WO2016101181A1 - 基于指标预报和解相似度分析的光刻工序动态调度方法 - Google Patents
基于指标预报和解相似度分析的光刻工序动态调度方法 Download PDFInfo
- Publication number
- WO2016101181A1 WO2016101181A1 PCT/CN2014/094837 CN2014094837W WO2016101181A1 WO 2016101181 A1 WO2016101181 A1 WO 2016101181A1 CN 2014094837 W CN2014094837 W CN 2014094837W WO 2016101181 A1 WO2016101181 A1 WO 2016101181A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- scheduling
- sub
- solution
- workpiece
- lithography
- Prior art date
- Legal status (The legal status 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 status listed.)
- Ceased
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
- G05B19/00—Program-control systems
- G05B19/02—Program-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- 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
- G05B19/00—Program-control systems
- G05B19/02—Program-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- 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 belongs to the fields of advanced manufacturing, automation and information, and particularly relates to a lithography process dynamic scheduling method for lithography process scheduling of semiconductor production lines, based on index prediction and solution similarity analysis.
- the lithography process scheduling problem for the semiconductor production line to which the present invention is directed is a single-process scheduling problem with the sum of the total weighted flow times as the optimization target, with machine suitability constraints and order related preparation time.
- the photolithography process is one of the key processes in the semiconductor production line, and its scheduling effect has a greater impact on the production performance indicators of the entire production line.
- the existing scheduling methods mainly include precise optimization methods, classical artificial intelligence methods, heuristic rules and intelligent optimization methods.
- the existing scheduling method is still not ideal when dealing with the above-mentioned scheduling problems of large scale. Therefore, it is important to propose a dynamic scheduling method for lithography processes with better performance.
- the present invention proposes a lithography process dynamic scheduling method (hereinafter referred to as PASM) based on the index prediction and solution similarity analysis.
- PASM lithography process dynamic scheduling method
- the lithography process scheduling problem for the semiconductor production line to which the present invention is directed is a single-process scheduling problem with a total weighted flow time sum as an optimization target, with machine suitability constraints and order related preparation time.
- the above scheduling problem is decomposed into the device selection scheduling sub-problem and the workpiece scheduling sub-problem.
- the sub-problem scheduling problem is constructed and the performance index prediction model is constructed.
- the function of the above-mentioned scheduling sub-problem performance index prediction model is to predict the performance of the corresponding sub-problem problem by analyzing the characteristic information of the scheduling sub-problem without solving the scheduling sub-problem.
- a differential evolution algorithm based on solution similarity analysis is proposed to solve the equipment selection scheduling sub-problem.
- the workpiece scheduling sub-problem performance index prediction model is used for the equipment.
- the solution of the scheduling sub-problem is selected to perform a quick evaluation of the global scheduling performance, thereby improving the global optimization performance.
- the lithography process scheduling problem of the semiconductor production line can be specifically described as follows:
- M ⁇ 1, 2, . . . , m ⁇
- N ⁇ 1, 2, . . . , n ⁇ .
- Each workpiece needs to be processed on a lithography machine.
- the processing time, weight, and release time of the workpiece j (j ⁇ N) on the machine l are recorded as p l, j , w j and r j , and the workpiece j is also Corresponding to a machinable lithography machine set ⁇ j and lithography plate model b j , only the lithography machine in the set can process the workpiece, and during processing, if the lithography plate corresponding to the previous processing task is the same as this time If the corresponding lithography plate is the same model, the required switching time is 0, otherwise a fixed reticle switching time is required.
- am j (am j ⁇ M) is the processing machine assigned to workpiece j
- f j is the machining completion time of workpiece j
- the switching time between the two is zero, otherwise a certain switching time is required.
- (1) represents the optimization goal
- (2) represents the workpiece release time constraint
- (3) represents the machine fit constraint
- (4) represents the device uniqueness constraint and the workpiece switching time constraint.
- the present invention first decomposes the above scheduling problem, and decomposes the original scheduling problem into a device selection scheduling sub-problem and an artifact scheduling sub-problem.
- the two scheduling sub-problems can be described as follows:
- ⁇ k be the set of all the workpieces assigned to the lithography machine k
- f( ⁇ k ) is the total weighted flow time corresponding to the workpieces in the set ⁇ k .
- Equation (5) is the objective function corresponding to the model
- Equation (6) indicates that the device allocation scheme of the workpiece should satisfy the device suitability constraint. It can be seen that the search space of the model is greatly reduced compared with the original problem, because there is no need to give a specific workpiece sorting scheme.
- the workpiece scheduling subproblem can be regarded as m independent suboptimization problems, where k
- the suboptimization problem can be described as follows:
- Equation (7) corresponds to the objective function of device k (ie, total weighted transit time)
- equation (8) represents the release time constraint of the workpiece
- equation (9) represents the device uniqueness constraint and the preparation time constraint.
- a performance index prediction model of the workpiece sorting scheduling sub-problem will be established. It should be noted that, in the present invention, the performance indicator prediction model is not based on the solution of the given workpiece scheduling sub-problem, but directly uses the key features corresponding to the workpiece scheduling sub-question as input to perform scheduling. Sub-problem performance indicator forecast.
- the present invention employs a minimum norm extreme learning machine (MN-ELM) to establish a performance indicator prediction model for the above-described scheduling sub-problem.
- MN-ELM minimum norm extreme learning machine
- the input feature extraction is first performed. After analyzing the characteristics of the above-mentioned workpiece sorting scheduling sub-problem, combined with a large number of numerical calculation experiments, we determined the following problem feature quantity as the input of the performance index of the workpiece sorting scheduling sub-problem for forecasting a given machine:
- the interval i corresponds to the total number of workpieces:
- , i 1, 2, ..., I.
- the maximum and minimum values of all workpiece release times, the starting time of the interval is r i,min ;
- the sub-sequence problem of the workpiece sorting for a given machine is used to construct the performance index prediction model of the sub-problem problem.
- I is [4] according to the problem scale.
- 8] interval prediction effect is better.
- Cr is an indicator reflecting whether there is congestion in front of the machine. The larger the value, the greater the possibility of congestion.
- L i,j be the contribution of the workpiece j to L i .
- the following steps are used to establish a scheduling sub-problem performance indicator prediction model. It should be noted that the training data required for the training process of the scheduling sub-problem performance indicator prediction model is gradually obtained with the operation of the algorithm. Therefore, the extreme learning machine used should be based on the online learning framework.
- ELM Extreme Learning Machine
- the input is recorded as Where x i represents a vector consisting of 2I + 4 dimensional data per i samples; the corresponding output of the N sample inputs is recorded as y i is the performance indicator value of the corresponding scheduling sub-problem;
- Step (2) Algorithm initialization
- the weighting parameter W t of the extreme learning machine ELM is initialized to:
- X t represents the sample that has been obtained at time t, and the number of samples is N, so the resulting extreme learning machine mapping matrix is:
- ⁇ is the penalty coefficient
- Step (3) Online learning process
- the t+1 time limit learning machine weight parameter W t+1 is updated as follows:
- K t IA t -1 H(X IC ) T [H(X IC )A t -1 H(X IC ) T +I k ⁇ k ] -1 H(X IC )
- a t+1 -1 K t A t -1
- I k ⁇ k is an identity matrix with a diagonal of 1;
- K t and A t -1 are introduced intermediate variables, thereby simplifying the expression of the updated weight parameter W t+1 ;
- Step (4) termination of the training process
- the invention proposes a differential evolution algorithm based on the performance index prediction model and the solution similarity analysis, which is used to solve the dynamic scheduling problem of the original lithography process, and dynamically gives a scheduling scheme.
- the proposed differential evolution algorithm is performed on the computer by the following steps:
- Step (1) Algorithm initialization
- the solution for each device selection scheduling subproblem can be expressed as:
- r j is a real number indicating that the workpiece j corresponds to the processing machine, r j ⁇ (0,
- the solution of the NP device selection scheduling sub-problems is first generated to form an initial solution set (also referred to as an initial population), which is generated for each workpiece from its corresponding optional device set ⁇ j .
- an initial solution set also referred to as an initial population
- several parameters in the differential evolution algorithm (DE) are set, including the crossover rate CR and the scaling factor F.
- the stopping condition of the algorithm is that the running time of the algorithm reaches the running time limit.
- each parameter in the ordering sub-question is also determined.
- the present invention employs a branch and bound algorithm (B&B) (Rabia Nessah, Imed Kacem. Branch-and-bound method for minimizing the weighted completion time scheduling problem on a single machine with release dates. Computers & Operations research, 2012, 39: 471-478 ) to solve each sorting sub-problem separately, so as to obtain the corresponding performance index value of each device selection scheduling sub-problem solution.
- B&B branch and bound algorithm
- the obtained data can be used, and the initial scheduling sub-problem performance index prediction model is generated by the method of the foregoing third section.
- Selection probability matrix select probability vector obtained M p M p (r 1, ⁇ ) (i.e., the probability of selecting a r-th row of the matrix M p), for the selection probability vector, roulette embodiment of the method, selecting based on two mutually The same solution (ie, the probability of selection is approximately inversely proportional to its distance).
- the crossover operation of the solution is performed by the following method: the post-variation solution for the step (2) For each element, a real number r ⁇ [0,1] is randomly generated. If r ⁇ CR, the element replaces the element in the corresponding position in the target solution, otherwise the element in the corresponding position in the target solution is retained.
- Step (4) Evaluation and selection
- the present invention needs to evaluate all target solutions in the solution set.
- the evaluation process is divided into two phases, first with a rough evaluation and second with an accurate evaluation.
- the performance evaluation model of the scheduling sub-problem established above is used to evaluate the performance of each device selection scheduling sub-problem in the solution set (and also each solution in the differential evolution algorithm solution set).
- the better solution of the pre-p is selected (that is, the corresponding total weighted solution with a smaller time), and the branching and delimiting algorithm is used to accurately evaluate it.
- the data obtained by the accurate evaluation is also used for the online training of the performance evaluation model of the sub-problem, and the online training method is as described in the third section.
- a new next-generation solution set is selected from the solution set using the standard roulette method.
- Figure 1 Schematic diagram of hardware system structure of dynamic scheduling method for lithography process based on index prediction and solution similarity analysis.
- Figure 2 Schematic diagram of the lithography process dynamic scheduling method based on indicator prediction and solution similarity analysis.
- the dynamic scheduling method proposed by the invention relies on a related data acquisition system, and is implemented by a scheduling system client and a scheduling server.
- a schematic diagram of a software and hardware architecture for applying the present invention to dynamic scheduling of a lithography area of an actual semiconductor production line is shown in FIG. 1, and an embodiment of the present invention is as follows.
- Step (1) Obtain data corresponding to the dynamic scheduling problem of the lithography area of the above semiconductor production line.
- Step (2) Decomposition of dynamic scheduling problem in lithography area
- the method is decomposed into the device selection scheduling sub-problem and the workpiece scheduling scheduling sub-problem by the method of the second section of the "Summary of the Invention".
- the above two sub-problems are iteratively solved to form a final lithography zone dynamic scheduling scheme.
- Step (3) Solving the dynamic scheduling problem in the lithography zone
- the methods of the third section and the fourth section of the "invention content" are used to solve the above problem, and a dynamic scheduling scheme is formed.
- a i dimension is 2I+3 dimensions, and the value of each dimension is randomly selected from [-1 1], b i is 1 dimension, Value from choose randomly;
- the penalty factor ⁇ in the performance model of the scheduling sub-problem performance indicator is 2 -15 according to experience;
- the NP initial solutions of the device selection scheduling sub-problem are generated to form an initial solution set, and then NP/2 solutions are randomly selected.
- the branch and bound algorithm is used for accurate evaluation, and the scheduling objective function value corresponding to each solution (ie, the total weighted transit time) is obtained.
- the prediction model learning method in the third section of "Invention Content” using the obtained scheduling sub-problem and its corresponding objective function value data, the initial scheduling sub-problem performance index prediction model is obtained.
- step (3) and step (4) of the fourth section of the "Summary of the Invention" the solution in the solution set is first subjected to a differential mutation operation, and then the cross operation is performed. After the operation is completed, a new solution set is formed.
- the solution in the solution set is firstly evaluated by the scheduling sub-problem performance indicator prediction model. On this basis, the better solution of the pre-p% is selected to be accurate. Evaluation, then, using standard roulette methods to select, forming a new generation of solution sets.
- step (3.3) If the running time of the algorithm has reached the set value, stop; otherwise, go to step (3.3) for iterative optimization.
- the present invention performs a large number of simulation experiments, and the running hardware environment is: P4 2.8 GHz CPU, 4 G RAM, and operating system is Windows 7. Due to space limitations, only some of the experimental results are listed.
- ⁇ ( ⁇ R + ) is the blocking coefficient, which reflects the intensity of the workpiece release interval in this problem
- n is the number of workpieces
- m is the number of machines
- U[ ⁇ , ⁇ ] represents the uniform distribution of the given range
- avg (p l,j ) is the average of all processing times.
- Table 1 lists the scheduling method proposed by the present invention (abbreviated as SM-DE) and the typical differential evolution optimization algorithm in the literature (MGEpitropakis, DKTasoulis, NGPavlidis, VPPlagianakos, MNVrahatis. Enhance differential evolution utilizing proximity-based mutation operators. IEEE Transactions on Evolutionary Computation, 2011, 15(1): 99-119, abbreviated as Pro-DE) Application comparison on instances of randomly generated scheduling problems.
- avg TFT and std TFT are respectively the average value and variance of the total weighted transit time obtained by solving the problem with the corresponding algorithm for 20 times.
- the algorithm allows the running time to be 100 seconds. Marked as "blackened”. It can be seen that SM-DE is superior to Pro-DE algorithm in most cases under the condition that the algorithm allows the same running time.
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
基于指标预报和解相似度分析的光刻工序动态调度方法,属于先进制造、自动化和信息领域,针对半导体生产线光刻工序动态调度问题,提出一种动态调度方法。该方法首先将光刻工序动态调度问题分解为设备选择调度子问题和工件排序调度子问题,并在线建立工件排序调度子问题的性能指标预报模型,然后,利用基于解相似度分析的差分进化算法求解原调度问题。在差分进化算法中,上述工件排序调度子问题性能指标预报模型用于对设备选择调度子问题的解进行全局调度性能的快速粗评价。在对调度解的评价过程中,采用精确评价和粗评价相结合的方式进行差分进化算法中解的性能评价;使用该调度方法可显著提升光刻工序生产调度的效率和效果。
Description
本发明属于先进制造、自动化和信息领域,具体涉及一种面向半导体生产线光刻工序调度、基于指标预报和解相似度分析的光刻工序动态调度方法。
本发明所针对的半导体生产线光刻工序调度问题是以总加权流经时间之和为优化目标、带有机器适配性约束和顺序相关准备时间的单工序调度问题。光刻工序是半导体生产线的关键工序之一,其调度效果对整个生产线的生产性能指标有较大影响。针对该类问题,已有的调度方法主要包括精确优化方法、经典人工智能方法、启发式规则和智能优化方法等。然而,已有调度方法在处理较大规模的上述调度问题时,调度性能仍然不够理想,因此,提出具有较好性能的光刻工序动态调度方法具有重要意义。
发明内容
为解决半导体生产线光刻工序以最小化总加权流经时间为优化目标的调度问题,本发明提出一种基于指标预报和解相似度分析的光刻工序动态调度方法(以下简称为PASM)。
本发明所针对的半导体生产线光刻工序调度问题是以总加权流经时间之和为优化目标、带有机器适配性约束和顺序相关准备时间的单工序调度问题,在本发明中,首先将上述调度问题分解为设备选择调度子问题和工件排序调度子问题,在此基础上,针对工件排序调度子问题,构建其性能指标预报模型。上述调度子问题性能指标预报模型的作用是,在不求解该调度子问题的前提下,通过分析该调度子问题的特征信息来预报该调度子问题对应较优解的性能优劣。在上述调度子问题性能指标预报模型基础上,提出基于解相似度分析的差分进化算法来求解设备选择调度子问题,其中,工件排序调度子问题性能指标预报模型用于对设备
选择调度子问题的解进行全局调度性能的快速评价,从而改善全局优化性能。
(一)问题描述
半导体生产线光刻工序调度问题可具体描述如下:
光刻工序有m台光刻机,n个待调度的工件,分别记为M={1,2,...,m}和N={1,2,...,n}。每个工件需要在某台光刻机上进行加工,工件j(j∈N)在机器l上的加工时间、权重、释放时间记为pl,j,wj和rj,另外,工件j还对应一个可加工的光刻机集合μj以及光刻板型号bj,只有该集合内的光刻机才可加工此工件,且在加工时,如果上一个加工任务对应的光刻板型号与本次任务对应的光刻板型号相同,则所需的切换时间为0,否则需要一个固定的光刻板切换时间。另外,还考虑如下假设:同一个机器一个时刻只能加工一个工件,同一个工件一个时刻只能在一个机器上加工,而且一旦开始加工,不可中断直至加工完成。现需要安排工件在光刻机上加工,使得总加权流经时间最短。
假设amj(amj∈M)为工件j所指派的加工机器,fj为工件j的加工完成时间,S为工件间切换时间矩阵,S={spq}n×n,其中,spq为工件p与工件q在同一个光刻机上相邻加工时所需的切换时间。就本发明所针对的光刻工序动态调度问题而言,若两个工件采用相同的光刻板,则二者之间的切换时间为零,否则需要一定的切换时间。上述光刻工序调度问题可采用混合整数规划模型描述,具体如下:
s.t.
stj≥rj,j=1,2,…,n (2)
amj∈μj,j=1,2,…,n (3)
stl,j-stl,i≥pl,i+sij∪stl,i-stl,j≥pl,j+sji
k=1,2,…,m,i,j=1,2,…,n,i≠j (4)
其中,(1)表示优化目标,(2)表示工件释放时间约束,(3)表示机器适配性约束,(4)表示设备唯一性约束和工件切换时间约束。
(二)问题分解
为求解上述调度模型,本发明首先将上述调度问题进行分解,将原调度问题分解为设备选择调度子问题和工件排序调度子问题,两个调度子问题可描述如下:
(1)设备选择调度子问题
设Θk为指定到光刻机k上所有工件的集合,f(Θk)为集合Θk中工件对应的总加权流经时间,则设备选择调度子问题的数学模型描述如下:
s.t.
amj∈μj,j=1,2,…,n (6)
式(5)为该模型对应的目标函数,式(6)表示工件的设备分配方案应满足设备适配性约束。可以看到与原问题相比,该模型的搜索空间大大缩小,因为不需给出具体的工件排序方案。
(2)工件排序调度子问题
给定了设备选择调度子问题的解,即Θk(k=1,2,…,m)给定,工件排序调度子问题可看作是m个相互独立的子优化问题,其中,第k个子优化问题可描述如下:
s.t.
stj≥rj,j∈Θk (8)
stl,j-stl,i≥pl,i+sij∪stl,i-stl,j≥pl,j+sji
i,j∈Θk,i≠j (9)
式(7)设备k对应的目标函数(即总加权流经时间),式(8)表示工件的释放时间约束,式(9)表示设备唯一性约束和准备时间约束。
(三)调度子问题性能指标预报模型构建
在上述问题分解完成以后,在本发明中将建立工件排序调度子问题的性能指标预报模型。需要说明的是,在本发明中,该性能指标预报模型并非是以给定的工件排序调度子问题的解作为输入,而是直接以该工件排序调度子问题对应的关键特征作为输入来进行调度子问题性能指标预报。
本发明采用最小范数极限学习机(MN-ELM)来建立上述调度子问题的性能指标预报模型。
首先进行输入特征提取。我们在分析了上述工件排序调度子问题的特征之后,结合大量的数值计算实验,确定了如下问题特征量作为预报给定机器的工件排序调度子问题性能指标的输入:
●光刻板类别数量:NB
●指派到当前光刻机的工件释放时间的集中程度:Cr
●采用最小加权加工时间规则所获得的目标函数值:TWFTswpt
●区间i对应工件的总数量:|Ωi|,i=1,2,…,I.
其中,pl,j,wj和rj分别为工件j在光刻机l上的加工时间、权重、释放时间,j=1,2,…,n,Ωi为分配到区间i的工件集合,区间的划分方法为:把整个调度时间轴划分为I个区间,I为整数,每个区间的长度为u=(ri,max+pi,max-ri,min)/I,pi,max为所有工件中加工时间的最大值,ri,max和ri,min为
所有工件释放时间的最大值和最小值,区间的起始时刻为ri,min;
按照上述特征选择方法,对给定机器的工件排序调度子问题,用于构建调度子问题性能指标预测模型的特征共有2I+4个,其中,根据问题规模的不同,I的取值在[4,8]区间预测效果较好。Cr是反映该机器前是否会存在拥堵的指标,该值越大,表明存在拥堵的可能性越大。
Cr的计算步骤如下:
1)令Li(i=1,2,…,I)表示第i个区间的总负载,Li,j为工件j对Li的贡献。
2)对工件j(j∈Ωi),令stj=rj,则cj=rj+pl,j,通过式(10)计算Li,j:
4)通过式(11)计算Cr:
1)将所有工件按其释放时间由小到大的顺序排序,不失一般性,记j′1,j′2,…,j′n为排序后的各个工件,r′1,r′2,…,r′n为对应的释放时间。
2)对工件j′k(i=1,2,…,n),如果iu≤r′k<(i+1)u成立,其中i为时间窗口的序号,则j′k属于第i个时间窗口对应的工件集合。
在采用上述输入特征属性的基础上,基于极限学习机(ELM)模型框架,采用如下步骤建立调度子问题性能指标预报模型。需要说明的是,由于调度子问题性能指标预报模型训练过程所需的训练数据是随着算法的运行逐步得到的,因此,所采用的极限学习机应基于在线学习框架。
步骤(1):模型参数初始化
给定基于结构风险最小化的极限学习机的隐层节点数L,采用径向基函数作为特征变换函数,函数形式为i=1,2,…,L,其中ai,bi为径向基函数的参数,ai维数为2I+3维,该值从[-1 1]中随机选取,bi为1维,取值为从 随机选取;根据极限学习机算法的逼近理论,只要隐层节点数足够大,算法能够以任意精度逼近任意的函数,因此本发明中隐层节点数选取一个相对较大的值即可,如L>20。
于是,生成的极限学习机特征映射矩阵H(X)为:
步骤(2):算法初始化
对于时刻t而言,极限学习机ELM的权值参数Wt初始化值为:
其中:
Xt表示t时刻已经获得的样本,样本数量为N,于是产生的极限学习机映射矩阵为:
ν为惩罚系数;
步骤(3):在线学习过程
t+1时刻极限学习机权值参数Wt+1按照如下方式更新:
Wt+1=KtWt+KtAt
-1H(XIC)TYIC
其中:
Kt=I-At
-1H(XIC)T[H(XIC)At
-1H(XIC)T+Ik×k]-1H(XIC)
At+1
-1=KtAt
-1
Ik×k为对角线为1的单位矩阵;
Kt、At
-1为引入的中间变量,从而简化更新后权值参数Wt+1的表达形式;
步骤(4):训练过程终止
当所有的训练数据都参与训练后,训练过程终止,此时输出训练完成后的极限学习机权值参数W;
(四)基于性能指标预报模型和解相似度分析的差分进化算法
本发明提出了基于性能指标预报模型和解相似度分析的差分进化算法,用来求解原光刻工序动态调度问题,动态地给出调度方案。所提出的差分进化算法在计算机上由如下步骤进行:
步骤(1):算法初始化
每个设备选择调度子问题的解可表示为:
A=[r1,r2,…,rn]
其中,rj为表示工件j对应加工机器的实数,rj∈(0,|μj|]。
在算法初始化中,首先产生NP个设备选择调度子问题的解形成初始解集合(也可称为初始种群),产生方法为:为每个工件,从其对应的可选设备集合μj中随机选择一台设备作为其加工设备。同时,设定差分进化算法(DE)中的若干参数,包括交叉率CR,缩放因子F。在本发明中,CR∈[0,1],F∈[0.5,1]。算法的停止条件为算法运行时间达到运行时间限制为止。
在算法初始化中,还需要训练产生初始的调度子问题性能指标预报模型。在本发明所针对的问题中,一旦解集合中设备选择调度子问题的解给定,那么,排序子问题中的各个参数也即确定。本发明采用分枝定界算法(B&B)(Rabia Nessah,Imed Kacem.Branch-and-bound method for minimizing the weighted completion time scheduling problem on a single machine with release dates.Computers&Operations research,2012,39:471-478)来分别求解各个排序子问题,从而获取相应的每个设备选择调度子问题解的性能指标值。上述求解过程完成后,即可使用所获得的数据,采用前述第三节的方法训练产生初始的调度子问题性能指标预报模型。在算法初始化阶段,进行精确评价的解的数量为N0个,在本发明中,选择N0=NP/2。
步骤(2):差分变异
针对给定解集合中的各个解,首先计算解的相似度矩阵:
在上述解相似度矩阵Md基础上,计算选择概率矩阵Mp:
其中,i,j=1,2,…,NP。从当前解集合中随机选择一个解,记为基于选择概率矩阵Mp可得到选择概率向量Mp(r1,·)(即选择概率矩阵Mp的第r1行),针对该选择概率向量,实施轮盘赌方法,选择2个互不相同的解(即选择概率与其距离近似成反比)。不失一般性,记所选中的另两个解为采用如下公式来获得变异后的解:
步骤(3):交叉操作
在本发明中,采用如下方法进行解的交叉操作:分别对于步骤(2)产生的变异后解的每个元素,随机产生一个实数r∈[0,1],如果r≤CR,则该元素替换目标解中相应位置的元素,否则保留目标解中相应位置的元素。
步骤(4):评价与选择
在上述寻优操作完成之后,本发明需要对解集合中的所有目标解进行评价。评价过程分成两个阶段,首先进行粗评价,其次进行精确评价。在粗评价阶段,采用前述建立的调度子问题性能评价模型对解集合中的每个设备选择调度子问题的解(同时也是差分进化算法解集合中的每个解)进行性能评价,在此基础上,选择前p的较好解(即对应的总加权流经时间较小的解),采用前述分枝定界算法进行对其进行精确评价。精确评价所获得的数据同时用于调度子问题性能评价模型的在线训练,在线训练的方法如第三节所述。在评价过程完成以后,采用标准轮盘赌方法从解集合中选择出新的下一代解集合。
图1:基于指标预报和解相似度分析的光刻工序动态调度方法硬件系统结构示意图。
图2:基于指标预报和解相似度分析的光刻工序动态调度方法流程示意图。
本发明提出的动态调度方法依赖于相关数据采集系统,由调度系统客户端和调度服务器实现。在实际半导体生产线光刻区动态调度中应用本发明的软硬件架构示意图如图1所示,本发明的实施方式如下。
步骤(1):获取上述半导体生产线光刻区动态调度问题对应的数据。
包括设备数量、各设备的释放时间、待加工的工件的释放时间/加工时间/优先级/可加工机器组信息,并存储至调度数据库中,并采用“发明内容”第一节的方法,形成待求解的半导体生产线光刻区动态调度问题实例。
步骤(2):光刻区动态调度问题分解
针对所获得的光刻区动态调度问题实例,采用“发明内容”第二节的方法,将该实例分解为设备选择调度子问题和工件排序调度子问题。在后续的步骤中,上述两个子问题迭代求解,形成最终的光刻区动态调度方案。
步骤(3):光刻区动态调度问题求解
针对上述光刻区动态调度问题实例,采用“发明内容”第三节和第四节的方法,求解上述问题,形成动态调度方案。
步骤(3.1):差分进化算法初始化
设定差分进化算法与调度子问题性能指标预报模型的相关参数:
差分进化算法中的解集合规模:NP=30;
差分进化算法中的缩放因子:F=0.95;
差分进化算法中的交叉率:CR=0.5;
差分进化算法中的精确评价比例:p=20%;
差分进化算法中的停止条件:需要根据不同的问题场景,设定不同的算法运
行时间限制,具体见后续实验结果说明;
步骤(3.2):调度子问题性能指标预报模型初始化
调度子问题性能指标预报模型中的区间划分参数:I=6;
调度子问题性能指标预报模型中的隐层节点数:L=20;
调度子问题性能指标预报模型中的惩罚因子ν,按经验取2-15;
在上述参数设置基础上,采用本发明“发明内容”第四节步骤(2)的方法,产生设备选择调度子问题的NP个初始解形成初始解集合,然后,随机选择NP/2个解,采用分枝定界算法进行精确评价,获得各个解对应的调度目标函数值(即总加权流经时间)。在此基础上,采用“发明内容”第三节的预报模型学习方法,利用所获得的调度子问题及其对应的目标函数值的数据,获得初始的调度子问题性能指标预报模型。
步骤(3.3):差分变异和交叉
采用“发明内容”第四节步骤(3)和步骤(4)的方法,对解集合中的解,首先进行差分变异操作,然后进行交叉操作。操作完成后,形成新的解集合。
步骤(3.4):评价与选择
采用“发明内容”第四节步骤(5)的方法,对解集合中的解,首先采用调度子问题性能指标预报模型进行粗评价,在此基础上,选择前p%的较好解进行精确评价,然后,采用标准轮盘赌方法进行选择,形成新一代解集合。
步骤(3.5):在线训练更新预报模型参数,形成新的调度子问题性能指标预报模型
采用“发明内容”第三节的方法,结合步骤(3.4)中获得的前p%的较好解的精确评价数据,在线训练,更新原预报模型参数,形成新的调度子问题性能指标预报模型。
步骤(3.6):算法终止条件判别
若算法运行时间已达到设定值,则停止;否则转步骤(3.3)进行迭代优化。
根据上述所提出的基于指标预报和解相似度分析的光刻工序动态调度方法,本发明做了大量的仿真试验,运行的硬件环境为:P4 2.8GHz CPU,4G RAM,操作系统为Windows 7。由于篇幅所限,仅列出部分实验结果。首先,基于实际光刻区的生产数据,随机产生若干动态调度问题实例,其中,工件的加工时间、权重、释放时间按如下方式产生:
pl,j~U[1,20]
wj~U[1,10]
其中,δ(δ∈R+)为阻塞系数,反映该问题中工件释放间隔时间的密集程度;n为工件数量,m为机器数量,U[·,·]表示给定范围的均匀分布,avg(pl,j)为所有加工时间的平均值。为验证本发明方法的有效性,在数值计算中对上述已产生的问题实例基础上对工件的加工时间、释放时间参数施加了随机扰动。表1列出了本发明所提出的调度方法(简记为SM-DE)与文献中的典型差分进化优化算法(M.G.Epitropakis,D.K.Tasoulis,N.G.Pavlidis,V.P.Plagianakos,M.N.Vrahatis.Enhancing differential evolution utilizing proximity-based mutation operators.IEEE Transactions on Evolutionary Computation,2011,15(1):99-119,简记为Pro-DE)在所随机产生的调度问题实例上的应用对比。
表1 实验结果对比
在表1中,avgTFT,stdTFT分别为调度问题实例采用相应算法求解20次得到的总加权流经时间的平均值和方差,算法允许运行时间为100秒,在表1中较好的解标注为“加黑”状态。可以看出,在算法允许运行时间相同的条件下,SM-DE在绝大多数的情况都优于Pro-DE算法。
Claims (2)
- 基于指标预报和解相似度分析的光刻工序动态调度方法,其特征在于,该方法是一种采用基于解相似度分析的差分进化算法进行迭代优化的过程中,不断地利用精确评价所获得的工件排序调度子问题实例和调度解性能指标数据,对工件排序调度子问题性能指标预报模型进行在线学习,以提升预报模型的预报精度,进而改善差分进化算法寻优效率和效果的方法;所述方法在计算机上依次按如下步骤实现:步骤(1):获取半导体生产线光刻区动态调度问题对应的数据;基于半导体生产线上的制造执行系统或其他数据采集系统,获取与光刻区动态调度问题相关的数据,具体包括光刻区可用设备数量、各设备的释放时间、光刻板类型及数量、待加工的各工件的释放时间/加工时间/优先级/可加工设备信息,并存储至调度数据库中,形成待求解的半导体生产线光刻区动态调度问题实例;步骤(2):光刻区动态调度问题分解针对所获得的光刻区动态调度问题实例,将该实例分解为设备选择调度子问题和工件排序调度子问题;步骤(3):光刻区动态调度问题求解步骤(3.1):差分进化算法初始化设定差分进化算法与调度子问题性能指标预报模型的相关参数:差分进化算法中的解集合规模NP,在区间[20,1000]之间;差分进化算法中的缩放因子F,在区间[0.5,1]之间;差分进化算法中的交叉率CR,在区间[0,1]之间;差分进化算法中的精确评价比例p,在区间[10%,30%]之间;差分进化算法中的停止条件:需要根据不同的需要,设定不同的算法运行时间限制,在区间[5秒,2000秒]之间;步骤(3.2):调度子问题性能指标预报模型初始化调度子问题性能指标预报模型中的区间划分参数I,在区间[4,8]之间;调度子问题性能指标预报模型中的径向基函数的参数:ai维数为2I+3维,其 每一维的取值从[-11]中随机选取,bi为1维,取值为从随机选取;调度子问题性能指标预报模型中的隐层节点数L,在区间[5,100]之间;调度子问题性能指标预报模型中的惩罚因子ν,按经验取2-15;在上述参数设置基础上,随机产生设备选择调度子问题的NP个初始解形成初始解集合,然后,随机选择1至NP个解,采用分枝定界算法进行精确评价,获得各个解对应的调度目标函数值;在此基础上,采用极限学习机的在线学习方法,利用所获得的调度子问题及其对应的目标函数值的数据,获得初始的调度子问题性能指标预报模型;步骤(3.3):差分变异和交叉对解集合中的解,首先计算其距离矩阵,在此基础上进行基于解相似性分析的差分变异操作,最后进行交叉操作;操作完成后,形成新的解集合;步骤(3.4):基于粗评价与精确评价相结合的评价与选择对解集合中的解,首先采用调度子问题性能指标预报模型进行粗评价,在此基础上,从当前解集合中选择1至NP较好解进行精确评价,然后,采用标准轮盘赌方法进行选择,形成新一代解集合;步骤(3.5):使用极限学习机的在线学习方法,在线学习更新调度子问题性能指标预报模型参数,形成新的调度子问题性能指标预报模型;步骤(3.6):算法终止条件判别若算法运行时间已达到设定值,则停止;否则转步骤(3.3)进行迭代优化。
- 如权利要求2所述基于指标预报和解相似度分析的光刻工序动态调度方法,其特征在于,所述的调度子问题性能指标预报模型的输入包括如下属性:●光刻板类别数量:NB●指派到当前光刻机的工件释放时间的集中程度:Gr●采用最小加权加工时间规则所获得的目标函数值:TWFTswpt●区间i对应工件的总数量:|Ωi|,i=1,2,…,I.其中,pl,j,wj和rj分别为工件j在光刻机l上的加工时间、权重、释放时 间,j=1,2,…,n,Ωi为分配到区间i的工件集合,区间的划分方法为:把整个调度时间轴划分为I个区间,I为整数,每个区间的长度为u=(ri,max+pi,max-ri,min)/I,pi,max为所有工件中加工时间的最大值,ri,max和ri,min为所有工件释放时间的最大值和最小值,区间的起始时刻为ri,min;Cr的计算步骤如下:1)令Li(i=1,2,…,I)表示第i个区间的总负载,Li,j为工件j对Li的贡献;2)对工件j(j∈Ωi),令stj=rj,则cj=rj+pl,j,通过下式计算Li,j:4)通过下式计算Cr:1)将该光刻机上的所有工件按其释放时间由小到大的顺序排序,不失一般性,记j′1,j′2,…,j′n为排序后的各个工件,r′1,r′2,…,r′n为对应的释放时间;2)对工件j′k(k=1,2,…,n),如果iu≤r′k<(i+1)u成立,其中i为时间窗口的序号,则j′k属于第i个时间窗口对应的工件集合;按照上述输入属性选择方法,对给定的单台设备的工件排序调度子问题,用于构建预测模型的特征共有2I+4个,根据问题规模的不同,I的取值在区间[4,8]之间。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410805103.5 | 2014-12-23 | ||
| CN201410805103.5A CN104536412B (zh) | 2014-12-23 | 2014-12-23 | 基于指标预报和解相似度分析的光刻工序动态调度方法 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2016101181A1 true WO2016101181A1 (zh) | 2016-06-30 |
Family
ID=52851955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2014/094837 Ceased WO2016101181A1 (zh) | 2014-12-23 | 2014-12-24 | 基于指标预报和解相似度分析的光刻工序动态调度方法 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN104536412B (zh) |
| WO (1) | WO2016101181A1 (zh) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590603A (zh) * | 2017-09-11 | 2018-01-16 | 合肥工业大学 | 基于改进变邻域搜索和差分进化算法的调度方法及系统 |
| CN109885563A (zh) * | 2019-02-01 | 2019-06-14 | 沈阳航空航天大学 | 一种基于动态规则约束的数据清洗算法 |
| CN110991732A (zh) * | 2019-11-28 | 2020-04-10 | 武汉理工大学 | 一种基于能耗聚类的建材装备制造过程优化调度方法 |
| CN111784058A (zh) * | 2020-07-06 | 2020-10-16 | 兰州理工大学 | 一种生产线递阶分解建模并行寻优技术 |
| CN112232578A (zh) * | 2020-10-26 | 2021-01-15 | 上海华力集成电路制造有限公司 | 基于关键指标算法的光刻机台效能评价系统及其应用方法 |
| CN112836359A (zh) * | 2021-01-21 | 2021-05-25 | 红塔烟草(集团)有限责任公司 | 一种卷烟生产企业供配电设备的安全性评估方法 |
| CN112947345A (zh) * | 2021-03-09 | 2021-06-11 | 河海大学 | 面向确定性可重入传感器车间动态批调度智能优化方法 |
| CN113011785A (zh) * | 2021-04-21 | 2021-06-22 | 广东机电职业技术学院 | 基于自适应调整参数的多订单混合调度优化方法、介质 |
| CN113341896A (zh) * | 2021-06-07 | 2021-09-03 | 电子科技大学 | 面向离散制造的动态集成车间调度与装配序列规划方法 |
| CN113780883A (zh) * | 2021-09-26 | 2021-12-10 | 无锡唯因特数据技术有限公司 | 生产车间调度方法、装置和存储介质 |
| CN114186813A (zh) * | 2021-11-25 | 2022-03-15 | 西北工业大学 | 考虑切换时间的两班倒多任务调度优化方法 |
| CN115941581A (zh) * | 2022-09-30 | 2023-04-07 | 咪咕互动娱乐有限公司 | 云游戏路由调度方法、设备、存储介质及装置 |
| CN116149263A (zh) * | 2021-11-18 | 2023-05-23 | 中国科学院沈阳自动化研究所 | 基于多工件并行生产的离散型柔性机加生产线控制方法 |
| CN116661947A (zh) * | 2023-05-25 | 2023-08-29 | 中国电子科技集团公司第二十八研究所 | 一种面向不同训练内容的训练环境一键式切换方法 |
| CN116679628A (zh) * | 2023-05-12 | 2023-09-01 | 闽都创新实验室 | 一种考虑备料计划的柔性作业车间动态调度优化方法及系统 |
| CN116869550A (zh) * | 2023-05-31 | 2023-10-13 | 上海术理智能科技有限公司 | 基于时域能量的运动想象时间校准方法及装置 |
| CN116165892B (zh) * | 2023-02-16 | 2023-10-27 | 广东工业大学 | 模型预测控制的半自动化产线节能策略制定方法和系统 |
| CN117707096A (zh) * | 2024-02-01 | 2024-03-15 | 张家港广大特材股份有限公司 | 基于性能需求的特种钢材加工工艺动态优化方法及系统 |
| CN118672756A (zh) * | 2024-08-23 | 2024-09-20 | 济南浪潮数据技术有限公司 | 一种宿主机调度方法、装置、设备、介质及计算机程序 |
| CN119362110A (zh) * | 2024-12-30 | 2025-01-24 | 金锚电力控股有限公司 | 面向铝基接线端子加工的冲压控制系统和方法 |
| CN120104607A (zh) * | 2025-05-07 | 2025-06-06 | 湘潭大学 | 工程机械的采集数据预处理方法、系统及介质 |
| CN120746242A (zh) * | 2025-09-05 | 2025-10-03 | 山东大学 | 海港综合能源系统全流程物流-能量联合调度方法及系统 |
| CN121504103A (zh) * | 2026-01-13 | 2026-02-10 | 福建科烨数控科技有限公司 | 机械加工产线生产资源优化管理方法及系统 |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104881688A (zh) * | 2015-06-11 | 2015-09-02 | 电子科技大学 | 一种两阶段的基于差分进化和模糊c-均值的聚类算法 |
| EP3316193B1 (en) * | 2016-11-01 | 2023-04-12 | Hitachi, Ltd. | Production support system |
| CN109523136A (zh) * | 2018-10-29 | 2019-03-26 | 同济大学 | 一种面向智能制造的调度知识管理系统 |
| CN111190393B (zh) * | 2018-11-14 | 2021-07-23 | 长鑫存储技术有限公司 | 半导体制程自动化控制方法及装置 |
| CN112149987B (zh) * | 2020-09-17 | 2024-09-06 | 清华大学 | 基于深度强化学习的多目标柔性作业车间调度方法和装置 |
| CN113031542A (zh) * | 2021-02-22 | 2021-06-25 | 同济大学 | 一种基于负载均衡的半导体生产线动态调度方法 |
| CN113157995A (zh) * | 2021-03-17 | 2021-07-23 | 惠州市汇流实业有限公司 | 一种数据归类方法、门窗参数归尺方法、处理装置以及存储介质 |
| CN113240353B (zh) * | 2021-07-12 | 2021-11-02 | 南京擎天全税通信息科技有限公司 | 一种面向跨境电商的出口工厂分类方法及装置 |
| CN115049140A (zh) * | 2022-06-27 | 2022-09-13 | 武汉尉来科技有限责任公司 | 一种雕塑工程用3d模型柔性制造系统 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6604012B1 (en) * | 1999-10-23 | 2003-08-05 | Samsung Electronics Co., Ltd. | Lots dispatching method for variably arranging processing equipment and/or processing conditions in a succeeding process according to the results of a preceding process and apparatus for the same |
| JP2005267371A (ja) * | 2004-03-19 | 2005-09-29 | Trecenti Technologies Inc | ロットディスパッチ方法および半導体装置の製造方法 |
| CN103310285A (zh) * | 2013-06-17 | 2013-09-18 | 同济大学 | 可用于半导体生产线动态调度的性能预测方法 |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6845280B1 (en) * | 2002-11-26 | 2005-01-18 | Advanced Micro Devices, Inc. | Work in progress management program interface |
| CN100580594C (zh) * | 2008-06-11 | 2010-01-13 | 清华大学 | 基于加工能力特征模型的机器组调度方法 |
| CN101782769B (zh) * | 2010-03-08 | 2011-10-26 | 清华大学 | 一种基于指标补偿的平均流经时间快速预测方法 |
| CN101788819B (zh) * | 2010-03-08 | 2011-09-14 | 清华大学 | 大规模生产过程一种基于迭代式分解和流松弛的调度方法 |
| CN103116324B (zh) * | 2012-12-17 | 2014-06-04 | 清华大学 | 基于指标预测和在线学习的微电子生产线调度方法 |
| CN103106331B (zh) * | 2012-12-17 | 2015-08-05 | 清华大学 | 基于降维和增量式极限学习机的光刻线宽智能预测方法 |
| CN103217960B (zh) * | 2013-04-08 | 2015-04-29 | 同济大学 | 一种半导体生产线动态调度策略自动选择方法 |
| CN103439886B (zh) * | 2013-07-26 | 2016-01-20 | 同济大学 | 一种半导体生产线自适应动态调度装置 |
-
2014
- 2014-12-23 CN CN201410805103.5A patent/CN104536412B/zh active Active
- 2014-12-24 WO PCT/CN2014/094837 patent/WO2016101181A1/zh not_active Ceased
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6604012B1 (en) * | 1999-10-23 | 2003-08-05 | Samsung Electronics Co., Ltd. | Lots dispatching method for variably arranging processing equipment and/or processing conditions in a succeeding process according to the results of a preceding process and apparatus for the same |
| JP2005267371A (ja) * | 2004-03-19 | 2005-09-29 | Trecenti Technologies Inc | ロットディスパッチ方法および半導体装置の製造方法 |
| CN103310285A (zh) * | 2013-06-17 | 2013-09-18 | 同济大学 | 可用于半导体生产线动态调度的性能预测方法 |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107590603A (zh) * | 2017-09-11 | 2018-01-16 | 合肥工业大学 | 基于改进变邻域搜索和差分进化算法的调度方法及系统 |
| CN109885563B (zh) * | 2019-02-01 | 2023-10-20 | 沈阳航空航天大学 | 一种基于动态规则约束的数据清洗算法 |
| CN109885563A (zh) * | 2019-02-01 | 2019-06-14 | 沈阳航空航天大学 | 一种基于动态规则约束的数据清洗算法 |
| CN110991732A (zh) * | 2019-11-28 | 2020-04-10 | 武汉理工大学 | 一种基于能耗聚类的建材装备制造过程优化调度方法 |
| CN111784058A (zh) * | 2020-07-06 | 2020-10-16 | 兰州理工大学 | 一种生产线递阶分解建模并行寻优技术 |
| CN111784058B (zh) * | 2020-07-06 | 2022-09-30 | 兰州理工大学 | 一种生产线递阶分解建模并行寻优技术 |
| CN112232578A (zh) * | 2020-10-26 | 2021-01-15 | 上海华力集成电路制造有限公司 | 基于关键指标算法的光刻机台效能评价系统及其应用方法 |
| CN112836359B (zh) * | 2021-01-21 | 2024-05-07 | 红塔烟草(集团)有限责任公司 | 一种卷烟生产企业供配电设备的安全性评估方法 |
| CN112836359A (zh) * | 2021-01-21 | 2021-05-25 | 红塔烟草(集团)有限责任公司 | 一种卷烟生产企业供配电设备的安全性评估方法 |
| CN112947345A (zh) * | 2021-03-09 | 2021-06-11 | 河海大学 | 面向确定性可重入传感器车间动态批调度智能优化方法 |
| CN112947345B (zh) * | 2021-03-09 | 2022-04-01 | 河海大学 | 面向确定性可重入传感器车间动态批调度智能优化方法 |
| CN113011785A (zh) * | 2021-04-21 | 2021-06-22 | 广东机电职业技术学院 | 基于自适应调整参数的多订单混合调度优化方法、介质 |
| CN113011785B (zh) * | 2021-04-21 | 2023-06-13 | 广东机电职业技术学院 | 基于自适应调整参数的多订单混合调度优化方法、介质 |
| CN113341896A (zh) * | 2021-06-07 | 2021-09-03 | 电子科技大学 | 面向离散制造的动态集成车间调度与装配序列规划方法 |
| CN113341896B (zh) * | 2021-06-07 | 2022-08-05 | 电子科技大学 | 面向离散制造的动态集成车间调度与装配序列规划方法 |
| CN113780883A (zh) * | 2021-09-26 | 2021-12-10 | 无锡唯因特数据技术有限公司 | 生产车间调度方法、装置和存储介质 |
| CN116149263A (zh) * | 2021-11-18 | 2023-05-23 | 中国科学院沈阳自动化研究所 | 基于多工件并行生产的离散型柔性机加生产线控制方法 |
| CN114186813A (zh) * | 2021-11-25 | 2022-03-15 | 西北工业大学 | 考虑切换时间的两班倒多任务调度优化方法 |
| CN115941581A (zh) * | 2022-09-30 | 2023-04-07 | 咪咕互动娱乐有限公司 | 云游戏路由调度方法、设备、存储介质及装置 |
| CN116165892B (zh) * | 2023-02-16 | 2023-10-27 | 广东工业大学 | 模型预测控制的半自动化产线节能策略制定方法和系统 |
| US12174599B2 (en) | 2023-02-16 | 2024-12-24 | Guangdong University Of Technology | Method and system for formulating an energy-saving strategy for semi-automatic production line based on model predictive control |
| CN116679628A (zh) * | 2023-05-12 | 2023-09-01 | 闽都创新实验室 | 一种考虑备料计划的柔性作业车间动态调度优化方法及系统 |
| CN116661947A (zh) * | 2023-05-25 | 2023-08-29 | 中国电子科技集团公司第二十八研究所 | 一种面向不同训练内容的训练环境一键式切换方法 |
| CN116869550A (zh) * | 2023-05-31 | 2023-10-13 | 上海术理智能科技有限公司 | 基于时域能量的运动想象时间校准方法及装置 |
| CN117707096A (zh) * | 2024-02-01 | 2024-03-15 | 张家港广大特材股份有限公司 | 基于性能需求的特种钢材加工工艺动态优化方法及系统 |
| CN118672756A (zh) * | 2024-08-23 | 2024-09-20 | 济南浪潮数据技术有限公司 | 一种宿主机调度方法、装置、设备、介质及计算机程序 |
| CN119362110A (zh) * | 2024-12-30 | 2025-01-24 | 金锚电力控股有限公司 | 面向铝基接线端子加工的冲压控制系统和方法 |
| CN120104607A (zh) * | 2025-05-07 | 2025-06-06 | 湘潭大学 | 工程机械的采集数据预处理方法、系统及介质 |
| CN120746242A (zh) * | 2025-09-05 | 2025-10-03 | 山东大学 | 海港综合能源系统全流程物流-能量联合调度方法及系统 |
| CN121504103A (zh) * | 2026-01-13 | 2026-02-10 | 福建科烨数控科技有限公司 | 机械加工产线生产资源优化管理方法及系统 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104536412A (zh) | 2015-04-22 |
| CN104536412B (zh) | 2017-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016101181A1 (zh) | 基于指标预报和解相似度分析的光刻工序动态调度方法 | |
| CN112949837A (zh) | 一种基于可信网络的目标识别联邦深度学习方法 | |
| Wang et al. | An improved consensus-based model for large group decision making problems considering experts with linguistic weighted information | |
| CN116307215A (zh) | 一种电力系统的负荷预测方法、装置、设备及存储介质 | |
| WO2017071369A1 (zh) | 一种预测用户离网的方法和设备 | |
| CN116187835A (zh) | 一种基于数据驱动的台区理论线损区间估算方法及系统 | |
| CN104698838B (zh) | 基于论域动态划分和学习的模糊调度规则挖掘方法 | |
| CN110750572A (zh) | 一种科技成果启发式评价的自适应方法和装置 | |
| Son et al. | Building projects with time–cost–quality–environment trade-off optimization using adaptive selection slime mold algorithm | |
| CN118940906A (zh) | 业务风险预测方法、装置、设备、存储介质及程序产品 | |
| Son et al. | Optimization of construction projects time-cost-quality-environment trade-off problem using adaptive selection slime mold algorithm | |
| CN112990575A (zh) | 基于知识图谱的产业发展路径预测方法及其装置 | |
| CN113470739B (zh) | 一种基于混合隶属度随机块模型的蛋白质相互作用预测方法和系统 | |
| CN116595362A (zh) | 多分类预测模型训练方法、绩效考核分数预测方法及装置 | |
| Ni et al. | The analysis and research of clustering algorithm based on PCA | |
| Li | Applying grey system theory to evaluate the relationship between industrial characteristics and innovation capabilities within Chinese high-tech industries | |
| Pavliuk et al. | Machine-learning method for analyzing and predicting the number of hospitalizations of children during the fourth wave of the COVID-19 pandemic in the Lviv region | |
| CN107578130A (zh) | 一种结构和参数联合学习的tsk型模糊系统的铜期货价格预测的方法 | |
| Hsu et al. | Large-Scale Data Retrieve in Road Networks With Optimized k-Retriever Routing | |
| CN113034316B (zh) | 一种专利价值转换的分析方法及系统 | |
| Lian et al. | Training algorithm for radial basis function neural network based on quantum-behaved particle swarm optimization | |
| CN116957161A (zh) | 工单预警方法、设备及计算机可读存储介质 | |
| CN108509984A (zh) | 激活值量化训练方法及装置 | |
| Rudy et al. | GACO: a parallel evolutionary approach to multi-objective scheduling | |
| CN106447065A (zh) | 碳纤维原丝生产过程中凝固浴环节性能指标的预测方法 |
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: 14908749 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: 14908749 Country of ref document: EP Kind code of ref document: A1 |









