Self-adaptive Method Research Articles

Self-adaptive network structure tuning method based on NSGA-III

Self-adaptive network structure tuning method based on NSGA-III

Self-adaptive network structure tuning method based on NSGA-III

Neural networks are arising a wave in the various areas of artificial intelligence and they have adopted in daily life successfully. The structure tuning of neural networks is crucial when building the relative models. The structure of neural networks is usually designed and tuned with experience and plenty of attempts. To reduce the difficulty and cost of structure tuning meanwhile improving its rationality, we propose a new method to tune the structure of neural networks adaptively. In this method, the related structure parameters are optimised. A many-objective algorithm is employed as the optimised tool to get a better structure. We design the experiments combining convolutional neural network (CNN) with Non-dominated Sorting Genetic Algorithm III (NSGA-III). The related experiments are conducted on the MNIST and Malware image datasets. Results show that the method has promising performance on neural networks tuning and can improve the robustness.

具有滑动边界条件Stokes问题的自适应Uzawa块松弛算法

A self-adaptive Uzawa block relaxation method was designed for Stokes problems under nonlinear slip boundary conditions. For the variational formulation of the problem, an auxiliary unknown was introduced to transform the problem into a saddle-point one based on an augmented Lagrangian function, which can be solved with the Uzawa block relaxation method. To improve the performance of the method, a self-adaptive rule was proposed with the proper penalty parameter chosen automatically. The main advantage of this method is that each iterative step consists of a linear problem while the auxiliary unknown can be computed explicitly. The convergence of the algorithm was analyzed. The numerical results show the feasibility and effectiveness of the proposed method.

A Wireless High-Sensitivity Fetal Heart Sound Monitoring System

In certain cases, the condition of the fetus can be revealed by the fetal heart sound. However, when the sound is detected, it is mixed with noise from the external environment as well as internal disturbances. Our exclusive sensor, which was constructed of copper with an enclosed cavity, was designed to prevent external noise. In the sensor, a polyvinylidene fluoride (PVDF) piezoelectric film, with a frequency range covering that of the fetal heart sound, was adopted to convert the sound into an electrical signal. The adaptive support vector regression (SVR) algorithm was proposed to reduce internal disturbance. The weighted-index average algorithm with deviation correction was proposed to calculate the fetal heart rate. The fetal heart sound data were weighted automatically in the window and the weight was modified with an exponent between windows. The experiments show that the adaptive SVR algorithm was superior to empirical mode decomposition (EMD), the self-adaptive least square method (LSM), and wavelet transform. The weighted-index average algorithm weakens fetal heart rate jumps and the results are consistent with reality.

Automatic Industry PCB Board DIP Process Defect Detection System Based on Deep Ensemble Self-Adaption Method

A deep ensemble convolutional neural network (CNN) model to inspect printed circuit board (PCB) board dual in-line package (DIP) soldering defects with Hybrid-YOLOv2 (YOLOv2 as a foreground detector and ResNet-101 as a classifier) and Faster RCNN with ResNet-101 and Feature Pyramid Network (FPN) (FRRF) achieved a detection rate of 97.45% and a false alarm rate (FAR) of 20%–30% in the previous study [34] . However, applying the method to other production lines, environmental variations, such as lighting, orientations of the sample feeds, and mechanical deviations, led to the degradation in detection performance. This article proposes an effective self-adaption method that collects “exception data” like the samples with which the Artificial Intelligent (AI) model made mistakes from the automated optical inspection inference edge to the training server, retraining with exceptions on the server and deploying back to the edge. The proposed defect detection system has been verified with real tests that achieved a detection rate of 99.99% with an FAR 20%–30% and less than 15 s of inspection time on a resolution $7296 \times 6000$ PCB image. The proposed system has proven capable of shortening inspection and repair time for online operators, where a 33% efficiency boost from the three production lines of the collaborated factory has been reported [6] . The contribution of the proposed retraining mechanism is threefold: 1) because the retraining process directly learns from the exceptions, the model can quickly adapt to the characteristic of each production line, leading to a fast and reliable mass deployment; 2) the proposed retraining mechanism is a necessary self-service for conventional users as it incrementally improves the detection performance without professional guidance or fine-tuning; and 3) the semiautomatic exception data collection method helps to reduce the time-consuming manual labeling during the retraining process.

Mode decomposition method integrating mode reconstruction, feature extraction, and ELM for tourist arrival forecasting

A novel hybrid learning process based on the "decompose-ensemble" principle is proposed in this paper, integrating the NSRX learning structure with extreme learning machine (ELM) as an efficient predictor. While training the proposed model, the self-adaptive decomposition method of empirical mode decomposition (EMD) is first used to divide a training set of tourist arrival series into several relatively regular sub-series. Then, these decomposed sub-series are reconstructed into three components of high, moderate, and low frequency based on the balance of reconstructed components’ relative stationarity and the fluctuation patterns between components and the original data series. Next, extracted features and forecasting results for the three components, obtained via ELM, are combined with d -lags historical data from the undecomposed training set; this set serves as the training sample input to train the hybrid model for enhanced tourist arrival prediction. For illustration and verification purposes, the proposed learning paradigm is applied to predict Hong Kong's monthly inbound tourist arrivals from 14 source markets from January 2007 to December 2018. Empirical results demonstrate that the proposed novel ensemble-learning paradigm outperforms all benchmark models, including five popular single models and five ensemble models, in terms of prediction accuracy. These findings suggest that the proposed model shows promise in forecasting complicated time series demonstrating high volatility and irregularity.

High-Order Delayed Detached Eddy Simulation of Separated Flow with Self-Adaptive Dissipation

A self-adaptive dissipation method based on a fifth-order dissipative compact scheme is proposed to reduce the numerical dissipation in separated flow. The method involves a self-adaptive operating parameter to adjust the weight of upwind part, which is a major source of numerical dissipation. Cooperated with delayed detached eddy simulation, the method can perform with less numerical dissipation in a large-eddy simulation region to resolve more small-scale structures, and return to normal dissipation in a Reynolds-averaged Navier–Stokes region to stabilize simulation. Firstly, the decay of isotropic turbulence is simulated to study the influence of the method over the energy spectrum and resolution of turbulent structures. Secondly, the plane channel flow is simulated to test the stability under the pressure gradient and turbulent fluctuation. Finally, the typical separated flow over NACA0021 airfoil and circular cylinder is investigated, and the results are compared with experimental data.

A Self-Adaptive Shrinking Projection Method with an Inertial Technique for Split Common Null Point Problems in Banach Spaces

In this paper, we present a new self-adaptive inertial projection method for solving split common null point problems in p-uniformly convex and uniformly smooth Banach spaces. The algorithm is designed such that its convergence does not require prior estimate of the norm of the bounded operator and a strong convergence result is proved for the sequence generated by our algorithm under mild conditions. Moreover, we give some applications of our result to split convex minimization and split equilibrium problems in real Banach spaces. This result improves and extends several other results in this direction in the literature.

Strong convergence inertial projection and contraction method with self adaptive stepsize for pseudomonotone variational inequalities and fixed point problems

In this paper, we introduce a new inertial self-adaptive projection method for finding a common element in the set of solution of pseudomonotone variational inequality problem and set of fixed point of a pseudocontractive mapping in real Hilbert spaces. The self-adaptive technique ensures the convergence of the algorithm without any prior estimate of the Lipschitz constant. With the aid of Moudafi’s viscosity approximation method, we prove a strong convergence result for the sequence generated by our algorithm under some mild conditions. We also provide some numerical examples to illustrate the accuracy and efficiency of the algorithm by comparing with other recent methods in the literature.

Self-adaptive process optimisation method for SBS cloud application based on reinforcement learning

To solve the problem of poor comprehensive performance of the traditional SBS cloud application adaptive process optimisation method, a new SBS cloud application adaptive process optimisation method based on reinforcement learning was proposed. Establish the adaptive action type selection model, realise the optimal choice of operation type, build the cloud application adaptive process optimisation model for resource cost, convert the problem into the corresponding mathematical model, solve and make the mathematical model of the algorithm, and obtain the best adaptive process optimisation scheme SBS cloud application. The simulation results show that the predicted load value of the method is the closest to the actual load value, the relative error of the prediction is less than 21.03, and the average time is less than 2.3 s, indicating that the method has good performance and high practical application value.

Empirical Mode Decomposition Applied to Proton Exchange Membrane Electrolyzer for Non-Intrusive Diagnosis

The water electrolysis based on Polymeric Electrolyte Membrane technology (E-PEM) is an interesting solution for efficient carbon-free hydrogen production. By the end of the 21st century, the contribution of hydrogen will continue to achieve significant rate in the energy mix. As there have been advances of efficient end-use technologies, hydrogen could even become the main energy carrier [1]. Regarding diagnosis purposes, Empirical Model Decomposition (EMD) method has proven to be a versatile and efficient tool to analyze non-stationary signals and extract features from them [2].As a starting point of its decomposition, oscillations are considered, at a local level, as the sum of a specified number of high and low frequency contributions called Intrinsic Mode Functions (IMFs). IMFs represent the natural oscillatory mode embedded in the signal and work as the basis functions, which makes EMD a self-adaptive method. fig.1 shows the decomposition of the E-PEM current into a finite set of intrinsic mode functions.This study presents a non-intrusive tool designed to fulfill on-line diagnosis requirements. Indeed, the proposed method does not require any excitation signal or stabilization period as Electrochemical Impedance Spectroscopy-based approaches [3]. Therefore, the electrolyzer remains continuously available, even while the diagnosis is being performed. Besides, it only requires measurement of current and has a low computational costs, which are significant economic and technical advantages. Here, EMD has been used to study the anode flow rate dynamics. Several experiments have been conducted and experimental results have demonstrated the effectiveness of the proposed diagnosis tool and its advantages compared to other methods. Acknowledgements This project has received funding from the Reunion Island Region and the European Commission – ERDF References Barbir, “PEM electrolysis for production of hydrogen from renewable energy sources,” Solar Energy, vol. 78, no. 5, pp. 661–669, May 2005, doi: 10.1016/j.solener.2004.09.003. Damour, M. Benne, B. Grondin-Perez, M. Bessafi, D. Hissel, and J.-P. Chabriat, “Polymer electrolyte membrane fuel cell fault diagnosis based on empirical mode decomposition,” Journal of Power Sources, vol. 299, pp. 596–603, Dec. 2015, doi: 10.1016/j.jpowsour.2015.09.041. C. Garcia-Navarro, M. Schulze, and K. A. Friedrich, “Measuring and modeling mass transport losses in proton exchange membrane water electrolyzers using electrochemical impedance spectroscopy,” Journal of Power Sources, vol. 431, pp. 189–204, Aug. 2019, doi: 10.1016/j.jpowsour.2019.05.027. Figure 1: Intrinsic mode functions decomposition for operating conditions of 1.6 V and 0.5 ml.min-1 Figure 1

A Generalized Viscosity Inertial Projection and Contraction Method for Pseudomonotone Variational Inequality and Fixed Point Problems

We introduce a new projection and contraction method with inertial and self-adaptive techniques for solving variational inequalities and split common fixed point problems in real Hilbert spaces. The stepsize of the algorithm is selected via a self-adaptive method and does not require prior estimate of norm of the bounded linear operator. More so, the cost operator of the variational inequalities does not necessarily needs to satisfies Lipschitz condition. We prove a strong convergence result under some mild conditions and provide an application of our result to split common null point problems. Some numerical experiments are reported to illustrate the performance of the algorithm and compare with some existing methods.

Surface roughness stabilization method based on digital twin-driven machining parameters self-adaption adjustment: a case study in five-axis machining

Surface roughness, which has a significant influence on fatigue strength and wear resistance, is an important technical parameter. In practical machining, it is unstable and may be larger than the acceptable surface roughness due to unstable machining process. This will seriously deteriorate the surface performance of the workpieces. Therefore, an effective surface roughness stabilization method is of great significance to improve machining efficiency and reduce machining cost. In this paper, a surface roughness stabilization method is proposed and illustrated by taking five-axis machining as an example. A self-learning surface roughness prediction model based on Pigeon-Inspired Optimization and Support Vector Machine is firstly constructed and its prediction error is only 8.69% in the initial stage. This model has the self-learning ability that the prediction accuracy can be improved with the increase of training data. Furthermore, a machining parameters self-adaption adjustment method based on digital twin is proposed to make the machined surface quality stable. In this method, considering the feasibility of practical machining operation, the cutter posture (i.e. lead angle and tilt angle in five-axis machining) and spindle speed are selected as the adjustable parameters. When the predicted surface roughness doesn’t meet the requirements, the Gradient Descent algorithm is applied to recalculate the new parameters for adjustment. According to the experimental results, the proposed method can stabilize surface roughness and improve the surface quality, which is vital for the precision manufacturing of complex workpiece. Meanwhile, it also greatly improves the intelligence level of manufacturing and production.

Inertial Iterative Self-Adaptive Step Size Extragradient-Like Method for Solving Equilibrium Problems in Real Hilbert Space with Applications

A number of applications from mathematical programmings, such as minimization problems, variational inequality problems and fixed point problems, can be written as equilibrium problems. Most of the schemes being used to solve this problem involve iterative methods, and for that reason, in this paper, we introduce a modified iterative method to solve equilibrium problems in real Hilbert space. This method can be seen as a modification of the paper titled “A new two-step proximal algorithm of solving the problem of equilibrium programming” by Lyashko et al. (Optimization and its applications in control and data sciences, Springer book pp. 315–325, 2016). A weak convergence result has been proven by considering the mild conditions on the cost bifunction. We have given the application of our results to solve variational inequality problems. A detailed numerical study on the Nash–Cournot electricity equilibrium model and other test problems is considered to verify the convergence result and its performance.

Cyber–Physical Codesign of Field-Level Reconfigurations in Networked Motion Controllers

To be successful in the quickly evolving future of machine building and meet the increasingly complex requirements of manufacturers, equipment manufacturers face challenges of reconfigurability on the motion controller. This article proposes a cyber-physical codesign approach to enable plug-and-play of field devices via real-time Ethernet in controllers. In our proposal, we first design a modular runtime framework to facilitate auto-discovery and self-configuration of servo drives with EtherCAT. Then, we implement a self-adaptive period synthesis method for real-time scheduling. The method can automatically attain a combination of minimized periods for communication and control task during startup and achieve dynamic compensations of drifts and jitters occurred in the network. Through experiments, we show that for various combinations of cyber-physical settings, our proposal can ensure low jitters ($<; $10 μs) and stable latencies with a 125 μs cycle time and achieve runtime reconfiguration with a 250 μs or larger cycle time.

Self-adaptive combination method for temporal evidence based on negotiation strategy

In temporal information fusion, the information collected by sensors is obtained dynamically with the passage of time. Unlike the spatial information fusion, temporal fusion should be dynamic. Evidence theory has been applied to fuse temporal and spatial information; however, existing temporal fusion methods do not treat conflicting and non-conflicting evidence sources distinctively. Moreover, unlike spatial evidence sources, which are obtained simultaneously, temporal evidence sources cannot be evaluated simultaneously to obtain their degree of reliability. Thus, it is necessary to develop a method for temporal evidence combination. In this paper, a self-adaptive combination method for temporal evidence is proposed based on the negotiation strategy. In the proposed method, a set called an evidence set is constructed by the cumulative temporal fusion results of the previous moment, current moment, and future moment. The evidence set is evaluated as conflicting or non-conflicting according to the maximum power pignistic probability distance between each pair of evidence sources in the set. Then, temporal evidence sources are self-adaptively combined by different methods according to the degree of conflict. Numerical experiments were conducted to evaluate the performance of the proposed method. The results indicated that the proposed method is sufficiently effective and robust to support decision making.

A New Bi-Level Optimisation Framework for Optimising a Multi-Mode Wave Energy Converter Design: A Case Study for the Marettimo Island, Mediterranean Sea

To advance commercialisation of ocean wave energy and for the technology to become competitive with other sources of renewable energy, the cost of wave energy harvesting should be significantly reduced. The Mediterranean Sea is a region with a relatively low wave energy potential, but due to the absence of extreme waves, can be considered at the initial stage of the prototype development as a proof of concept. In this study, we focus on the optimisation of a multi-mode wave energy converter inspired by the CETO system to be tested in the west of Sicily, Italy. We develop a computationally efficient spectral-domain model that fully captures the nonlinear dynamics of a wave energy converter (WEC). We consider two different objective functions for the purpose of optimising a WEC: (1) maximise the annual average power output (with no concern for WEC cost), and (2) minimise the levelised cost of energy (LCoE). We develop a new bi-level optimisation framework to simultaneously optimise the WEC geometry, tether angles and power take-off (PTO) parameters. In the upper-level of this bi-level process, all WEC parameters are optimised using a state-of-the-art self-adaptive differential evolution method as a global optimisation technique. At the lower-level, we apply a local downhill search method to optimise the geometry and tether angles settings in two independent steps. We evaluate and compare the performance of the new bi-level optimisation framework with seven well-known evolutionary and swarm optimisation methods using the same computational budget. The simulation results demonstrate that the bi-level method converges faster than other methods to a better configuration in terms of both absorbed power and the levelised cost of energy. The optimisation results confirm that if we focus on minimising the produced energy cost at the given location, the best-found WEC dimension is that of a small WEC with a radius of 5 m and height of 2 m.

Improved δ-SPH Scheme with Automatic and Adaptive Numerical Dissipation

In this work we present a δ-Smoothed Particle Hydrodynamics (SPH) scheme for weakly compressible flows with automatic adaptive numerical dissipation. The resulting scheme is a meshless self-adaptive method, in which the introduced artificial dissipation is designed to increase the dissipation in zones where the flow is under-resolved by the numerical scheme, and to decrease it where dissipation is not required. The accuracy and robustness of the proposed methodology is tested by solving several numerical examples. Using the proposed scheme, we are able to recover the theoretical decay of kinetic energy, even where the flow is under-resolved in very coarse particle discretizations. Moreover, compared with the original δ-SPH scheme, the proposed method reduces the number of problem-dependent parameters.

A self-adaptive auxiliary fixture for deformation control in blade machining

The aero-engine blades are mostly thin-walled with complex structures, which are prone to flutter, deformation during processing. All these characteristics make it difficult to machine the blade qualified. In order to improve the precision and efficiency of blades machining, a self-adaptive clamp machining process method is proposed in this paper. Then a self-adaptive auxiliary fixture of low-melting-point alloy which have simple structures is firstly designed based on the self-adaptive clamp method. The blade machining experiments of the low-melting-point alloy auxiliary fixture are carried out. And the experimental results show that the self-adaptive clamp method can improve both precision and efficiency in blade machining. But the low-melting-point alloy auxiliary fixture is still cumbersome and danger to the operators. Therefore, through analyzing the deformation in blade machining, an improved self-adaptive auxiliary fixture which is safe, efficient, and easy operated is re-designed.

A new self-adaptive method for the split equality common fixed-point problem of quasi-nonexpansive mappings

ABSTRACT In this paper, we introduce a new iterative algorithm from primal-dual methods for solving the split equality common fixed-point problem of quasi-nonexpansive mappings in real Hilbert space. Our algorithm includes the simultaneous iterative algorithm as special case which has been proposed by Moudafi and Al-Shemas for solving the split equality common fixed-point problem. We use a way of selecting the stepsizes such that the implementation of our algorithm does not need any prior information about bounded linear operator norms. It avoids the difficult task of estimating the operator norms. Under suitable conditions, we get the weak convergence of the proposed algorithm. The performance of the proposed algorithm is also illustrated by preliminary numerical experiments. The results presented in the paper improve and extend some corresponding results.