Feedforward Approach Research Articles

Evolutionary Techniques for the Solution of Bio-Heat Equation Arising in Human Dermal Region Model

The proposed research work analyzes the bio-inspired problem through artificial neural networks with a feed-forward approach utilized to approximate the numerical results for singular nonlinear bio-heat equation (BHE) with boundary conditions based on four different scenarios created on the variation of environmental temperature to illustrate the effects of temperature on the human dermal region. The log-sigmoid function is used to construct the fitness function, while the optimization solvers: pattern search and genetic algorithm, are then hybridized with the active set technique, interior point technique, sequential quadratic programming for accurate and reliable results of the proposed BHE with various scenarios where the convergence of the numerical results is also analyzed. Moreover, a comparison of the proposed technique is expressed through residual error that reveals the nature of the numerical results and their efficiency. Additionally, a comprehensive statistical analysis is presented for the designed technique to better illustrate the accuracy, reliability, and efficiency of the obtained results.

Deep incremental random vector functional-link network: A non-iterative constructive sketch via greedy feature learning

The incremental version of randomized neural networks provides a greedy constructive algorithm for the shallow network, which adds new nodes through different stochastic methods rather than gradient optimization. However, the potential of the random incremental mechanism is still underutilized in deep structures. To address this research gap, we propose an unsupervised algorithm termed the incremental randomization-based autoencoder (IR-AE) for greedy feature learning, which applies an integrated optimized constructive algorithm to train the feature extractor. Using IR-AE as a hierarchical stacked block, we synthesize the deep incremental random vector functional-link (DI-RVFL) network that builds a deep structure with overall feature-output links through a feedforward approach. Furthermore, it is a novel data-driven initialization to implement the feedforward constructive sketch (CoSketch) as a pre-trained model for multi-layer perceptron. The simulation results empirically demonstrate that the proposed IR-AE can realize a higher reconstruction efficiency than AE and randomization-based AE. Moreover, DI-RVFL shows the advantages of deep structures in higher-level feature extraction compared to other stacked random structures. The overall performance of deep RVFLs outperforms those of multi-layer extreme learning machines. As data-driven initialization, CoSketch significantly improves the convergence performance of gradient descent.

Basic study of sensorless path tracking control based on the musculoskeletal potential method

In a musculoskeletal system, the musculoskeletal potential method utilizes the potential property generated by the internal force between muscles; posture control can be achieved by the step input of muscular tension balancing at the desired posture. The remarkable aspect of this method is that neither sensory feedback nor complicated real-time calculation is required at all. However, previous studies addressed only point-to-point control as motion control. In other words, with the focus on the convergence to the desired posture, path tracking has not been discussed. Extending the previous studies, this paper proposes a path tracking control based on a sensorless feedforward approach. The proposed method first finds the optimal set of muscular forces that can form the potential field to the desired potential shape realizing the desired path; next, inputting the obtained muscular forces into the system achieves path tracking. For verification, this paper demonstrates a case study of a musculoskeletal system with two joints and six muscles. In this case study, a constrained nonlinear programming method is used to find the optimal muscular force, and the path trackability is verified by numerical simulation.

A transimpedance preamplifier using a feedforward approach for robust rejection of DC photogenerated currents.

The preamplifier proposed in this paper is designed to extract weak variable photogenerated signals from a high-level continuous background ensuring low noise and high transimpedance gain. An efficient cancellation of the DC component directly at the photodetector output, exploiting a feedforward approach, allows us to properly amplify the variable signal components of interest avoiding saturation of the preamplifier. Furthermore, the large transimpedance gain allows for minimizing the effects of the noise introduced by the following stages on the signal processing chain. In the paper, we present the proposed approach and a possible circuit realization with a signal AC/DC ratio as small as 1/1000 ensuring low noise, high gain, and a considerable bandwidth. The realized preamplifier offers a Noise Equivalent Power NEP ≃ 1.12nW, an in-band transimpedance gain of 4.4MΩ, and a wide bandwidth from about 1Hz up to 100kHz, making it suitable for use in several applications both in biomedical and industrial fields.

Excitation for Adaptive Optimal Control of Nonlinear Systems in Differential Games

This article focuses on the fulfillment of the persistent excitation (PE) condition for signals which result from transformations by means of polynomials. This is essential, e.g., for the convergence of adaptive dynamic programming algorithms due to commonly used polynomial function approximators. As theoretical statements are scarce regarding the nonlinear transformation of PE signals, we propose conditions on the system state such that its transformation by polynomials is PE. To validate our theoretical statements, we develop an exemplary excitation procedure based on our conditions using a feed-forward control approach and demonstrate the effectiveness of our method in a nonzero-sum differential game. In this setting, our approach outperforms commonly used probing noise in terms of convergence time and the degree of PE, shown by a numerical example.

Feedforward Control in the Presence of Input Nonlinearities: With Application to a Wirebonder

The increasing demands on throughput and accuracy of semiconductor manufacturing equipment necessitates accurate feedforward motion control that includes compensation of input nonlinearities. The aim of this paper is to develop a data-driven feedforward approach consisting of a Wiener feedforward, i.e., linear parameterization with an output nonlinearity, to achieve high tracking accuracy and task flexibility for a class of Hammerstein systems. The developed approach exploits iterative learning control to learn a feedforward signal from data that minimizes the error and utilizes a control-relevant cost function to learn the parameters of a Wiener feedforward parameterization. Experimental validation on a wirebonder shows that the developed approach enables high tracking accuracy and task flexibility.

The Cooperative Output Regulation by the Distributed Observer Approach

Survey/review study The Cooperative Output Regulation by the Distributed Observer Approach Youfeng Su 1, He Cai 2, and Jie Huang 3,* 1 College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China 2 School of Automation Science and Engineering, South China University of Technology, Guangzhou 510641, China 3 Department of Mechanical and Automation Engineering, The Chinese University of Hong Kong, Hong Kong, China * Correspondence: jhuang@mae.cuhk.edu.hk Received: 7 November 2022 Accepted: 13 November 2022 Published: 22 December 2022 Abstract: The cooperative output regulation problem (CORP) is an extension of the leader-following consensus problem of multi-agent systems (MASs), and has been studied by two approaches, namely, the distributed observer (DO) approach and the distributed internal model (DIM) approach. The two approaches are, respectively, the extensions of the classical feedforward control approach and the classical internal model approach (for a single system) to the MASs. This paper overviews the CORP by the DO approach with the emphasis on linear MASs. After formulating the CORP, we present the evolution process of three types of DOs and the corresponding solutions to the CORP. Furthermore, some variants and extensions of the DO approach are also briefly surveyed for completeness.

A feedforward compensation approach for cable-driven musculoskeletal systems

AbstractThis paper presents a feedforward compensation approach for musculoskeletal systems (MSs). Compared with traditional rigid robots, human arms have the advantages of flexibility and safety in operation in unstructured environments. However, the influence of external unknown disturbances, inner friction effects, and dynamic uncertainties of the MS makes it difficult to model and practically apply. In order to reduce the inner friction effects of the hardware platform and the over-relaxation/tension of the cable-pull drive, a feedforward friction compensation method for the cable-pulled artificial muscle unit is proposed. The method analyzes the friction causes of the hardware structure and establishes a mapping network relationship between the joint variables and the muscle force error in the muscle space. The experimental results show that the method can effectively improve the control accuracy and reduce the artificial muscle over-relaxation/tension instability.

Feedback in the instrumental music lesson: A qualitative study

This study focuses on the role of feedback in teaching with particular emphasis on its effect on learner performance, motivation, and self-regulation. A critical account of feedback and applicable models highlight conceptual guidelines of how individual, relational, and environmental factors can impact on the utility of feedback as a performance changing device, and reasons for theory–practice disjunction. A qualitative methodology investigated 25 instrumental music teachers in Victoria, Australia, realizing the effect of studio teaching feedback on students from teachers’ perspectives and recollections of their studio teaching practice. Knowledge and skills, positive attribution, and music and relational qualities are reported through these reflections of feedback, feed-up, and feed-forward approaches to student engagement. The study highlights positive feedback encounters are typified by learner engagement and teacher–student relationality, contesting the traditional, behaviorist “feedback ritual” and teacher-centered approaches in the music lesson. The study offers implications for purposeful and structured learning opportunities, and cyclical engagement that builds impactful feedback episodes and feedback design that factors in the influence of context, culture, and differentiated relationships in learning. The study encourages educators to consider balance of “drill and thrill,” where feedback is embedded as an influential pedagogical/relational device, rather than discreet episodes of educators “telling” learners about their performance.

Feedforward control of thermal history in laser powder bed fusion: Toward physics-based optimization of processing parameters

We developed and applied a model-driven feedforward control approach to mitigate thermal-induced flaw formation in laser powder bed fusion (LPBF) additive manufacturing process. The key idea was to avert heat buildup in a LPBF part before it is printed by adapting process parameters layer-by-layer based on insights from a physics-based thermal simulation model. The motivation being to replace cumbersome empirical build-and-test parameter optimization with a physics-guided strategy. The approach consisted of three steps: prediction, analysis, and correction. First, the temperature distribution of a part was predicted rapidly using a graph theory-based computational thermal model. Second, the model-derived thermal trends were analyzed to isolate layers of potential heat buildup. Third, heat buildup in affected layers was corrected before printing by adjusting process parameters optimized through iterative simulations. The effectiveness of the approach was demonstrated experimentally on two separate build plates. In the first build plate, termed fixed processing, ten different nickel alloy 718 parts were produced under constant processing conditions. On a second identical build plate, called controlled processing, the laser power and dwell time for each part was adjusted before printing based on thermal simulations to avoid heat buildup. To validate the thermal model predictions, the surface temperature of each part was tracked with a calibrated infrared thermal camera. Post-process the parts were examined with non-destructive and destructive materials characterization techniques. Compared to fixed processing, parts produced under controlled processing showed superior geometric accuracy and resolution, finer grain size, increased microhardness, and reduced surface roughness.

Active Control of Highly Autocorrelated Machinery Noise in Multivariate Nonminimum Phase Systems

In this paper, a novel multivariate active noise control scheme, designed to attenuate disturbances with high autocorrelation characteristics and preserve background signals, is proposed. The algorithm belongs to the class of feedback controllers and, unlike the popular feedforward FX-LMS approach, does not require availability of a reference signal. The proposed approach draws its inspiration from the iterative learning control and repetitive mode control methods, and employs a modified inverse model learning law. The classical inverse model learning law is well known to offer fast convergence and high steady-state performance, provided that the secondary path is minimum phase and well known. The proposed modified inverse model learning law employs a spectral factorization trick, which allows one to use the method with nonminimum phase plants of arbitrary order. Moreover, our scheme includes a controller bandwidth limiting mechanism that can be used to tune the disturbance rejection bandwidth and to improve the closed-loop robustness to errors in the model of the secondary path. The algorithm’s behavior and performance are verified with computer simulations that demonstrate suppression of electrical transformer noise and include realistic models of the secondary path. The results show high-level selective attenuation and fast convergence.

Artificial Neural Network and Weighted Arithmetic Indexing Approach for Surface Water Quality Assessment of the Brahmani River

<p>An approach was used in this study to relate the predicted and calculated water quality index (WQI) of the Brahmani River. The WQI was predicted using an artificial neural network (ANN) tool, and the weighted Arithmetic Index technique was used to calculate the WQI (WAI). The WQI is calculated using physicochemical parameters as input data. Pollution Control Board (India) data was utilised to train and evaluate the model, as well as to forecast WQI. The ANN model is trained using the feed-forward back-propogation approach. 70 percent of the data was used for training, whereas 30 percent was used for testing and validation (15 percent) (15 percent). The regression coefficients for all of the stations were greater than 0.9, indicating that ANN modelling produced successful results. For all stations, the average percent of variance between anticipated and computed WQI is 8.63 percent. According to the findings of this study, the ANN model may be useful for predicting the WQI of both surface and groundwater.</p>

A Deep-Learning Approach to Load Modeling in Modern Power Distribution System

Modern Power Distribution Networks (MPDNs) are no longer passive because Distributed Generations (DGs) are integrated with them to enhance system reliability and power quality. For this reason, load modeling has to be updated to capture the new dynamics of active DNs. This paper presents a composite load modeling for a grid-connected photovoltaic (PV) distribution network using the Levenberg-Marquardt algorithm in the deep learning feed-forward neural network approach. Load modeling is constructing a relationship between input excitation(s) and output response(s); it can be used for simulation studies, stability analysis, and control/protection design. A grid-connected PV distribution network was modeled in Matlab/Simulink and generates data for training and model estimation. The estimated model was tested and validated using a laboratory experimental test bed. Results of the model exhibit a good fitness of 99.8% and 97.2% in active and reactive power models respectively during training. While 97.84% and 94.65% respectively were obtained during testing. The estimation errors were found to be 0.0025 and 0.0049 for active and reactive powers respectively with 0.0473 and 0.0701 corresponding errors in testing.

A Harmonic Mitigation Technique for Multi-Parallel Grid-Connected Inverters in Distribution Networks

Different harmonic mitigation techniques have been utilized in grid-connected inverters to suppress the effect of grid voltage distortion on the output current of these inverters. In practice, to scale up the injected current into the grid, a set of parallel grid-connected inverters are often utilized rather than a single high-power inverter in solar Photovoltaic or motor drive systems. Conventional Point of Common Coupling (PCC) feedforward approaches have been used for harmonic rejection of multi-parallel grid-connected inverters. However, these methods need to implement a separate feedforward scheme for each individual inverter. In this paper, a novel full PCC voltage feedforward strategy is proposed to reduce the cost investment, which is implemented only in one of the grid-connected inverters. The proposed strategy is based on cancelling the total parallel admittance of the system by adding a virtual negative admittance to the target inverter. It is shown that the proposed scheme causes no instability issue on the system since it does not affect the system phase margin. To verify the efficiency of the proposed strategy against emitted harmonics from the grid, simulations and experiments on a system with two parallel single-phase grid-tied inverters are performed.

Formation preview tracking for heterogeneous multi-agent systems: A dynamical feedforward output regulation approach

The distributed formation tracking with preview information is investigated for discrete-time heterogeneous linear multi-agent systems (MASs) over directed communication networks. Firstly, by constructing an augmented system containing virtual regulation output and previewable information, the original problem is converted into a state regulation problem. Secondly, due to the coupling restriction of the eigenvalues of the exosystem matrix and the communication topology matrix, a linear distributed observer is proposed by introducing two extra parameters to realize asymptotic estimation. Using the output information of the observer, the problem was further formulated in the form of feedforward output regulation. Moreover, by solving the output regulation problem, the sufficient conditions are deduced for ensuring the achievement of the formation preview tracking. Meanwhile, numerical simulations show that the distributed design with preview actions has positive effect on the improvement of the transient response.

Output containment control for heterogeneous discrete-time linear descriptor multi-agent systems by a feedforward output regulation approach

This paper studies the cooperative output containment control of the heterogeneous linear discrete-time descriptor multi-agent systems based on the output regulation theory. First, the output containment control problem is transformed into a standard cooperative output regulation problem. Second, since only a portion of the followers can directly obtain the information of the leaders, a new distributed observer is designed for each follower to estimate the combinations of the leaders’ states by using the local state containment errors. Third, two types of distributed control algorithms, as well as the corresponding sufficient conditions, are provided to ensure the achievement of the output containment control. Finally, numerical simulation results illustrate the validity of the proposed method.

2x2 Array Microstrip Patch Antenna Designing and Validation with Artificial Neural Networks

A novel and successful method for RF, microwave modelling, and antenna design has gained attention: computational modules based on neural networks. The behavior of active or passive components or circuits can be taught to neural networks. The design of a microstrip patch antenna utilizing an artificial neural network (ANN) is discussed in this research. Computer Simulation Technology (CST) is used to establish the antenna's size and characteristics in order to create a successful ANN model. The feed-forward back-propagation neural network and Levenberg Marquardt optimization algorithm are used to model the antenna design. High-Frequency Structure Simulator (HFSS) software, operating at 2.4 GHz, is used to build the initial microstrip patch (ISM band).A 2.4GHz operating frequency is used to create a 2*2 microstrip planar array. A variety of neural networks are evaluated and trained to produce the most ideal results after generating and modelling discoveries using HFSS simulation software and the Finite Difference Time Domain (FTDT) approach. In this research, neural networks are utilized. In order to identify the most ideal solution, optimization is performed using a radial basis function neural network (RBF NN) and a feed-forward backpropagation approach.

Capturing Small, Fast-Moving Objects: Frame Interpolation via Recurrent Motion Enhancement

Interpolating video frames involving large motions remains an elusive challenge. In case that frames involve small and fast-moving objects, conventional feed-forward neural network-based approaches that estimate optical flow and synthesize in-between frames sequentially often result in loss of motion features and thus blurred boundaries. To address the problem, we propose a novel Recurrent Motion-Enhanced Interpolation Network (ReMEI-Net) by assigning attention to the motion features of small objects from both the intra-scale and inter-scale perspectives. Specifically, we add recurrent feedback blocks in the existing multi-scale autoencoder pipeline, aiming to iteratively enhance the motion information of small objects across different scales. Second, to further refine the motion features of the highly moving objects, we propose a Multi-Directional ConvLSTM (MD-ConvLSTM) block to capture the global spatial contextual information of motion from multiple directions. In this way, the coarse-scale features can be utilized to correct and enhance the fine-scale features through the feedback mechanism. Extensive experiments on various datasets demonstrate the superiority of our proposed method over state-of-the-art approaches in terms of clear locations and complete shape.

Scoring Graphical Responses in TIMSS 2019 Using Artificial Neural Networks.

Automated scoring of free drawings or images as responses has yet to be used in large-scale assessments of student achievement. In this study, we propose artificial neural networks to classify these types of graphical responses from a TIMSS 2019 item. We are comparing classification accuracy of convolutional and feed-forward approaches. Our results show that convolutional neural networks (CNNs) outperform feed-forward neural networks in both loss and accuracy. The CNN models classified up to 97.53% of the image responses into the appropriate scoring category, which is comparable to, if not more accurate, than typical human raters. These findings were further strengthened by the observation that the most accurate CNN models correctly classified some image responses that had been incorrectly scored by the human raters. As an additional innovation, we outline a method to select human-rated responses for the training sample based on an application of the expected response function derived from item response theory. This paper argues that CNN-based automated scoring of image responses is a highly accurate procedure that could potentially replace the workload and cost of second human raters for international large-scale assessments (ILSAs), while improving the validity and comparability of scoring complex constructed-response items.

Feed-forward neural networks for fitting of kinetic energy and its functional derivative

We present a feed-forward NN approach for fitting of kinetic energy and its functional derivative for a 1-dimensional system. The density is represented in terms of orthogonal basis functions. The coefficients of basis functions forms the inputs to NN. Using this approach we found no oscillatory behaviour in functional derivative. Using NN based functional derivative we determine the ground-state density by solving the Euler–Lagrange equation. The presented approach can open up new ways for accurate calculations kinetic energy and the functional derivative, which can be considered as an important step towards advancement of machine learning based OF-DFT methods.