Search results
1 – 8 of 8It is of a great significance for the health monitoring of a liquid rocket engine to build an accurate and reliable fault prediction model. The thrust of a liquid rocket engine is…
Abstract
Purpose
It is of a great significance for the health monitoring of a liquid rocket engine to build an accurate and reliable fault prediction model. The thrust of a liquid rocket engine is an important indicator for its health monitoring. By predicting the changing value of the thrust, it can be judged whether the engine will fail at a certain time. However, the thrust is affected by various factors, and it is difficult to establish an accurate mathematical model. Thus, this study uses a mixture non-parametric regression prediction model to establish the model of the thrust for the health monitoring of a liquid rocket engine.
Design/methodology/approach
This study analyzes the characteristics of the least squares support vector regression (LS-SVR) machine . LS-SVR is suitable to model on the small samples and high dimensional data, but the performance of LS-SVR is greatly affected by its key parameters. Thus, this study implements the advanced intelligent algorithm, the real double-chain coding target gradient quantum genetic algorithm (DCQGA), to optimize these parameters, and the regression prediction model LSSVRDCQGA is proposed. Then the proposed model is used to model the thrust of a liquid rocket engine.
Findings
The simulation results show that: the average relative error (ARE) on the test samples is 0.37% when using LS-SVR, but it is 0.3186% when using LSSVRDCQGA on the same samples.
Practical implications
The proposed model of LSSVRDCQGA in this study is effective to the fault prediction on the small sample and multidimensional data, and has a certain promotion.
Originality/value
The original contribution of this study is to establish a mixture non-parametric regression prediction model of LSSVRDCQGA and properly resolve the problem of the health monitoring of a liquid rocket engine along with modeling the thrust of the engine by using LSSVRDCQGA.
Details
Keywords
Xiao Yao, Dongxiao Wu, Zhiyong Li and Haoxiang Xu
Since stock return and volatility matters to investors, this study proposes to incorporate the textual sentiment of annual reports in stock price crash risk prediction.
Abstract
Purpose
Since stock return and volatility matters to investors, this study proposes to incorporate the textual sentiment of annual reports in stock price crash risk prediction.
Design/methodology/approach
Specific sentences gathered from management discussions and their subsequent analyses are tokenized and transformed into numeric vectors using textual mining techniques, and then the Naïve Bayes method is applied to score the sentiment, which is used as an input variable for crash risk prediction. The results are compared between a collection of predictive models, including linear regression (LR) and machine learning techniques.
Findings
The experimental results find that those predictive models that incorporate textual sentiment significantly outperform the baseline models with only accounting and market variables included. These conclusions hold when crash risk is proxied by either the negative skewness of the return distribution or down-to-up volatility (DUVOL).
Research limitations/implications
It should be noted that the authors' study focuses on examining the predictive power of textual sentiment in crash risk prediction, while other dimensions of textual features such as readability and thematic contents are not considered. More analysis is needed to explore the predictive power of textual features from various dimensions, with the most recent sample data included in future studies.
Originality/value
The authors' study provides implications for the information value of textual data in financial analysis and risk management. It suggests that the soft information contained within annual reports may prove informative in crash risk prediction, and the incorporation of textual sentiment provides an incremental improvement in overall predictive performance.
Details
Keywords
Introduction: The insurance industry has unprecedented growth, and the demand for insurance has outgrown in the recent past due to the prevailing pandemic. The companies have a…
Abstract
Introduction: The insurance industry has unprecedented growth, and the demand for insurance has outgrown in the recent past due to the prevailing pandemic. The companies have a large base of the data set at their disposal, and companies must appropriately handle these data to come out with valuable solutions. Data mining enables insurance companies to gain an insightful approach to map strategies and gain competitive advantage, thus strengthening the profits that will allow them to identify the effectiveness of back-propagation neural network (BPNN) and support vector machines (SVMs) for the companies considered under study. Data mining techniques are the data-driven extraction techniques of information from large data repositories, thus discovering useful patterns from the voluminous data (Weiss & Indurkya, 1998).
Purpose: The present study is performed to investigate the comparative performance of BPNNs and SVMs for the selected Indian insurance companies.
Methodology: The study is conducted by extracting daily data of Indian insurance companies listed on the CNX 500. The data were then transformed into technical indicators for predictive model building using BPNN and SVMs. The daily data of the selected insurance companies for four years, that is, 1 April 2017 to 21 March 2021, were used for this. The data were further transformed into 90 data sets for different periods by categorising them into biannual, annual, and two-year collective data sets. Additionally, the comparison was made for the models generated with the help of BPNNs and SVMs for the six Indian insurance companies selected under this study.
Findings: The findings of the study exhibited that the predictive performance of the BPNN and SVM models are significantly different from each other for SBI data, General Insurance Corporation of India (GICRE) data, HDFC data, New India Assurance Company Ltd. (NIACL) data, and ICICIPRULI data at a 5% level of significance.
Details
Keywords
Ackmez Mudhoo, Gaurav Sharma, Khim Hoong Chu and Mika Sillanpää
Adsorption parameters (e.g. Langmuir constant, mass transfer coefficient and Thomas rate constant) are involved in the design of aqueous-media adsorption treatment units. However…
Abstract
Adsorption parameters (e.g. Langmuir constant, mass transfer coefficient and Thomas rate constant) are involved in the design of aqueous-media adsorption treatment units. However, the classic approach to estimating such parameters is perceived to be imprecise. Herein, the essential features and performances of the ant colony, bee colony and elephant herd optimisation approaches are introduced to the experimental chemist and chemical engineer engaged in adsorption research for aqueous systems. Key research and development directions, believed to harness these algorithms for real-scale water treatment (which falls within the wide-ranging coverage of the Sustainable Development Goal 6 (SDG 6) ‘Clean Water and Sanitation for All’), are also proposed. The ant colony, bee colony and elephant herd optimisations have higher precision and accuracy, and are particularly efficient in finding the global optimum solution. It is hoped that the discussions can stimulate both the experimental chemist and chemical engineer to delineate the progress achieved so far and collaborate further to devise strategies for integrating these intelligent optimisations in the design and operation of real multicomponent multi-complexity adsorption systems for water purification.
Details
Keywords
Maan Habib, Bashar Bashir, Abdullah Alsalman and Hussein Bachir
Slope stability analysis is essential for ensuring the safe design of road embankments. While various conventional methods, such as the finite element approach, are used to…
Abstract
Purpose
Slope stability analysis is essential for ensuring the safe design of road embankments. While various conventional methods, such as the finite element approach, are used to determine the safety factor of road embankments, there is ongoing interest in exploring the potential of machine learning techniques for this purpose.
Design/methodology/approach
Within the study context, the outcomes of the ensemble machine learning models will be compared and benchmarked against the conventional techniques used to predict this parameter.
Findings
Generally, the study results have shown that the proposed machine learning models provide rapid and accurate estimates of the safety factor of road embankments and are, therefore, promising alternatives to traditional methods.
Originality/value
Although machine learning algorithms hold promise for rapidly and accurately estimating the safety factor of road embankments, few studies have systematically compared their performance with traditional methods. To address this gap, this study introduces a novel approach using advanced ensemble machine learning techniques for efficient and precise estimation of the road embankment safety factor. Besides, the study comprehensively assesses the performance of these ensemble techniques, in contrast with established methods such as the finite element approach and empirical models, demonstrating their potential as robust and reliable alternatives in the realm of slope stability assessment.
Details
Keywords
Rohollah Hasanzadeh Fereydooni, Hassan Siahkali, Heidar Ali Shayanfar and Amir Houshang Mazinan
This paper aims to propose an innovative adaptive control method for lower-limb rehabilitation robots.
Abstract
Purpose
This paper aims to propose an innovative adaptive control method for lower-limb rehabilitation robots.
Design/methodology/approach
Despite carrying out various studies on the subject of rehabilitation robots, the flexibility and stability of the closed-loop control system is still a challenging problem. In the proposed method, surface electromyography (sEMG) and human force-based dual closed-loop control strategy is designed to adaptively control the rehabilitation robots. A motion analysis of human lower limbs is performed by using a wavelet neural network (WNN) to obtain the desired trajectory of patients. In the outer loop, the reference trajectory of the robot is modified by a variable impedance controller (VIC) on the basis of the sEMG and human force. Thenceforward, in the inner loop, a model reference adaptive controller with parameter updating laws based on the Lyapunov stability theory forces the rehabilitation robot to track the reference trajectory.
Findings
The experiment results confirm that the trajectory tracking error is efficiently decreased by the VIC and adaptively correct the reference trajectory synchronizing with the patients’ motion intention; the model reference controller is able to outstandingly force the rehabilitation robot to track the reference trajectory. The method proposed in this paper can better the functioning of the rehabilitation robot system and is expandable to other applications of the rehabilitation field.
Originality/value
The proposed approach is interesting for the design of an intelligent control of rehabilitation robots. The main contributions of this paper are: using a WNN to obtain the desired trajectory of patients based on sEMG signal, modifying the reference trajectory by the VIC and using model reference control to force rehabilitation robot to track the reference trajectory.
Details
Keywords
Jaganathan Gokulachandran and K. Mohandas
The accurate assessment of tool life of any given tool is a great significance in any manufacturing industry. The purpose of this paper is to predict the life of a cutting tool…
Abstract
Purpose
The accurate assessment of tool life of any given tool is a great significance in any manufacturing industry. The purpose of this paper is to predict the life of a cutting tool, in order to help decision making of the next scheduled replacement of tool and improve productivity.
Design/methodology/approach
This paper reports the use of two soft computing techniques, namely, neuro-fuzzy logic and support vector regression (SVR) techniques for the assessment of cutting tools. In this work, experiments are conducted based on Taguchi approach and tool life values are obtained.
Findings
The analysis is carried out using the two soft computing techniques. Tool life values are predicted using aforesaid techniques and these values are compared.
Practical implications
The proposed approaches are relatively simple and can be implemented easily by using software like MATLAB and Weka.
Originality/value
The proposed methodology compares neuro – fuzzy logic and SVR techniques.
Details
Keywords
Igor Gomes Vidigal, Mariana Pereira de Melo, Adriano Francisco Siqueira, Domingos Sávio Giordani, Érica Leonor Romão, Eduardo Ferro dos Santos and Ana Lucia Gabas Ferreira
This study aims to describe a bibliometric analysis of recent articles addressing the applications of e- noses with particular emphasis on those dealing with fuel-related…
Abstract
Purpose
This study aims to describe a bibliometric analysis of recent articles addressing the applications of e- noses with particular emphasis on those dealing with fuel-related products. Documents covering the general area of e-nose research and published between 1975 and 2021 were retrieved from the Web of Science database, and peer-reviewed articles were selected and appraised according to specific descriptors and criteria.
Design/methodology/approach
Analyses were performed by mapping the knowledge domain using the software tools VOSviewer and RStudio. It was possible to identify the countries, research organizations, authors and disciplines that were most prolific in the area, together with the most cited articles and the most frequent keywords. A total of 3,921 articles published in peer-reviewed journals were initially retrieved but only 47 (1.19%) described fuel-related e-nose applications with original articles published in indexed journals. However, this number was reduced to 38 (0.96%) articles strictly related to the target subject.
Findings
Rigorous appraisal of these documents yielded 22 articles that could be classified into two groups, those aimed at predicting the values of key parameters and those dealing with the discrimination of samples. Most of these 22 selected articles (68.2%) were published between 2017 and 2021, but little evidence was apparent of international collaboration between researchers and institutions currently working on this topic. The strategy of switching energy systems away from fossil fuels towards low-carbon renewable technologies that has been adopted by many countries will generate substantial research opportunities in the prediction, discrimination and quantification of volatiles in biofuels using e-nose.
Research limitations/implications
It is important to highlight that the greatest difficulty in using the e-nose is the interpretation of the data generated by the equipment; most studies have so far used the maximum value of the electrical resistance signal of each e-nose sensor as the only data provided by this sensor; however, from 2019 onwards, some works began to consider the entire electrical resistance curve as a data source, extracting more information from it.
Originality/value
This study opens a new and promising way for the effective use of e-nose as a fuel analysis instrument, as low-cost sensors can be developed for use with the new data analysis methodology, enabling the production of portable, cheaper and more reliable equipment.
Details