Mathematical Problems in Engineering

This paper reviews methods to fix a number of hidden neurons in neural networks for the past 20 years. And it also proposes a new method to fix the hidden neurons in Elman networks for wind speed prediction in renewable energy systems. The random selection of a number of hidden neurons might cause either overfitting or underfitting problems. This paper proposes the solution of these problems. To fix hidden neurons, 101 various criteria are tested based on the statistical errors. The results show that proposed model improves the accuracy and minimal error. The perfect design of the neural network based on the selection criteria is substantiated using convergence theorem. To verify the effectiveness of the model, simulations were conducted on real-time wind data. The experimental results show that with minimum errors the proposed approach can be used for wind speed prediction. The survey has been made for the fixation of hidden neurons in neural networks. The proposed model is simple, with minimal error, and efficient for fixation of hidden neurons in Elman networks.

Decision making trial and evaluation laboratory (DEMATEL) is considered as an effective method for the identification of cause-effect chain components of a complex system. It deals with evaluating interdependent relationships among factors and finding the critical ones through a visual structural model. Over the recent decade, a large number of studies have been done on the application of DEMATEL and many different variants have been put forward in the literature. The objective of this study is to review systematically the methodologies and applications of the DEMATEL technique. We reviewed a total of 346 papers published from 2006 to 2016 in the international journals. According to the approaches used, these publications are grouped into five categories: classical DEMATEL, fuzzy DEMATEL, grey DEMATEL, analytical network process- (ANP-) DEMATEL, and other DEMATEL. All papers with respect to each category are summarized and analyzed, pointing out their implementing procedures, real applications, and crucial findings. This systematic and comprehensive review holds valuable insights for researchers and practitioners into using the DEMATEL in terms of indicating current research trends and potential directions for further research.

The objective of this study is to investigate and compare the results of three data mining approaches, the support vector machines (SVM), decision tree (DT), and Naïve Bayes (NB) models for spatial prediction of landslide hazards in the Hoa Binh province (Vietnam). First, a landslide inventory map showing the locations of 118 landslides was constructed from various sources. The landslide inventory was then randomly partitioned into 70% for training the models and 30% for the model validation. Second, ten landslide conditioning factors were selected (i.e., slope angle, slope aspect, relief amplitude, lithology, soil type, land use, distance to roads, distance to rivers, distance to faults, and rainfall). Using these factors, landslide susceptibility indexes were calculated using SVM, DT, and NB models. Finally, landslide locations that were not used in the training phase were used to validate and compare the landslide susceptibility maps. The validation results show that the models derived using SVM have the highest prediction capability. The model derived using DT has the lowest prediction capability. Compared to the logistic regression model, the prediction capability of the SVM models is slightly better. The prediction capability of the DT and NB models is lower.

Mục tiêu chính của nghiên cứu này là đánh giá và so sánh hiệu suất của các thuật toán học máy (ML) khác nhau, cụ thể là Mạng Nơron Nhân Tạo (ANN), Máy Học Tăng Cường (ELM) và thuật toán Cây Tăng Cường (Boosted), khi xem xét ảnh hưởng của các tỷ lệ đào tạo đối với kiểm tra trong việc dự đoán độ bền cắt của đất, một trong những tính chất kỹ thuật địa chất quan trọng nhất trong thiết kế và xây dựng công trình. Để thực hiện điều này, một cơ sở dữ liệu gồm 538 mẫu đất thu thập từ dự án nhà máy điện Long Phú 1, Việt Nam, đã được sử dụng để tạo ra các bộ dữ liệu cho quá trình mô hình hóa. Các tỷ lệ khác nhau (tức là 10/90, 20/80, 30/70, 40/60, 50/50, 60/40, 70/30, 80/20, và 90/10) đã được sử dụng để chia bộ dữ liệu thành bộ dữ liệu đào tạo và kiểm tra nhằm đánh giá hiệu suất của các mô hình. Các chỉ số thống kê phổ biến, chẳng hạn như Lỗi Bình Phương Trung Bình (RMSE), Lỗi Tuyệt Đối Trung Bình (MAE) và Hệ Số Tương Quan (R), đã được sử dụng để đánh giá khả năng dự báo của các mô hình dưới các tỷ lệ đào tạo và kiểm tra khác nhau. Ngoài ra, mô phỏng Monte Carlo đã được thực hiện đồng thời để đánh giá hiệu suất của các mô hình đề xuất, có tính đến ảnh hưởng của lấy mẫu ngẫu nhiên. Kết quả cho thấy mặc dù cả ba mô hình ML đều hoạt động tốt, nhưng ANN là mô hình chính xác nhất và ổn định nhất về mặt thống kê sau 1000 lần mô phỏng Monte Carlo (R Trung Bình = 0.9348) so với các mô hình khác như Boosted (R Trung Bình = 0.9192) và ELM (R Trung Bình = 0.8703). Điều tra về hiệu suất của các mô hình cho thấy khả năng dự báo của các mô hình ML bị ảnh hưởng lớn bởi các tỷ lệ đào tạo/kiểm tra, trong đó tỷ lệ 70/30 thể hiện hiệu suất tốt nhất của các mô hình. Một cách ngắn gọn, kết quả được trình bày ở đây thể hiện một cách thức hiệu quả trong việc lựa chọn các tỷ lệ dữ liệu phù hợp và mô hình ML tốt nhất để dự đoán chính xác độ bền cắt của đất, điều này sẽ hữu ích trong các giai đoạn thiết kế và kỹ thuật của các dự án xây dựng.

The peristaltic transport of Johnson‐Segalman fluid by means of an infinite train of sinusoidal waves traveling along the walls of a two‐dimensional flexible channel is investigated. The fluid is electrically conducted by a transverse magnetic field. A perturbation solution is obtained for the case in which amplitude ratio is small. Numerical results are reported for various values of the physical parameters of interest.

The smart mobile devices have emerged during the past decade and have become one of the most dominant consumer electronic products. Therefore, exploring and understanding the factors which can influence the acceptance of novel mobile technology have become the essential task for the vendors and distributors of mobile devices. The Phablets, integrated smart devices combining the functionality and characteristics of both tablet PCs and smart phones, have gradually become possible alternatives for smart phones. Therefore, predicting factors which can influence the acceptance of Phablets have become indispensable for designing, manufacturing, and marketing of such mobile devices. However, such predictions are not easy. Meanwhile, very few researches tried to study related issues. Consequently, the authors aim to explore and predict the intentions to use and use behaviors of Phablets. The second generation of the Unified Theory of Acceptance and Use of Technology (UTAUT2) is introduced as a theoretic basis. The Decision Making Trial and Evaluation Laboratory (DEMATEL) based Network Process (DNP) will be used to construct the analytic framework. In light of the analytic results, the causal relationships being derived by the DEMATEL demonstrate the direct influence of the habit on other dimensions. Also, based on the influence weights being derived, the use intention, hedonic motivation, and performance expectancy are the most important dimensions. The analytic results can serve as a basis for concept developments, marketing strategy definitions, and new product designs of the future Phablets. The proposed analytic framework can also be used for predicting and analyzing consumers’ preferences toward future mobile devices.

Fatigue is among the most critical forms of damage potentially occurring in steel bridges, while accurate assessment or prediction of the fatigue damage status as well as the remaining fatigue life of steel bridges is still a challenging and unsolved issue. There have been numerous investigations on the fatigue damage evaluation and life prediction of steel bridges by use of deterministic or probabilistic methods. The purpose of this review is devoted to presenting a summary on the development history and current status of fatigue condition assessment of steel bridges, containing basic aspects of fatigue, classical fatigue analysis methods, data-driven fatigue life assessment, and reliability-based fatigue condition assessment.

Flexible Job Shop Scheduling Problem (FJSSP) is an extension of the classical Job Shop Scheduling Problem (JSSP). The FJSSP is known to be NP-hard problem with regard to optimization and it is very difficult to find reasonably accurate solutions of the problem instances in a rational time. Extensive research has been carried out in this area especially over the span of the last 20 years in which the hybrid approaches involving Genetic Algorithm (GA) have gained the most popularity. Keeping in view this aspect, this article presents a comprehensive literature review of the FJSSPs solved using the GA. The survey is further extended by the inclusion of the hybrid GA (hGA) techniques used in the solution of the problem. This review will give readers an insight into use of certain parameters in their future research along with future research directions.

The bottleneck of a production line is a machine that impedes the system performance in the strongest manner. In production lines with the so‐called Markovian model of machine reliability, bottlenecks with respect to the downtime, uptime, and the cycle time of the machines can be introduced. The two former have been addressed in recent publications [1] and [2]. The latter is investigated in this paper. Specifically, using a novel aggregation procedure for performance analysis of production lines with Markovian machines having different cycle time, we develop a method for c‐bottleneck identification and apply it in a case study to a camshaft production line at an automotive engine plant.

This paper is devoted to the study of the two‐dimensional flow of a Johnson‐Segalman fluid in a planar channel having walls that are transversely displaced by an infinite, harmonic travelling wave of large wavelength. Both analytical and numerical solutions are presented. The analysis for the analytical solution is carried out for small Weissenberg numbers. (A Weissenberg number is the ratio of the relaxation time of the fluid to a characteristic time associated with the flow.) Analytical solutions have been obtained for the stream function from which the relations of the velocity and the longitudinal pressure gradient have been derived. The expression of the pressure rise over a wavelength has also been determined. Numerical computations are performed and compared to the perturbation analysis. Several limiting situations with their implications can be examined from the presented analysis.