Search results
1 – 10 of 10The purpose of this study is to establish a friction coefficient prediction model using texture parameters and then using the optimal texture parameters to obtain the minimum…
Abstract
Purpose
The purpose of this study is to establish a friction coefficient prediction model using texture parameters and then using the optimal texture parameters to obtain the minimum friction coefficient.
Design/methodology/approach
Based on texture technology and the cavitation phenomenon conditions, a test scheme based on two-factor and five-level texture parameters is designed using central composite design and then the response surface methodology and hybrid back-propagation genetic algorithm (BP-GA) models are used to establish a friction coefficient prediction model and optimize the friction coefficient.
Findings
The result indicates that the values predicted using two methodologies agree well with the experimental data, but the hybrid BP-GA model is superior to the response surface methodology model in both prediction and optimization.
Originality/value
Two methodologies are used to study the influence of the texture parameters on the friction coefficient under the cavitation condition. It is expected that the result can be used to obtain optimum texture parameters to reduce the friction coefficient.
Details
Keywords
Sajad Ahmad Rather and P. Shanthi Bala
In this paper, a newly proposed hybridization algorithm namely constriction coefficient-based particle swarm optimization and gravitational search algorithm (CPSOGSA) has been…
Abstract
Purpose
In this paper, a newly proposed hybridization algorithm namely constriction coefficient-based particle swarm optimization and gravitational search algorithm (CPSOGSA) has been employed for training MLP to overcome sensitivity to initialization, premature convergence, and stagnation in local optima problems of MLP.
Design/methodology/approach
In this study, the exploration of the search space is carried out by gravitational search algorithm (GSA) and optimization of candidate solutions, i.e. exploitation is performed by particle swarm optimization (PSO). For training the multi-layer perceptron (MLP), CPSOGSA uses sigmoid fitness function for finding the proper combination of connection weights and neural biases to minimize the error. Secondly, a matrix encoding strategy is utilized for providing one to one correspondence between weights and biases of MLP and agents of CPSOGSA.
Findings
The experimental findings convey that CPSOGSA is a better MLP trainer as compared to other stochastic algorithms because it provides superior results in terms of resolving stagnation in local optima and convergence speed problems. Besides, it gives the best results for breast cancer, heart, sine function and sigmoid function datasets as compared to other participating algorithms. Moreover, CPSOGSA also provides very competitive results for other datasets.
Originality/value
The CPSOGSA performed effectively in overcoming stagnation in local optima problem and increasing the overall convergence speed of MLP. Basically, CPSOGSA is a hybrid optimization algorithm which has powerful characteristics of global exploration capability and high local exploitation power. In the research literature, a little work is available where CPSO and GSA have been utilized for training MLP. The only related research paper was given by Mirjalili et al., in 2012. They have used standard PSO and GSA for training simple FNNs. However, the work employed only three datasets and used the MSE performance metric for evaluating the efficiency of the algorithms. In this paper, eight different standard datasets and five performance metrics have been utilized for investigating the efficiency of CPSOGSA in training MLPs. In addition, a non-parametric pair-wise statistical test namely the Wilcoxon rank-sum test has been carried out at a 5% significance level to statistically validate the simulation results. Besides, eight state-of-the-art meta-heuristic algorithms were employed for comparative analysis of the experimental results to further raise the authenticity of the experimental setup.
Details
Keywords
ShunXiang Wei, Haibo Wu, Liang Liu, YiXiao Zhang, Jiang Chen and Quanfeng Li
To achieve stable gait planning and enhance the motion performance of quadruped robot, this paper aims to propose a motion control strategy based on central pattern generator…
Abstract
Purpose
To achieve stable gait planning and enhance the motion performance of quadruped robot, this paper aims to propose a motion control strategy based on central pattern generator (CPG) and back-propagation neural network (BPNN).
Design/methodology/approach
First, the Kuramoto phase oscillator is used to construct the CPG network model, and a piecewise continuous phase difference matrix is designed to optimize the duty cycle of walk gait, so as to realize the gait planning and smooth switching. Second, the mapper between CPG output and joint drive is established based on BP neural network, so that the quadruped robot based on CPG control has better foot trajectory to enhance the motion performance. Finally, to obtain better mapping effect, an evaluation function is resigned to evaluate the proximity between the actual foot trajectory and the ideal foot trajectory. Genetic algorithm and particle swarm optimization are used to optimize the initial weights and thresholds of BPNN to obtain more accurate foot trajectory.
Findings
The method provides a solution for the smooth gait switching and foot trajectory of the robot. The quintic polynomial trajectory is selected to testify the validity and practicability of the method through simulation and prototype experiment.
Originality/value
The paper solved the incorrect duty cycle under the walk gait of CPG network constructed by Kuramoto phase oscillator, and made the robot have a better foot trajectory by mapper to enhance its motion performance.
Details
Keywords
Kabir Bala, Shehu Ahmad Bustani and Baba Shehu Waziri
The purpose of this study was develop a computer-based cost prediction model for institutional building projects in Nigeria through the use of artificial neural network (ANN…
Abstract
Purpose
The purpose of this study was develop a computer-based cost prediction model for institutional building projects in Nigeria through the use of artificial neural network (ANN) technique. The back-propagation network learns by example and provides good prediction to novel cases.
Design/methodology/approach
The input variables were derived from related works with modification and advices from professionals through a field survey. Two hundred and sixty completed project data were used for training and development of the ANN model. Back-propagation algorithm using the gradient descent delta learning rule with a learning coefficient of 0.4 was used. The input layer of the model comprised of nine variables; building height, compactness of building, construction duration, external wall area, gross floor area, number of floors, proportion of opening on external walls, location index and time index.
Findings
Several multi-layer perceptron networks were developed with varying architecture from which the network 9-7-5-1 was selected. The performance of the model over the validation sample revealed that the model has a mean absolute per cent error of 5.4 per cent and average error of prediction of −2.5 per cent over the sample. The ANN model was considered to be effective for construction cost prediction.
Research limitations/implications
The model may not be suitable for other building types because of the uniqueness of such facility even though significant difference is not anticipated for buildings such as commercial and residential. The models were evaluated based on the prediction errors; other means of evaluation were not used.
Originality/value
The study thus provides a simple, yet effective means of predicting construction costs of institutional building projects in Nigeria using an ANN model.
Details
Keywords
Arzu Vuruskan, Turker Ince, Ender Bulgun and Cuneyt Guzelis
– The purpose of this paper is to develop an intelligent system for fashion style selection for non-standard female body shapes.
Abstract
Purpose
The purpose of this paper is to develop an intelligent system for fashion style selection for non-standard female body shapes.
Design/methodology/approach
With the goal of creating natural aesthetic relationship between the body shape and the shape of clothing, garments designed for the upper and lower body are combined to fit different female body shapes, which are classified as V, A, H and O-shapes. The proposed intelligent system combines genetic algorithm (GA) with a neural network classifier, which is trained using the particle swarm optimization (PSO). The former, called genetic search, is used to find the optimal design parameters corresponding to a best fit for the desired target, while the task of the latter, called neural classification, is to evaluate fitness (goodness) of each evolved new fashion style.
Findings
The experimental results are fashion styling recommendations for the four female body shapes, drawn from 260 possible combinations, based on variations from 15 attributes. These results are considered to be a strong indication of the potential benefits of the application of intelligent systems to fashion styling.
Originality/value
The proposed intelligent system combines the effective searching capabilities of two approaches. The first approach uses the GA for identifying best fits to the target shape of the body in the solution space. The second is the PSO for finding optimal (with respect to training mean-squared error) weight and threshold parameters of the neural classifier, which is able to evaluate the fitness of successively evolved fashion styles.
Details
Keywords
Zhao Dong, Ziqiang Sheng, Yadong Zhao and Pengpeng Zhi
Mechanical products usually require deterministic finite element analysis in the design phase to determine whether their structures meet the requirements. However, deterministic…
Abstract
Purpose
Mechanical products usually require deterministic finite element analysis in the design phase to determine whether their structures meet the requirements. However, deterministic design ignores the influence of uncertainties in the design and manufacturing process of mechanical products, leading to the problem of a lack of design safety or excessive redundancy in the design. In order to improve the accuracy and rationality of the design results, a robust design method for structural reliability based on an active-learning marine predator algorithm (MPA)–backpropagation (BP) neural network is proposed.
Design/methodology/approach
The MPA was used to obtain the optimal weights and thresholds of a BP neural network, and an active-learning function applicable to neural networks was proposed to efficiently improve the prediction performance of the BP neural network. On this basis, a robust optimization design method for mechanical product reliability based on the active-learning MPA-BP model was proposed. Random moving quadrilateral sampling was used to obtain the sample points required for training and testing of the neural network, and the reliability sensitivity corresponding to each sample point was calculated by subset simulated significant sampling (SSIS). The total mass of the mechanical product and the structural reliability sensitivity of the trained active-learning MPA-BP model output were taken as the optimization objectives, and a multi-objective reliability-robust optimization design model was constructed, which was solved by the second-generation non-dominated ranking genetic algorithm (NSGA-II). Then, the dominance function was used in the obtained Pareto solution set to make a dominance-seeking decision to obtain the final reliability-robust optimization design solution. The feasibility of the proposed method was verified by a reliability-robust optimization design example of the bogie frame.
Findings
The prediction error of the active-learning MPA-BP neural network was smaller than those of the particle swarm optimization (PSO)-BP, marine predator algorithm (MPA)-BP and genetic algorithm (GA)-BP neural networks under the same basic parameter settings of the algorithm, which indicated that the improvement strategy proposed in this paper improved the prediction accuracy of the BP neural network. To ensure the reliability of the bogie frame, the reliability sensitivity and total mass of the bogie frame were reduced, which not only realized the lightweight design of the bogie frame, but also improved the reliability and robustness of the bogie.
Originality/value
The MPA algorithm with a higher optimization efficiency was introduced to find the weights and thresholds of the BP neural network. A new active-learning function was proposed to improve the prediction accuracy of the MPA-BP neural network.
Details
Keywords
Pengpeng Cheng, Daoling Chen and Jianping Wang
For comfort evaluation of underwear pressure, this paper proposes an improved GA algorithm to optimize the weight and threshold of BP neural network, namely PSO-GA-BP neural…
Abstract
Purpose
For comfort evaluation of underwear pressure, this paper proposes an improved GA algorithm to optimize the weight and threshold of BP neural network, namely PSO-GA-BP neural network prediction model.
Design/methodology/approach
The objective parameters of underwear, body shape data, skin deformation and other data are selected for simulation experiments to predict the objective pressure and subjective evaluation in dynamic and static state. Compared with the prediction results of BP neural network prediction model, GA-BP neural network prediction model and PSO-BP neural network prediction model, the performance of each prediction model is verified.
Findings
The results show that the BP neural network model optimized by PSO-GA algorithm can accelerate the convergence speed of the neural network and improve the prediction accuracy of underwear pressure.
Originality/value
PSO-GA-BP model provides data support for underwear design, production and processing and has guiding significance for consumers to choose underwear.
Details
Keywords
Cuicui Du and Deren Kong
Three-axis accelerometers play a vital role in monitoring the vibrations in aircraft machinery, especially in variable flight temperature environments. The sensitivity of a…
Abstract
Purpose
Three-axis accelerometers play a vital role in monitoring the vibrations in aircraft machinery, especially in variable flight temperature environments. The sensitivity of a three-axis accelerometer under different temperature conditions needs to be calibrated before the flight test. Hence, the authors investigated the efficiency and sensitivity calibration of three-axis accelerometers under different conditions. This paper aims to propose the novel calibration algorithm for the three-axis accelerometers or the similar accelerometers.
Design/methodology/approach
The authors propose a hybrid genetic algorithm–particle swarm optimisation–back-propagation neural network (GA–PSO–BPNN) algorithm. This method has high global search ability, fast convergence speed and strong non-linear fitting capability; it follows the rules of natural selection and survival of the fittest. The authors describe the experimental setup for the calibration of the three-axis accelerometer using a three-comprehensive electrodynamic vibration test box, which provides different temperatures. Furthermore, to evaluate the performance of the hybrid GA–PSO–BPNN algorithm for sensitivity calibration, the authors performed a detailed comparative experimental analysis of the BPNN, GA–BPNN, PSO–BPNN and GA–PSO–BPNN algorithms under different temperatures (−55, 0 , 25 and 70 °C).
Findings
It has been showed that the prediction error of three-axis accelerometer under the hybrid GA–PSO–BPNN algorithm is the least (approximately ±0.1), which proved that the proposed GA–PSO–BPNN algorithm performed well on the sensitivity calibration of the three-axis accelerometer under different temperatures conditions.
Originality/value
The designed GA–PSO–BPNN algorithm with high global search ability, fast convergence speed and strong non-linear fitting capability has been proposed to decrease the sensitivity calibration error of three-axis accelerometer, and the hybrid algorithm could reach the global optimal solution rapidly and accurately.
Details
Keywords
Ni Zhang, Yi-fei Pu, Suiquan Yang, Jinkang Gao, Zhu Wang and Ji-liu Zhou
This paper aims to build a legal intelligent auxiliary discretionary system for predicting the penalty and damage compensation values. After extensively considering current the…
Abstract
Purpose
This paper aims to build a legal intelligent auxiliary discretionary system for predicting the penalty and damage compensation values. After extensively considering current the characteristics of the current Chinese legal system, a practical legal intelligent auxiliary discretionary system based on genetic algorithm-backpropagation (GA-BP) neural network (NN) is proposed herein.
Design/methodology/approach
An experiment is designed to analyze cases involving mental anguish compensation in medical disputes, and a Chinese legal intelligent auxiliary discretionary adviser system is built based on a GA-BP NN. Because BP neural networks perform well for nonlinear problems and GAs can improve their ability to find optimal values, and accelerate their convergence, a combined GA–BP algorithm is used. In addition, an ontology is used to reduce the semantic ambiguities and extract the implied semantic information.
Findings
We confirm that a case-based legal intelligent auxiliary discretionary adviser system based on a GA-BP NN and ontology techniques has good performance in prediction. By predicting the mental anguish compensation values, the legal intelligent auxiliary discretionary adviser system can help judges to handle cases more quickly and ordinary people to discover the suggested compensation or penalty. In contrast to BP NN or SVM, the result seems more close to the actual compensation rate.
Practical implications
Recently, smart court has been developed in China; the purpose of which is to build the legal advice system for improving judicial justice and reducing differences in sentencing. A practical legal advice system is an urgent requirement for the judiciary.
Originality/value
This paper presents a study of a case-based legal intelligent auxiliary discretionary adviser system based on a GA-BP NN and ontology techniques. The findings offer advice to optimize legal intelligent auxiliary discretionary adviser systems for mental anguish compensation in medical disputes.
Details
Keywords
S. Yazdani, Esmaeil Hadavandi, James Hower and Saeed Chehreh Chelgani
Hardgrove grindability index (HGI) is an important physical parameter used to demonstrate the relative hardness of coal particles. Modeling of HGI based on coal conventional…
Abstract
Purpose
Hardgrove grindability index (HGI) is an important physical parameter used to demonstrate the relative hardness of coal particles. Modeling of HGI based on coal conventional properties is a quite complicated procedure. The paper aims to develop a new accurate model for prediction of HGI that is called optimized evolutionary neural network (OPENN).
Design/methodology/approach
The procedure for generation of the proposed OPENN predictive model was performed in two stages. In the first stage, as the high dimensionality involved in the input space, a correlation-based feature selection (CFS) algorithm was used to select the most important influencing variables for HGI prediction. In the second stage, a combination of differential evolution (DE) and biography-based optimization (BBO) algorithms as a global search method were applied to evolve weights of a multi-layer perception neural network.
Findings
The proposed OPENN was examined and compared with other typical models using a wide range of Kentucky coal samples. The testing results showed that the accuracy of the proposed OPENN model is significantly better than the other typical models and can be considered as a promising alternative for HGI prediction.
Originality/value
As HGI test is relatively expensive procedure, there is an economical interest on HGI modeling based on coal conventional properties (proximate, ultimate and petrography); the proposed OPENN model to estimate HGI would be a valuable and practical tool for coal industry.
Details