A fuzzy hierarchical reinforcement learning based scheduling method for semiconductor wafer manufacturing systems

Scheduling semiconductor wafer manufacturing systems has been viewed as one of the most challenging optimization problems owing to the complicated constraints, and dynamic system environment. This paper proposes a fuzzy hierarchical reinforcement learning (FHRL) approach to schedule a SWFS, which controls the cycle time (CT) of each wafer lot to improve on-time delivery by adjusting the priority of each wafer lot. To cope with the layer correlation and wafer correlation of CT due to the re-entrant process constraint, a hierarchical model is presented with a recurrent reinforcement learning (RL) unit in each layer to control the corresponding sub-CT of each integrated circuit layer. In each RL unit, a fuzzy reward calculator is designed to reduce the impact of uncertainty of expected finishing time caused by the rematching of a lot to a delivery batch. The results demonstrate that the mean deviation (MD) between the actual and expected completion time of wafer lots under the scheduling of the FHRL approach is only about 30 % of the compared methods in the whole SWFS.     

Physics-guided logistic classification for tool life modeling and process parameter optimization in machining

This paper describes a physics-guided logistic classification method for tool life modeling and process parameter optimization in machining. Tool life is modeled using a classification method since the exact tool life cannot be measured in a typical production environment where tool wear can only be directly measured when the tool is replaced. In this study, laboratory tool wear experiments are used to simulate tool wear data normally collected during part production. Two states are defined: tool not worn (class 0) and tool worn (class 1). The non-linear reduction in tool life with cutting speed is modeled by applying a logarithmic transformation to the inputs for the logistic classification model. A method for interpretability of the logistic model coefficients is provided by comparison with the empirical Taylor tool life model. The method is validated using tool wear experiments for milling. Results show that the physics-guided logistic classification method can predict tool life using limited datasets. A method for pre-process optimization of machining parameters using a probabilistic machining cost model is presented. The proposed method offers a robust and practical approach to tool life modeling and process parameter optimization in a production environment.     

Intelligent tool wear monitoring based on parallel residual and stacked bidirectional long short-term memory network

Effective tool wear monitoring (TWM) is essential for accurately assessing the degree of tool wear and for timely preventive maintenance. Existing data-driven monitoring methods mainly rely on complex feature engineering, which reduces the monitoring efficiency. This paper proposes a novel TWM model based on a parallel residual and stacked bidirectional long short-term memory (PRes–SBiLSTM) network. First, a parallel residual network (PResNet) is used to extract the multi-scale local features of sensor signals adaptively. Subsequently, a stacked bidirectional long short-term memory (SBiLSTM) network is used to obtain the time-series features related to the tool wear characteristics. Finally, the predicted tool wear value is outputted through a fully connected network. A smoothing correction method is applied to improve the prediction accuracy. The proposed model is experimentally verified to have a high prediction accuracy without sacrificing its generalization ability. A TWM system framework based on the PRes–SBiLSTM network is proposed, which has a certain reference value for TWM in actual industrial environments.     

Improving human robot collaboration through Force/Torque based learning for object manipulation

Human–Robot Collaboration (HRC) is a term used to describe tasks in which robots and humans work together to achieve a goal. Unlike traditional industrial robots, collaborative robots need to be adaptive; able to alter their approach to better suit the situation and the needs of the human partner. As traditional programming techniques can struggle with the complexity required, an emerging approach is to learn a skill by observing human demonstration and imitating the motions; commonly known as Learning from Demonstration (LfD). In this work, we present a LfD methodology that combines an ensemble machine learning algorithm (i.e. Random Forest (RF)) with stochastic regression, using haptic information captured from human demonstration. The capabilities of the proposed method are evaluated using two collaborative tasks; co-manipulation of an object (where the human provides the guidance but the robot handles the objects weight) and collaborative assembly of simple interlocking parts. The proposed method is shown to be capable of imitation learning; interpreting human actions and producing equivalent robot motion across a diverse range of initial and final conditions. After verifying that ensemble machine learning can be utilised for real robotics problems, we propose a further extension utilising Weighted Random Forest (WRF) that attaches weights to each tree based on its performance. It is then shown that the WRF approach outperforms RF in HRC tasks.     

Land‐use dynamic discovery based on heterogeneous mobility sources

Nowadays, cities are the most relevant type of human settlement and their population has been endlessly growing for decades. At the same time, we are witnessing an explosion of digital data that capture many different aspects and details of city life. This allows detecting human mobility patterns in urban areas with more detail than ever before. In this context, based on the fusion of mobility data from different and heterogeneous sources, such as public transport, transport‐network connectivity and Online Social Networks, this study puts forward a novel approach to uncover the actual land use of a city. Unlike previous solutions, our work avoids a time‐invariant approach and it considers the temporal factor based on the assumption that urban areas are not used by citizens all the time in the same manner. We have tested our solution in two different cities showing high accuracy rates.     

On‐off iterative adaptive controller for low‐power micro‐robotic step regulation

A novel model‐free iterative adaptive controller is presented for low‐power control of piezoelectric actuators. The controller uses simple adaptation rules based on known general behavior of piezoelectric actuators to adjust on‐off switching times to drive piezoelectric actuators through a desired transient step motion. Adaptation rules are based on small numbers of measurements taken during each iteration of the actuator movement. Combined with the use of only on‐off control inputs, controller implementation can be possible at much lower overall power levels than would be needed to implement a conventional control strategy such as through pulse‐width‐modulation (PWM) with real‐time feedback. Such power savings are particularly important for the intended controller application to piezoelectric microactuators driving autonomous terrestrial micro‐robots. A method for predicting convergence of systems with nominally linear dynamics and unknown, bounded nonlinearities is described, and applied to a sample target piezoelectric actuator. The controller is tested in simulation and experimentally on a piezoelectric cantilever actuator, and shows predicted convergence to the desired response. Copyright © 2011 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

Heuristic collision-free path planning for an autonomous platform

In this paper, a heuristic and learning, algorithmic scheme for collision-free navigation is presented. This scheme determines an optimum collision-free navigation path of an autonomous platform by using a trial and error process, past navigation knowledge and current information extracted from the generated surrounding environment.     

A Heuristic Approach to the Discovery of Macro-Operators

This paper describes a heuristic approach to the discovery of useful macro-operators (macros) in problem solving. The approach has been implemented in a program, MACLEARN, that has three parts: macro-proposer, static filter, and dynamic filter. Learning occurs during problem solving, so that performance improves in the course of a single problem trial. Primitive operators and macros are both represented within a uniform representational framework that is closed under composition. This means that new macros can be defined in terms of others, which leads to a definitional hierarchy. The representation also supports the transfer of macros to related problems. MACLEARN is embedded in a supporting system that carries out best-first search. Experiments in macro learning were conducted for two classes of problems: peg solitaire (generalized Hi-Q puzzle), and tile sliding (generalized Fifteen puzzle). The results indicate that MACLEARN'S filtering heuristics all improve search performance, sometimes dramatically. When the system was given practice on simpler training problems, it learned a set of macros that led to successful solutions of several much harder problems.     

A Universal Method of Scientific Inquiry

A paradigm of scientific discovery is defined within a first-order logical framework. Within this paradigm, the concept of successful scientific inquiry is formalized and investigated. Among other results, it is shown that a simple method of scientific inquiry is universal in the sense that it leads to success on every problem for which success is in principle possible.     

选择性集成算法分类与比较

选择性集成是当前机器学习领域的研究热点之一。由于选择性集成属于NP"难"问题,人们多利用启发式方法将选择性集成转化为其他问题来求得近似最优解,因为各种算法的出发点和描述角度各不相同,现有的大量选择性集成算法显得繁杂而没有规律。为便于研究人员迅速了解和应用本领域的最新进展,本文根据选择过程中核心策略的特征将选择性集成算法分为四类,即迭代优化法、排名法、分簇法、模式挖掘法;然后利用UCI数据库的20个常用数据集,从预测性能、选择时间、结果集成分类器大小三个方面对这些典型算法进行了实验比较;最后总结了各类方法的优缺点,并展望了选择性集成的未来研究重点。