WO2021147193A1 - 一种生成操作行为记录集的仿真方法、系统和设备 - Google Patents

一种生成操作行为记录集的仿真方法、系统和设备 Download PDF

Info

Publication number
WO2021147193A1
WO2021147193A1 PCT/CN2020/086226 CN2020086226W WO2021147193A1 WO 2021147193 A1 WO2021147193 A1 WO 2021147193A1 CN 2020086226 W CN2020086226 W CN 2020086226W WO 2021147193 A1 WO2021147193 A1 WO 2021147193A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
working condition
basic working
evaluation
operating
Prior art date
Application number
PCT/CN2020/086226
Other languages
English (en)
French (fr)
Inventor
刘煜
孙再连
梅瑜
Original Assignee
厦门邑通软件科技有限公司
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 厦门邑通软件科技有限公司 filed Critical 厦门邑通软件科技有限公司
Priority to JP2022544441A priority Critical patent/JP2023511398A/ja
Priority to EP20915151.3A priority patent/EP4095773A4/en
Priority to US17/794,306 priority patent/US20230085290A1/en
Publication of WO2021147193A1 publication Critical patent/WO2021147193A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0633—Workflow analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06398—Performance of employee with respect to a job function
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/067—Enterprise or organisation modelling
    • 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
    • Y02P80/00—Climate change mitigation technologies for sector-wide applications
    • Y02P80/10—Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier

Definitions

  • the present invention relates to the technical field of management systems, in particular to a simulation method, system and equipment for generating an operation behavior record set.
  • the core of the operating behavior record management system is to accumulate the operating experience of people or machines in various scenarios, and summarize and summarize the best experience to guide the operations of people or machines in such scenarios, so as to achieve the purpose of overall improvement.
  • the process often requires a long period of online training and learning to obtain sufficient operational knowledge to guide daily optimization operations.
  • This kind of online training is a very high application threshold for application scenarios with few human operations.
  • the current operating behavior record management system basically requires long-term online learning. It is not possible for some application scenarios with specific conditions to use the system to learn offline independently to solve the problem of obtaining new operating behavior records, making the operating behavior record management system in some areas The application of is restricted.
  • the present invention provides a simulation method, system and equipment for generating an operating behavior record set.
  • the operating behavior record management system refers to the landing scene of a type of intelligent system. This type of operating behavior record management system is aimed at the industrial field,
  • the specific landing scenarios in the service field have refined three types of data theories and specific solutions, which have realized the offline accumulation, induction and reuse of expert operating experience and worker labor skills, and realized the skills and experience in machines and systems, systems and systems.
  • the transfer between people, systems and machines, and machines and machines solves the problems of energy saving, quality control, efficiency improvement, safe operation, resource optimization and other goals, and at the same time solves the difficulty of training high-skilled workers in enterprises, high turnover, and skills of workers. Unbalanced problem.
  • a simulation method for generating operation behavior record set including:
  • the model is based on a known mapping relationship or an association relationship with industry credibility, and calculates the evaluation data of the optimization target from the basic working condition data and the operation data, and the evaluation data includes the optimization target value Or a constraining result value; specifically,
  • the constraint conditions include the following options: the calculation conditions of the evaluation data; basic engineering Constraints between the dimensions of the operating data and operating data; the reasonable range of the evaluation data defined by the basic operating data;
  • Simulation Exhaustively generate basic working condition data and operating data within a reasonable range, and calculate evaluation data through mapping or association relationships. If the constraint conditions are met, and the evaluation data is higher than the evaluation data of other operating data under the same basic working condition data in the record Better, generate new operation behavior records;
  • basic working condition data refers to factors that actually exist in the production process, such as external input, external environment, production plan, etc., that cannot be changed or are not suitable for change, and have an impact on the production process and results.
  • Operational data represents human intervention in the production process, such as the configuration of the machine, the operation of the worker on the equipment, and so on.
  • the evaluation data indicates the goal of optimization, such as energy saving and consumption reduction, quality control, efficiency improvement, safe operation, resource optimization, such as: the lower the energy consumption (target value), the better (direction), the higher the pass rate (target value), the better (Direction), the higher the molten steel rate (target value), the better (direction), the lower the ammonia escape rate (target value), the better (direction), the shorter the turnaround time (target value), the better (direction).
  • optimization such as energy saving and consumption reduction, quality control, efficiency improvement, safe operation
  • resource optimization such as: the lower the energy consumption (target value), the better (direction), the higher the pass rate (target value), the better (Direction), the higher the molten steel rate (target value), the better (direction), the lower the ammonia escape rate (target value), the better (direction), the shorter the turnaround time (target value), the better (direction).
  • the constraint conditions include compliance constraints, a negative list of operating data, and preconditions for achieving optimization goals;
  • the compliance constraint refers to a situation that violates national standards, affects product quality compliance, or has adverse effects on subsequent process flow in various result evaluation data caused by basic working condition data and operations;
  • the negative list of operating data refers to dangerous operating behaviors that should be prohibited due to equipment safety, personnel safety reasons, or other safety reasons;
  • the prerequisite for achieving the optimization goal means that the system needs to achieve the optimization goal while ensuring the prerequisites, such as reducing energy consumption on the premise that the product quality meets the standard.
  • the exit condition includes exiting from the simulated self-learning after completing the full state exhaustion.
  • the exit condition includes that the coverage rate of basic operating condition data reaches a predetermined ratio.
  • a simulation system for generating an operation behavior record set adopts the above-mentioned simulation method for generating an operation behavior record set, and includes a basic working condition data generation module, an operation data generation module, and a data analysis module.
  • the basic working condition data generating module generates basic working condition data and transmits it to the data analysis module;
  • the operating data generating module generates operating data and transmits it to the data analysis module;
  • the data analysis module prestores: reasonable intervals of each dimension of basic working condition data, operation data, and evaluation data; constraint conditions of basic working condition data, operation data, and evaluation data; self-learning exit conditions; basic working condition data, operation Data and optimization target evaluation data The mapping relationship between the optimization target or the correlation relationship with industry credibility;
  • the data analysis module exhaustively or randomly generates basic working condition data and operation data within a reasonable range, and calculates the evaluation data through the mapping relationship or the association relationship. If the constraint conditions are met, and the evaluation data is lower than the same basic working condition data in the record The evaluation data corresponding to other operation data is better, and the operation behavior record is recorded; the simulation self-learning is repeated until the exit condition is established.
  • a simulation device for generating an operation behavior record set which adopts the above-mentioned simulation method and system for generating an operation behavior record set, and includes a basic working condition data generation device, an operation data generation device, and a data analysis device;
  • the basic working condition data generating device includes various sensors for collecting data, which can generate basic working condition data and transmit it to the data analysis device;
  • the operation data generating device generates operation data and transmits it to the data analysis device;
  • the data analysis device prestores: reasonable intervals of each dimension of basic working condition data, operation data, and evaluation data; constraint conditions of basic working condition data, operation data, and evaluation data; self-learning exit conditions; basic working condition data, operation The mapping relationship between data and evaluation data or an association relationship with industry credibility;
  • the data analysis device exhaustively or randomly generates basic working condition data and operating data within a reasonable range, and calculates the evaluation data through the mapping relationship or the association relationship. If the constraint conditions are met, and the evaluation data is lower than the same basic working condition data in the record The evaluation data corresponding to other operation data is better, and the new operation behavior record is recorded; the simulation self-learning is repeated until the exit condition is established.
  • the simulation method, system and device for generating operation behavior record set proposed by the present invention have the following advantages:
  • the present invention does not rely on historical knowledge and online training, can solve the problem of fewer learning samples, and improve reliability;
  • the present invention does not rely on historical knowledge and online training, can solve the problem of long learning cycle, and reduce the time cost of online training;
  • the present invention can directly launch a well-trained system, establish an operating experience library with full coverage of working conditions and optimized objectives, and it can be practical after going online.
  • a simulation method for generating operation behavior record set the steps include:
  • S10 Establish an optimization target calculation model; the model is based on a known mapping relationship or an association relationship with industry credibility to calculate the evaluation data of the optimization target from the basic working condition data and the operation data, and the evaluation data includes optimization The target value or the result value that has a binding effect.
  • S20 Set reasonable intervals for each dimension of basic working condition data, operation data, and evaluation data, and set constraint conditions for basic working condition data, operation data, and evaluation data; the constraint conditions include the following options: the evaluation data can be calculated conditions ; Restriction conditions between each dimension data of the basic working condition data and each dimension data of the operation data; the reasonable range of the evaluation data defined by the basic working condition data.
  • the constraint conditions include compliance constraints, a negative list of operating data, and preconditions for achieving optimization goals;
  • the compliance constraints refer to various result evaluation data caused by basic operating condition data and operations, in which violations occur National standards, conditions that affect product quality standards, or have adverse effects on subsequent process flow;
  • the negative list of operating data refers to dangerous operating behaviors that should be prohibited due to equipment safety and personnel safety reasons; those that achieve optimization goals Prerequisites mean that the system needs to achieve optimization goals while guaranteeing the prerequisites.
  • S40 Exhaustively generate basic working condition data and operating data within a reasonable range, and calculate the optimization target value through the mapping or association relationship. If the constraint conditions are met, and the value of the optimization target is higher than other operating data under the same basic working condition data in the record The target value of is better, and the new operation behavior record is recorded.
  • the method of randomly generating basic working condition data and operation data may be: generating basic working condition data and operation data in a reasonable interval using an exhaustive method, that is, setting steps for each basic working condition data and operation data. Enter the length, and generate basic working condition data and operating data through exhaustive methods.
  • step S50 Repeat step S40 until the exit condition is satisfied.
  • the first embodiment is specifically applied to a simulation system for generating operation behavior record sets, including a basic working condition data generation module, an operation data generating module, and a data analysis module, which are respectively used to produce basic working condition data, operating data, and perform data analysis ,
  • Data analysis includes the generation of random data of basic working condition data and operation data, calculation of evaluation data and realization of self-learning.
  • Embodiments 1 and 2 are specifically applied to a simulation device for generating operating behavior record sets, including a basic operating condition data generating device, an operating data generating device, and a data analysis device, which are used to collect basic operating condition data, operating data, and data, respectively Analysis, data analysis includes the generation of random data of basic working condition data and operating data, calculation of evaluation data and realization of self-learning.
  • the first embodiment is specifically applied to the scene of repairing the imbalance of engine blades.
  • the number of 4-9 stages of the engine's rotor blades are 68, 75, 82, 82, 80, and 76 respectively.
  • the dynamic unbalance machine can detect the magnitude and the unbalance force on the 4th and 9th stages of the rotor plane. direction.
  • each rotor blade can add 1 patch, the weight is 1.3 grams or 2 grams, and the rotor radius is 8.28 and 8.33 inches. The goal is to obtain a reasonable correction plan to make the rotor plane force and axial force less than Settings.
  • the re-test result of the dynamic unbalance machine that is, the dynamic unbalance force of level 4 and 9 is less than 5 grams-inch;
  • the total weight of the patch placed for a single rotor repair at one time is not more than 10 grams.
  • the simulation process is as follows:
  • the initial unbalance force of the 4th and 9th grade rotors is 0-200 gram-inch, the accuracy is 1 gram-inch, the direction is between 0-360 degrees, and the accuracy is 1 degree.
  • Operating data The number of rotor blades added: 6 rotors, each rotor can choose 0-7 blades, and the selected blade is placed with 1 patch (1.3g or 2g).
  • Evaluation data the repaired result, that is, the projection of the resultant force on the 4th and 9th rotors.
  • the dynamic unbalance force of level 4 and level 9 (the projection of the resultant force on the level 4 and level 9 rotors) is less than 5 grams inches; the less rotors involved in the correction scheme, the better; the number of rotors involved in the correction scheme At the same time, the smaller the total number of patches, the better.
  • Step 1 Exhaust the initial unbalance detection value.
  • Step 2 For the current initial unbalance detection value, set the counter of the reasonable plan to zero;
  • Step 3 Randomly generate a correction plan.
  • Step 4 Calculate the direction and magnitude of the resultant force, calculate the projection of the resultant force on the 4th and 9th level rotor plane; if both projections are less than 5 grams inches, save the correction plan to the reasonable operation record set corresponding to the current initial unbalance detection value , The reasonable plan counter increases by one.
  • Step 5 If the reasonable solution counter is less than 20, go to step 3. Otherwise, if the exhaustion is not over, take the initial unbalance detection value and go to step 2. If the exhaustion is over, go to step 6.
  • Step 6 The simulation process ends.
  • Basic working condition data molten iron temperature, molten iron weight, molten iron sulfur content, target value of molten iron sulfur content after desulfurization
  • Evaluation data Under the condition that the sulfur content reaches the standard after desulfurization, the lower the consumption of passivated magnesium, the better.
  • Constraints The ratio of the injection volume of passivated magnesium to the injection volume of passivated lime is the set value.
  • Sulfur content after desulfurization% sulfur content before desulfurization%-passivation magnesium injection volume/(hot metal volume * passivation magnesium unit consumption)
  • the injection volume of passivated lime is calculated from the injection volume of passivated lime according to the specified ratio.
  • Step 1 Randomly generate basic working condition data and operation data
  • Step 2 Calculate the sulfur content after desulfurization. If the sulfur content after desulfurization is less than the target value of sulfur content after desulfurization, add the basic working condition data, operation data, and target data to the record set.
  • Step 3 If the basic working condition data coverage rate reaches 90% or more, go to step 4, otherwise go to step 1.
  • Step 4 The simulation process ends.
  • Embodiment 6 is a diagrammatic representation of Embodiment 6
  • Operating data working status of a single electromagnetic field (secondary voltage, secondary current, power supply mode, pulse frequency)
  • the dust concentration of the outlet flue gas can be calculated.
  • This model has a certain error. When using this model, the calculation error should be considered.
  • the inlet flue gas flow rate ranges from 2 to 3 million m3/h, with an accuracy of 10,000 m3/h;
  • inlet flue gas concentration 2000-3000mg/Nm3, and the accuracy is 50mg/Nm3;
  • the number of electromagnetic fields and the sequence of electromagnetic fields are fixed.
  • the range of secondary voltage is 0-100%, and the accuracy is 1%;
  • the range of secondary current is 80-100A, and the accuracy is 1A;
  • the power supply mode is DC power supply ⁇ pulse power supply
  • Pulse frequency power supply 10-40 milliseconds, power-off 10-40 milliseconds, precision 10 milliseconds.
  • the outlet soot concentration is less than the configured value, which is lower than the national emission standard minus the calculation error.
  • Step 1 Randomly generate basic working condition data and operation data
  • Step 2 Calculate the outlet smoke and dust concentration. If the outlet smoke and dust concentration is less than the configured value, add the basic working condition data, operation data, and target data to the record set.
  • Step 3 If the basic working condition data coverage rate reaches 80% or more, go to step 4, otherwise go to step 1.
  • Step 4 The simulation process ends.
  • the simulation method for generating operation behavior record set proposed by the present invention has the following advantages:
  • This method does not rely on historical knowledge and online training, and can solve the problem of fewer learning samples
  • This method does not rely on historical knowledge and online training, which can reduce the time cost of online training;
  • This method can directly launch a well-trained system, establish an operating experience library with full coverage of working conditions and optimized objectives, and it will be practical when it is launched.

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种生成操作行为记录集的仿真方法、系统和设备。传统的操作行为记录集通常是实际发生过的，有积累周期长的弊端。该方法针对具备评价数据可计算的情况，对基础工况数据、操作行为数据进行仿真，结合计算出的评价数据，形成包含基础工况数据、操作数据和评价数据的完整的操作行为记录，实现快速积累操作行为记录，针对工业和服务领域的具体落地场景，实现专家操作经验、工人劳动技能的线下积累、归纳和再利用，实现了技能与经验在机器与系统、系统与人、系统与机器、机器与机器之间的转移，在解决节能降耗、品质控制、提升效率、安全运行、资源优化等目标的同时，解决了企业高技能工人培养难、流失高、工人技能不平衡的难题。

Description

一种生成操作行为记录集的仿真方法、系统和设备 技术领域
本发明涉及管理系统技术领域，尤其涉及一种生成操作行为记录集的仿真方法、系统和设备。
背景技术
操作行为记录管理系统的核心是积累人或机器在各类情景下的操作经验，归纳、总结出最优秀经验用来指导人或机器在该类情景下的操作，从而达到整体提升的目的，这个过程往往需要一段较长时间的在线训练学习，才能获得充足的操作知识来指导日常优化操作。这种在线训练对于人为操作次数少的应用场景是个很高的应用门槛。
目前的操作行为记录管理系统，基本都是需要长时间在线学习，无法针对一些具备特定条件的应用场景，通过系统离线自主学习，解决新操作行为记录获取问题，使得操作行为记录管理系统在一些领域的应用受到限制。
发明内容
本发明提供了一种生成操作行为记录集的仿真方法、系统和设备，其中所述操作行为记录管理系统是指一类智能化系统的落地场景，这类操作行为记录管理系统，针对工业领域、服务领域的具体落地场景，提炼出了三类数据理论和具体解决方案，实现了专家操作经验、工人劳动技能的线下积累、归纳和再利用，实现了技能与经验在机器与系统、系统与人、系统与机器、机器与机器之间的转移，在解决节能降耗、品质控制、提升效率、安全运行、资源优化等目标的同时，解决了企业高技能工人培养难、流失高、工人技能不平衡的难题。
一种生成操作行为记录集的仿真方法，包括：
建立优化目标计算模型；所述模型是根据已知的映射关系或者是具有行业公信力的关联关系，由基础工况数据和操作数据计算所述优化目标的评价数据，所述评价数据包括优化目标值或具有约束作用的结果值；具体的，
设置基础工况数据、操作数据、评价数据各维度的合理区间，设置基础工况数据、操作数据、评价数据的约束条件；所述约束条件包括下列可选项：评价数据的可计算条件；基础工况数据、操作数据各维度数据之间的制约条件；基础工况数据限定的评价数据的合理范围；
建立退出条件；
仿真：在合理区间内穷举生成基础工况数据和操作数据，通过映射关系或者关联关系计算评价数据，如果符合约束条件，且评价数据比记录中同一基础工况数据下其它操作数据的 评价数据较优，产生新操作行为记录；
重复仿真，直到退出条件成立。
本申请中，基础工况数据，表示外来输入、外部环境、生产计划等生产过程中现实存在的、不可改变或不太适合改变的、对生产过程和结果有影响的一类因素。
操作数据代表人对生产过程的干预，如机台的配置、工人对设备的操控动作等。
评价数据表示优化的目标，如节能降耗、品质控制、提升效率、安全运行、资源优化，如：能耗(目标值)越低越好(方向)、合格率(目标值)越高越好(方向)、出钢水率(目标值)越高越好(方向)、氨逃逸率(目标值)越低越好(方向)、周转时长(目标值)越短越好(方向)。
进一步的，所述约束条件包括合规约束、操作数据的负面清单和达成优化目标的前提条件；
其中，所述合规约束是指由基础工况数据和操作引起的各种结果评价数据中，出现违反国家标准、影响产品质量达标或对后续工艺流程有不良影响的情况；
所述操作数据的负面清单是指因设备安全、人员安全原因或其它安全原因而应该禁止的、危险的操作行为；
所述达成优化目标的前提条件是指系统需要在保障前提条件的情况下实现优化目标，如在产品质量达标的前提下降低能耗。
进一步的，在合理区间内使用穷举的方式生成基础工况数据和操作数据，即对各基础工况数据和操作数据设置步进长度，并通过穷举方式生成基础工况数据和操作数据,计算每组基础工况数据和操作数据对应的评价数据，如果符合约束条件，且评价数据比记录中同一基础工况数据下其它操作数据对应的的评价数据较优，产生新操作行为记录。
进一步的，所述退出条件包括完成全状态穷举后退出仿真式自学习。
进一步的，在合理区间内随机生成基础工况数据和操作数据，通过映射关系或者关联关系计算评价数据，如果符合约束条件，且评价数据比记录中同一基础工况下其它操作数据对应的的评价数据较优，产生新操作行为记录。
进一步的，所述退出条件包括基础工况数据覆盖率达到预定比例。
一种生成操作行为记录集的仿真系统，采用上述的生成操作行为记录集的仿真方法，包括基础工况数据生成模块、操作数据生成模块和数据分析模块。
所述基础工况数据生成模块生成基础工况数据，并传送给数据分析模块；
所述操作数据生成模块生成操作数据，并传送给数据分析模块；
所述数据分析模块预存有：基础工况数据、操作数据和评价数据的各维度的合理区间； 基础工况数据、操作数据、评价数据的约束条件；自学习退出条件；基础工况数据、操作数据和优化目标的评价数据三者之间优化目标的映射关系或者是具有行业公信力的关联关系；
所述数据分析模块在合理区间内穷举或随机生成基础工况数据和操作数据，并通过映射关系或者关联关系计算评价数据，如果符合约束条件，且评价数据比记录中同一基础工况数据下其它操作数据对应的的评价数据较优，记录操作行为记录；重复仿真式自学习，直到退出条件成立。
一种生成操作行为记录集的仿真设备，采用上述的生成操作行为记录集的仿真方法和系统，包括基础工况数据生成装置、操作数据生成装置和数据分析装置；
所述基础工况数据生成装置包括各种用于采集数据的传感器，能够生成基础工况数据，并传送到所述数据分析装置；
所述操作数据生成装置生成操作数据，并传送到所述数据分析装置；
所述数据分析装置预存有：基础工况数据、操作数据和评价数据的各维度的合理区间；基础工况数据、操作数据、评价数据的约束条件；自学习退出条件；基础工况数据、操作数据和评价数据三者之间的映射关系或者是具有行业公信力的关联关系；
所述数据分析装置在合理区间内穷举或随机生成基础工况数据和操作数据，并通过映射关系或者关联关系计算评价数据，如果符合约束条件，且评价数据比记录中同一基础工况数据下其它操作数据对应的的评价数据较优，记录新操作行为记录；重复仿真式自学习，直到退出条件成立。
由上述对本发明的描述可知，和现有技术相比，本发明提出的一种生成操作行为记录集的仿真方法、系统和设备具有如下优点：
1、本发明不依赖历史知识和在线训练，可解决学习样本少的问题，可靠度得到提高；
2、本发明不依赖历史知识和在线训练，可解决学习周期长问题，降低在线训练的时间成本；
3、本发明可直接推出训练完备的系统，建立工况全覆盖、目标最优化的操作经验库，上线即可实用。
具体实施方式
为了使本发明所要解决的技术问题、技术方案及有益效果更加清楚、明白，以下结合实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。
实施例一：
一种生成操作行为记录集的仿真方法，步骤包括：
S10：建立优化目标计算模型；所述模型是根据已知的映射关系或者是具有行业公信力的关联关系，由基础工况数据和操作数据计算所述优化目标的评价数据，所述评价数据包括优化目标值或具有约束作用的结果值。
S20：设置基础工况数据、操作数据、评价数据的各维度的合理区间，设置基础工况数据、操作数据、评价数据的约束条件；所述约束条件包括下列可选项：评价数据的可计算条件；基础工况数据各维度数据、操作数据各维度数据之间的制约条件；由基础工况数据限定的评价数据的合理范围。
具体的，所述约束条件包括合规约束、操作数据的负面清单和达成优化目标的前提条件；所述合规约束是指由基础工况数据和操作引起的各种结果评价数据中，出现违反国家标准、影响产品质量达标或对后续工艺流程有不良影响的情况；所述操作数据的负面清单是指因设备安全、人员安全原因而应该禁止的、危险的操作行为；所述达成优化目标的前提条件是指系统需要在保障前提条件的情况下实现优化目标。
S30：建立退出条件，例如基础工况数据覆盖率达到预定比例；
S40：在合理区间内穷举生成基础工况数据和操作数据，通过映射关系或者关联关系计算优化目标值，如果符合约束条件，且优化目标的值比记录中同一基础工况数据下其它操作数据的目标值较优，记录新操作行为记录。
在其它实施例中，基础工况数据和操作数据的随机生成方式可以是：在合理区间内使用穷举的方式生成基础工况数据和操作数据，即对各基础工况数据和操作数据设置步进长度，并通过穷举方式生成基础工况数据和操作数据。
S50：重复步骤S40，直到退出条件成立。
实施例二：
将实施例一具体应用于一种生成操作行为记录集的仿真系统，包括基础工况数据生成模块、操作数据生成模块和数据分析模块，分别用于生产基础工况数据、操作数据和进行数据分析，数据分析包括基础工况数据和操作数据的随机数据的生成、计算评价数据并实现自学习。
实施例三：
将实施例一和二具体应用于一种生成操作行为记录集的仿真设备，包括基础工况数据生成装置、操作数据生成装置和数据分析装置，分别用于采集基础工况数据、操作数据和数据分析，数据分析包括基础工况数据和操作数据的随机数据的生成、计算评价数据并实现自学习。
实施例四：
将实施例一具体应用于发动机叶片不平衡修补场景中。
某型发动机叶片动不平衡修正：
该发动机的4-9级转子叶片个数分别为68、75、82、82、80、76片，动不平衡机可以检测出在第4和第9级转子平面上的不平衡力的大小和方向。
已知各转子每个叶片都可以加1个贴片，重量为1.3克或2克，转子半径为8.28、8.33英寸，目标是获得一种合理的修正方案，使转子平面合力、轴向合力小于设置值。
操作行为记录管理系统的三类数据及约束条件：
1、基础工况数据：
动不平衡机检测的第4和第9级转子平面上的不平衡力的大小和方向；
2、操作数据：
第4–9级转子上贴片的放置方案；
3、评价数据：
优化目标和方向：
动不平衡机再次检测结果，即4级、9级的动不平衡力小于5克英寸；
修正方案涉及的转子越少越好；
修正方案涉及的转子数相同时，总贴片数越少越好。
4、约束条件：
单个转子一次修复放置的贴片总重量不大于10克。
仿真流程如下：
1、建立评价数据计算模型；
问题的分析：
1)这是个力的分解问题，分解的可能性巨大，其合理的解空间也较大，企业目前是技工凭经验估算，通常需要较多次数试验才能达到要求。
2)力的合成，其结果是唯一的，即对任何一种维修方案，都可以通过力学公式计算出合力方向和大小，且结果是唯一的。
2、设置三类数据各维度的合理区间
基础工况数据：4级和9级转子的初始不平衡力在0～200克英寸，精度为1克英寸，方向在0–360度之间，精度为1度。
操作数据：转子添加叶片数：6个转子，每个转子可选择0–7个叶片，选中的叶片放置1个贴片(1.3克或2克)。
评价数据：修复后的结果，即合力在4级和9级转子上的投影。
优化目标和方向：4级、9级的动不平衡力(合力在4级和9级转子上的投影)小于5克英寸；修正方案涉及的转子越少越好；修正方案涉及的转子数相同时，总贴片数越少越好。
3、建立退出条件：穷举完基础工况数据。
4、仿真式自主学习
步骤1：穷举初始不平衡检测值。
步骤2：针对当前的初始不平衡检测值，合理方案计数器设置零；
步骤3：随机生成一种修正方案。
步骤4：计算合力方向和大小，计算合力在4级、9级转子平面的投影；如果两个投影均小于5克英寸，把该修正方案保存到当前初始不平衡检测值对应的合理操作记录集中，合理方案计数器加一。
步骤5：如果合理方案计数器小于20，转步骤3，否则如果穷举未结束，取下一个初始不平衡检测值并转步骤2，如果穷举结束，转步骤6。
步骤6：仿真过程结束。
实施例五：
将本申请提出的方案应用于炼钢流程中的铁水预脱硫。
操作行为记录管理系统的三类数据：
基础工况数据：铁水温度、铁水重量、铁水硫成分、脱硫后铁水硫成分目标值
操作数据：钝化镁喷吹量、钝化石灰喷吹量
评价数据：优化目标：在脱硫后硫含量达标的条件下，钝化镁消耗量越低越好。
约束条件：钝化镁喷吹量和钝化石灰喷吹量之比为设定值。
仿真流程：
1、建立评价数据计算模型；
1)按铁水温度分级
2)评价指标之一：脱硫后硫含量计算公式
脱硫后硫含量％＝脱硫前硫含量％-钝化镁喷吹量/(铁水量*钝化镁单位消耗量)
3)评价指标之二：优化目标值——钝化镁消耗量
注释：
1)钝化镁消耗量＝钝化镁喷吹量
2)钝化镁单位消耗量，即当前铁水温度下，每吨铁水降低1％的硫需要的钝化镁喷吹量，该数据可以通过实验获得。
2、设置三类数据各维度的合理区间：
基础工况数据：
数据维度 数据范围 精度
铁水温度 1210–1450度 10度
铁水重量 80–90吨 0.1吨
铁水硫成分 0.01％-0.08％ 0.01％
脱硫后铁水硫成分目标值 常用的10个目标值 0.01％
操作数据：
钝化镁喷吹量，数据范围：80–120公斤，精度：1公斤。
钝化石灰喷吹量按指定比例由钝化石灰喷吹量计算。
评价数据：脱硫后硫含量。
3、建立退出条件；基础工况数据覆盖率达到90％以上。
4、仿真式自主学习
步骤1：随机生成基础工况数据、操作数据
步骤2：计算脱硫后硫含量，如果脱硫后硫含量小于脱硫后硫含量目标值，把基础工况数据、操作数据、目标数据加入到记录集中。
步骤3：如果基础工况数据覆盖率达到90％以上转步骤4，否则转步骤1。
步骤4：仿真过程结束。
实施例六：
将本申请提出的方案应用于烟气的电除尘器。
操作行为记录管理系统的三类数据：
基础工况数据：入口烟气流量、入口烟气浓度、电磁场数量、电磁场排列次序
操作数据：单个电磁场的工作状态(二次电压、二次电流、供电方式、脉冲频率)
3、评价数据：出口烟尘浓度、各电磁场总功率
优化目标：在出口烟尘浓度达标条件下各电磁场总功率越低越好。
4、约束条件：出口烟尘浓度低于国家标准。
仿真流程：
1、建立评价数据计算模型；
电除尘器厂商可以通过实验获得如下经验值：
1)单个电磁场在各种状态(二次电压、二次电流、脉冲频率)下粉尘的脱除率；
2)各级电磁场的粉尘的脱除率的逐级递减系数。
根据上述经验值和入口烟气浓度、电磁场数量、电磁场排列次序及电磁场状态，可计算出出口烟气的粉尘浓度。
说明：该模型有一定的误差，使用该模型时，要考虑计算误差。
2、设置三类数据各维度的合理区间
基础工况数据：
入口烟气流量的范围200-300万m3/h，精度1万m3/h；
入口烟气浓度的范围2000–3000mg/Nm3，精度50mg/Nm3；
在特定场景中，电磁场数量、电磁场排列次序是固定的。
操作数据：
单个电磁场的工作状态
二次电压的范围0–100％，精度1％；
二次电流的范围80–100A，精度1A；
供电方式为直流供电\脉冲供电；
脉冲频率：供电10–40毫秒，断电10-40毫秒，精度10毫秒。
评价数据：
出口烟尘浓度
约束条件：
出口烟尘浓度小于配置值，该配置值要低于国家排放标准减计算误差。
3、建立退出条件：基础工况数据覆盖率达到80％以上。
4、仿真式自主学习
步骤1：随机生成基础工况数据、操作数据
步骤2：计算出口烟尘浓度，如果出口烟尘浓度小于配置值，把基础工况数据、操作数据、目标数据加入到记录集中。
步骤3：如果基础工况数据覆盖率达到80％以上转步骤4，否则转步骤1。
步骤4：仿真过程结束。
由上述对本发明的描述可知，和现有技术相比，本发明提出的一种生成操作行为记录集的仿真方法具有如下优点：
1、本方法不依赖历史知识和在线训练，可解决学习样本少的问题；
2、本方法不依赖历史知识和在线训练，可降低在线训练的时间成本；
3、本方法可直接推出训练完备的系统，建立工况全覆盖、目标最优化的操作经验库，上 线即可实用。
上面结合实施例对本发明进行了示例性描述，显然本发明具体实现并不受上述方式的限制，只要采用了本发明的方法构思和技术方案进行的各种非实质性的改进，或未经改进将本发明的构思和技术方案直接应用于其它场合的，均在本发明的保护范围之内。

Claims (8)

  1. 一种生成操作行为记录集的仿真方法，其特征在于，所述方法包括：
    建立优化目标计算模型；所述模型是根据已知的映射关系或者是具有行业公信力的关联关系，由基础工况数据和操作数据计算优化目标的评价数据，所述评价数据包括优化目标值或具有约束作用的结果值；
    设置基础工况数据、操作数据、评价数据各维度的合理区间；设置基础工况数据、操作数据、评价数据的约束条件；所述约束条件包括评价数据的可计算条件，基础工况数据、操作数据各维度数据之间的制约条件，基础工况限定的评价数据的合理范围；建立退出条件；
    在合理区间内穷举生成基础工况数据和操作数据，通过映射关系或者关联关系计算评价数据，如果符合约束条件，且评价数据比记录中同一基础工况下其它操作数据对应的的评价数据较优，产生新操作行为记录；
    重复上述流程，直到退出条件成立。
  2. 根据权利要求1所述的一种生成操作行为记录集的仿真方法，其特征在于，所述约束条件包括合规约束、操作数据的负面清单和达成优化目标的前提条件；
    所述合规约束是指由基础工况数据和操作数据引起的各种结果评价数据中，出现违反国家标准、影响产品质量达标或对后续工艺流程有不良影响的情况；
    所述操作数据的负面清单是指因设备安全、人员安全原因而应该禁止的、危险的操作行为；
    所述达成优化目标的前提条件是指在保障前提条件的情况下实现优化目标。
  3. 根据权利要求1或2所述的一种生成操作行为记录集的仿真方法，其特征在于，在合理区间内使用穷举的方式生成基础工况数据和操作数据，即对各基础工况数据和操作数据设置步进长度，并通过穷举方式生成基础工况数据和操作数据,计算每组基础工况数据和操作数据对应的评价数据，如果符合约束条件，且评价数据比记录中同一基础工况下其它操作数据对应的的评价数据较优，产生新操作行为记录。
  4. 根据权利要求3所述的一种生成操作行为记录集的仿真方法，其特征在于，所述退出条件包括完成全状态穷举后退出仿真式自学习。
  5. 根据权利要求1或2所述的一种生成操作行为记录集的仿真方法，其特征在于，在合理区间内随机生成基础工况数据和操作数据，通过映射关系或者关联关系计算评价数据，如果符合约束条件，且评价数据比记录中同一基础工况下其它操作数据对应的的评价数据较优，产生新操作行为记录。
  6. 根据权利要求5所述的一种生成操作行为记录集的仿真方法，其特征在于，所述退出条件包括基础工况覆盖率达到预定比例。
  7. 一种生成操作行为记录集的仿真系统，其特征在于，采用权利要求1到6任一项所述的一种生成操作行为记录集的仿真方法，包括：基础工况数据生成模块、操作数据生成模块和数据分析模块；
    所述基础工况数据生成模块生成基础工况数据，并传送到所述数据分析模块；
    所述操作数据生成模块生成操作数据，并传送到所述数据分析模块；
    所述数据分析模块预存有：基础工况数据、操作数据和评价数据的各维度数据的合理区间；基础工况数据、操作数据、评价数据的约束条件；自学习退出条件；基础工况数据、操作数据和评价数据三者之间的映射关系或者是具有行业公信力的关联关系；
    所述数据分析模块在合理区间内穷举或随机生成基础工况数据和操作数据，并通过映射关系或者关联关系计算评价数据，如果符合约束条件，且评价数据比记录中同一基础工况数据下其它操作数据对应的的评价数据较优，记录新操作行为记录；重复仿真式自学习，直到退出条件成立。
  8. 一种生成操作行为记录集的仿真设备，其特征在于，采用权利要求1到6任一项所述的一种生成操作行为记录集的仿真方法，包括基础工况数据生成装置、操作数据生成装置和数据分析装置；
    所述基础工况数据生成装置生成基础工况数据，并传送到所述数据分析装置；
    所述操作数据生成装置生成操作数据，并传送到所述数据分析装置；
    所述数据分析装置预存有：基础工况数据、操作数据和评价数据的各维度数据的合理区间；基础工况数据、操作数据、评价数据的约束条件；自学习退出条件；基础工况数据、操作数据和评价数据三者之间的映射关系或者是具有行业公信力的关联关系；
    所述数据分析装置在合理区间内穷举或随机生成基础工况数据和操作数据，并通过映射关系或者关联关系计算评价数据，如果符合约束条件，且评价数据比记录中同一基础工况数据下其它操作数据对应的的评价数据较优，记录新操作行为记录；重复仿真式自学习，直到退出条件成立。
PCT/CN2020/086226 2020-01-21 2020-04-22 一种生成操作行为记录集的仿真方法、系统和设备 WO2021147193A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2022544441A JP2023511398A (ja) 2020-01-21 2020-04-22 操業アクション記録セットを生成するためのシミュレーション方法、システム及び設備
EP20915151.3A EP4095773A4 (en) 2020-01-21 2020-04-22 SIMULATION METHOD, SYSTEM AND DEVICE FOR GENERATING A SET OF OPERATIONAL BEHAVIOR RECORDS
US17/794,306 US20230085290A1 (en) 2020-01-21 2020-04-22 Simulation method, system, and device for generating operational behavior record set

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010071981.4 2020-01-21
CN202010071981.4A CN113222307A (zh) 2020-01-21 2020-01-21 一种生成操作行为记录集的仿真方法、系统和设备

Publications (1)

Publication Number Publication Date
WO2021147193A1 true WO2021147193A1 (zh) 2021-07-29

Family

ID=76993124

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/086226 WO2021147193A1 (zh) 2020-01-21 2020-04-22 一种生成操作行为记录集的仿真方法、系统和设备

Country Status (5)

Country Link
US (1) US20230085290A1 (zh)
EP (1) EP4095773A4 (zh)
JP (1) JP2023511398A (zh)
CN (1) CN113222307A (zh)
WO (1) WO2021147193A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113991700A (zh) * 2021-10-22 2022-01-28 中国大唐集团科学技术研究总院有限公司华东电力试验研究院 基于历史数据的一次调频优化决策方法及装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130159208A1 (en) * 2011-12-19 2013-06-20 Byung Jun Song Shipper-oriented logistics base optimization system
CN105117341A (zh) * 2015-09-06 2015-12-02 电子科技大学 一种基于动态符号执行的分布式自动测试案例生成方法
CN108234169A (zh) * 2016-12-15 2018-06-29 北京仿真中心 一种分布式仿真网络结构实时动态优化方法
CN109145352A (zh) * 2017-06-16 2019-01-04 达索系统公司 用于学习取图像作为输入的函数的数据集
CN109609887A (zh) * 2019-02-11 2019-04-12 北京联合涂层技术有限公司 一种热喷涂方法及系统

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH093556A (ja) * 1995-06-20 1997-01-07 Nippon Steel Corp 焼結機における操業変更アクション決定方法とその装置
JP2005115560A (ja) * 2003-10-06 2005-04-28 Micron Seimitsu Kk センタレス研削機の制御プログラム、及びセンタレス研削機の調節方法
JP5715004B2 (ja) * 2011-08-11 2015-05-07 株式会社神戸製鋼所 最適解探索装置
JP6816949B2 (ja) * 2014-11-26 2021-01-20 ゼネラル・エレクトリック・カンパニイ 発電プラント発電ユニットの制御を強化するための方法
WO2016198047A1 (de) * 2015-06-10 2016-12-15 Fev Gmbh Verfahren für die erstellung eines simulationsmodells zur abbildung zumindest eines funktionalen prozesses einer antriebstrangkomponente
CN105183993B (zh) * 2015-09-09 2018-04-24 哈尔滨工业大学 一种电磁轨道炮综合仿真平台及方法
US10732621B2 (en) * 2016-05-09 2020-08-04 Strong Force Iot Portfolio 2016, Llc Methods and systems for process adaptation in an internet of things downstream oil and gas environment
US10908602B2 (en) * 2017-08-02 2021-02-02 Strong Force Iot Portfolio 2016, Llc Systems and methods for network-sensitive data collection
CN110059348B (zh) * 2019-03-12 2023-04-25 南京工程学院 一种轴向分相磁悬浮飞轮电机悬浮力数值建模方法
CN110532613B (zh) * 2019-07-26 2023-05-02 中国船舶重工集团公司第七一九研究所 船舶动力系统运行工况识别方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130159208A1 (en) * 2011-12-19 2013-06-20 Byung Jun Song Shipper-oriented logistics base optimization system
CN105117341A (zh) * 2015-09-06 2015-12-02 电子科技大学 一种基于动态符号执行的分布式自动测试案例生成方法
CN108234169A (zh) * 2016-12-15 2018-06-29 北京仿真中心 一种分布式仿真网络结构实时动态优化方法
CN109145352A (zh) * 2017-06-16 2019-01-04 达索系统公司 用于学习取图像作为输入的函数的数据集
CN109609887A (zh) * 2019-02-11 2019-04-12 北京联合涂层技术有限公司 一种热喷涂方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4095773A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113991700A (zh) * 2021-10-22 2022-01-28 中国大唐集团科学技术研究总院有限公司华东电力试验研究院 基于历史数据的一次调频优化决策方法及装置
CN113991700B (zh) * 2021-10-22 2024-03-12 中国大唐集团科学技术研究总院有限公司华东电力试验研究院 基于历史数据的一次调频优化决策方法及装置

Also Published As

Publication number Publication date
EP4095773A4 (en) 2024-02-21
CN113222307A (zh) 2021-08-06
JP2023511398A (ja) 2023-03-17
US20230085290A1 (en) 2023-03-16
EP4095773A1 (en) 2022-11-30

Similar Documents

Publication Publication Date Title
RU2013130996A (ru) Оптимизированное интегрированное управление для электростанции, работающей на сжигании кислородного топлива
Xie et al. Robust stochastic configuration network multi-output modeling of molten iron quality in blast furnace ironmaking
WO2021147193A1 (zh) 一种生成操作行为记录集的仿真方法、系统和设备
CN105205730A (zh) 一种火电厂典型环保工程环境与经济性能的综合评价方法
CN101109950A (zh) 高炉生产过程控制信息智能化系统
CN110445787A (zh) 基于dhr架构拟态防御平台的异构性测试装置及方法
CN105354350A (zh) 火电厂烟气脱硝scr催化剂全过程管理模式的构建实施方法
CN115738622B (zh) 一种脱硫设备的尾气排放检测系统
CN103559543A (zh) 一种高炉煤气发生量的预测方法及装置
US20070282588A1 (en) Electric power system training simulation software and process for electric power system training
CN102592004B (zh) 钢铁联合企业全工序能况在线分析诊断系统及方法
CN103996146A (zh) 一种炼钢-连铸生产的调度系统及方法
JP5621414B2 (ja) 設備管理方法
CN103400515B (zh) 一种用于塔机操作培训的虚拟考核评分装置和方法
CN106979327A (zh) 一种液力耦合器多档位调速和设备安全运行控制系统及其实现方法
CN110197037A (zh) 基于奇异值分解的机器人的动力学参数辨识方法及系统
CN106202974A (zh) 一种火电机组锅炉燃烧优化控制效果评估计算方法
CN106094572A (zh) 一种源侧涉网生产试验闭环仿真辨识应用方法
CN208104457U (zh) 一种防止转炉冶炼煤气泄爆的自动控制系统
DE19748315B4 (de) Verfahren zur Optimierung des Betriebes von fossil befeuerten Kraftwerksanlagen
CN110206675A (zh) 一种水轮机功率模式静态试验仿真测试仪及使用方法
CN104451012B (zh) 高炉软水密闭循环系统的膨胀罐液位故障检测软测量方法
JP2004021291A (ja) 運転訓練用シミュレータシステム
KR20110047025A (ko) 제철소 설비의 운전 교육 시스템의 제어방법
Xie et al. Research and Application of Maintenance Scheme Evaluating Model in Hot-Blast Stove

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: 20915151

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022544441

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020915151

Country of ref document: EP

Effective date: 20220822