Search results

Process monitoring is a way to manage the quality characteristics of products in manufacturing processes. Several process monitoring based on machine learning algorithms have been proposed in the literature and have gained the attention of many researchers. In this paper, the authors developed machine learning-based control charts for monitoring fraction non-conforming products in smart manufacturing. This study proposed a relevance vector machine using Bayesian sparse kernel optimized by differential evolution algorithm for efficient monitoring in manufacturing.

A new approach was carried out about data analysis, modelling and monitoring in the manufacturing industry. This study developed a relevance vector machine using Bayesian sparse kernel technique to improve the support vector machine used to both regression and classification problems. The authors compared the performance of proposed relevance vector machine with other machine learning algorithms, such as support vector machine, artificial neural network and beta regression model. The proposed approach was evaluated by different shift scenarios of average run length using Monte Carlo simulation.

The authors analyse a real case study in a manufacturing company, based on best machine learning algorithms. The results indicate that proposed relevance vector machine-based process monitoring are excellent quality tools for monitoring defective products in manufacturing process. A comparative analysis with four machine learning models is used to evaluate the performance of the proposed approach. The relevance vector machine has slightly better performance than support vector machine, artificial neural network and beta models.

This research is different from the others by providing approaches for monitoring defective products. Machine learning-based control charts are used to monitor product failures in smart manufacturing process. Besides, the key contribution of this study is to develop different models for fault detection and to identify any change point in the manufacturing process. Moreover, the authors’ research indicates that machine learning models are adequate tools for the modelling and monitoring of the fraction non-conforming product in the industrial process.

Surface curvature is needed to analyze the range data of real objects and is widely applied in object recognition and segmentation, robotics, and computer vision. Therefore, it is not easy to estimate the curvature of the scanned data. In recent years, machine learning classification methods have gained importance in various fields such as finance, health, engineering, etc. The purpose of this study is to classify surface points based on principal curvatures to find the best method for determining surface point types.

A feature selection method is presented to find the best feature vector that achieves the highest accuracy. For this reason, ten different feature selections are used and six sample datasets of different sizes are classified using these feature vectors.

The author examined the surface examples based on the feature vector using the machine learning classification methods. Also, the author compared the results for each experiment.

To the best of the author's knowledge, this is the first study to examine surface points according to principal curvatures using machine learning classification methods.

Diabetes is a major metabolic disorder which can affect entire body system adversely. Undiagnosed diabetes can increase the risk of cardiac stroke, diabetic nephropathy and other disorders. All over the world millions of people are affected by this disease. Early detection of diabetes is very important to maintain a healthy life. This disease is a reason of global concern as the cases of diabetes are rising rapidly. Machine learning (ML) is a computational method for automatic learning from experience and improves the performance to make more accurate predictions. In the current research we have utilized machine learning technique in Pima Indian diabetes dataset to develop trends and detect patterns with risk factors using R data manipulation tool. To classify the patients into diabetic and non-diabetic we have developed and analyzed five different predictive models using R data manipulation tool. For this purpose we used supervised machine learning algorithms namely linear kernel support vector machine (SVM-linear), radial basis function (RBF) kernel support vector machine, k-nearest neighbour (k-NN), artificial neural network (ANN) and multifactor dimensionality reduction (MDR).

This paper examines whether the successful bid rate of the OnBid public auction, published by Korea Asset Management Corporation, can identify and forecast the Korea business-cycle expansion and contraction regimes characterized by the OECD reference turning points. We use logistic regression and support vector machine in performing the OECD regime classification and predicting three-month-ahead regime. We find that the OnBid auction rate conveys important information for detecting the coincident and future regimes because this information might be closely related to deleveraging regarding default on debt obligations. This finding suggests that corporate managers and investors could use the auction information to gauge the regime position in their decision-making. This research has an academic significance that reveals the relationship between the auction market and the business-cycle regimes.

With the continuous upgrading of the production mode of the manufacturing system, the characteristics of multi-variety, small batch and mixed fluidization are presented, and the production environment becomes more and more complex. To improve the efficiency of solving multi-objective flexible job shop scheduling problem (FJSP), an improved hybrid particle swarm optimization algorithm (IH-PSO) is proposed.

After reviewing literatures on FJSP, an IH-PSO algorithm for solving FJSP is developed. First, IH-PSO algorithm draws on the crossover and mutation operations of genetic algorithm (GA) algorithm and proposes a new method for updating particles, which makes the offspring particles inherit the superior characteristics of the parent particles. Second, based on the improved simulated annealing (SA) algorithm, the method of updating the individual best particles expands the search scope of the domain and solves the problem of being easily trapped in local optimum. Finally, analytic hierarchy process (AHP) is used in this paper to solve the optimal solution satisfying multi-objective optimization.

Through the benchmark experiment and the production example experiment, it is verified that the proposed algorithm has the advantages of high quality of solution and fast speed of convergence.

This method does not consider the unforeseen events that occur during the process of scheduling and cause the disruption of normal production scheduling activities, such as machine breakdown.

IH-PSO algorithm combines PSO algorithm with GA and SA algorithms. This algorithm retains the advantage of fast convergence speed of traditional PSO algorithm and has the characteristic of inheriting excellent genes. In addition, the improved SA algorithm is used to solve the problem of falling into local optimum.

This research provides an efficient scheduling method for solving the FJSP problem.

This research proposes an IH-PSO algorithm to solve the FJSP more efficiently and meet the needs of multi-objective optimization.

The purpose of this paper is analysis of the sensorless control system of induction machine with broken rotor for diagnostic purposes. Increasing popularity of sensorless controlled variable speed drives requires research in area of reliability, range of stable operation, fault symptoms and application of diagnosis methods.

T transformation used for conversion of instantaneous rotor currents electrical circuit representation to space vector components is investigated to apply with closed‐loop modeling algorithm. Evaluation of the algorithm is based on analysis of asymmetry influence to the orthogonal and zero components of space vector representation. Multiscalar model of the machine and selected structures of state observers are used for sensorless control system synthesis. Proposed method of frequency characteristics calculation is used for state observers analysis in open‐loop operation.

New algorithm of applying the T transformation allows for closed‐loop and sensorless control system simulation with asymmetric machine due to broken rotor. Compensating effect of the closed‐loop control system with speed measurements and diagnosis information in control system variables are identified. Proposed frequency analysis of state observers is presented and applied. Variables with amplified characteristic frequency components related to rotor asymmetry are compared for selected structures of state observers and with closed‐loop and open‐loop operation. Method of improving the sensorless system stability is proposed.

In closed‐loop and sensorless control system rotor fault can be diagnosed by using PI output controllers variables. Compensating effect of mechanical variables sets limitation to specified diagnosis methods. Rotor asymmetry affects sensorless control system stability depending on estimator structure.

This paper concentrates upon sensorless control system operation with machine asymmetry and indicates rotor fault symptoms.

An approach to extract machining features for casting parts is presented. It is capable of recognizing interacting machining features. There are five phases in the recognition process: Boolean difference of the final part model and the raw part; identification of machining faces (M‐faces) from the final part model and the raw part model; decomposition of the removed simple volumes into delta simple volumes based on M‐faces; gluing the delta simple volumes into sets of feasible simple volumes based on M‐faces; testing. This strategy is process‐oriented and feature‐independent. It recognizes all features that can be produced by common machining operations in a uniform way and produces alternative sets of machining features.

In the present study, wire electro-spark machining of Titanium alloy is performed with the machining parameter such as spark-on time, spark-off time, current and servo voltage. The purpose of this study is to model surface roughness using machine learning approach for input/controllable variable. Machined surface examined using scanning electron microscope (SEM) and XRD methods.

Full factorial approach has been used to design the experiments with varying machining parameters into three-level four factors. Obtained surface roughness was modeled using machine learning methods namely Gaussian process regression (GPR) and support vector machine (SVM) methods. These methods were compared for both training and testing data with a coefficient of correlation and root mean square error basis. Machined surface examined using scanned electron microscopy and XRD for surface quality produced and check migration of tool material to workpiece material.

Machine learning algorithms has excellent scope for prediction quality response for the wire electric discharge machining (WEDM) process, resulting in saving of time and cost as it is difficult to find each time experimentally. It has been found that the proposed model with minimum computational time, provides better solution and avoids priority weightage calculation by decision-makers.

The proposed modeling provides better predication about surface produced while machining of Ti6Al7Nb using zinc-coated brass wire electrode during WEDM operation.

This research navigates the confluence of data analytics, machine learning, and artificial intelligence to revolutionize the management of urban services in smart cities. The study thoroughly investigated with advanced tools to scrutinize key performance indicators integral to the functioning of smart cities, thereby enhancing leadership and decision-making strategies. Our work involves the implementation of various machine learning models such as Logistic Regression, Support Vector Machine, Decision Tree, Naive Bayes, and Artificial Neural Networks (ANN), to the data. Notably, the Support Vector Machine and Bernoulli Naive Bayes models exhibit robust performance with an accuracy rate of 70% precision score. In particular, the study underscores the employment of an ANN model on our existing dataset, optimized using the Adam optimizer. Although the model yields an overall accuracy of 61% and a precision score of 58%, implying correct predictions for the positive class 58% of the time, a comprehensive performance assessment using the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) metrics was necessary. This evaluation results in a score of 0.475 at a threshold of 0.5, indicating that there's room for model enhancement. These models and their performance metrics serve as a key cog in our data analytics pipeline, providing decision-makers and city leaders with actionable insights that can steer urban service management decisions. Through real-time data availability and intuitive visualization dashboards, these leaders can promptly comprehend the current state of their services, pinpoint areas requiring improvement, and make informed decisions to bolster these services. This research illuminates the potential for data analytics, machine learning, and AI to significantly upgrade urban service management in smart cities, fostering sustainable and livable communities. Moreover, our findings contribute valuable knowledge to other cities aiming to adopt similar strategies, thus aiding the continued development of smart cities globally.

The purpose of this paper is to examine the applicability and capability of models based on a genetic algorithm and support vector machine (GA-SVM) and a genetic algorithm and relevance vector machine (GA-RVM) for the prediction of phytoplankton abundances associated with algal blooms in a Macau freshwater reservoir, and compare their performances with an artificial neural network (ANN) model.

The hybrid models GA-SVM and GA-RVM were developed for the optimal control of parameters for predicting (based on the current month’s variables) and forecasting (based on the previous three months’ variables) phytoplankton dynamics in a Macau freshwater reservoir, MSR, which has experienced cyanobacterial blooms in recent years. There were 15 environmental parameters, including pH, SiO₂, alkalinity, bicarbonate (HCO₃−), dissolved oxygen (DO), total nitrogen (TN), UV254, turbidity, conductivity, nitrate (NO₃−), orthophosphate (PO₄³⁻), total phosphorus (TP), suspended solids (SS) and total organic carbon (TOC) selected from the correlation analysis, with eight years (2001-2008) of data for training, and the most recent three years (2009-2011) for testing.

For both accuracy performance and generalized performance, the ANN, GA-SVM and GA-RVM had similar predictive powers of R² of 0.73-0.75. However, whereas ANN and GA-RVM models showed very similar forecast performances, GA-SVM models had better forecast performances of R² (0.862), RMSE (0.266) and MAE (0.0710) with the respective parameters of 0.987, 0.161 and 0.032 optimized using GA.

This is the first application of GA-SVM and GA-RVM models for predicting and forecasting algal bloom in freshwater reservoirs. GA-SVM was shown to be an effective new way for monitoring algal bloom problem in water resources.