THE DESIGN AND ANALYSIS OF EXPERIMENTS. By Oscar Kempthorne. New York, John Wiley and Sons, Inc., 1952. 631 pp. $8.50. This book by a teacher of statistics (as well as a consultant for \"experimenters\") is a comprehensive study of the philosophical background for the statistical design of experiment. It is necessary to have some facility with algebraic notation and manipulation to be able to use the volume intelligently. The problems are presented from the theoretical point of view, without such practical examples as would be helpful for those not acquainted with mathematics. The mathematical justification for the techniques is given. As a somewhat advanced treatment of the design and analysis of experiments, this volume will be interesting and helpful for many who approach statistics theoretically as well as practically. With emphasis on the \"why,\" and with description given broadly, the author relates the subject matter to the general theory of statistics and to the general problem of experimental inference. MARGARET J. ROBERTSON

The Design and Analysis of Experiments

Prediction and optimization of machining parameters for minimizing power consumption and surface roughness in machining

A smart factory is a highly digitized and connected production facility that relies on smart manufacturing. Additionally, artificial intelligence is the core technology of smart factories. The use of machine learning and deep learning algorithms has produced fruitful results in many fields like image processing, speech recognition, fault detection, object detection, or medical sciences. With the increment in the use of smart machinery, the faults in the machinery equipment are expected to increase. Machinery fault detection and diagnosis through various deep learning algorithms has increased day by day. Many types of research have been done and published using both open-source and closed-source datasets, implementing the deep learning algorithms. Out of many publicly available datasets, Case Western Reserve University (CWRU) bearing dataset has been widely used to detect and diagnose machinery bearing fault and is accepted as a standard reference for validating the models. This paper summarizes the recent works which use the CWRU bearing dataset in machinery fault detection and diagnosis employing deep learning algorithms. We have reviewed the published works and presented the working algorithm, result, and other necessary details in this paper. This paper, we believe, can be of good help for future researchers to start their work on machinery fault detection and diagnosis using the CWRU dataset.

/pdf/bearing-fault-detection-and-diagnosis-using-case-western-1af0gxj849.pdf

Bearing Fault Detection and Diagnosis Using Case Western Reserve University Dataset With Deep Learning Approaches: A Review

Machining operation optimization improves the quality of the product, reduces cost, enhances overall efficiency by reducing human error, and enables consistent and efficient operation. It is a vital decision-making process and achieves the best solution within constraints. It reduces reliance on machine-tool technicians and handbooks to identify cutting parameters, as a lack of awareness of the optimal combination of machining parameters leads to several machining inefficiencies. Subsequently, the optimization of the machining process is more useful for units of production, particularly machining units. In multi-objective optimization (MOO) problems, weights of importance are assigned, mostly identical. But, nowadays, the weights assignment techniques have received a lot of consideration from the professionals and researchers in MOO problems. Various techniques are developed to assign weights of significance to responses in MOO. The Entropy weights method (EWM) continues to work pleasingly across diverse machining operations to allocate objective weights. In this paper, a literature review is conducted to classify the articles on EWM applications in machining operations. The categorization proposal for the EWM reviews included 65 academic articles from different journals, books, and conferences since the year 2009. The EWM applications were separated into 18 categories of conventional and non-conventional machining operations. The implementation procedure of EWM is presented with an example along with method development. Scholarly articles in the EWM applications are further inferred based on (1) implementation of EWM in different machining operations, (2) MOO methods used with entropy weights in machining operations, (3) application of entropy weights by citation index and publication year, and (4) entropy weights applications in other fields. The review paper provided constructive insight into the EWM applications and ended with suggestions for further research in machining and different areas.

Revealing the benefits of entropy weights method for multi-objective optimization in machining operations: A critical review

Fused deposition modeling (FDM) is gaining distinct advantages because of its ability to fabricate the 3D physical prototypes without the restrictions of geometric complexities, while when it comes to accuracy and efficiency, the advantages of FDM is not distinct, and so how to improve them is worthy of study. Focusing on process parameter optimization, such parameters as line width compensation, extrusion velocity, filling velocity, and layer thickness are selected as control factors, input variables, and dimensional error, warp deformation, and built time are selected as output responses, evaluation indexes. Experiment design is assigned according to uniform experiment design, and then the three output responses are converted with fuzzy inference system to a single comprehensive response. The relation between the comprehensive response and the four input variables is derived with second-order response surface methodology, the correctness of which is further validated with artificial neural network. Fitness function is created using penalty function and is solved with genetic algorithm toolbox in Matlab software. With confirmation test, the results are obtained preferring to the results of the experiment 1 with the best comprehensive response among the 17 experiment runs, which confirms that the proposed approach in this study can effectively improve accuracy and efficiency in the FDM process.

Process parameter optimization for fused deposition modeling using response surface methodology combined with fuzzy inference system

This paper investigates an optimisation design of the various machining parameters for the electrical discharge machining (EDM) processes on AISI D2 tool steel using a hybrid optimisation method. A new combination of response surface methodology (RSM) and grey relational analysis coupled with principal component analysis (PCA) has been proposed to evaluate and estimate the effect of machining parameters on the responses. The major responses selected for this analysis are material removal rate, tool wear rate and radial overcut or gap, and the corresponding machining parameters considered for this study were pulse current (Ip), pulse duration (Ton), duty cycle (Tau) and discharge voltage (V). Thirty experiments were conducted on AISI D2 steel workpiece materials based on a face-centred central composite design. The experimental results obtained were used in grey relational analysis, and the weights of the responses were determined by the PCA and further evaluated using RSM. The results indicate that the grey relational grade (GRG) was significantly affected by the machining parameters considered and some of their interactions. The $R^2$
 value for the GRG model was found to be 0.83, and the optimal parameter setting was determined for the grey relational grades. The analysis of variance results reveal that Tau is the most influencing parameter having 28.57 of percentage contribution followed by Ip, V and Ton with 11.52, 5.89 and 5.83 %, respectively. The interaction of the parameters contributes 31.19 % of percentage contribution. These results provide useful information on how to control the machining parameters and thereby responses and ensure high productivity and accuracy of the EDMed component. This method is simple with easy operability, and the results have also been verified by running confirmation tests.

Estimating the effect of process parameters on MRR, TWR and radial overcut of EDMed AISI D2 tool steel by RSM and GRA coupled with PCA

Fault detection analysis in rolling element bearing: A review

In the present research, two neuro-fuzzy models and a neural network model are presented for predictions of material removal rate (MRR), tool wear rate (TWR), and radial overcut (G) in die sinking electrical discharge machining (EDM) process for American Iron and Steel Institute D2 tool steel with copper electrode. The discharge current (I
 p), pulse duration (T
 on), duty cycle (τ), and voltage (V) are considered as inputs to the network. A full-factorial design was used to conduct the experiments with various levels of I
 p, T
 on, τ, and V. The analysis of variance results reveal that I
 p is the most influencing factor for MRR and G, having the highest degree of contributions of 87.61% and 81.90%, respectively. In case of TWR, T
 on has the highest degree of contribution of 46.05% and is the most significant factor. The half of the experimental data set was used to train the networks and was tested for convergence with a different set of data to obtain appropriate number of neurons, epoch, and the fuzzy rule base. The mean square error convergence criteria, both in training and testing, came out very well. The developed models are found to approximate the responses quite accurately. Moreover, the predicted results based on above models have been confirmed with unseen validation set of experiments and are found to be in good agreement with the experimental results. The comparison results reveal that the artificial neural network and the neuro-fuzzy models are comparable in terms of accuracy and speed, and further, the proposed models can be employed successfully in prediction of MRR, TWR, and G of the stochastic and complex EDM process.

Neuro-fuzzy and neural network-based prediction of various responses in electrical discharge machining of AISI D2 steel

In this work, two different artificial neural network (ANN) models — back-propagation neural network (BPN) and radial basis function neural network (RBFN) — are presented for the prediction...

http://dspace.nitrkl.ac.in:8080/dspace/bitstream/2080/1018/1/comparison.pdf

Mohan Kumar Pradhan

Papers

Estimating the effect of process parameters on MRR, TWR and radial overcut of EDMed AISI D2 tool steel by RSM and GRA coupled with PCA

Fault detection analysis in rolling element bearing: A review

Neuro-fuzzy and neural network-based prediction of various responses in electrical discharge machining of AISI D2 steel

Comparisons of neural network models on surface roughness in electrical discharge machining

Characteristic behaviour of aluminium metal matrix composites: A review