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

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Matrix Factorization Techniques for Recommender Systems

A review on empirical mode decomposition in fault diagnosis of rotating machinery

Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data

A comprehensive investigation of lithium-ion battery degradation performance at different discharge rates

In traditional Dynamical Fault Tree analysis, it is necessary to modularize DFT tree firstly so as to obtain static subtrees and dynamic subtrees. Generally, Binary Decision Diagram (BDD) and Markov chains are utilized in the DFT to process static and dynamic subtrees, respectively. However, due to the possibility of state combinatorial explosion problem in Markov chain, it is difficult to analyze system with DFT in some cases. This paper investigated Petri net method in DFT in order to solve this problem. An example of processor system is analyzed with the proposed Petri net based DFT, which contains many dynamic logic gates in two classes. The analysis results show that the proposed method can overcome the state combinatorial explosion problem and guarantee high accuracy.

Dynamic fault tree analysis based on Petri nets

Vibration signals collected from machines can contain rich machine degradation information, such as impulsiveness and cyclo-stationarity. In the field of machine condition monitoring (MCM), quantification of impulsiveness has attracted many researchers’ interests because impulsiveness often indicates an occurrence of incipient faults. Impulsiveness-based health indicators (HIs) (e.g., Gini index, kurtosis, entropy, smoothness index, etc.) are some kinds of statistical parameters that can quantify the impulsiveness of vibration signals. Hence, they have been widely studied during recent years for MCM. However, a thorough comparitive study of those HIs is seldom reported. This paper aims to compare seven impulsiveness-based HIs including kurtosis, skewness, smoothness index, negative entropy, Gini index, Hoyer measure, and the ratio of L2 to L1 norm for MCM according to three properties including the robustness to the length of a signal, the gradient for sparsity or impulsiveness, and quantification of impulsiveness and cyclo-stationarity. Among the seven HIs, it was experimentally found that the Gini index is better than the other indicators to satisfy the three suggested properties for MCM.

A Comparison of Machine Health Indicators Based on the Impulsiveness of Vibration Signals

Rolling bearings are widely used in rotating machinery and their failures may result in machine breakdown. Cage failure is of great concern because it may cause disassembly of bearing components. Since fault features of rolling bearing cage have characteristics of low frequency and small amplitude, which are often overwhelmed by strong noise and other irrelevant vibration components, there are a few research works about fault diagnosis of bearing cage, especially fault diagnosis of space bearing cage. Therefore, fault feature extraction of space bearing cage is a challenging topic. Toward this topic, a time-varying envelope filtering (TVEF) method is proposed in this article to extract the weak fault features of space bearing cage. Novel TVEF kernel functions are deduced by solving an envelope signal model, in which instantaneous frequencies (IFs) and instantaneous amplitudes (IAs) of signal components are modeled as redundant Fourier series. Fault characteristic components and their IFs and IAs can be accurately extracted by using TVEF kernel functions, which improve the signal-to-noise ratio of raw vibration signals. Based on the extracted IFs and IAs, a high-resolution time–frequency distribution is reconstructed to precisely extract the fault features of space bearing cage. Experiments designed in a flywheel test rig have verified the potential and effectiveness of the proposed TVEF method in exhibiting space bearing cage fault features than other existing methods.

Time-Varying Envelope Filtering for Exhibiting Space Bearing Cage Fault Features

This paper introduces a joint bearing fault characteristic frequency detection method using empirical mode decomposition (EMD) and independent component analysis (ICA). Independent component analysis can be used to separate multiple sets of one-dimensional time series into independent time series, which need at least two transducers to obtain more than one set of time series for separation of different sources. To overcome this restriction, preprocessing is needed to construct multiple sets of time series. Empirical mode decomposition has attracted attention in recent years due to its ability to self-adaptively process non-stationary and non-linear signals with multiple intrinsic mode functions being obtained through EMD decomposition. Hence, considering this superiority, this paper employs EMD to transform one set of one-dimensional series into multiple sets of one-dimensional series for pre-processing. After that, independent components (IC) are extracted, which include fault-related signatures in the frequency spectrum. To validate the proposed method, real motor bearing vibration data, including normal bearing data, outer race fault data, and inner race fault data, are used in a case study. The results show that the proposed method can be used for bearing fault extraction.

/pdf/rolling-element-bearing-fault-feature-extraction-using-emd-z11c3fqimg.pdf

Dong Wang

Papers

A comprehensive investigation of lithium-ion battery degradation performance at different discharge rates

Dynamic fault tree analysis based on Petri nets

A Comparison of Machine Health Indicators Based on the Impulsiveness of Vibration Signals

Time-Varying Envelope Filtering for Exhibiting Space Bearing Cage Fault Features

Rolling element bearing fault feature extraction using EMD-based independent component analysis