Neural network-based estimation of power electronic waveforms

Forecasts of future events are required in many of the activities associated with the planning and operation of the components of a water resource system. For the hydrologic component, there is a need for both short- and long-term forecasts of river flow events in order to optimize the system or to plan for future expansion or reduction. This paper presents the comparison of different artificial neural network (ANN) techniques in short- and long-term continuous and intermittent daily streamflow forecasting. The studies in modelling the intermittent series are quite limited because of the complexity of fitting models in to these series. The available conventional models necessitate the adjustment of numerous parameters for calibration. Three different ANN techniques, namely, feed-forward back propagation (FFBP), generalized regression neural networks, and radial basis function-based neural networks (RBF) are applied to continuous and intermittent river flow data of two Turkish rivers for short-range and long-range forecasting studies. The k-fold partitioning method is employed for preparing the ANN training data successfully. In general, the forecasting performance of RBF is found to be superior to the other two ANN techniques and a time series model in terms of the selected performance criteria. It was observed that the FFBP method had some drawbacks such as a local minima problem and negative flow generation.

In this paper, we present a design of modem and vocoder digital signal processor (DSP) chips for CDMA mobile station. The modem chip integrates CDMA reverse link modulator, CDMA forward link demodulator and Viterbi decoder. This chip contains 89,000 gates and 29 kbit RAMS, and the chip size is 10 mm x 10.1 mm which is fabricated using a 0.8 μm 2 metal CMOS technology. To carry out the system-level simulation, models of the base station modulator, the fading channel, the automatic gain control loop, and the microcontroller were developed and interfaced with a gate-level description of the modem application specific integrated circuit (ASIC). The Modem chip is now successfully working in the real CDMA mobile station on its first fab-out. A new DSP architecture was designed to implement the Qualcomm code exited linear prediction (QCELP) vocoder algorithm in an efficient way. The 16 bit vocoder DSP chip has an architecture which supports direct and immediate addressing modes in one instruction cycle, combined with a RISC-type instruction set. This turns out to be effective for the implementation of vocoder algorithm in terms of performance and power consumption. The implementation of QCELP algorithm in our DSP requires only 28 million instruction per second (MIPS) of computation and 290 mW of power consumption. The DSP chip contains 32,000 gates, 32k (2k x 16 bit) RAM, and 240k (10kx24 bit) ROM. The die size is 8.7 mmx8.3 mm and the chip is fabricated using 0.8 μm CMOS technology.

In this paper, a low power mechanism with power block management is proposed to reduce the power consumption in DSP chips. Because the digital signal processing (DSP) chips use many functional units in the data-path to achieve parallel processing, the unnecessary functional units are also executed simultaneously, and they dissipate the power. In the paper, we classify the types of instruction sets based on their data flow in the DSP to generate the control signals which active the necessary units in their data-path. The mechanism is called power block management (PBM). We employ particular guarded circuits in the different situations to avoid the actions of unnecessary functional units so as to reduce the power dissipation. The experimental results show that the power consumption can be saved about 14% at the cost of less than 2.7% area increment.

Digital signal processing (DSP) has been widely applied in optical communication systems to mitigate various signal distortions and has become one of the key technologies that have sustained data traffic growth over the past decade. However, the strict energy budget of application-specific integrated circuit-based DSP chips has prevented the deployment of some powerful but computationally costly DSP algorithms in real applications. As a result, fiber nonlinearity-induced signal distortions impede fiber communication systems, especially in wavelength-division multiplexed (WDM) transmission systems. To solve these challenges in DSP, there has been a surge of interest in implementing neural networks-based signal processing using photonics hardware (i.e., photonic neural networks). Photonic neural networks promise to break performance limitations in electronics and gain advantages in bandwidth, latency, and power consumption in solving intellectual tasks that are unreachable by conventional digital electronic platforms. This work proposes a photonic recurrent neural network (RNN) capable of simultaneously resolving dispersion and both intra and inter-channel fiber nonlinearities in multiple WDM channels in the photonic domain, for the first time to our best knowledge. Furthermore, our photonic RNN can directly process optical WDM signals in the photonic domain, avoiding prohibitive energy consumption and speed overhead in analog to digital converters (ADCs). Our proposed photonic RNN is fully compatible with mature silicon photonic fabrications. We demonstrate in simulation that our photonic RNN can process multiple WDM channels simultaneously and achieve a reduced bit error rate compared to typical DSP algorithms for all WDM channels in a pulse-amplitude modulation 4-level (PAM4) transmission system, thanks to its unique capability to address inter-channel fiber nonlinearities. In addition to signal quality performance, the proposed system also promises to significantly reduce the power consumption and the latency compared to the state-of-the-art DSP chips, according to our power and latency analysis.

The potential of multiple linear regression (MLR) and artificial neural network (ANN) techniques in predicting transient water levels over a groundwater basin were compared. MLR and ANN modeling was carried out at 17 sites in Japan, considering all significant inputs: rainfall, ambient temperature, river stage, 11 seasonal dummy variables, and influential lags of rainfall, ambient temperature, river stage and groundwater level. Seventeen site-specific ANN models were developed, using multi-layer feed-forward neural networks trained with Levenberg-Marquardt backpropagation algorithms. The performance of the models was evaluated using statistical and graphical indicators. Comparison of the goodness-of-fit statistics of the MLR models with those of the ANN models indicated that there is better agreement between the ANN-predicted groundwater levels and the observed groundwater levels at all the sites, compared to the MLR. This finding was supported by the graphical indicators and the residual analysis. Thus, it is concluded that the ANN technique is superior to the MLR technique in predicting spatio-temporal distribution of groundwater levels in a basin. However, considering the practical advantages of the MLR technique, it is recommended as an alternative and cost-effective groundwater modeling tool.

This paper illustrates the Artificial Neural Network (ANN) technique to predict the joint torque estimation model for arm rehabilitation device in a clear manner. This device acts as an exoskeleton for people who had failure of their limb. Electromyography (EMG) is the techniques to analyze the presence of electrical activity in musculoskeletal systems. The electrical activity in muscles of disable person is failed to contract the muscle for movements. In order to prevent the muscles from paralysis becomes spasticity the force of movements should minimize the mental efforts. The objective of this work is to model the muscle EMG signal to torque using ANN technique. The EMG signal is collected from Biceps Brachii muscles to estimate the elbow joint torque. A two layer feed-forward network is trained using Back Propagation Neural Network (BPNN). The experimental results show that ANN can well represent EMG-torque relationship for arm rehabilitation device control.

Number of vehicles in use worldwide per person and depending on this traffic accidents increase day by day. Until today, various studies have been made on detection of the faulty vehicles in traffic. This study; in accordance with this purpose, is realized in order to recognize, classify vehicles on a photo or video that captured on a autoban or road which has two lanes and detect faulty ones between them by using ANN (Artificial Neural Network) and image processing techniques. In this system that developed by using Convolutional Neural Network, the vehicles can be recognized, classified according to their vehicle types and faulty vehicles can be detected with drawing a frame around them.

Algebraic Reconstruction Technique (ART) is an age-old method used for solving the problem of three-dimensional (3-D) reconstruction from projections in electron microscopy and radiology. In medical applications, direct 3-D reconstruction is at the forefront of investigation. The simultaneous iterative reconstruction technique (SIRT) is an ART-type algorithm with the potential of generating in a few iterations tomographic images of a quality comparable to that of convolution backprojection (CBP) methods. Pixel-based reconstruction (PBR) is similar to SIRT reconstruction, and it has been shown that PBR algorithms give better quality pictures compared to those produced by SIRT algorithms. In this work, we propose a few modifications to the PBR algorithms. The modified algorithms are shown to give better quality pictures compared to PBR algorithms. The PBR algorithm and the modified PBR algorithms are highly compute intensive, Not many attempts have been made to reconstruct objects in the true 3-D sense because of the high computational overhead. In this study, we have developed parallel two-dimensional (2-D) and 3-D reconstruction algorithms based on modified PBR. We attempt to solve the two problems encountered by the PBR and modified PBR algorithms, i.e., the long computational time and the large memory requirements, by parallelizing the algorithm on a multiprocessor system. We investigate the possible task and data partitioning schemes by exploiting the potential parallelism in the PBR algorithm subject to minimizing the memory requirement. We have implemented an extended hypercube (EH) architecture for the high-speed execution of the 3-D reconstruction algorithm using the commercially available fast floating point digital signal processor (DSP) chips as the processing elements (PEs) and dual-port random access memories (DPR) as channels between the PEs. We discuss and compare the performances of the PBR algorithm on an IBM 6000 RISC workstation, on a Silicon Graphics Indigo 2 workstation, and on an EH system. The results show that an EH(3,1) using DSP chips as PEs executes the modified PBR algorithm about 100 times faster than an LBM 6000 RISC workstation. We have executed the algorithms on a 4-node IBM SP2 parallel computer. The results show that execution time of the algorithm on an EH(3,1) is better than that of a 4-node IBM SP2 system. The speed-up of an EH(3,1) system with eight PEs and one network controller is approximately 7.85.

Predictive control is widely used in power electronic converters for its simplicity, clear objectives, and ease of constraint implementation. However, its computational demand increases with the pursuit of higher accuracy and performance, potentially compromising real-time operation due to the fast dynamics of converters. To address this challenge, this paper applies a novel differentiable predictive control method for real-time control of power converters. By integrating predictive control principles into the neural network framework, the method transforms the network into an automated predictive control solver through gradient descent optimization offline. Unlike supervised learning-based neural networks, this approach eliminates the need for pre-labeled data or extensive training, offering an efficient solution for achieving precise and timely control. This new method enhances the implementation feasibility of predictive control in real-time applications, addressing computational challenges while still maintaining high performance in power electronic systems.

Power electronics are used to minimize losses in converting the energy produced by the generator in a wind turbine, and to drive motors that control the pitch and yaw of the wind turbine to ensure maximum power extraction. The power electronic system is based on a series of three-phase pulse width modulated (PWM) power modules consisting of IGBT power switches and associated diodes that are soldered to a ceramic substrate and interconnected with wirebonds. The design of the packaging and cooling of the power electronics is crucial to enhancing the energy efficiency and the reliability of the electronics, which generate heat loads in the hundreds of watts/cm2, and are often placed in harsh and inaccessible offshore environments. Without adequate heat removal, the increase in device temperature will reduce the efficiency of power electronic devices leading to thermal runaway and eventual failure of the entire power electronic system. Furthermore, the increased temperatures can lead to failure of the packaging elements as well. This paper will provide an overview of the fundamental packaging level mechanisms that can cause failures in the power electronic system. These include wirebond and lead fatigue, die attach fatigue, substrate cracking, and lead bonding fatigue.

This paper traces the development of three-phase induction motor controls using the Semikron advanced integration (SKAI) power electronics system. The SKAI was developed for hybrid and electric vehicles and integrates all the components of a three-phase inverter. As such, it promises to deliver significant cost savings. The SKAI utilizes a digital signal processor (DSP) controller. However, Semikron does not supply the necessary software for the DSP controller. The DSP used in the controller is manufactured by Texas Instruments. Texas Instruments provides an array of DSP programming utilities. This paper discusses aspects of programming and testing the DSP controller

Artificial Neural Network (ANN) techniques have recently been applied to many different fields and have demonstrated their capabilities in solving complex problems. In a business environment, the techniques have been applied to predict bond ratings and stock price performance. In these applications, ANN techniques outperformed widely-used multivariate statistical techniques. The purpose of this paper is to compare the ANN method with the Discriminant Analysis (DA) method in order to understand the merits of ANN that are responsible for the higher level of performance. The paper provides an overview of the basic concepts of ANN techniques in order to enhance the understanding of this emerging technique. The similarities and differences between ANN and DA techniques in representing their models are described. This study also proposes a method to overcome the limitations of the ANN approach, Finally, a case study using a data set in a business environment demonstrates the superiority of ANN over DA as a method of classification of observations.

In this paper, the modified single phase nine-level CHB-MLI is proposed based on the selective harmonic elimination pulse width modulation (SHE-PWM) using artificial neural network (ANN) technique. The number of proposed switching devices reduced in a now modified CHB-MLI compared with the conventional structure of CHB-MLI which decreases the switching frequency of the system, leading to a decrease in the total power switching losses. The switching angles of CHB-MLI in this paper are detected and controlled based on the ANN technique into selective harmonic elimination transcendental nonlinear equation which is considered as the popular and powerful method for minimizing the harmonic order at the output voltage waveform of the MLI and produces a low ratio of total harmonic distortion (THD%). This paper aims to design, simulate and build up new modified structure of the single-phase nine-levels CHB-MLI and predict the real-time switch in order to generate superior switching angles by using ANN technique. MATLAB simulation has been used for designing and simulating the nine-levels single-phase CHB-MLI with ANN technique for switching angles prediction. It is found the proposed technique able to reduce harmonic contents of output waveform.

<div class="htmlview paragraph">Artificial Neural Network(ANN) techniques are used to develop a system to detect High Impedance Faults(HIFs) in electric power distribution lines. Encouraging results were observed with a simple Multi-layer Perceptron(MLP) trained with the backpropagation learning algorithm. Although the results are not significantly better than those reported with other algorithmic approaches, ANN techniques have potential advantages over the other approaches; namely, ability to train the system easily to accommodate different feeder characteristics, ability to adapt and so become a better detector with experience and better fault tolerance. When these features are incorporated, the system is expected to perform better than existing systems.</div> <div class="htmlview paragraph">The system we developed for the current phase, the training strategies used, the tests conducted and the results obtained are discussed in this paper. Also background discussions on existing HIF detection techniques, and ANN techniques can be found in this paper. A feature extraction method based on fuzzy logic and a bin structure is discussed.</div>

Turkey’s net energy consumption