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.     

Screening model for assessing ‘cost’ of minimum flow requirements in the Svartå River,Sweden

The minimum flow requirements in the Svartå River in Sweden are directed at maintaining fishlife and providing suitable dilution for waste flows. The implications of varying the minimum flow requirements in the river are examined using a mixed integer optimisation model. The model is formulated as a modified method-of-weights technique with the economic issues of hydro-electricity generation, irrigation and urban water supply placed in the objective function and the minimum flows specified within the constraint set. The integer component of the model is required to model the operating policy at the major flow regulation facility in the system and the restricted validity of the irrigation permits. Application of the model shows that in dry years where competition between minimum flow levels and the other economic uses, is most intense, the levels achieved by the various economic objectives are only slightly reduced even with significant increases in the minimum flow requirements. Variations in minimum flow requirements of up to 45% only produce changes of 10% or less in the economic objectives. The lack of sensitivity of the objective levels is due primarily to the level of control exerted indirectly on the whole system in dry years by the release regulation policy and the restricted validity of the irrigation permits. In normal to wet years these policies are not as restrictive and more choice is available. In such years, however, there is generally sufficient water to satisfy all requirements and allocation is not a critical issue. The model itself is formulated generally so that a range of scenarios beyond those examined specifically in the paper can be considered.     

Human error identification in human reliability assessment. Part 2: Detailed comparison of techniques

This is the second part of a two-part review of human error identification (HEI) approaches in human reliability assessment (HRA). Part 1 reviewed the probabilistic risk assessment (PRA) context in which HRA occurs, and then detailed 12 HEI techniques which have evolved in the field of HRA. Part 2 attempts to compare the way these techniques perform against a range of criteria relevant to HEI theoretical and empirical validity, and practical usefulness in applied HRA. It is hoped that these comparisons will help assessors in the selection of techniques for practical applications. The comparisons also point to research and development needs in the area of applied HEI.     

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.     

一种新的修正恒模算法

阐述了恒模算法(CMA)、修正恒模算法(MCMA)和判决引导(DD)算法的基本原理。针对CMA和MCMA收敛速度慢,固定步长条件下收敛速度和剩余误差之间存在矛盾的缺陷,在分析CMA误差特性的基础上,利用DD算法误差函数的模值和判决器输出构造新的误差函数,提出了一种新的变步长MCMA。新算法在加快收敛速度的同时保持小的剩余误差。仿真结果表明,新算法比CMA和MCMA收敛速度快,均衡输出剩余码间干扰(ISI)小而且能克服相位偏移,具有很好的实用性。