Predictive Maintenance of Industrial Shredders: Efficient Operation through Real-Time Monitoring Using Statistical Machine Learning

The shredding of waste materials is a key step in the recycling process towards circular economy. Industrial shredders for waste processing operate in very harsh operating conditions, leading to the need of frequent maintenance of critical components. The maintenance optimization is particularly important also to increase the machine’s efficiency, thereby reducing the operational costs. In this work, a monitoring system has been developed and deployed on an industrial shredder located at a waste recycling plant in Austria. The machine has been monitored for several months and methods for predictive maintenance have been developed for two key components: the cutting knives and the drive belt. The large amount of collected data is leveraged by statistical machine learning techniques, thereby not requiring a very detailed knowledge of the machine or its live operating conditions. The results show that, despite the wide range of operating conditions, a reliable estimate of the optimal time for maintenance can be derived. Moreover, the trade-off between the cost of maintenance and the increase in power consumption due to the wear state of the monitored components of the machine is investigated. This work proves the benefits of real-time monitoring system for efficient operation of industrial shredders.

Handover for Dense Small Cells Heterogeneous Networks: A Power-Efficient Game Theoretical Approach

In this paper, a non-cooperative game method is formulated where all players compete to transmit at higher power. Every base station represents a player in the game. The game is solved by obtaining the Nash equilibrium (NE) where the game converges to optimality. The proposed method, named Power Efficient Handover Game Theoretic (PEHO-GT) approach, aims to control the handover in dense small cell networks. Players optimize their payoff by adjusting the transmission power to improve the performance in terms of throughput, handover, power consumption and load balancing. To select the desired transmission power for a player, the payoff function considers the gain of increasing the transmission power. Then, the cell selection takes place by deploying Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS). A game theoretical method is implemented for heterogeneous networks to validate the improvement obtained. Results reveal that the proposed method gives a throughput improvement while reducing the power consumption and minimizing the frequent handover.

Experimental Demonstration of an Ultra-Low Power Vertical-Cavity Surface-Emitting Laser for Optical Power Generation

This paper reports on an experimental investigation into the influence of current modulation on the properties of a vertical-cavity surface-emitting laser (VCSEL) with a direct square wave modulation. The optical output power response, as a function of the pumping current, modulation frequency, and amplitude, is measured for an 850 nm VCSEL. We demonstrate that modulation frequency and amplitude play important roles in reducing the VCSEL’s power consumption for optical generation. Indeed, even when the biasing current is below the static threshold, the VCSEL emits optical power under the square wave modulation. The power consumed by the device to generate light is significantly reduced to > 50%, which is below the threshold current, in response to both the modulation frequency and amplitude. An operating VCSEL device at low power is very desirable for less thermal effects, which are essential for a high-speed modulation bandwidth.

A Survey of Field Programmable Gate Array-Based Convolutional Neural Network Accelerators

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Reduction of Energy Consumption Using Smart Home Techniques in the Household Sector

Outcomes of exhaustion of natural resources started influencing each spirit on this planet. Energy is an essential factor in this aspect. To restore the circumstance to the appropriate track, all attempts must focus on two fundamental branches: producing electricity from clean and renewable reserves and decreasing the overall unnecessary consumption of energy. The focal point of this paper will be on lessening the power consumption in the household's segment. This paper is an attempt to give a clear understanding of a framework called Reduction of Energy Consumption in Household Sector (RECHS) and how it should help householders to reduce their power consumption by substituting their household appliances, turning-off the appliances when stand-by modus is detected, and scheduling their appliances operation periods. Technically, the framework depends on utilizing Z-Wave compatible plug-ins which will be connected to the usual house devices to gauge and control them remotely and semi-automatically. The suggested framework underpins numerous quality characteristics, for example, integrability, scalability, security and adaptability.

Air Handling Units Power Consumption Using Generalized Additive Model for Anomaly Detection: A Case Study in a Singapore Campus

The emergence of digital twin technology, a digital replica of physical world, has improved the real-time access to data from sensors about the performance of buildings. This digital transformation has opened up many opportunities to improve the management of the building by using the data collected to help monitor consumption patterns and energy leakages. One example is the integration of predictive models for anomaly detection. In this paper, we use the GAM (Generalised Additive Model) for the anomaly detection of Air Handling Units (AHU) power consumption pattern. There is ample research work on the use of GAM for the prediction of power consumption at the office building and nation-wide level. However, there is limited illustration of its anomaly detection capabilities, prescriptive analytics case study, and its integration with the latest development of digital twin technology. In this paper, we applied the general GAM modelling framework on the historical data of the AHU power consumption and cooling load of the building between Jan 2018 to Aug 2019 from an education campus in Singapore to train prediction models that, in turn, yield predicted values and ranges. The historical data are seamlessly extracted from the digital twin for modelling purposes. We enhanced the utility of the GAM model by using it to power a real-time anomaly detection system based on the forward predicted ranges. The magnitude of deviation from the upper and lower bounds of the uncertainty intervals is used to inform and identify anomalous data points, all based on historical data, without explicit intervention from domain experts. Notwithstanding, the domain expert fits in through an optional feedback loop through which iterative data cleansing is performed. After an anomalously high or low level of power consumption detected, a set of rule-based conditions are evaluated in real-time to help determine the next course of action for the facilities manager. The performance of GAM is then compared with other approaches to evaluate its effectiveness. Lastly, we discuss the successfully deployment of this approach for the detection of anomalous power consumption pattern and illustrated with real-world use cases.

Secured Mutual Authentication Protocol for Radio Frequency Identification Systems

Radio Frequency Identification (RFID) is a blooming technology which uses radio frequency to track the objects. This technology transmits signals between tag and reader to fetch information from the tag with a unique serial identity. Generally, the drawbacks of RFID technology are high cost, high consumption of power and weak authentication systems between a reader and a tag. The proposed protocol utilizes less dynamic power using reversible truncated multipliers which are implemented in RFID tag-reader with mutual authentication protocol system to reduce both leakage and dynamic power consumption. The proposed system was simulated using Xilinx and Cadence tools.

Radish Sprout Growth Dependency on LED Color in Plant Factory Experiment

Recent rapid progress in ICT (Information and Communication Technology) has advanced the penetration of sensor networks (SNs) and their attractive applications. Agriculture is one of the fields well able to benefit from ICT. Plant factories control several parameters related to plant growth in closed areas such as air temperature, humidity, water, culture medium concentration, and artificial lighting by using computers and AI (Artificial Intelligence) is being researched in order to obtain stable and safe production of vegetables and medicinal plants all year anywhere, and attain self-sufficiency in food. By providing isolation from the natural environment, a plant factory can achieve higher productivity and safe products. However, the biggest issue with plant factories is the return on investment. Profits are tenuous because of the large initial investments and running costs, i.e. electric power, incurred. At present, LED (Light Emitting Diode) lights are being adopted because they are more energy-efficient and encourage photosynthesis better than the fluorescent lamps used in the past. However, further cost reduction is essential. This paper introduces experiments that reveal which color of LED lighting best enhances the growth of cultured radish sprouts. Radish sprouts were cultivated in the experimental environment formed by a hydroponics kit with three cultivation shelves (28 samples per shelf) each with an artificial lighting rack. Seven LED arrays of different color (white, blue, yellow green, green, yellow, orange, and red) were compared with a fluorescent lamp as the control. Lighting duration was set to 12 hours a day. Normal water with no fertilizer was circulated. Seven days after germination, the length, weight and area of leaf of each sample were measured. Electrical power consumption for all lighting arrangements was also measured. Results and discussions: As to average sample length, no clear difference was observed in terms of color. As regards weight, orange LED was less effective and the difference was significant (p < 0.05). As to leaf area, blue, yellow and orange LEDs were significantly less effective. However, all LEDs offered higher productivity per W consumed than the fluorescent lamp. Of the LEDs, the blue LED array attained the best results in terms of length, weight and area of leaf per W consumed. Conclusion and future works: An experiment on radish sprout cultivation under 7 different color LED arrays showed no clear difference in terms of sample size. However, if electrical power consumption is considered, LEDs offered about twice the growth rate of the fluorescent lamp. Among them, blue LEDs showed the best performance. Further cost reduction e.g. low power lighting remains a big issue for actual system deployment. An automatic plant monitoring system with sensors is another study target.

Design of a Telemetry, Tracking, and Command Radio-Frequency Receiver for Small Satellites Based on Commercial Off-The-Shelf Components

From several years till now the aerospace industry is developing more and more small satellites for Low-Earth Orbit (LEO) missions. Such satellites have a low cost of making and launching since they have a size and weight smaller than other types of satellites. However, because of size limitations, small satellites need integrated electronic equipment based on digital logic. Moreover, the LEOs require telecommunication modules with high throughput to transmit to earth a big amount of data in a short time. In order to meet such requirements, in this paper we propose a Telemetry, Tracking & Command module optimized through the use of the Commercial Off-The-Shelf components. The proposed approach exploits the major flexibility offered by these components in reducing costs and optimizing the performance. The method has been applied in detail for the design of the front-end receiver, which has a low noise figure (1.5 dB) and DC power consumption (smaller than 2 W). Such a performance is particularly attractive since it allows fulfilling the energy budget stringent constraints that are typical for LEO small platforms.

Study on the Addition of Solar Generating and Energy Storage Units to a Power Distribution System

Installation of micro-generators based on renewable energy in power distribution system has increased in recent years, with the main renewable sources being solar and wind. Due to the intermittent nature of renewable energy sources, such micro-generators produce time-varying energy which does not correspond at certain times of the day to the peak energy consumption of end users. For this reason, the use of energy storage units next to the grid contributes to the proper leveling of the buses’ voltage level according to Brazilian energy quality standards. In this work, the effect of the addition of a photovoltaic solar generator and a store of energy in the busbar voltages of an electric system is analyzed. The consumption profile is defined as the average hourly use of appliances in a common residence, and the generation profile is defined as a function of the solar irradiation available in a locality. The power summation method is validated with analytical calculation and is used to calculate the modules and angles of the voltages in the buses of an electrical system based on the IEEE standard, at each hour of the day and with defined load and generation profiles. The results show that bus 5 presents the worst voltage level at the power consumption peaks and stabilizes at the appropriate range with the inclusion of the energy storage during the night time period. Solar generator maintains improvement of the voltage level during the period when it receives solar irradiation, having peaks of production during the 12 pm (without exceeding the appropriate maximum levels of tension).

Optical Flow Based System for Cross Traffic Alert

This document describes an advanced system and methodology for Cross Traffic Alert (CTA), able to detect vehicles that move into the vehicle driving path from the left or right side. The camera is supposed to be not only on a vehicle still, e.g. at a traffic light or at an intersection, but also moving slowly, e.g. in a car park. In all of the aforementioned conditions, a driver’s short loss of concentration or distraction can easily lead to a serious accident. A valid support to avoid these kinds of car crashes is represented by the proposed system. It is an extension of our previous work, related to a clustering system, which only works on fixed cameras. Just a vanish point calculation and simple optical flow filtering, to eliminate motion vectors due to the car relative movement, is performed to let the system achieve high performances with different scenarios, cameras and resolutions. The proposed system just uses as input the optical flow, which is hardware implemented in the proposed platform and since the elaboration of the whole system is really speed and power consumption, it is inserted directly in the camera framework, allowing to execute all the processing in real-time.

Experimental Investigation of Visual Comfort Requirement in Garment Factories and Identify the Cost Saving Opportunities

Visual comfort is one of the major parameters that can be taken to measure the human comfort in any environment. If the provided illuminance level in a working environment does not meet the workers visual comfort, it will lead to eye-strain, fatigue, headache, stress, accidents and finally, poor productivity. However, improvements in lighting do not necessarily mean that the workplace requires more light. Unnecessarily higher illuminance levels will also cause poor visual comfort and health risks. In addition, more power consumption on lighting will also result in higher energy costs. So, during this study, visual comfort and the illuminance requirement for the workers in textile/apparel industry were studied to perform different tasks (i.e. cutting, sewing and knitting) at their workplace. Experimental studies were designed to identify the optimum illuminance requirement depending upon the varied fabric colour and type and finally, energy saving potentials due to controlled illuminance level depending on the workforce requirement were analysed. Visual performance of workers during the sewing operation was studied using the ‘landolt ring experiment’. It was revealed that around 36.3% of the workers would like to work if the illuminance level varies from 601 lux to 850 lux illuminance level and 45.9% of the workers are not happy to work if the illuminance level reduces less than 600 lux and greater than 850 lux. Moreover, more than 65% of the workers who do not satisfy with the existing illuminance levels of the production floors suggested that they have headache, eye diseases, or both diseases due to poor visual comfort. In addition, findings of the energy analysis revealed that the energy-saving potential of 5%, 10%, 24%, 8% and 16% can be anticipated for fabric colours, red, blue, yellow, black and white respectively, when the 800 lux is the prevailing illuminance level for sewing operation.

Electricity Price Forecasting: A Comparative Analysis with Shallow-ANN and DNN

Electricity prices have sophisticated features such as high volatility, nonlinearity and high frequency that make forecasting quite difficult. Electricity price has a volatile and non-random character so that, it is possible to identify the patterns based on the historical data. Intelligent decision-making requires accurate price forecasting for market traders, retailers, and generation companies. So far, many shallow-ANN (artificial neural networks) models have been published in the literature and showed adequate forecasting results. During the last years, neural networks with many hidden layers, which are referred to as DNN (deep neural networks) have been using in the machine learning community. The goal of this study is to investigate electricity price forecasting performance of the shallow-ANN and DNN models for the Turkish day-ahead electricity market. The forecasting accuracy of the models has been evaluated with publicly available data from the Turkish day-ahead electricity market. Both shallow-ANN and DNN approach would give successful result in forecasting problems. Historical load, price and weather temperature data are used as the input variables for the models. The data set includes power consumption measurements gathered between January 2016 and December 2017 with one-hour resolution. In this regard, forecasting studies have been carried out comparatively with shallow-ANN and DNN models for Turkish electricity markets in the related time period. The main contribution of this study is the investigation of different shallow-ANN and DNN models in the field of electricity price forecast. All models are compared regarding their MAE (Mean Absolute Error) and MSE (Mean Square) results. DNN models give better forecasting performance compare to shallow-ANN. Best five MAE results for DNN models are 0.346, 0.372, 0.392, 0,402 and 0.409.

Deep Learning for Renewable Power Forecasting: An Approach Using LSTM Neural Networks

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Lighting Consumption Analysis in Retail Industry: Comparative Study

This article is referring to a comparative study regarding the electrical energy consumption for lighting on diverse types of big sizes commercial buildings built in Romania after 2007, having 3, 4, 5 versus 8, 9, 10 operational years. Some buildings have installed building management systems (BMS) to monitor also the lighting performances starting with the opening days till the present days but some have chosen only local meters to implement. Firstly, for each analyzed building, the total required energy power and the energy power consumption for lighting were calculated depending on the lamps number, the unit power and the average daily running hours. All objects and installations were chosen depending on the destination/location of the lighting (exterior parking or access, interior or covering parking, building interior and building perimeter). Secondly, to all lighting objects and installations, mechanical counters were installed, and to the ones linked to BMS there were installed the digital meters as well for a better monitoring. Some efficient solutions are proposed to improve the power consumption, for example the 1/3 lighting functioning for the covered and exterior parking lighting to those buildings if can be done. This type of lighting share can be performed on each level, especially on the night shifts. Another example is to use the dimmers to reduce the light level, depending on the executed work in the respective area, and a 30% power energy saving can be achieved. Using the right BMS to monitor, the energy consumption depending on the average operational daily hours and changing the non-performant unit lights with the ones having LED technology or economical ones might increase significantly the energy performances and reduce the energy consumption of the buildings.

Performance Study of ZigBee-Based Wireless Sensor Networks

The IEEE 802.15.4 standard is designed for low-rate wireless personal area networks (LR-WPAN) with focus on enabling wireless sensor networks. It aims to give a low data rate, low power consumption, and low cost wireless networking on the device-level communication. The objective of this study is to investigate the performance of IEEE 802.15.4 based networks using simulation tool. In this project the network simulator 2 NS2 was used to several performance measures of wireless sensor networks. Three scenarios were considered, multi hop network with a single coordinator, star topology, and an ad hoc on demand distance vector AODV. Results such as packet delivery ratio, hop delay, and number of collisions are obtained from these scenarios.

Reversible Binary Arithmetic for Integrated Circuit Design

Application of reversible logic in integrated circuits results in the improved optimization of power consumption. This technology can be put into use in a variety of low power applications such as quantum computing, optical computing, nano-technology, and Complementary Metal Oxide Semiconductor (CMOS) Very Large Scale Integrated (VLSI) design etc. Logic gates are the basic building blocks in the design of any logic network and thus integrated circuits. In this paper, reversible Dual Key Gate (DKG) and Dual key Gate Pair (DKGP) gates that work singly as full adder/full subtractor are used to realize the basic building blocks of logic circuits. Reversible full adder/subtractor and parallel adder/ subtractor are designed using other reversible gates available in the literature and compared with that of DKG & DKGP gates. Efficient performance of reversible logic circuits relies on the optimization of the key parameters viz number of constant inputs, garbage outputs and number of reversible gates. The full adder/subtractor and parallel adder/subtractor design with reversible DKGP and DKG gates results in least number of constant inputs, garbage outputs, and number of reversible gates compared to the other designs. Thus, this paper provides a threshold to build more complex arithmetic systems using these reversible logic gates, leading to the enhanced performance of computing systems.

Hardware Implementation of Local Binary Pattern Based Two-Bit Transform Motion Estimation

Nowadays, demand for using real-time video transmission capable devices is ever-increasing. So, high resolution videos have made efficient video compression techniques an essential component for capturing and transmitting video data. Motion estimation has a critical role in encoding raw video. Hence, various motion estimation methods are introduced to efficiently compress the video. Low bit‑depth representation based motion estimation methods facilitate computation of matching criteria and thus, provide small hardware footprint. In this paper, a hardware implementation of a two-bit transformation based low-complexity motion estimation method using local binary pattern approach is proposed. Image frames are represented in two-bit depth instead of full-depth by making use of the local binary pattern as a binarization approach and the binarization part of the hardware architecture is explained in detail. Experimental results demonstrate the difference between the proposed hardware architecture and the architectures of well-known low-complexity motion estimation methods in terms of important aspects such as resource utilization, energy and power consumption.

An 8-Bit, 100-MSPS Fully Dynamic SAR ADC for Ultra-High Speed Image Sensor

In this paper, a dynamic and power efficient 8-bit and 100-MSPS Successive Approximation Register (SAR) Analog-to-Digital Converter (ADC) is presented. The circuit uses a non-differential capacitive Digital-to-Analog (DAC) architecture segmented by 2. The prototype is produced in a commercial 65-nm 1P7M CMOS technology with 1.2-V supply voltage. The size of the core ADC is 208.6 x 103.6 µm2. The post-layout noise simulation results feature a SNR of 46.9 dB at Nyquist frequency, which means an effective number of bit (ENOB) of 7.5-b. The total power consumption of this SAR ADC is only 1.55 mW at 100-MSPS. It achieves then a figure of merit of 85.6 fJ/step.

Design and Implementation of 4 Bit Multiplier Using Fault Tolerant Hybrid Full Adder

The fault tolerant system plays a crucial role in the critical applications which are being used in the present scenario. A fault may change the functionality of circuits. Aim of this paper is to design multiplier using fault tolerant hybrid full adder. Fault tolerant hybrid full adder is designed to check and repair any fault in the circuit using self-checking circuit and the self-repairing circuit. Further, the use of conventional logic circuits may result in more area, delay as well as power consumption. In order to reduce these parameters of the circuit, GDI (Gate Diffusion Input) techniques with less number of transistors are used compared to conventional full adder circuit. This reduces the area, delay and power consumption. The proposed method solves the major problems occurring in the most crucial and critical applications.