WO2020140564A1 - 一种基于仿真技术的空气压缩机群组优化调度决策方法 - Google Patents

一种基于仿真技术的空气压缩机群组优化调度决策方法 Download PDF

Info

Publication number
WO2020140564A1
WO2020140564A1 PCT/CN2019/112956 CN2019112956W WO2020140564A1 WO 2020140564 A1 WO2020140564 A1 WO 2020140564A1 CN 2019112956 W CN2019112956 W CN 2019112956W WO 2020140564 A1 WO2020140564 A1 WO 2020140564A1
Authority
WO
WIPO (PCT)
Prior art keywords
air compressor
air
group
scheduling
compressor group
Prior art date
Application number
PCT/CN2019/112956
Other languages
English (en)
French (fr)
Inventor
赵珺
刘洋
周帆
韩中洋
王霖青
王伟
Original Assignee
大连理工大学
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 大连理工大学 filed Critical 大连理工大学
Publication of WO2020140564A1 publication Critical patent/WO2020140564A1/zh
Priority to US16/928,672 priority Critical patent/US11126765B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/048—Fuzzy inferencing
    • 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
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/0275—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using fuzzy logic only
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/08—Computing arrangements based on specific mathematical models using chaos models or non-linear system models
    • 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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/04—Constraint-based CAD
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2111/00—Details relating to CAD techniques
    • G06F2111/10—Numerical modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/06—Power analysis or power optimisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
    • 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
    • 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
    • Y02P90/80—Management or planning
    • Y02P90/82—Energy audits or management systems therefor

Definitions

  • the invention belongs to the field of information technology and relates to data-based dynamic modeling of air compressors, energy efficiency evaluation of air compressor groups based on equivalent electricity, optimization and solution of air compressor combination models based on depth-first tree search algorithm, and preference-based
  • the theory of intelligent optimization of information is a decision-making method of air compressor group optimization scheduling based on simulation technology.
  • the present invention uses expert experience to construct an air compressor energy consumption model sample set, and uses the least squares algorithm to learn the relevant parameters of the air compressor energy consumption model; then the maximum energy conversion efficiency based on equivalent electricity and the minimum economic cost are taken as the objective functions, Application of simulation technology and depth-first tree search algorithm to solve multi-objective optimal scheduling model of air compressor group; Finally, fuzzy logic theory is used to describe the preferences of decision makers, and introduced into interactive decision-making, so as to assist production staff to develop safe, economic, Efficient and environmentally friendly operation scheme, to achieve the operation mode of maximizing the use of air compressor group resources. This method also has wide application value in different industrial fields.
  • the air compressor has the characteristics of simple structure, small system maintenance, and low price of components. It is the main power source for industrial production processes such as metallurgy, industrial manufacturing, and biopharmaceuticals. With the increasingly severe energy situation in my country, the evaluation of energy-saving potential and the decision-making of optimal dispatching have become more and more important for enterprises and researchers.
  • the air compressor group is a complex system with time-varying, time-lag and nonlinearity. Due to the unreasonable and untimely scheduling of the unit, the air compression system has low resource utilization rate and high energy consumption, and there is a large space for energy saving.
  • the reasonable evaluation of energy saving potential and optimal scheduling of air compressor units can achieve structural optimization of the production resources of the air compression system, meet the gas demand of different production users, and provide basic support for production safety, energy saving and consumption reduction; on the other hand It can also improve the overall operating efficiency of the air compressor unit, and make the air compressor unit run at the best working point as much as possible, so as to improve the energy saving and economy of the air compression system.
  • the common air compressor group scheduling is a non-linear, non-convex, high-dimensional, multi-constrained complex optimization problem.
  • Related solutions-intelligent search algorithms are usually divided into three categories: (1) breadth-first search.
  • the algorithm is also called width-first search or horizontal-first search, and it traverses all nodes of the tree along the width of the tree.
  • Existing results include distributed constrained optimization based on breadth-first tree search (Chen, Ziyu, et al. (2017).
  • An improved DPOP algorithm based on breadth first search pseudo-tree distributed for optimization optimization. Applied Intelligence, 47, 607-623. ), parallel distributed breadth-first search applied to Kepler structure (Bisson, M., et.al. (2016).
  • Depth-first tree search The purpose of this algorithm is to reach all nodes of the searched structure.
  • Existing results include an optimized Bayesian network triangulation (Li, C., et.al. (2017). An extended depth-first search algorithm for optimal triangulation of Bayesian networks. International Journal of Approximate Reasoning, 80, 294-312 .), depth-first search for multi-graph set approximation pattern mining (Acosta-Mendoza, N. (2016). A new algorithm for approximation pattern in multi-graph collections. Knowledge-Based Systems, 109, 198-207.), etc.
  • the problem to be solved by the present invention is the air compressor group optimal scheduling decision problem.
  • the present invention first constructs a sample set of an air compressor model based on expert experience, and applies the least squares algorithm to online learning of the relevant parameters of the air compressor energy consumption model; and then aims at the maximum energy conversion efficiency and the minimum economic cost based on the equivalent electricity method Function, use simulation technology and depth-first tree search algorithm to solve multi-objective optimal scheduling model of air compressor group; finally use fuzzy logic theory to describe the preference of decision makers, and introduce it into interactive decision-making.
  • the invention can provide a safe and economic dispatching scheme for on-site workers, thereby improving the resource utilization rate of the air compressor unit.
  • Air compressor energy consumption model construction use expert experience to select the intake air flow, discharge flow and motor current of each air compressor over a period of time as the standard sample set of the air compressor energy consumption model; use least squares to learn air Compressor energy consumption model parameters, that is, the relationship between air compressor intake flow and energy consumption;
  • Air compressor group energy efficiency evaluation model construction abstract the air compressor group as a "black box” model, where the input is electrical energy and the output is produced compressed air, and the air compressor in the group passes through the release valve Discharge amount; convert the input and output of the air compressor group and the discharge into equivalent electricity based on the equivalent electricity method, and then conduct an energy efficiency assessment of the air compressor group;
  • the established air compressor energy efficiency evaluation and scheduling model includes multiple goals such as economic cost and air compressor energy efficiency Function, and then combined with the characteristics of the production process, using simulation technology and depth-first tree search algorithm to solve the multi-objective optimal scheduling model of air compressors, and to simulate the economy and comprehensive energy conversion efficiency of the air compressor group;
  • Intelligent optimization decision that introduces decision maker preference information: use simulation technology to obtain various evaluation index values, and introduce the decision maker preference information into the solution process of Pareto optimal solution, so that the intelligent optimization decision result is more reasonable; Decision maker's preference information is described by fuzzy rules.
  • the invention makes full use of the data modeling method to establish a universal air compressor energy consumption model; comprehensively considers the "quality” and “quantity” of energy types, and establishes an integrated energy efficiency assessment model of the air compressor based on the equivalent electricity method; Combined with the actual operating state of the air compressor equipment, the simulation technology and the depth-first tree search algorithm are used to quickly solve the multi-objective optimal scheduling model of the air compressor unit; in addition, the present invention uses fuzzy rules to describe the preferences of decision makers and is reasonably introduced into dynamic intelligence Decision-making process.
  • FIG. 1 is a flowchart between various modules in the present invention.
  • FIG. 2 is a diagram of the composition and plant area distribution of the air compressor group of the present invention.
  • Fig. 3 is a description of fuzzy membership of expert preference information of the present invention
  • Fig. 3(a) is a fuzzy membership function of input variable energy conversion efficiency
  • Fig. 3(b) is a fuzzy membership function of input variable economic operating cost
  • Fig. 3 (c) is the fuzzy membership function of the output variable importance factor.
  • FIG. 4 is a specific implementation flowchart of the present invention.
  • the present invention takes the air compressor group scheduling of a metallurgical enterprise as an example, and describes the implementation of the present invention in detail with reference to FIGS. 2 and 3.
  • Step 1 Air compressor energy consumption model construction and parameter learning
  • the intake air flow of the jth air compressor of the i-th air compressor group is ⁇ ij .
  • the energy consumption of the air compressor is different in the three stages of opening, loading and unloading.
  • a piecewise function is used to express as follows :
  • the jth air compressor of the ith air compressor group is in the start-up phase And uninstall phase
  • the energy consumption of the power is a fixed value, which can be obtained by the integration of energy consumption during the start and stop period;
  • ⁇ ( ⁇ ij ) represents the intake air flow rate and the jth air compressor of the ith air compressor group
  • the relationship between the motor currents is obtained by fitting the sample set of the air compressor group energy consumption model by the least square algorithm.
  • Step 2 On-line energy efficiency assessment of air compressor unit and modeling of optimal scheduling system
  • S i represents the opening strategy of the air compressor in the i-th air compressor group
  • ⁇ 1 and ⁇ 1 are the coefficients of compressed air converted into standard coal and the conversion of standard coal into equivalent electricity
  • q i is the loss coefficient of the air compressor in the i-th air compressor group
  • ⁇ ′ ij represents the intake air flow of the j-th air compressor in the i-th air compressor group under the opening strategy S i ;
  • the objective function representing the economic cost of air compressors in m air compressor groups Represents the unit price of electrical energy (kw/yuan), Represents the power consumption (kw) of m air compressor groups under the turn-on strategy S i in the period of (t 0 , t 1 ), And ⁇ ij represent the starting cost, unloading cost and depreciation cost of the j-th air compressor in the i-th air compressor group, respectively.
  • the quantity of air produced by an air compressor, Q need means the air demand of the air demand user
  • the shortest and longest time constraints of the jth air compressor of the i-th air compressor group which are designed to avoid frequent start and stop of the air compressor and long-term use of the air compressor;
  • H L and H H are the upper and lower pressure limits of the pipe network, H 0 represents the initial state of the outlet pressure of the air compressor group, and ⁇ H is the corresponding change;
  • Step 3 Solve the air compressor group optimal scheduling model based on simulation technology and depth-first tree search algorithm
  • This patent proposes a depth-first tree search algorithm based on simulation technology to quickly obtain the simulation results of the air compressor unit combination scheme.
  • the algorithm solving steps are as follows:
  • each air compressor of the air compressor group is regarded as a node, and the site personnel set the state of the node according to the production conditions or production plan.
  • each combined scheduling scheme carries out numerical simulation of economy and energy conversion efficiency. If the combined scheduling scheme has been searched, the next combined scheduling scheme is simulated;
  • Step 4 Intelligent optimization decision based on decision maker preference information
  • the characteristic value of the a-th index of the b-th evaluation object is x ab
  • I 1 is the energy conversion efficiency index of the air compressor
  • I 2 is the economic operating cost index
  • the intelligent optimal dispatching decision system of the air compressor group uses fuzzy reasoning to describe the dispatcher's preference information and the uncertainty information such as the index weight changes caused by complex working conditions, thereby increasing the feasibility and effectiveness of the dispatching decision plan.
  • the present invention utilizes the Mamdani fuzzy model widely used to describe uncertain information of industrial production systems, and its fuzzy rules can be defined as:
  • the input values are standardized for energy conversion efficiency and economic operation indicators, respectively, P represents the importance factor;
  • a f1 and A f2 respectively represent the fuzzy subset of energy conversion efficiency and economic operation, and
  • B f1 represents the fuzzy subset of importance factors.
  • the fuzzy rules are shown in Table 1:
  • the largest y value represents the comprehensive optimal plan for scheduling decisions
  • y k represents the comprehensive evaluation value of the kth scheduling plan
  • P k represents the importance factor of energy conversion efficiency.
  • Table 2 gives a comparison of the effects of the method of the present invention and the manual scheduling method

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computer Hardware Design (AREA)
  • Data Mining & Analysis (AREA)
  • Geometry (AREA)
  • Computing Systems (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Fuzzy Systems (AREA)
  • Automation & Control Theory (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Algebra (AREA)
  • Nonlinear Science (AREA)
  • Educational Administration (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Manufacturing & Machinery (AREA)
  • General Health & Medical Sciences (AREA)

Abstract

一种基于仿真技术的空气压缩机群组优化调度决策方法，属于信息技术领域。该方法利用专家经验构建空气压缩机能耗模型样本集，应用最小二乘算法对空气压缩机能耗模型相关参数进行学习，以基于等效电的能源转化效率最大和经济成本最小为目标函数，应用仿真技术和深度优先树搜索算法求解空气压缩机群组多目标优化调度模型，最后利用模糊逻辑理论描述决策者的偏好，在交互式决策中引入决策者的偏好信息，从而协助生产工作人员制定安全、经济、高效和环保的运行方案，实现空气压缩机群组资源最大化利用的运行模式。该方法在不同的工业领域中亦有广泛的应用价值。

Description

一种基于仿真技术的空气压缩机群组优化调度决策方法 技术领域
本发明属于信息技术领域，涉及到基于数据的空气压缩机动态建模、基于等效电的空气压缩机群组能效评估、基于深度优先树搜索算法的空气压缩机组合模型优化求解、以及基于偏好信息的智能优化等理论，是一种基于仿真技术的空气压缩机群组优化调度决策方法。本发明利用专家经验构建空气压缩机能耗模型样本集，并应用最小二乘算法对空气压缩机能耗模型相关参数进行学习；随后以基于等效电的能源转化效率最大和经济成本最小为目标函数，应用仿真技术和深度优先树搜索算法求解空压机群组多目标优化调度模型；最后利用模糊逻辑理论描述决策者的偏好，并引入到交互式决策中，从而协助生产工作人员制定安全、经济、高效和环保的运行方案，实现空气压缩机群组资源最大化利用的运行模式。该方法在不同的工业领域中亦有广泛的应用价值。
背景技术
空气压缩机具有结构简单、系统维护量小、元器件价格低廉的特点，是冶金、工业制造、生物制药等工业生产过程的主要动力能源。随着我国能源形势的日益严峻，其节能潜力评估和优化调度决策越来越成为企业和研究人员关注的重点。空气压缩机群组是一个时变、时滞和非线性的复杂系统，由于机组调度的不合理、不及时等原因，导致空气压缩系统资源利用率低、能耗高，存在较大节能空间。因此，合理的空气压缩机组节能潜力评估和优化调度一方面能够实现空气压缩系统生产资源的结构性优化，满足不同生产用户的用气需求，为生产安全、节能降耗提供基础支撑；另一方面也可提高空气压缩机组综合运行效率，尽可能使空气压缩机组运行在最佳工况点，以提升空气压缩系统的节能性和经济性。
常见的空气压缩机群组调度是一个非线性、非凸、高维、多约束的复杂优化问题，相关解决方案——智能搜索算法通常分为三类：(1)广度优先搜索。该算法又称为宽度优先搜索或横向优先搜索，沿着树的宽度遍历树的所有节点。现有成果包括基于广度优先树搜索的分布式约束优化(Chen,Ziyu,et al.(2017).An improved DPOP algorithm based on breadth first search pseudo-tree for distributed constraint optimization.Applied Intelligence,47,607-623.)、并行分布式广度优先搜索应用于开普勒结构(Bisson,M.,et al.(2016).Parallel distributed breadth first search on the kepler architecture.IEEE Transactions on Parallel&Distributed Systems,27,2091-2102.)等。(2)蒙特卡洛树搜索。该算法将蒙特卡洛模拟和树搜索算法结合，用计算机统计模拟或抽样，以获得复杂问题的近似解。现有成果包括Monte Carlo树搜索应用于计算机快速行动值估计(Gelly,S.,et al.(2011).Monte-carlo tree search and rapid action value estimation in computer go.Artificial Intelligence,175,1856-1875.)混合蒙特卡罗树搜索方法应用于晶体结 构确定(Shankland,K.,et al.(2005).Characterization of a hybrid monte carlo search algorithm for structure determination.Journal of Applied Crystallography,38,107-111.)等。(3)深度优先树搜索。该算法的目的是达到被搜索结构的所有结点。现有成果包括用于优化贝叶斯网络三角剖分(Li,C.,et al.(2017).An extended depth-first search algorithm for optimal triangulation of Bayesian networks.International Journal of Approximate Reasoning,80,294-312.)，深度优先搜索用于多图集合近似模式挖掘(Acosta-Mendoza,N.(2016).A new algorithm for approximate pattern mining in multi-graph collections.Knowledge-Based Systems,109,198-207.)等。
除以上问题和局限外，如何将设备模型的特点与智能优化算法相结合，并实现空气压缩机组的快速精确求解，是目前相关研究的重点和难点。冶金能源系统中存在多个空气压缩机组，它们分布于厂区的不同位置，通过管网实现多机组跨区域供能。如何实现不同区域不同机组空压机的合理配置，其难点在于：(1)面向不同类型、不同型号的空气压缩机，其设备机理和参数各有差异，因此难以建立一个普适性的空气压缩机机理模型；(2)空气压缩机组能效在线评估模型如何兼顾能源种类的“质”和“量”；(3)从实际应用上出发，将设备模型的特点与深度优先树搜索算法结合快速准确求解空气压缩机群组多目标优化模型是十分困难的；(4)在人机交互动态智能优化决策中引入决策者偏好信息是一项具有挑战性的工作。目前还缺少一种有效的方法能够系统性的同时解决上述所有问题。
发明内容
本发明要解决的是空压机群组优化调度决策问题。本发明首先基于专家经验构造空压机模型样本集，应用最小二乘算法对空压机能耗模型相关参数进行在线学习；然后以基于等效电法的能源转换效率最大和经济成本最小为目标函数，利用仿真技术和深度优先树搜索算法求解空压机群组多目标优化调度模型；最后利用模糊逻辑理论描述决策者的偏好，引入到交互式决策中。该发明可以为现场工作人员提供既安全又经济的调度方案，从而提高空气压缩机组的资源利用率。
本发明技术方案：
基于仿真技术的空气压缩机群组优化调度决策方法，如附图1所示，具体步骤如下：
(1)空气压缩机能耗模型构建：利用专家经验选取每台空气压缩机一段时间内的进气流量、放散流量和电机电流，作为空气压缩机能耗模型的标准样本集；利用最小二乘法学习空气压缩机能耗模型参数，即空气压缩机进气流量与能耗之间关系；
(2)空气压缩机群组能效评估模型构建：将空气压缩机群组抽象为“黑箱”模型，其中输入是电能，输出是生产的压缩空气，放散为群组中空气压缩机通过放散阀的放散量；基于等效电法将空气压缩机群组输入输出以及放散转化为等效电，进而对空气压缩机群组进行能 效评估；
(3)基于模拟仿真和深度优先树搜索算法的空气压缩机群组多目标优化调度建模与求解：所建立的空气压缩机能效评估和调度模型包含经济成本、空气压缩机能效等多个目标函数，进而结合生产工艺特点，应用仿真技术和深度优先树搜索算法求解空气压缩机多目标优化调度模型，并模拟空气压缩机群组的经济性和综合能源转换效率；
(4)引入决策者偏好信息的智能优化决策：利用仿真技术获得各项评价指标值，将决策者的偏好信息引入到Pareto最优解的求解过程中，使智能优化决策结果更加合理；其中，决策者的偏好信息利用模糊规则描述。
本发明的效果和益处：将空气压缩机工况特征与调度目标密切结合，应用模拟仿真技术和深度优先树搜索算法快速求解空气压缩机群组多目标优化模型，实现优化调度方案的经济性和综合能效模拟，有效降低空气压缩机群组调度的盲目性，进而实现空气压缩机群组的经济、安全、高效的运行。本发明充分利用数据建模方法，建立一种普适性的空气压缩机能耗模型；综合考虑能源种类的“质”和“量”，建立基于等效电法的空气压缩机综合能效评估模型；结合空气压缩机设备的实际运行状态，利用仿真技术和深度优先树搜索算法结合快速求解空气压缩机组多目标优化调度模型；此外，本发明利用模糊规则描述决策者的偏好，并合理引入到动态智能化决策的过程中。
附图说明
图1为本发明中各个模块间的流程图。
图2为本发明空气压缩机群组的构成及厂区分布图。
图3为本发明专家偏好信息的模糊隶属度描述；图3(a)为输入变量能源转化效率的模糊隶属度函数；图3(b)为输入变量经济运行成本的模糊隶属度函数；图3(c)为输出变量重要性因子的模糊隶属度函数。
图4为本发明的具体实施流程图。
具体实施方式
为了更好地理解本发明的技术方案，本发明以冶金企业空压机群组调度为例，结合附图2和附图3对本发明的实施方式作详细描述。
一种基于仿真技术的空气压缩机群组优化调度决策方法，步骤如下：
步骤1：空气压缩机能耗模型构建及其参数学习
从数据库中获取第i个空气压缩机群组第j台空气压缩机一段时间内的进气流量、放散流量和电机电流；依据专家经验，从上述时间段内选择部分样本，构造该空气压缩机能耗模型的样本集；按照上述方式，依次初始化不同空气压缩机群组中每台空气压缩机的样本集；
在一个交替运行周期内，设第i个空气压缩机组第j台空气压缩机的进气流量为υ ij，空气压缩机能耗在开启、加载和卸载三个阶段不同，采用一个分段函数表示如下：
Figure PCTCN2019112956-appb-000001
其中，第i个空气压缩机群组第j台空气压缩机在启动阶段
Figure PCTCN2019112956-appb-000002
和卸载阶段
Figure PCTCN2019112956-appb-000003
的电力耗能为一个固定的数值，分别可通过启停时间段能耗的积分获得；U ij和
Figure PCTCN2019112956-appb-000004
分别表示第i个空气压缩机群组第j台空气压缩机的电压和驱动电机的功率因数；Ψ(υ ij)表示第i个空气压缩机群组第j台空气压缩机的进气流量与电机电流之间的关系，两者之间关系通过最小二乘算法拟合空气压缩机群组能耗模型样本集得到。
步骤2：空气压缩机组在线能效评估及优化调度系统建模
1)目标函数
①基于等效电的综合能源转化效率最大化
Figure PCTCN2019112956-appb-000005
其中，
Figure PCTCN2019112956-appb-000006
表示m个空气压缩机组基于等效电的能源转化效率目标函数，S i表示第i个空气压缩机组中空气压缩机的开启策略，
Figure PCTCN2019112956-appb-000007
表示第i个空气压缩机组第j个空气压缩机在开启策略S i下的加载功率，α 1和β 1分别为压缩空气折算成标准煤的系数和标准煤折算成等效电的系数，q i为第i个空气压缩机组中空气压缩机的损失系数，υ′ ij表示第i个空气压缩机组第j空气压缩机在开启策略S i下的进气流量；
②经济运行成本最小
Figure PCTCN2019112956-appb-000008
其中，
Figure PCTCN2019112956-appb-000009
表示m个空气压缩机组中空气压缩机经济成本的目标函数，
Figure PCTCN2019112956-appb-000010
表示电能的单价(kw/元)，
Figure PCTCN2019112956-appb-000011
表示在(t 0,t 1)时间段内m个空气压缩机组在开启策略S i下的电力耗能(kw)，
Figure PCTCN2019112956-appb-000012
和ε ij分别表示第i个空气压缩机组中第j个空气 压缩机的启动成本、卸载成本以及折旧成本。
2)目标函数的约束条件
Figure PCTCN2019112956-appb-000013
①空气压缩机进气流量的开度约束：
Figure PCTCN2019112956-appb-000014
和
Figure PCTCN2019112956-appb-000015
分别表示第i个空气压缩机群组第j台空气压缩机进气流量的最大最小约束；
②空气压缩机群组产气量与用气量匹配约束：
Figure PCTCN2019112956-appb-000016
表示m个空气压缩机群组中
Figure PCTCN2019112956-appb-000017
台空气压缩机的产气量，Q need表示空气需求用户的空气需求量；
③空气压缩机的产气量约束
Figure PCTCN2019112956-appb-000018
和
Figure PCTCN2019112956-appb-000019
分别表示第i个空气压缩机群组第j台空气压缩机出气流量的最大和最小约束；
④空气压缩机运行时间约束
Figure PCTCN2019112956-appb-000020
和
Figure PCTCN2019112956-appb-000021
分别表示第i个空气压缩机群组第j台空气压缩机运行的最短和最长时间约束，该约束旨在避免空气压缩机的频繁启停和空气压缩机的长时间使用；
⑤管网压力变化约束
H L、H H分别是管网的压力上下限，H 0表示空气压缩机群组出口压力的初始状态，ΔH则是对应的变化量；
步骤3：基于仿真技术和深度优先树搜索算法求解空气压缩机群组优化调度模型
本专利提出一种基于仿真技术的深度优先树搜索算法，以快速获取空气压缩机机组组合方案的仿真模拟结果，该算法求解步骤如下：
1)初始化运行状态：空气压缩机组每台空气压缩机看作一个节点，现场人员依据生产工况或生产计划设定节点的状态，状态State＝1表示空气压缩机处于正常状态，状态State＝0表示空气压缩机处于检修或故障状态；处于State＝0的空气压缩机不能作为组合调度优化求解的备选设备；
2)组合方案仿真模拟：每一条组合调度方案进行经济性和能源转化效率的数值模拟，如 果该组合调度方案已经搜索过，则进行下一条组合调度方案的仿真模拟；
3)模拟仿真结果存储：每一条组合调度方案的经济性和能源转化效率的模拟数值进行存储，待组合调度方案全部遍历完后，进入基于决策者偏好信息的智能优化决策分析流程。
步骤4：基于决策者偏好信息的智能优化决策
设有能源转化效率和经济性两个评价指标来评价k个调度方案，第b个评价对象的第a个指标的特征值为x ab，得到调度方案的特征矩阵为X＝(x ab) 2×k；将得到的特征矩阵进行标准化处理，消除指标间由于量纲不同带来的差异；标准化后处理得到的矩阵为
Figure PCTCN2019112956-appb-000022
X各值标准化的方法为：
Figure PCTCN2019112956-appb-000023
Figure PCTCN2019112956-appb-000024
其中，I 1为空气压缩机能源转化效率指标，I 2为经济性运行成本指标；
空气压缩机组智能优化调度决策系统利用模糊推理描述调度人员的偏好信息和复杂工况引起的指标权重变化等不确定性信息，从而增加调度决策方案的可行性和有效性。本发明借助广泛用于描述工业生产系统不确定信息的Mamdani模糊模型，其模糊规则可以定义为：
Figure PCTCN2019112956-appb-000025
其中，
Figure PCTCN2019112956-appb-000026
和
Figure PCTCN2019112956-appb-000027
分别为能源转化效率和经济运行指标标准化的输入数值，P表示重要性因子；A f1和A f2分别表示能源转化效率和经济运行的模糊子集，B f1表示重要性因子的模糊子集。模糊规则如表1所示：
表1模糊规则表
Figure PCTCN2019112956-appb-000028
含偏好信息的多目标综合评价指标计算公式为：
Figure PCTCN2019112956-appb-000029
y＝Max(y 1,y 2,…y k) (9)
其中，y值最大表示调度决策综合最优的方案，y k表示第k个调度方案的综合评价数值，P k表示能源转化效率的重要性因子。
以某冶金企业空压机群系统为例，假设压缩气体在管道中传输为理想状态，空气压缩机用户的需求总量为人工设定，不考虑空气压缩机组的耗电价格不同时间的差别，即电价一律按0.458元/千瓦时计算。表2给出了本发明方法与人工调度方法的效果对比。
表2给出了本发明方法与人工调度方法的效果对比
Figure PCTCN2019112956-appb-000030
Figure PCTCN2019112956-appb-000031

Claims (1)

  1. 一种基于仿真技术的空气压缩机群组优化调度决策方法，步骤如下：
    步骤1：空气压缩机能耗模型构建及其参数学习
    从数据库中获取第i个空气压缩机群组第j台空气压缩机一段时间内的进气流量、放散流量和电机电流；按照经验从上述时间段内选择部分样本，构造空气压缩机能耗模型的样本集；依次初始化不同空气压缩机群组每台空气压缩机的样本集；
    在一个交替运行周期内，设第i个空气压缩机组第j台空气压缩机的进气流量为υ ij，空气压缩机能耗在开启、加载和卸载三个阶段不同，采用一个分段函数表示如下：
    Figure PCTCN2019112956-appb-100001
    其中，第i个空气压缩机群组第j台空气压缩机在启动阶段
    Figure PCTCN2019112956-appb-100002
    和卸载阶段
    Figure PCTCN2019112956-appb-100003
    的电力耗能为一个固定的数值，分别通过启停时间段能耗的积分获得；U ij和
    Figure PCTCN2019112956-appb-100004
    分别表示第i个空气压缩机群组第j台空气压缩机的电压和驱动电机的功率因数；Ψ(υ ij)表示第i个空气压缩机群组第j台空气压缩机的进气流量与电机电流之间的关系，两者之间关系通过最小二乘算法拟合空气压缩机群组能耗模型样本集得到；
    步骤2：空气压缩机组在线能效评估及优化调度系统建模
    1)目标函数
    ①基于等效电的综合能源转化效率最大化
    Figure PCTCN2019112956-appb-100005
    其中，
    Figure PCTCN2019112956-appb-100006
    表示m个空气压缩机组基于等效电的能源转化效率目标函数，S i表示第i个空气压缩机组中空气压缩机的开启策略，
    Figure PCTCN2019112956-appb-100007
    表示第i空气压缩机组第j空气压缩机在开启策略S i下的加载功率，α 1和β 1分别为压缩空气折算成标准煤的系数和标准煤折算成等效电的系数，q i为第i个空气压缩机组中空气压缩机的损失系数，υ′ ij表示第i个空气压缩机组第j个空气压缩机在开启策略S i下的进气流量；
    ②经济运行成本最小
    Figure PCTCN2019112956-appb-100008
    其中，
    Figure PCTCN2019112956-appb-100009
    表示m个空气压缩机组中空气压缩机经济成本的目标函数，
    Figure PCTCN2019112956-appb-100010
    表示电能的单价，kw/元；
    Figure PCTCN2019112956-appb-100011
    dt表示在(t 0,t 1)时间段内m个空气压缩机组在开启策略S i下的电力耗能，kw；
    Figure PCTCN2019112956-appb-100012
    和ε ij分别表示第i个空气压缩机组中第j个空气压缩机的启动成本、卸载成本以及折旧成本；
    2)目标函数的约束条件
    Figure PCTCN2019112956-appb-100013
    目标函数约束条件的描述如下：
    ①空气压缩机进气流量的开度约束
    Figure PCTCN2019112956-appb-100014
    和
    Figure PCTCN2019112956-appb-100015
    分别表示第i个空气压缩机群组第j台空气压缩机进气流量的最大最小约束；
    ②空气压缩机群组产气量与用气量匹配约束
    Figure PCTCN2019112956-appb-100016
    表示m个空气压缩机群组中
    Figure PCTCN2019112956-appb-100017
    台空气压缩机的产气量，Q need表示空气需求用户的空气需求量；
    ③空气压缩机的产气量约束
    Figure PCTCN2019112956-appb-100018
    和
    Figure PCTCN2019112956-appb-100019
    分别表示第i个空气压缩机群组第j台空气压缩机出气流量的最大和最小约束；
    ④空气压缩机运行时间约束
    Figure PCTCN2019112956-appb-100020
    和
    Figure PCTCN2019112956-appb-100021
    分别表示第i个空气压缩机群组第j台空气压缩机运行的最短和最长时间约束，该约束旨在避免空气压缩机的频繁启停和空气压缩机的长时间使用；
    ⑤管网压力变化约束
    H L、H H分别是管网的压力上下限，H 0表示空气压缩机群组出口压力的初始状态，ΔH则是对应的变化量；
    步骤3：基于仿真技术和深度优先树搜索算法求解空气压缩机群组优化调度模型
    基于仿真技术的深度优先树搜索算法，以快速获取空气压缩机机组组合方案的仿真模拟 结果，该算法求解过程自上而下步骤如下：
    1)初始化运行状态：空气压缩机组每台空气压缩机看作一个节点，现场人员依据生产工况或生产计划设定节点的状态；状态State＝1表示空气压缩机处于正常状态；状态State＝0表示空气压缩机处于检修或故障状态，处于该状态的空气压缩机不能作为组合调度优化求解的备选设备；
    2)组合方案仿真模拟：每一条组合调度方案进行经济性和能源转化效率的数值模拟，如果该组合调度方案已经搜索过，则进行下一条组合调度方案的仿真模拟；
    3)模拟仿真结果存储：对每一条组合调度方案的经济性和能源转化效率的数值模拟结果进行存储，待组合调度方案全部遍历完后，进入基于决策者偏好信息的智能优化决策分析流程；
    步骤4：基于决策者偏好信息的智能优化决策系统
    设有能源转化效率和经济性两个评价指标来评价k个调度方案，第b个评价对象的第a个指标的特征值为x ab，得到调度方案的特征矩阵为X＝(x ab) 2×k；将得到的特征矩阵进行标准化处理，消除指标间由于量纲不同带来的差异；标准化后处理得到的矩阵为
    Figure PCTCN2019112956-appb-100022
    X各值标准化的方法为：
    Figure PCTCN2019112956-appb-100023
    Figure PCTCN2019112956-appb-100024
    其中，I 1为空气压缩机能源转化效率指标，I 2为经济性运行成本指标；
    Mamdani模糊模型广泛用于描述工业生产系统的不确定信息，其模糊规则定义为：
    Figure PCTCN2019112956-appb-100025
    其中，
    Figure PCTCN2019112956-appb-100026
    和
    Figure PCTCN2019112956-appb-100027
    分别为能源转化效率和经济运行指标标准化的输入数值，P表示重要性因子；A f1和A f2分别表示能源转化效率和经济运行的模糊子集，B f1表示重要性因子的模糊子集；模糊规则如表1所示：
    表1模糊规则表
    Figure PCTCN2019112956-appb-100028
    含偏好信息的多目标综合评价指标计算公式为：
    Figure PCTCN2019112956-appb-100029
    y＝Max(y 1,y 2,…y k)  (9)
    其中，y值最大表示调度决策综合最优的方案，y k表示第k个调度方案的综合评价数值，P k表示能源转化效率的重要性因子。
PCT/CN2019/112956 2019-01-02 2019-10-24 一种基于仿真技术的空气压缩机群组优化调度决策方法 WO2020140564A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US16/928,672 US11126765B2 (en) 2019-01-02 2020-07-14 Method for optimal scheduling decision of air compressor group based on simulation technology

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910001583.2A CN109783916B (zh) 2019-01-02 2019-01-02 一种基于仿真技术的空气压缩机群组优化调度决策方法
CN201910001583.2 2019-01-02

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/928,672 Continuation US11126765B2 (en) 2019-01-02 2020-07-14 Method for optimal scheduling decision of air compressor group based on simulation technology

Publications (1)

Publication Number Publication Date
WO2020140564A1 true WO2020140564A1 (zh) 2020-07-09

Family

ID=66499707

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/112956 WO2020140564A1 (zh) 2019-01-02 2019-10-24 一种基于仿真技术的空气压缩机群组优化调度决策方法

Country Status (3)

Country Link
US (1) US11126765B2 (zh)
CN (1) CN109783916B (zh)
WO (1) WO2020140564A1 (zh)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113297812A (zh) * 2021-05-19 2021-08-24 浙江国祥股份有限公司 一种多机头变频离心式冷水机组能效寻优控制算法
CN114707369A (zh) * 2022-06-07 2022-07-05 武汉雄韬氢雄燃料电池科技有限公司 一种基于空压机的燃料电池空路子系统建模仿真方法
CN114893402A (zh) * 2022-04-06 2022-08-12 合肥工业大学 基于人工智能的并联空压机能耗调控方法及系统
CN115099142A (zh) * 2022-06-22 2022-09-23 国网安徽省电力有限公司电力科学研究院 基于模型预测的碳控排企业能量优化调度方法
CN116681311A (zh) * 2023-07-28 2023-09-01 华中科技大学 基于时空尺度的电站运维决策优化方法、系统及介质
CN117154727A (zh) * 2023-11-01 2023-12-01 浙江优能电力设计有限公司 电力系统可靠性控制方法及系统

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109783916B (zh) * 2019-01-02 2021-06-18 大连理工大学 一种基于仿真技术的空气压缩机群组优化调度决策方法
CN110173958B (zh) * 2019-05-31 2021-03-23 新奥数能科技有限公司 一种天然气液化制冷优化方法及装置
CN110429893B (zh) * 2019-08-29 2021-10-08 上海电机学院 一种电机控制器载频动态优化方法及电机控制器
CN112613733A (zh) * 2020-12-22 2021-04-06 江苏晟能科技有限公司 一种园区能源的智能管控方法及系统
CN113050573B (zh) * 2021-03-26 2022-09-13 山东莱钢永锋钢铁有限公司 一种基于生产节奏的空压机节能的方法
CN113361763B (zh) * 2021-06-02 2023-12-01 中海石油气电集团有限责任公司 一种输气管网的全时段运行优化方法及系统
CN113408194B (zh) * 2021-06-10 2022-12-02 北京宜能高科科技有限公司 常减压装置的通盘优化方法
CN113568307B (zh) * 2021-07-02 2022-04-01 福建时代星云科技有限公司 一种储充站的控制策略优化方法及终端
CN113537644B (zh) * 2021-08-23 2022-07-08 中冶赛迪技术研究中心有限公司 一种多空压站动态协同优化调控系统及方法
CN113807015B (zh) * 2021-09-17 2023-12-26 南方电网科学研究院有限责任公司 压缩空气储能系统参数优化方法、装置、设备及存储介质
CN114358418B (zh) * 2021-12-31 2024-06-07 中冶赛迪信息技术(重庆)有限公司 一种低碳城市钢厂网络规划系统和方法
CN114781274B (zh) * 2022-05-17 2023-07-14 江苏泰坦智慧科技有限公司 仿真与决策交替学习的综合能源系统控制优化方法与系统
CN115048773B (zh) * 2022-05-24 2024-03-29 西安交通大学 双时间尺度室温控制建模方法
CN116244863B (zh) * 2023-03-09 2024-05-17 北京理工大学 基于多粒度案例柔性重构的回流焊焊点仿真设计决策系统
CN116703321B (zh) * 2023-06-09 2023-11-21 北京市永康药业有限公司 一种基于绿色生产的药厂管理方法及系统
CN117145742B (zh) * 2023-10-31 2024-02-06 深圳市信润富联数字科技有限公司 空压机节能方法、装置、设备及计算机可读存储介质
CN118093203A (zh) * 2024-04-24 2024-05-28 北京壁仞科技开发有限公司 数据搬运方法、分布式训练系统、电子设备和存储介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102109823A (zh) * 2010-12-13 2011-06-29 北京三博中自科技有限公司 用于电机驱动的流体输送设备能效计算的建模方法和系统
WO2012026229A2 (en) * 2010-08-27 2012-03-01 Mitsubishi Electric Corporation Method for scheduling the operation of power generators
CN104463360A (zh) * 2014-12-02 2015-03-25 大连理工大学 一种基于数学规划的冶金企业氧氮能源优化调度方法
CN104751373A (zh) * 2015-03-23 2015-07-01 国网重庆市电力公司电力科学研究院 计及污染气体排放风险的环境经济调度方法
CN106529021A (zh) * 2016-11-09 2017-03-22 东南大学 一种基于特征识别的空调系统仿真模拟方法
CN109164704A (zh) * 2018-08-07 2019-01-08 大连理工大学 一种基于混合模型的空压机群组优化调度方法
CN109783916A (zh) * 2019-01-02 2019-05-21 大连理工大学 一种基于仿真技术的空气压缩机群组优化调度决策方法

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103049625A (zh) * 2011-10-11 2013-04-17 新鼎系统股份有限公司 空压机操作预测管理方法
US9411326B2 (en) * 2012-08-21 2016-08-09 General Electric Company Plant control optimization system including visual risk display
US9910449B2 (en) * 2013-04-19 2018-03-06 Google Llc Generating and implementing thermodynamic models of a structure
US20140324404A1 (en) * 2013-04-26 2014-10-30 Jose de la Torre-Bueno Systems and Methods for Efficiently Creating An Electronic Description of A Building
US20170061444A1 (en) * 2015-08-25 2017-03-02 Schneider Electric Usa Inc. Analysis engine that correlates business operations with facility energy use
JP2018092248A (ja) * 2016-11-30 2018-06-14 トヨタ自動車株式会社 圧縮エア流量の算出方法、その装置、及びプログラム
CN106786603B (zh) * 2017-02-22 2019-07-19 天津大学 一种区域综合能源系统多目标最优混合潮流算法
CN107769215A (zh) * 2018-01-19 2018-03-06 国网天津市电力公司 基于能源集线器的园区混合能源系统优化调度方法
JP2019200040A (ja) * 2018-05-18 2019-11-21 ジョンソン コントロールズ テクノロジー カンパニーＪｏｈｎｓｏｎ Ｃｏｎｔｒｏｌｓ Ｔｅｃｈｎｏｌｏｇｙ Ｃｏｍｐａｎｙ モデル駆動型深層学習を有するｈｖａｃ制御システム

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012026229A2 (en) * 2010-08-27 2012-03-01 Mitsubishi Electric Corporation Method for scheduling the operation of power generators
CN102109823A (zh) * 2010-12-13 2011-06-29 北京三博中自科技有限公司 用于电机驱动的流体输送设备能效计算的建模方法和系统
CN104463360A (zh) * 2014-12-02 2015-03-25 大连理工大学 一种基于数学规划的冶金企业氧氮能源优化调度方法
CN104751373A (zh) * 2015-03-23 2015-07-01 国网重庆市电力公司电力科学研究院 计及污染气体排放风险的环境经济调度方法
CN106529021A (zh) * 2016-11-09 2017-03-22 东南大学 一种基于特征识别的空调系统仿真模拟方法
CN109164704A (zh) * 2018-08-07 2019-01-08 大连理工大学 一种基于混合模型的空压机群组优化调度方法
CN109783916A (zh) * 2019-01-02 2019-05-21 大连理工大学 一种基于仿真技术的空气压缩机群组优化调度决策方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
WEI, CHAO ET AL.: "Collaborative Optimization Method of the GWHP Central Air-conditioning System Based on the Change of the Characteristics of Pipe Networks", FLUID MACHINERY, vol. 42, no. 9, 30 September 2014 (2014-09-30), XP009521835, ISSN: 1005-0329 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113297812A (zh) * 2021-05-19 2021-08-24 浙江国祥股份有限公司 一种多机头变频离心式冷水机组能效寻优控制算法
CN113297812B (zh) * 2021-05-19 2022-07-05 浙江国祥股份有限公司 一种多机头变频离心式冷水机组能效寻优控制方法
CN114893402A (zh) * 2022-04-06 2022-08-12 合肥工业大学 基于人工智能的并联空压机能耗调控方法及系统
CN114707369A (zh) * 2022-06-07 2022-07-05 武汉雄韬氢雄燃料电池科技有限公司 一种基于空压机的燃料电池空路子系统建模仿真方法
CN115099142A (zh) * 2022-06-22 2022-09-23 国网安徽省电力有限公司电力科学研究院 基于模型预测的碳控排企业能量优化调度方法
CN116681311A (zh) * 2023-07-28 2023-09-01 华中科技大学 基于时空尺度的电站运维决策优化方法、系统及介质
CN116681311B (zh) * 2023-07-28 2023-10-10 华中科技大学 基于时空尺度的电站运维决策优化方法、系统及介质
CN117154727A (zh) * 2023-11-01 2023-12-01 浙江优能电力设计有限公司 电力系统可靠性控制方法及系统
CN117154727B (zh) * 2023-11-01 2024-01-16 浙江优能电力设计有限公司 电力系统可靠性控制方法及系统

Also Published As

Publication number Publication date
CN109783916A (zh) 2019-05-21
CN109783916B (zh) 2021-06-18
US20200342150A1 (en) 2020-10-29
US11126765B2 (en) 2021-09-21

Similar Documents

Publication Publication Date Title
WO2020140564A1 (zh) 一种基于仿真技术的空气压缩机群组优化调度决策方法
Liang et al. Analysis of factors affecting economic operation of electric vehicle charging station based on DEMATEL-ISM
WO2021189739A1 (zh) 一种基于生产计划的钢铁企业氧气负荷预测方法
CN108876131B (zh) 基于电网成效贡献度的储备项目优选方法
CN109164704B (zh) 一种基于混合模型的空压机群组优化调度方法
CN103235980B (zh) 一种基于多目标规划的用电管理避峰策略优化方法
Liu et al. A multistage decision-making method for multi-source information with Shapley optimization based on normal cloud models
Zhang et al. High spatial granularity residential heating load forecast based on Dendrite net model
Liu et al. An integrated fuzzy multi-energy transaction evaluation approach for energy internet markets considering judgement credibility and variable rough precision
Tang et al. Multi-objective optimal dispatch for integrated energy systems based on a device value tag
Gao et al. Multi-energy sharing optimization for a building cluster towards net-zero energy system
Zhang et al. Fusing domain knowledge and reinforcement learning for home integrated demand response online optimization
CN115965213A (zh) 基于深度强化学习混合动作空间的氧气系统调度优化方法
Shang et al. Study on quantitative estimation method of energy saving and emission reduction of renewable energy system based on fuzzy matter-element method
CN114358601A (zh) 多元能量系统多维评价指标体系构建的方法及装置
Wang et al. Multi-layer encoding genetic algorithm-based granular fuzzy inference for blast furnace gas scheduling
Wang et al. Evaluation Methods for the Development of New Power Systems Based on Cloud Model
Shang et al. Evaluation of Distribution Network Reconstruction Scheme Based on Dynamic Interval Intuitionistic Fuzzy Group Decision-Making
Shao et al. Optimization method based on load forecasting for three-phase imbalance mitigation in low-voltage distribution network
Chen et al. Research on long term power load grey combination forecasting based on fuzzy support vector machine
Can et al. Research on Multi-factorial Investment Decision of Distribution Network Based on Input-output Assessment and Genetic Algorithm
Kang et al. Power flow coordination optimization control method for power system with DG based on DRL
Yao et al. Short-term load forecasting of office building microgrid based on EA-NN
Qiao et al. Grid diagnosis coupled comprehensive evaluation for distribution network investment
Feng et al. A low-carbon evaluation method for urban" source-network-load-storage" integrated power system

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: 19907191

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: 19907191

Country of ref document: EP

Kind code of ref document: A1