Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Applications of machine learning to machine fault diagnosis: A review and roadmap

Machinery health prognostics: A systematic review from data acquisition to RUL prediction

Remaining useful life (RUL) prediction of rolling element bearings plays a pivotal role in reducing costly unplanned maintenance and increasing the reliability, availability, and safety of machines. This paper proposes a hybrid prognostics approach for RUL prediction of rolling element bearings. First, degradation data of bearings are sparsely represented using relevance vector machine regressions with different kernel parameters. Then, exponential degradation models coupled with the Frechet distance are employed to estimate the RUL adaptively. The proposed approach is evaluated using the vibration data from accelerated degradation tests of rolling element bearings and the public PRONOSTIA bearing datasets. Experimental results demonstrate the effectiveness of the proposed approach in improving the accuracy and convergence of RUL prediction of rolling element bearings.

A Hybrid Prognostics Approach for Estimating Remaining Useful Life of Rolling Element Bearings

Accurate health estimation and lifetime prediction of lithium-ion batteries are crucial for durable electric vehicles. Early detection of inadequate performance facilitates timely maintenance of battery systems. This reduces operational costs and prevents accidents and malfunctions. Recent advancements in “Big Data” analytics and related statistical/computational tools raised interest in data-driven battery health estimation. Here, we will review these in view of their feasibility and cost-effectiveness in dealing with battery health in real-world applications. We categorise these methods according to their underlying models/algorithms and discuss their advantages and limitations. In the final section we focus on challenges of real-time battery health management and discuss potential next-generation techniques. We are confident that this review will inform commercial technology choices and academic research agendas alike, thus boosting progress in data-driven battery health estimation and prediction on all technology readiness levels.

/pdf/data-driven-health-estimation-and-lifetime-prediction-of-12knsapmli.pdf

Data-driven health estimation and lifetime prediction of lithium-ion batteries: A review

http://www2.mae.ufl.edu/nkim/Papers/paper70.pdf

Practical options for selecting data-driven or physics-based prognostics algorithms with reviews

http://web.mae.ufl.edu/nkim/Papers/paper65.pdf

Prognostics 101: A tutorial for particle filter-based prognostics algorithm using Matlab

Prognostics and Health Management of Engineering Systems: An Introduction

Gear fault diagnosis using transmission error and ensemble empirical mode decomposition

A general method for shape design sensitivity analysis as applied to plane elasticity problems is developed with a direct boundary integral equation formulation, using the material derivative concept and adjoint variable method. The problem formulation is very general and a complete consideration is given to describing the boundary variation by including the tangential component of the velocity field. The method is then applied to obtain the sensitivity formula for a general stress constraint imposed over a small part of the boundary. The accuracy of the design sensitivity analysis is studied with a fillet and an elastic ring design problem. Among the several numerical implementations tested, the second order boundary elements with a cubic spline representation of the moving boundary have shown the best accuracy. A smooth characteristic function is found to be better than a plateau function for localization of the stress constraint. Optimal shapes for the two problems are presented to show numerical applications.

Joo-Ho Choi

Papers

Practical options for selecting data-driven or physics-based prognostics algorithms with reviews

Prognostics 101: A tutorial for particle filter-based prognostics algorithm using Matlab

Prognostics and Health Management of Engineering Systems: An Introduction

Gear fault diagnosis using transmission error and ensemble empirical mode decomposition

Boundary integral equation method for shape optimization of elastic structures