预处理方式以及建模方法；
    步骤4：将建模信息输入云存储和协同优化计算单元，在云端利用生产过程模型建立和测试模块进行数据建模和测试，同时根据模型精度及当前生产所处的工况，实时调整模型，并将建立好的模型传回本地协同生产运行优化控制单元的模型和策略管理模块；
    步骤5：用户在云存储和协同优化计算单元的生产运行优化策略配置和测试模块配置要优化的指标的策略，并对配置好的优化策略进行测试；策略的配置包括对目标指标、边界条件、决策变量、生产过程模型以及优化算法的配置；
    步骤6：云端实时运行多个优化策略，对策略结果进行评价，选出和历史实际设定值偏差最小的策略，将选出的策略传回到本地优化策略远程校正模块；
    步骤7：本地工况识别模块根据实时数据进行工况识别，将工况分析结果传递给优化策略切换模块，优化策略切换模块根据工况分析结果调整优化策略；
    步骤8：本地协同生产运行优化控制单元的生产运行优化策略运行模块对优化策略切换模块给出的优化策略进行实时运行计算，并给出计算结果；
    步骤9：根据生产运行优化策略运行模块给出的计算结果，通过数据传输单元将实际设定值发送给氧化铝生产过程中的底层控制装置。
PCT/CN2019/096632 2019-07-16 2019-07-19 一种基于云边协同的氧化铝生产运行优化系统及方法 WO2021007871A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/625,690 US20220326667A1 (en) 2019-07-16 2019-07-19 Aluminum oxide production operation optimization system and method based on cloud-edge collaboration

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910640300.9A CN110263494B (zh) 2019-07-16 2019-07-16 一种基于云边协同的氧化铝生产运行优化系统及方法
CN201910640300.9 2019-07-16

Publications (1)

Publication Number Publication Date
WO2021007871A1 true WO2021007871A1 (zh) 2021-01-21

Family

ID=67926405

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/096632 WO2021007871A1 (zh) 2019-07-16 2019-07-19 一种基于云边协同的氧化铝生产运行优化系统及方法

Country Status (3)

Country Link
US (1) US20220326667A1 (zh)
CN (1) CN110263494B (zh)
WO (1) WO2021007871A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117575108A (zh) * 2024-01-16 2024-02-20 山东三岳化工有限公司 一种化工厂能源数据分析系统

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110850833B (zh) * 2019-11-29 2022-08-23 东北大学 一种氧化铝溶出过程智能化设定系统及方法
CN111198530A (zh) * 2020-01-17 2020-05-26 济南浪潮高新科技投资发展有限公司 一种5g环境下云化机器人的系统及方法
CN112465274B (zh) * 2020-12-30 2024-03-29 镇江龙源铝业有限公司 生产车间智能化管理系统
CN114063579A (zh) * 2021-11-01 2022-02-18 青岛天人环境股份有限公司 工业互联网除臭边缘增效微平台设备
CN114154734A (zh) * 2021-12-08 2022-03-08 上海中联重科桩工机械有限公司 施工设备的参数寻优方法、系统、电子设备及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105021030A (zh) * 2014-04-21 2015-11-04 东北大学 一种氧化铝熟料窑综合自动化控制系统
CN105467946A (zh) * 2015-02-05 2016-04-06 贵阳铝镁设计研究院有限公司 一种基于精确感知与智能决策的铝电解mes系统
US20170339032A1 (en) * 2016-05-20 2017-11-23 Chun-Tai Yen Mobile manufacturing management and optimization platform

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104570739B (zh) * 2015-01-07 2017-01-25 东北大学 基于云和移动终端的选矿多生产指标优化决策系统及方法
CN104807321B (zh) * 2015-04-29 2016-12-07 东北大学 基于云计算技术的电熔镁炉运行过程监控系统及方法
CN106302739A (zh) * 2016-08-16 2017-01-04 北京大邦实创节能技术服务有限公司 一种工业锅炉监测及分析辅助决策云平台系统
CN106707769B (zh) * 2017-03-17 2019-07-09 中国科学院沈阳自动化研究所 一种油田管理系统与方法
CN109995546B (zh) * 2017-12-29 2021-02-05 中国科学院沈阳自动化研究所 边缘计算与云计算协同的智能工厂自动化系统

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105021030A (zh) * 2014-04-21 2015-11-04 东北大学 一种氧化铝熟料窑综合自动化控制系统
CN105467946A (zh) * 2015-02-05 2016-04-06 贵阳铝镁设计研究院有限公司 一种基于精确感知与智能决策的铝电解mes系统
US20170339032A1 (en) * 2016-05-20 2017-11-23 Chun-Tai Yen Mobile manufacturing management and optimization platform

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
GUI, WEIHUA ET AL.: "A Review of Intelligent Optimal Manufacturing for Aluminum Reduction Production", ACTA AUTOMATICA SINICA, vol. 44, no. 11, 30 November 2018 (2018-11-30), DOI: 20200326155603A *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117575108A (zh) * 2024-01-16 2024-02-20 山东三岳化工有限公司 一种化工厂能源数据分析系统

Also Published As

Publication number Publication date
CN110263494A (zh) 2019-09-20
US20220326667A1 (en) 2022-10-13
CN110263494B (zh) 2023-05-12

Similar Documents

Publication Publication Date Title
WO2021007871A1 (zh) 一种基于云边协同的氧化铝生产运行优化系统及方法
US9965722B2 (en) Optimized decision-making system and method for multiple ore dressing production indexes based on cloud server and mobile terminals
CN105467946B (zh) 一种铝电解生产精确感知与智能决策方法及mes系统
CN108763550B (zh) 高炉大数据应用系统
CN110889466B (zh) 一种基于线损分类器的台区线损分析方法
CN102809928B (zh) 一种工业企业热力设备能耗的控制优化方法
CN108830745A (zh) 基于监控信息的电网连锁故障诊断、预警、评估系统
WO2021007845A1 (zh) 一种氧化铝生产指标的云-边协同预报系统及方法
CN114372777A (zh) 一种智慧水务物联网在线监测系统
US20210065021A1 (en) Working condition state modeling and model correcting method
CN112926749A (zh) 一种智能电网信息设备监控系统及方法
CN107942873B (zh) 一种家具制造生产线的运营成本智能化核算及监控方法
CN114169570A (zh) 一种基于物联网与云计算技术的智慧能源管理平台
CN116028887B (zh) 一种连续性工业生产数据的分析方法
CN115099592A (zh) 一种信息监理风险的智能管控方法及系统
CN110378586B (zh) 基于动态闭环知识管理的变电设备缺陷预警方法及系统
CN103617447A (zh) 智能变电站的评价系统及评价方法
CN116822754B (zh) 一种基于企业服务项目模块化分类的数据规范分析系统
CN110412960B (zh) 基于云计算的制糖厂进榨及压榨智慧生产管理方法及系统
CN102693514A (zh) 一种基于设备风险预控、重点设备监控的变电站设备自动评价方法
CN116826976A (zh) 一种配网运行自动化监管控制系统
CN116704729A (zh) 一种基于大数据分析的工业窑炉预警系统及方法
CN116090702A (zh) 一种基于物联网的erp数据智能监管系统及方法
CN115438958A (zh) 一种基于互联网的智慧能效管理系统及其管理方法
WO2024066720A1 (zh) 指标阈值的确定方法、装置、存储介质及电子装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19937746

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19937746

Country of ref document: EP

Kind code of ref document: A1