Search results
1 – 10 of over 1000Bingwei Gao, Hongjian Zhao, Wenlong Han and Shilong Xue
This study proposes a predictive neural network model reference decoupling control method for the coupling problem between the leg joints of hydraulic quadruped robots, and…
Abstract
Purpose
This study proposes a predictive neural network model reference decoupling control method for the coupling problem between the leg joints of hydraulic quadruped robots, and verifies its decoupling effect..
Design/methodology/approach
The machine–hydraulic cross-linking coupling is studied as the coupling behavior of the hydraulically driven quadruped robot, and the mechanical dynamics coupling force of the robot system is controlled as the disturbance force of the hydraulic system through the Jacobian matrix transformation. According to the principle of multivariable decoupling, a prediction-based neural network model reference decoupling control method is proposed; each module of the control algorithm is designed one by one, and the stability of the system is analyzed by the Lyapunov stability theorem.
Findings
The simulation and experimental research on the robot joint decoupling control method is carried out, and the prediction-based neural network model reference decoupling control method is compared with the decoupling control method without any decoupling control method. The results show that taking the coupling effect experiment between the hip joint and knee joint as an example, after using the predictive neural network model reference decoupling control method, the phase lag of the hip joint response line was reduced from 20.3° to 14.8°, the amplitude attenuation was reduced from 1.82% to 0.21%, the maximum error of the knee joint coupling line was reduced from 0.67 mm to 0.16 mm and the coupling effect between the hip joint and knee joint was reduced from 1.9% to 0.48%, achieving good decoupling.
Originality/value
The prediction-based neural network model reference decoupling control method proposed in this paper can use the neural network model to predict the next output of the system according to the input and output. Finally, the weights of the neural network are corrected online according to the predicted output and the given reference output, so that the optimization index of the neural network decoupling controller is extremely small, and the purpose of decoupling control is achieved.
Details
Keywords
Nirodha Fernando, Kasun Dilshan T.A. and Hexin (Johnson) Zhang
The Government’s investment in infrastructure projects is considerably high, especially in bridge construction projects. Government authorities must establish an initial…
Abstract
Purpose
The Government’s investment in infrastructure projects is considerably high, especially in bridge construction projects. Government authorities must establish an initial forecasted budget to have transparency in transactions. Early cost estimating is challenging for Quantity Surveyors due to incomplete project details at the initial stage and the unavailability of standard cost estimating techniques for bridge projects. To mitigate the difficulties in the traditional preliminary cost estimating methods, there is a requirement to develop a new initial cost estimating model which is accurate, user friendly and straightforward. The research was carried out in Sri Lanka, and this paper aims to develop the artificial neural network (ANN) model for an early cost estimate of concrete bridge systems.
Design/methodology/approach
The construction cost data of 30 concrete bridge projects which are in Sri Lanka constructed within the past ten years were trained and tested to develop an ANN cost model. Backpropagation technique was used to identify the number of hidden layers, iteration and momentum for optimum neural network architectures.
Findings
An ANN cost model was developed, furnishing the best result since it succeeded with around 90% validation accuracy. It created a cost estimation model for the public sector as an accurate, heuristic, flexible and efficient technique.
Originality/value
The research contributes to the current body of knowledge by providing the most accurate early-stage cost estimate for the concrete bridge systems in Sri Lanka. In addition, the research findings would be helpful for stakeholders and policymakers to propose policy recommendations that positively influence the prediction of the most accurate cost estimate for concrete bridge construction projects in Sri Lanka and other developing countries.
Details
Keywords
Jamie L. Daigle, Gary Stading and Ashley Hall
The study aims to refine the local university’s supply chain management curriculum to meet regional industry demands, thus boosting the local economy.
Abstract
Purpose
The study aims to refine the local university’s supply chain management curriculum to meet regional industry demands, thus boosting the local economy.
Design/methodology/approach
Mixed-methods action research combined with neural network modeling was employed to align educational offerings with the needs of the local supply chain management industry.
Findings
The research indicates that curriculum revisions, informed by industry leaders and modeled through neural networks, can significantly improve the relevance of graduates' skills to the SCM sector.
Research limitations/implications
The study is specific to one region and industry, suggesting a need for broader application to verify the findings.
Practical implications
Adopting the recommended curricular changes can yield a workforce better prepared for the SCM industry, enhancing local business performance and economic health.
Social implications
The study supports a role for higher education in promoting economic vitality and social welfare through targeted, responsive curriculum development.
Originality/value
This study introduces an innovative approach, integrating neural network analysis with action research, to guide curriculum development in higher education based on industry requirements.
Details
Keywords
The purpose of this research is to achieve multi-task autonomous driving by adjusting the network architecture of the model. Meanwhile, after achieving multi-task autonomous…
Abstract
Purpose
The purpose of this research is to achieve multi-task autonomous driving by adjusting the network architecture of the model. Meanwhile, after achieving multi-task autonomous driving, the authors found that the trained neural network model performs poorly in untrained scenarios. Therefore, the authors proposed to improve the transfer efficiency of the model for new scenarios through transfer learning.
Design/methodology/approach
First, the authors achieved multi-task autonomous driving by training a model combining convolutional neural network and different structured long short-term memory (LSTM) layers. Second, the authors achieved fast transfer of neural network models in new scenarios by cross-model transfer learning. Finally, the authors combined data collection and data labeling to improve the efficiency of deep learning. Furthermore, the authors verified that the model has good robustness through light and shadow test.
Findings
This research achieved road tracking, real-time acceleration–deceleration, obstacle avoidance and left/right sign recognition. The model proposed by the authors (UniBiCLSTM) outperforms the existing models tested with model cars in terms of autonomous driving performance. Furthermore, the CMTL-UniBiCL-RL model trained by the authors through cross-model transfer learning improves the efficiency of model adaptation to new scenarios. Meanwhile, this research proposed an automatic data annotation method, which can save 1/4 of the time for deep learning.
Originality/value
This research provided novel solutions in the achievement of multi-task autonomous driving and neural network model scenario for transfer learning. The experiment was achieved on a single camera with an embedded chip and a scale model car, which is expected to simplify the hardware for autonomous driving.
Details
Keywords
Mohammad Ghalambaz, Mikhail A. Sheremet, Mohammed Arshad Khan, Zehba Raizah and Jana Shafi
This study aims to explore the evolving field of physics-informed neural networks (PINNs) through an analysis of 996 records retrieved from the Web of Science (WoS) database from…
Abstract
Purpose
This study aims to explore the evolving field of physics-informed neural networks (PINNs) through an analysis of 996 records retrieved from the Web of Science (WoS) database from 2019 to 2022.
Design/methodology/approach
WoS database was analyzed for PINNs using an inhouse python code. The author’s collaborations, most contributing institutes, countries and journals were identified. The trends and application categories were also analyzed.
Findings
The papers were classified into seven key domains: Fluid Dynamics and computational fluid dynamics (CFD); Mechanics and Material Science; Electromagnetism and Wave Propagation; Biomedical Engineering and Biophysics; Quantum Mechanics and Physics; Renewable Energy and Power Systems; and Astrophysics and Cosmology. Fluid Dynamics and CFD emerged as the primary focus, accounting for 69.3% of total publications and witnessing exponential growth from 22 papers in 2019 to 366 in 2022. Mechanics and Material Science followed, with an impressive growth trajectory from 3 to 65 papers within the same period. The study also underscored the rising interest in PINNs across diverse fields such as Biomedical Engineering and Biophysics, and Renewable Energy and Power Systems. Furthermore, the focus of the most active countries within each application category was examined, revealing, for instance, the USA’s significant contribution to Fluid Dynamics and CFD with 319 papers and to Mechanics and Material Science with 66 papers.
Originality/value
This analysis illuminates the rapidly expanding role of PINNs in tackling complex scientific problems and highlights its potential for future research across diverse domains.
Details
Keywords
Hongbin Li, Zhihao Wang, Nina Sun and Lianwen Sun
Considering the influence of deformation error, the target poses must be corrected when compensating for positioning error but the efficiency of existing positioning error…
Abstract
Purpose
Considering the influence of deformation error, the target poses must be corrected when compensating for positioning error but the efficiency of existing positioning error compensation algorithms needs to be improved. Therefore, the purpose of this study is to propose a high-efficiency positioning error compensation method to reduce the calculation time.
Design/methodology/approach
The corrected target poses are calculated. An improved back propagation (BP) neural network is used to establish the mapping relationship between the original and corrected target poses. After the BP neural network is trained, the corrected target poses can be calculated with short notice on the basis of the pose correction similarity.
Findings
Under given conditions, the calculation time when the trained BP neural network is used to predict the corrected target poses is only 1.15 s. Compared with the existing algorithm, this method reduces the calculation time of the target poses from the order of minutes to the order of seconds.
Practical implications
The proposed algorithm is more efficient while maintaining the accuracy of the error compensation.
Originality/value
This method can be used to quickly position the error compensation of a large parallel mechanism.
Details
Keywords
Bingzi Jin, Xiaojie Xu and Yun Zhang
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…
Abstract
Purpose
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.
Design/methodology/approach
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.
Findings
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.
Originality/value
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.
Details
Keywords
Bingzi Jin and Xiaojie Xu
Agriculture commodity price forecasts have long been important for a variety of market players. The study we conducted aims to address this difficulty by examining the weekly…
Abstract
Purpose
Agriculture commodity price forecasts have long been important for a variety of market players. The study we conducted aims to address this difficulty by examining the weekly wholesale price index of green grams in the Chinese market. The index covers a ten-year period, from January 1, 2010, to January 3, 2020, and has significant economic implications.
Design/methodology/approach
In order to address the nonlinear patterns present in the price time series, we investigate the nonlinear auto-regressive neural network as the forecast model. This modeling technique is able to combine a variety of basic nonlinear functions to approximate more complex nonlinear characteristics. Specifically, we examine prediction performance that corresponds to several configurations across data splitting ratios, hidden neuron and delay counts, and model estimation approaches.
Findings
Our model turns out to be rather simple and yields forecasts with good stability and accuracy. Relative root mean square errors throughout training, validation and testing are specifically 4.34, 4.71 and 3.98%, respectively. The results of benchmark research show that the neural network produces statistically considerably better performance when compared to other machine learning models and classic time-series econometric methods.
Originality/value
Utilizing our findings as independent technical price forecasts would be one use. Alternatively, policy research and fresh insights into price patterns might be achieved by combining them with other (basic) prediction outputs.
Details
Keywords
Xiaojie Xu and Yun Zhang
The Chinese housing market has gone through rapid growth during the past decade, and house price forecasting has evolved to be a significant issue that draws enormous attention…
Abstract
Purpose
The Chinese housing market has gone through rapid growth during the past decade, and house price forecasting has evolved to be a significant issue that draws enormous attention from investors, policy makers and researchers. This study investigates neural networks for composite property price index forecasting from ten major Chinese cities for the period of July 2005–April 2021.
Design/methodology/approach
The goal is to build simple and accurate neural network models that contribute to pure technical forecasts of composite property prices. To facilitate the analysis, the authors consider different model settings across algorithms, delays, hidden neurons and data spitting ratios.
Findings
The authors arrive at a pretty simple neural network with six delays and three hidden neurons, which generates rather stable performance of average relative root mean square errors across the ten cities below 1% for the training, validation and testing phases.
Originality/value
Results here could be utilized on a standalone basis or combined with fundamental forecasts to help form perspectives of composite property price trends and conduct policy analysis.
Details
Keywords
Yang Liu, Xin Xu, Shiqing Lv, Xuewei Zhao, Yuxiong Xue, Shuye Zhang, Xingji Li and Chaoyang Xing
Due to the miniaturization of electronic devices, the increased current density through solder joints leads to the occurrence of electromigration failure, thereby reducing the…
Abstract
Purpose
Due to the miniaturization of electronic devices, the increased current density through solder joints leads to the occurrence of electromigration failure, thereby reducing the reliability of electronic devices. The purpose of this study is to propose a finite element-artificial neural network method for the prediction of temperature and current density of solder joints, and thus provide reference information for the reliability evaluation of solder joints.
Design/methodology/approach
The temperature distribution and current density distribution of the interconnect structure of electronic devices were investigated through finite element simulations. During the experimental process, the actual temperature of the solder joints was measured and was used to optimize the finite element model. A large amount of simulation data was obtained to analyze the neural network by varying the height of solder joints, the diameter of solder pads and the magnitude of current loads. The constructed neural network was trained, tested and optimized using this data.
Findings
Based on the finite element simulation results, the current is more concentrated in the corners of the solder joints, generating a significant amount of Joule heating, which leads to localized temperature rise. The constructed neural network is trained, tested and optimized using the simulation results. The ANN 1, used for predicting solder joint temperature, achieves a prediction accuracy of 96.9%, while the ANN 2, used for predicting solder joint current density, achieves a prediction accuracy of 93.4%.
Originality/value
The proposed method can effectively improve the estimation efficiency of temperature and current density in the packaging structure. This method prevails in the field of packaging, and other factors that affect the thermal, mechanical and electrical properties of the packaging structure can be introduced into the model.
Details