Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Many industries, among which the cement industry, have showed growing interest in the exploitation of its gathered data to optimize its production line. In this work, typical problems occuring in cement plant are addressed.
The first one concerns the prediction of cyclones cloggings phenomena. Several methods are discussed in an attempt to solve this predictive maintenance problem. Whilst one method relies on operating points clustering via K-Means, the other one consists in modeling the problem as a binary classification task where samples close to cloggings get a value 1 and the normal samples get a value 0. After some processing to counteract the imbalanced dataset problem and a feature space reduction, the Random Forest, SVM and One-Class SVM algorithms are evaluated to conduct the classification.
The second task was the prediction of the clinker quality based on some measurements inside the production line. Through the collection of raw meal quality, fuels flows and clinker quality measurements, a multivariate time series problem is established and an autoregressive model (VAR) is used in this forecasting task.
In any case, the prediction performance is relatively low. Even if some alternative methods could improve the predictions, the main reasons explaining poor forecast can be found in the available dataset in which the sampling period of some key data was too low.
Ultimately, the understanding of monitoring data obtained from industrial plants could result in efficiency improvements and cost reductions.

machine learning --- predictive maintenance --- autoregression --- random forest --- support vector machine --- Ingénierie, informatique & technologie > Sciences informatiques

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Condition monitoring of machinery is one of the most important aspects of many modern industries. With the rapid advancement of science and technology, machines are becoming increasingly complex. Moreover, an exponential increase of demand is leading an increasing requirement of machine output. As a result, in most modern industries, machines have to work for 24 hours a day. All these factors are leading to the deterioration of machine health in a higher rate than before. Breakdown of the key components of a machine such as bearing, gearbox or rollers can cause a catastrophic effect both in terms of financial and human costs. In this perspective, it is important not only to detect the fault at its earliest point of inception but necessary to design the overall monitoring process, such as fault classification, fault severity assessment and remaining useful life (RUL) prediction for better planning of the maintenance schedule. Information theory is one of the pioneer contributions of modern science that has evolved into various forms and algorithms over time. Due to its ability to address the non-linearity and non-stationarity of machine health deterioration, it has become a popular choice among researchers. Information theory is an effective technique for extracting features of machines under different health conditions. In this context, this book discusses the potential applications, research results and latest developments of information theory-based condition monitoring of machineries.

Technology: general issues --- History of engineering & technology --- fault detection --- deep learning --- transfer learning --- anomaly detection --- bearing --- wind turbines --- misalignment --- fault diagnosis --- information fusion --- improved artificial bee colony algorithm --- LSSVM --- D–S evidence theory --- optimal bandwidth --- kernel density estimation --- JS divergence --- domain adaptation --- partial transfer --- subdomain --- rotating machinery --- gearbox --- signal interception --- peak extraction --- cubic spline interpolation envelope --- combined fault diagnosis --- empirical wavelet transform --- grey wolf optimizer --- low pass FIR filter --- support vector machine --- satellite momentum wheel --- Huffman-multi-scale entropy (HMSE) --- support vector machine (SVM) --- adaptive particle swarm optimization (APSO) --- rail surface defect detection --- machine vision --- YOLOv4 --- MobileNetV3 --- multi-source heterogeneous fusion --- n/a --- D-S evidence theory

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Condition monitoring of machinery is one of the most important aspects of many modern industries. With the rapid advancement of science and technology, machines are becoming increasingly complex. Moreover, an exponential increase of demand is leading an increasing requirement of machine output. As a result, in most modern industries, machines have to work for 24 hours a day. All these factors are leading to the deterioration of machine health in a higher rate than before. Breakdown of the key components of a machine such as bearing, gearbox or rollers can cause a catastrophic effect both in terms of financial and human costs. In this perspective, it is important not only to detect the fault at its earliest point of inception but necessary to design the overall monitoring process, such as fault classification, fault severity assessment and remaining useful life (RUL) prediction for better planning of the maintenance schedule. Information theory is one of the pioneer contributions of modern science that has evolved into various forms and algorithms over time. Due to its ability to address the non-linearity and non-stationarity of machine health deterioration, it has become a popular choice among researchers. Information theory is an effective technique for extracting features of machines under different health conditions. In this context, this book discusses the potential applications, research results and latest developments of information theory-based condition monitoring of machineries.

Technology: general issues --- History of engineering & technology --- fault detection --- deep learning --- transfer learning --- anomaly detection --- bearing --- wind turbines --- misalignment --- fault diagnosis --- information fusion --- improved artificial bee colony algorithm --- LSSVM --- D-S evidence theory --- optimal bandwidth --- kernel density estimation --- JS divergence --- domain adaptation --- partial transfer --- subdomain --- rotating machinery --- gearbox --- signal interception --- peak extraction --- cubic spline interpolation envelope --- combined fault diagnosis --- empirical wavelet transform --- grey wolf optimizer --- low pass FIR filter --- support vector machine --- satellite momentum wheel --- Huffman-multi-scale entropy (HMSE) --- support vector machine (SVM) --- adaptive particle swarm optimization (APSO) --- rail surface defect detection --- machine vision --- YOLOv4 --- MobileNetV3 --- multi-source heterogeneous fusion

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Fault diagnosis has always been a concern for industry. In general, diagnosis in complex systems requires the acquisition of information from sensors and the processing and extracting of required features for the classification or identification of faults. Therefore, fault diagnosis of sensors is clearly important as faulty information from a sensor may lead to misleading conclusions about the whole system. As engineering systems grow in size and complexity, it becomes more and more important to diagnose faulty behavior before it can lead to total failure. In the light of above issues, this book is dedicated to trends and applications in modern-sensor fault diagnosis.

Technology: general issues --- rolling bearing --- performance degradation --- hybrid kernel function --- krill herd algorithm --- SVR --- acoustic-based diagnosis --- gear fault diagnosis --- attention mechanism --- convolutional neural network --- stacked auto-encoder --- weighting strategy --- deep learning --- bearing fault diagnosis --- intelligent leak detection --- acoustic emission signals --- statistical parameters --- support vector machine --- wavelet denoising --- Shannon entropy --- adaptive noise reducer --- gaussian reference signal --- gearbox fault diagnosis --- one against on multiclass support vector machine --- varying rotational speed --- fault detection and diagnosis --- faults estimation --- actuator and sensor fault --- observer design --- Takagi-Sugeno fuzzy systems --- automotive --- perception sensor --- lidar --- fault detection --- fault isolation --- fault identification --- fault recovery --- fault diagnosis --- fault detection and isolation (FDIR) --- autonomous vehicle --- model predictive control --- path tracking control --- fault detection and isolation --- braking control --- nonlinear systems --- fault tolerant control --- iterative learning control --- neural networks --- cryptography --- wireless sensor networks --- machine learning --- scan-chain diagnosis --- artificial neural network --- NARX --- control valve --- decision tree --- signature matrix --- n/a

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Fault diagnosis has always been a concern for industry. In general, diagnosis in complex systems requires the acquisition of information from sensors and the processing and extracting of required features for the classification or identification of faults. Therefore, fault diagnosis of sensors is clearly important as faulty information from a sensor may lead to misleading conclusions about the whole system. As engineering systems grow in size and complexity, it becomes more and more important to diagnose faulty behavior before it can lead to total failure. In the light of above issues, this book is dedicated to trends and applications in modern-sensor fault diagnosis.

Technology: general issues --- rolling bearing --- performance degradation --- hybrid kernel function --- krill herd algorithm --- SVR --- acoustic-based diagnosis --- gear fault diagnosis --- attention mechanism --- convolutional neural network --- stacked auto-encoder --- weighting strategy --- deep learning --- bearing fault diagnosis --- intelligent leak detection --- acoustic emission signals --- statistical parameters --- support vector machine --- wavelet denoising --- Shannon entropy --- adaptive noise reducer --- gaussian reference signal --- gearbox fault diagnosis --- one against on multiclass support vector machine --- varying rotational speed --- fault detection and diagnosis --- faults estimation --- actuator and sensor fault --- observer design --- Takagi-Sugeno fuzzy systems --- automotive --- perception sensor --- lidar --- fault detection --- fault isolation --- fault identification --- fault recovery --- fault diagnosis --- fault detection and isolation (FDIR) --- autonomous vehicle --- model predictive control --- path tracking control --- fault detection and isolation --- braking control --- nonlinear systems --- fault tolerant control --- iterative learning control --- neural networks --- cryptography --- wireless sensor networks --- machine learning --- scan-chain diagnosis --- artificial neural network --- NARX --- control valve --- decision tree --- signature matrix