Search results

This study aims to present the concept of aircraft turbofan engine health status prediction with artificial neural network (ANN) pattern recognition but augmented with automated features engineering (AFE).

The main concept of engine health status prediction was based on three case studies and a validation process. The first two were performed on the engine health status parameters, namely, performance margin and specific fuel consumption margin. The third one was generated and created for the engine performance and safety data, specifically created for the final test. The final validation of the neural network pattern recognition was the validation of the proposed neural network architecture in comparison to the machine learning classification algorithms. All studies were conducted for ANN, which was a two-layer feedforward network architecture with pattern recognition. All case studies and tests were performed for both simple pattern recognition network and network augmented with automated feature engineering (AFE).

The greatest achievement of this elaboration is the presentation of how on the basis of the real-life engine operational data, the entire process of engine status prediction might be conducted with the application of the neural network pattern recognition process augmented with AFE.

This research could be implemented into the engine maintenance strategy and planning. Engine health status prediction based on ANN augmented with AFE is an extremely strong tool in aircraft accident and incident prevention.

Although turbofan engine health status prediction with ANN is not a novel approach, what is absolutely worth emphasizing is the fact that contrary to other publications this research was based on genuine, real engine performance operational data as well as AFE methodology, which makes the entire research very reliable. This is also the reason the prediction results reflect the effect of the real engine wear and deterioration process.

This study aims to present an innovative predictive methodology that transitions from traditional efficiency assessment techniques to a forward-looking strategy for evaluating working capital management(WCM) and its determinants by integrating data envelopment analysis (DEA) with artificial neural networks (ANN).

A slack-based measure (SBM) within DEA was used to evaluate the WCME of 1,388 firms in the Indian manufacturing sector across nine industries over the period from April 2009 to March 2024. Subsequently, a fixed-effects model was used to determine the relationships between selected determinants and WCME. Moreover, the multi-layer perceptron method was applied to calculate the artificial neural network (ANN). Finally, sensitivity analysis was conducted to determine the relative significance of key predictors on WCME.

Manufacturing firms consistently operate at around 50% WCME throughout the study period. Furthermore, among the selected variables, ability to create internal resources, leverage, growth, total fixed assets and productivity are relatively significant vital predictors influencing WCME.

The integration of SBM-DEA and ANN represents the primary contribution of this research, introducing a novel approach to efficiency assessment. Unlike traditional models, the SBM-DEA model offers unit invariance and monotonicity for slacks, allowing it to handle zero and negative data, which overcomes the limitations of previous DEA models. This innovation leads to more accurate efficiency scores, enabling robust analysis. Furthermore, applying neural networks provides predictive insights by identifying critical predictors for WCME, equipping firms to address WCM challenges proactively.

Predicting commodity futures trading volumes represents an important matter to policymakers and a wide spectrum of market participants. The purpose of this study is to concentrate on the energy sector and explore the trading volume prediction issue for the thermal coal futures traded in Zhengzhou Commodity Exchange in China with daily data spanning January 2016–December 2020.

The nonlinear autoregressive neural network is adopted for this purpose and prediction performance is examined based upon a variety of settings over algorithms for model estimations, numbers of hidden neurons and delays and ratios for splitting the trading volume series into training, validation and testing phases.

A relatively simple model setting is arrived at that leads to predictions of good accuracy and stabilities and maintains small prediction errors up to the 99.273th quantile of the observed trading volume.

The results could, on one hand, serve as standalone technical trading volume predictions. They could, on the other hand, be combined with different (fundamental) prediction results for forming perspectives of trading trends and carrying out policy analysis.

Artificial intelligence (AI) can enhance human resource resiliency (HRR) by providing the insights and resources needed to adapt to unexpected changes and disruptions. Therefore, the present research attempts to develop a framework for future researchers to gain insights into the actions of AI to enable HRR.

The present study used a systematic literature review, bibliometric analysis, and network analysis followed by content analysis. In doing so, we reviewed the literature to explore the present state of research in AI and HRR. A total of 98 articles were included, extracted from the Scopus database in the selected field of research.

The authors found that AI or AI-associated techniques help deliver various HRR-oriented outcomes, such as enhancing employee competency, performance management and risk management; enhancing leadership competencies and employee well-being measures; and developing effective compensation and reward management.

The present research has certain implications, such as increasing the HR team's proficiency, addressing the problem of job loss and how to fix it, improving working conditions and improving decision-making in HR.

The present research explores the role of AI in HRR following the COVID-19 pandemic, which has not been explored extensively.

The variance between the winning bid and the owner's estimated cost (OEC) is one of the construction management risks in the pre-tendering phase. The study aims to enhance the quality of the owner's estimation for predicting precisely the contract cost at the pre-tendering phase and avoiding future issues that arise through the construction phase.

This paper integrated artificial neural networks (ANN), deep neural networks (DNN) and time series (TS) techniques to estimate the ratio of a low bid to the OEC (R) for different size contracts and three types of contracts (building, electric and mechanic) accurately based on 94 contracts from King Saud University. The ANN and DNN models were evaluated using mean absolute percentage error (MAPE), mean sum square error (MSSE) and root mean sums square error (RMSSE).

The main finding is that the ANN provides high accuracy with MAPE, MSSE and RMSSE a 2.94%, 0.0015 and 0.039, respectively. The DNN's precision was high, with an RMSSE of 0.15 on average.

The owner and consultant are expected to use the study's findings to create more accuracy of the owner's estimate and decrease the difference between the owner's estimate and the lowest submitted offer for better decision-making.

This study fills the knowledge gap by developing an ANN model to handle missing TS data and forecasting the difference between a low bid and an OEC at the pre-tendering phase.

This paper aims to present a predictive model approach to estimate the tensile behavior of polylactic acid (PLA) under uncertainty using the fused deposition modeling (FDM) and American Society for Testing and Materials (ASTM) D638’s Types I and II test standards.

The prediction approach combines artificial neural network (ANN) and finite element analysis (FEA), Monte Carlo simulation (MCS) and experimental testing for estimating tensile behavior for FDM considering uncertainties of input parameters. FEA with variance-based sensitivity analysis is used to quantify the impacts of uncertain variables, resulting in determining the significant variables for use in the ANN model. ANN surrogates FEA models of ASTM D638’s Types I and II standards to assess their prediction capabilities using MCS. The developed model is applied for testing the tensile behavior of PLA given probabilistic variables of geometry and material properties.

The results demonstrate that Type I is more appropriate than Type II for predicting tensile behavior under uncertainty. With a training accuracy of 98% and proven presence of overfitting, the tensile behavior can be successfully modeled using predictive methods that consider the probabilistic nature of input parameters. The proposed approach is generic and can be used for other testing standards, input parameters, materials and response variables.

Using the proposed predictive approach, to the best of the authors’ knowledge, the tensile behavior of PLA is predicted for the first time considering uncertainties of input parameters. Also, incorporating global sensitivity analysis for determining the most contributing parameters influencing the tensile behavior has not yet been studied for FDM. The use of only significant variables for FEA, ANN and MCS minimizes the computational effort, allowing to simulate more runs with reduced number of variables within acceptable time.

Text classification is a widely accepted and adopted technique in organizations to mine and analyze unstructured and semi-structured data. With advancement of technological computing, deep learning has become more popular among academicians and professionals to perform mining and analytical operations. In this work, the authors study the research carried out in field of text classification using deep learning techniques to identify gaps and opportunities for doing research.

The authors adopted bibliometric-based approach in conjunction with visualization techniques to uncover new insights and findings. The authors collected data of two decades from Scopus global database to perform this study. The authors discuss business applications of deep learning techniques for text classification.

The study provides overview of various publication sources in field of text classification and deep learning together. The study also presents list of prominent authors and their countries working in this field. The authors also presented list of most cited articles based on citations and country of research. Various visualization techniques such as word cloud, network diagram and thematic map were used to identify collaboration network.

The study performed in this paper helped to understand research gaps that is original contribution to body of literature. To best of the authors' knowledge, in-depth study in the field of text classification and deep learning has not been performed in detail. The study provides high value to scholars and professionals by providing them opportunities of research in this area.

This paper aims to analyze deeply the effect of surface roughness conditions of the common interface of the two-layered riveted cantilever beams on their frictional damping during free lateral vibration at first mode. Here, the product, (µ × α), and damping ratio, ξ, are the parameters whose variations are analyzed in this investigation. For this, the influencing parameters considered are the natural frequency of vibration, f; the amplitude of initial excitation, y; and surface roughness value, Ra.

For experimentally evaluating logarithmic damping decrement, d, the frequency response function analyzer for the case of free lateral vibrations was used. Later, for evaluating the product, µ × α (where µ is the kinematic coefficient of friction and α is the dynamic slip ratio), and then, the damping ratio, ξ, the empirical relation suggested for logarithmic damping decrement, d, of riveted cantilever beams was used. After this, the full and reduced quadratic models of the product, µ × α, ξ, response surface methodology (RSM) with the help of Design Expert 11 software was used. Corresponding main effects plots, surface plots and prediction comparison plots were obtained to observe the variations of the product, µ × α, ξ for the variations of influencing parameters: f, y and Ra. Finally, a machine learning technique such as artificial neural networks (ANNs) using “nntool” present in MATLAB R13a software was used to predict the ξ for the different combinations of f, y and Ra.

The full and reduced quadratic regression models for the product, (µ × α) and the damping ratio, ξ of riveted cantilever beams for free lateral vibrations of the first mode in terms of the parameters: f, y and Ra were obtained. In addition, the main effects plots, surface plots and prediction comparison plots for the product, µ × α, ξ, with the corresponding experimental values of the product, µ × α, ξ, were obtained. Also, the execution of ANNs using MATLAB R13a software is proved to be the more accurate tool for the prediction of damping ratios in comparison to quadratic regression equations obtained from Design Expert 11 software. In the end, the assumption that the effect of surface roughness value on the product, (µ × α), and the damping ratio, ξ, is negligible is proved to be true using the main effects plots for the product, (µ × α) and ξ obtained from the Design Expert 11 software.

Obtaining the full and reduced quadratic regression equations for the product, (µ × α), and ξ of the two-layered riveted cantilever beams in terms of parameters: f, y and Ra was done. In addition, the conditions for the corresponding minimum and maximum values of the product, (µ × α), and ξ were obtained. Later, the main effects plots, surface plots and comparison plots of the predicted product, (µ × α), and ξ versus experimental product, (µ × α), and ξ were also obtained. Finally, the predicted values of the product, (µ × α), and ξ using the ANNs tool are observed to be the more accurate values in comparison to that obtained from RSM using the Design Expert 11 software.

The study aims to determine the the optimal value of output parameters of a variable compression ratio (CR) diesel engine are investigated at different loads, CR and fuel modes of operation experimentally. The output parameters of a variable compression ratio (CR) diesel engine are investigated at different loads, CR and fuel modes of operation experimentally. The performance parameters like brake thermal efficiency (BTE) and brake specific energy consumption (BSEC), whereas CO emission, HC emission, CO₂ emission, NO_x emission, exhaust gas temperature (EGT) and opacity are the emission parameters measured during the test. Tests are conducted for 2, 6 and 10 kg of load, 16.5 and 17.5 of CR.

In this investigation, the first engine was fueled with 100% diesel and 100% Calophyllum inophyllum oil in single-fuel mode. Then Calophyllum inophyllum oil with producer gas was fed to the engine. Calophyllum inophyllum oil offers lower BTE, CO and HC emissions, opacity and higher EGT, BSEC, CO₂ emission and NO_x emissions compared to diesel fuel in both fuel modes of operation observed. The performance optimization using the Taguchi approach is carried out to determine the optimal input parameters for maximum performance and minimum emissions for the test engine. The optimized value of the input parameters is then fed into the prediction techniques, such as the artificial neural network (ANN).

From multiple response optimization, the minimum emissions of 0.58% of CO, 42% of HC, 191 ppm NO_x and maximum BTE of 21.56% for 16.5 CR, 10 kg load and dual fuel mode of operation are determined. Based on generated errors, the ANN is also ranked for precision. The proposed ANN model provides better prediction with minimum experimental data sets. The values of the R² correlation coefficient are 1, 0.95552, 0.94367 and 0.97789 for training, validation, testing and all, respectively. The said biodiesel may be used as a substitute for conventional diesel fuel.

The blend of Calophyllum inophyllum oil-producer gas is used to run the diesel engine. Performance and emission analysis has been carried out, compared, optimized and validated.

Despite the considerable hype about how Big Data Analytics (BDA) can transform businesses and advance their capabilities, recognising its strategic value through successful adoption is yet to be appreciated. The purpose of this paper is to focus on the process-level value-chain realisation of BDA adoption between SMEs and large organisations.

Resource-based theory offered the lens for developing a conceptual BDA process-level value chain adoption model. A combined two-staged regression-artificial neural network approach has been utilised for 369 small, medium (SMEs) and large organisations to verify their critical value chain process-level drivers for successful organisational adoption of BDA.

The findings revealed that organisational BDA adoption success is driven predominantly by product—and service-process-level value, with distinctive discrepancies dependent on the organisation’s size. Large organisations primarily embrace BDA for their external value chain dimensions, while SMEs encompass its internal value chain cues. As such, businesses will be advised to acknowledge their organisational dynamics and precise size to develop the right strategies to adopt BDA successfully.

The study advances the understanding of the role of internal and external value chain drivers in influencing how BDA can be successfully adopted in SMEs and large organisations. Thus, appreciating the organisation’s unique attributes, including its size, will need to be carefully examined. By investigating these elements, this research has shed new light on how developing such innovative capabilities and competencies must be carefully crafted to help create a sustainable competitive advantage.

For an organisational positioning, acknowledging the role of internal and external value chain drivers is critical for implementing the right strategies for adopting BDA. For larger businesses, resources for innovation often can be widely available compared to SMEs. As such, they can manage their costs and associated risks resourcefully. By considering the identified value-chain-related adoption success factors, businesses should be better positioned to assess their competencies while being prepared to adopt BDA.

The study offers the research and business community empirical-based insights into the strategies needed to successfully adopt big data in an organisation from a process-level value chain perspective.