Multiple Input Parameters Research Articles

Modeling of Relative Exergy Destruction for Turboprop Engine Components Using Deep Learning Artificial Neural Networks

Abstract This study illustrates an deep learning approach supported by a metaheuristic design targeting the foremost features and parameters of artificial neural network (ANN) framework used in predicting relative exergy destruction ( ( f r e l , d e s t * ) (f_{rel, dest}^*) ) of a turboprop components. The development of deep ANN comprising of three-hidden layers using data obtained considering multiple engine input parameters was accomplished. Once the deep learning ANN frameworks were hybridized with a metaheuristic approach, such as genetic algorithms (GAs). The analysis of errors revealed a close fit involving the predicted values of the model and references made on data in f r e l , d e s t ∗ f_{rel, dest}^* for the engine main components. The use of appropriately chosen values in preceding networks weights produced more accurate testing results (Linear correlation coefficient values (R) for the engine components are found to be between 0.996497 and 0.998986) in networks using three hidden layers compared to those using lower hidden layers. Furthermore, optimizing deep ANNs using GAs delivers not only further improved accuracy (R is calculated to be in the range of 0.998929–0.999966 for the engine components) but also an effective utilization of time in the resulting models.

Multi-objective iterative optimization algorithm based optimal wavelet filter selection for multi-fault diagnosis of rolling element bearings

Rolling element bearings (REBs) play an essential role in modern machinery and their condition monitoring is significant in predictive maintenance. Due to the harsh operating conditions, multi-fault may co-exist in one bearing and vibration signal always exhibits low signal-to-noise ratio (SNR), which causes difficulties in detecting fault. In the previous studies, maximum correlated kurtosis deconvolution (MCKD) has been validated as an efficient method to extract fault feature in the fault signals. Nonetheless, there are still some challenges when MCKD is applied to fault detection owing to the rigorous requirements of multiple input parameters. To overcome limitation, a multi-objective iterative optimization algorithm (MOIOA) for multi-fault diagnosis is proposed. In this method, correlated kurtosis (CK) is taken as a criterion to select optimal Morlet wavelet filter using the whale optimization algorithm (WOA). Meanwhile, to further eliminate the effect of the inaccurate period on CK, the update process of period is incorporated. After that, the simulated and experimental signals are utilized to testify the validity and superiority of the MOIOA for multiple faults detection by the comparison with MCKD. The results indicate that MOIOA is efficient to extract weak fault features even with heavy noise and harmonic interferences.

Deciphering ∼45.000 years of Arctic Ocean lithostratigraphic variability through multivariate statistical analysis

Our understanding of past climate conditions in the Arctic Ocean has been hampered by poor age control caused in part by low sedimentation rates (<1 cm/kyr), hiatuses during glacial intervals as well as the scarcity and poor preservation of calcareous nanno- and microfossils in the sediments. Although recent advances using variations in single element (e.g. Mn) content or physical sediment properties (e.g. bulk density, grain size, colour) of the recovered sediments have aided Arctic core-to-core correlations, unique depositional events and post-depositional changes can complicate stratigraphic interpretations based on individual or even multiple, physical or chemical parameters. Furthermore, clear correlations between cores using physical and chemical parameters are not always possible to establish. To tackle this issue, we developed an algorithm that combines clustering and multivariate ordination to test the interrelation of multiple input parameters (e.g. an array of individual XRF elemental contents), and subsequently identifies statistically significant stratigraphic units on centimetre to decimetre scales. Our preliminary results show that a distinct sedimentological pattern during the past 45,000 years characterizes cores from the region of the Morris Jesup Rise and the Greenland side of the Lomonosov Ridge. Stratigraphic patterns of the Siberian Side of the Lomonosov Ridge yield distinct differences, thus allowing for novel insights into sedimentary processes shaping the different regions within the Arctic Ocean. We also argue that our approach can compensate for some of the weakness of single element or proxy applications, and hence aid the construction of a robust stratigraphic framework for a wide geographical range of Arctic Ocean sediments.

Efficient EMC Parameter Analysis for the Verification of Complex Automotive Simulation Models by the Utilization of Design of Experiments

Virtual electromagnetic compatibility (EMC) analysis improves the validation processes in the automotive industry by mitigating risks in early development stages. Detailed knowledge about adjustable parameters to improve the compatibility can greatly simplify and optimize the EMC of an entire system. The application of the quality tool design of experiment (DoE) to EMC simulations combines the statistical analysis of influencing parameters with the reduction and optimization of the simulation efforts. DoE is a toolbox used to determine the effect and interactions of multiple input parameters on a desired target value by varying all input parameters simultaneously and effectively. The DoE application in virtual EMC validation processes reduces the simulation efforts of full factorial optimization problems and leads to a clear understanding of the most influencing parameters, parameter strengths, and parameter interactions. The application of DoE is presented for complex screens of high-voltage cables as well as for high-voltage subsystems.

IoT based hydroponics system using Deep Neural Networks

Agriculture has the significant impact on the economy of the country. With the practice of modern farming techniques where plants can be grown without the need of soil by means of nutrient solution, Hydroponics and Aeroponics are in the rise. Now towards controlling the hydroponic plant growth, some amount of research has been done in applying machine learning algorithms like Neural Networks and Bayesian network.Internet of Things allows for Machine to Machine interaction and controlling the hydroponic system autonomously and intelligently. This work proposes to develop an intelligent IoT based hydroponic system by employing Deep Neural Networks which is first of its kind. The system so developed is intelligent enough in providing the appropriate control action for the hydroponic environment based on the multiple input parameters gathered. A prototype for Tomato plant growth as a case study was developed using Arduino, Raspberry Pi3 and Tensor Flow.

Generating Effective Test Suite for Multiparameter Software using ACTS Tool and its Verification using Code Coverage Tools

Combinatorial testing is a practical method to test software with multiple input parameters. National Institute of Standards and Technology has developed tools which aid combinatorial testing. ACTS is one such tool which is freely available to users. In spite of this, very few software being developed are being tested systematically. In this paper we explore the effectiveness and suitability of ACTS tool to test software which has a m ultiparameter input. We chose a Java based software, College Time Table, a software which involves multiparameter input, as system under test. We could achieve 90% coverage of instructions, line, method and 100% class coverage with practical time and effort with ACTS tool. The process involved in getting above mentioned results is documented in this paper. Empirical data generated with the code coverage confirms the effectiveness of ACTS generated test suite for a simple project.

Groundwater Potential Mapping in a Rural River Basin by Union (OR) and Intersection (AND) of Four Multi-criteria Decision-Making Models

Targeting groundwater in the river basin like Chandrabhaga with seasonal drought is a very urgent task especially for mitigating irrigation demand during the non-monsoon period. This paper delineated suitable groundwater potential zones based on the analytical hierarchy process (AHP), modified AHP, PCA-based weight and knowledge-based weight of multiple input parameters. For providing more certainty of the target zones in the derived models, union and intersection of all models were performed. A GIS-based multi-criteria approach using 13 relevant parameters has been adopted in this work. From the first four models, it is found that very suitable areas vary from 7.5 to 11% of the total basin area. The union and intersection models of the four individual models, respectively, delineated 13.91% and 3.69% suitable areas. Among the six models, the average yield of groundwater (5.96 L/s) is maximum in case of the intersection model, which is, therefore, more reliable than others. In case of the union model, the suitable area has 0.2 L/s less average yield than the intersection model. Therefore, for the harvesting more water, very good potential area delineated in the intersection model can be targeted. All these models will nevertheless help decision-makers to judge whether the existing groundwater harvesting structures are located properly or whether reorientation is needed.

An Efficient Method for Determining the Chemical Evolution of Gravitationally Collapsing Prestellar Cores

Abstract We develop analytic approximations to the density evolution of prestellar cores, based on the results of hydrodynamical simulations. We use these approximations as input for a time-dependent gas-grain chemical code to investigate the effects of differing modes of collapse on the molecular abundances in the core. We confirm that our method can provide reasonable agreement with an exact numerical solution of both the hydrodynamics and chemistry while being significantly less computationally expensive, allowing a large grid of models varying multiple input parameters to be run. We present results using this method to illustrate how the chemistry is affected not only by the collapse model adopted but also by the large number of unknown physical and chemical parameters. Models that are initially gravitationally unstable predict similar abundances despite differing densities and collapse timescales, while ambipolar diffusion (AD) produces more extended inner depleted regions that are not seen in observations of prestellar cores. Molecular observations are capable of discriminating between modes of collapse despite the unknown values of various input parameters. We also investigate the evolution of the AD timescale for a range of collapse modes, metallicities, and cosmic-ray ionization rates, finding that it remains comparable to or larger than the collapse timescale during the initial stages for all models we consider, but becomes smaller at later evolutionary stages. This confirms that AD is an important process for diffuse gas but becomes less significant as cores collapse to higher densities.

Agent-Based Modeling of Taxi Behavior Simulation with Probe Vehicle Data

Taxi behavior is a spatial–temporal dynamic process involving discrete time dependent events, such as customer pick-up, customer drop-off, cruising, and parking. Simulation models, which are a simplification of a real-world system, can help understand the effects of change of such dynamic behavior. In this paper, agent-based modeling and simulation is proposed, that describes the dynamic action of an agent, i.e., taxi, governed by behavior rules and properties, which emulate the taxi behavior. Taxi behavior simulations are fundamentally done for optimizing the service level for both taxi drivers as well as passengers. Moreover, simulation techniques, as such, could be applied to another field of application as well, where obtaining real raw data are somewhat difficult due to privacy issues, such as human mobility data or call detail record data. This paper describes the development of an agent-based simulation model which is based on multiple input parameters (taxi stay point cluster; trip information (origin and destination); taxi demand information; free taxi movement; and network travel time) that were derived from taxi probe GPS data. As such, agent’s parameters were mapped into grid network, and the road network, for which the grid network was used as a base for query/search/retrieval of taxi agent’s parameters, while the actual movement of taxi agents was on the road network with routing and interpolation. The results obtained from the simulated taxi agent data and real taxi data showed a significant level of similarity of different taxi behavior, such as trip generation; trip time; trip distance as well as trip occupancy, based on its distribution. As for efficient data handling, a distributed computing platform for large-scale data was used for extracting taxi agent parameter from the probe data by utilizing both spatial and non-spatial indexing technique.

Assessing mental stress from the photoplethysmogram: a numerical study

Objective: Mental stress is detrimental to cardiovascular health, being a risk factor for coronary heart disease and a trigger for cardiac events. However, it is not currently routinely assessed. The aim of this study was to identify features of the photoplethysmogram (PPG) pulse wave which are indicative of mental stress. Approach: A numerical model of pulse wave propagation was used to simulate blood pressure signals, from which simulated PPG pulse waves were estimated using a transfer function. Pulse waves were simulated at six levels of stress by changing the model input parameters both simultaneously and individually, in accordance with haemodynamic changes associated with stress. Thirty-two feature measurements were extracted from pulse waves at three measurement sites: the brachial, radial and temporal arteries. Features which changed significantly with stress were identified using the Mann–Kendall monotonic trend test. Main results: Seventeen features exhibited significant trends with stress in measurements from at least one site. Three features showed significant trends at all three sites: the time from pulse onset to peak, the time from the dicrotic notch to pulse end, and the pulse rate. More features showed significant trends at the radial artery (15) than the brachial (8) or temporal (7) arteries. Most features were influenced by multiple input parameters. Significance: The features identified in this study could be used to monitor stress in healthcare and consumer devices. Measurements at the radial artery may provide superior performance than the brachial or temporal arteries. In vivo studies are required to confirm these observations.

Numerically accurate computational techniques for optimal estimator analyses of multi-parameter models

Modelling unclosed terms in partial differential equations typically involves two steps: First, a set of known quantities needs to be specified as input parameters for a model, and second, a specific functional form needs to be defined to model the unclosed terms by the input parameters. Both steps involve a certain modelling error, with the former known as the irreducible error and the latter referred to as the functional error. Typically, only the total modelling error, which is the sum of functional and irreducible error, is assessed, but the concept of the optimal estimator enables the separate analysis of the total and the irreducible errors, yielding a systematic modelling error decomposition. In this work, attention is paid to the techniques themselves required for the practical computation of irreducible errors. Typically, histograms are used for optimal estimator analyses, but this technique is found to add a non-negligible spurious contribution to the irreducible error if models with multiple input parameters are assessed. Thus, the error decomposition of an optimal estimator analysis becomes inaccurate, and misleading conclusions concerning modelling errors may be drawn. In this work, numerically accurate techniques for optimal estimator analyses are identified and a suitable evaluation of irreducible errors is presented. Four different computational techniques are considered: a histogram technique, artificial neural networks, multivariate adaptive regression splines, and an additive model based on a kernel method. For multiple input parameter models, only artificial neural networks and multivariate adaptive regression splines are found to yield satisfactorily accurate results. Beyond a certain number of input parameters, the assessment of models in an optimal estimator analysis even becomes practically infeasible if histograms are used. The optimal estimator analysis in this paper is applied to modelling the filtered soot intermittency in large eddy simulations using a dataset of a direct numerical simulation of a non-premixed sooting turbulent flame.

A long-term comparative assessment of human health risk to leachate-contaminated groundwater from heavy metal with different liner systems.

The handling and management of municipal solid waste (MSW) are major challenges for solid waste management in developing countries. Open dumping is still the most common waste disposal method in India. However, landfilling also causes various environmental, social, and human health impacts. The generation of heavily polluted leachate is a major concern to public health. Engineered barrier systems (EBSs) are commonly used to restrict potentially harmful wastes by preventing the leachate percolation to groundwater and overflow to surface water bodies. The EBSs are made of natural (e.g., soil, clay) and/or synthetic materials such as polymeric materials (e.g., geomembranes, geosynthetic clay liners) by arranging them in layers. Various studies have estimated the human health risk from leachate-contaminated groundwater. However, no studies have been reported to compare the human health risks, particularly due to the leachate contamination with different liner systems. The present study endeavors to quantify the human health risk to contamination from MSW landfill leachate using multiple simulations for various EBSs. To quantify the variation in health risks to groundwater consumption to the child and adult populations, the Turbhe landfill of Navi Mumbai in India has been selected. The leachate and groundwater samples were collected continuously throughout January-September in 2015 from the landfill site, and heavy metal concentrations were analyzed using an inductively coupled plasma system. The LandSim 2.5 Model, a landfill simulator, was used to simulate the landfill activities for various time slices, and non-carcinogenic human health risk was determined for selected heavy metals. Further, the uncertainties associated with multiple input parameters in the health risk model were quantified under a Monte Carlo simulation framework.

Tuning of PID Parameters by Integrated Taguchi Approach

Objectives: The effectiveness of Taguchi approach of tuning of PID controller by traditional hit and trail method is presented. Methods/Statistical Analysis: In multiple input parameter process, for obtaining the best output, one method is to conduct all possible experiments covering the entire range of parameters, a times, resulting in a huge number of experiments. To reduce the number of experimentation, a representative sample of experiments may be chosen and analyzed. Taguchi arrays helps selects the subset in such a way that ensures that all levels of all factors are represented equally. Findings: It has been shown that tuning of PID parameters by traditional hit and trial approach can be improved and made more effective by implementing the process with Taguchi approach. Using Taguchi's Method nearly best result can be obtained using lesser number of experimentations. Results thus obtained are authenticated by comparing them with those obtained by Exhaustive Search i.e. by conducting the entire set of experiments involving all possible combinations of the input parameters at different levels. Application/Improvements: Taguchi method helps achieve the target by conducting lesser number of experiments, thus saving on time, effort and cost, without compromising on the quality of result.

The Gate Automatic Control Based on Multi-input Parameters, Time-independent and Self-adaptive Fuzzy PID

The gate control system has some features such as multiple input parameters, nonlinearity, hysteresis, time change etc., therefore it can’t achieve good results by using traditional PID. In consideration of these characteristics, based on self-adaptive fuzzy PID control, we improved it and created a new time-independent, deterministic fuzzy PID. Then by auto-fusion of multiple input parameters, we have established a multi-input parameters fusion, time-independent and self-adaptive fuzzy PID controller and used it to control the reservoir gate and water level automatically under heavy rainfall. Simulations and experiments have shown that this method can offer faster response, smaller overshoot and better static and dynamic performance.

A new state-of-charge estimation method for electric vehicle lithium-ion batteries based on multiple input parameter fitting model

Summary The estimation of state-of-charge (SOC) is crucial to determine the remaining capacity of the Lithium-Ion battery, and thus plays an important role in many electric vehicle control and energy storage management problems. The accuracy of the estimated SOC depends mostly on the accuracy of the battery model, which is mainly affected by factors like temperature, State of Health (SOH), and chemical reactions. Also many characteristic parameters of the battery cell, such as the output voltage, the internal resistance and so on, have close relations with SOC. Battery models are often identified by a large amount of experiments under different SOCs and temperatures. To resolve this difficulty and also improve modeling accuracy, a multiple input parameter fitting model of the Lithium-Ion battery and the factors that would affect the accuracy of the battery model are derived from the Nernst equation in this paper. Statistics theory is applied to obtain a more accurate battery model while using less measurement data. The relevant parameters can be calculated by data fitting through measurement on factors like continuously changing temperatures. From the obtained battery model, Extended Kalman Filter algorithm is applied to estimate the SOC. Finally, simulation and experimental results are given to illustrate the advantage of the proposed SOC estimation method. It is found that the proposed SOC estimation method always satisfies the precision requirement in the relevant Standards under different environmental temperatures. Particularly, the SOC estimation accuracy can be improved by 14% under low temperatures below 0 °C compared with existing methods. Copyright © 2017 John Wiley & Sons, Ltd.

Translating landfill methane generation parameters among first-order decay models

ABSTRACTLandfill gas (LFG) generation is predicted by a first-order decay (FOD) equation that incorporates two parameters: a methane generation potential (L0) and a methane generation rate (k). Because non-hazardous waste landfills may accept many types of waste streams, multiphase models have been developed in an attempt to more accurately predict methane generation from heterogeneous waste streams. The ability of a single-phase FOD model to predict methane generation using weighted-average methane generation parameters and tonnages translated from multiphase models was assessed in two exercises. In the first exercise, waste composition from four Danish landfills represented by low-biodegradable waste streams was modeled in the Afvalzorg Multiphase Model and methane generation was compared to the single-phase Intergovernmental Panel on Climate Change (IPCC) Waste Model and LandGEM. In the second exercise, waste composition represented by IPCC waste components was modeled in the multiphase IPCC and compared to single-phase LandGEM and Australia’s Solid Waste Calculator (SWC). In both cases, weight-averaging of methane generation parameters from waste composition data in single-phase models was effective in predicting cumulative methane generation from -7% to +6% of the multiphase models. The results underscore the understanding that multiphase models will not necessarily improve LFG generation prediction because the uncertainty of the method rests largely within the input parameters. A unique method of calculating the methane generation rate constant by mass of anaerobically degradable carbon was presented (kc) and compared to existing methods, providing a better fit in 3 of 8 scenarios. Generally, single phase models with weighted-average inputs can accurately predict methane generation from multiple waste streams with varied characteristics; weighted averages should therefore be used instead of regional default values when comparing models.Implications: Translating multiphase first-order decay model input parameters by weighted average shows that single-phase models can predict cumulative methane generation within the level of uncertainty of many of the input parameters as defined by the Intergovernmental Panel on Climate Change (IPCC), which indicates that decreasing the uncertainty of the input parameters will make the model more accurate rather than adding multiple phases or input parameters.

Uncertainty Analysis in Lorentz Force Eddy Current Testing

The paper addresses the analysis of uncertainties in the framework of the nondestructive evaluation technique Lorentz force eddy current testing. A non-intrusive generalized polynomial chaos expansion is used in order to quantify the impact of multiple unknown input parameters. In this context, the statistics of the velocity and the conductivity of the specimen as well as the magnetic remanence and the lift-off distance of the permanent magnet are determined experimentally and modeled as $\beta $ -distributed and uniform distributed random variables. The results are compared with Monte Carlo simulations and showed errors <0.2%. Furthermore, the numerically predicted force profiles are validated with experiments. A sensitivity analysis by means of the Sobol decomposition revealed that the magnetic remanence and the lift-off distance contribute to more than 90% of the total variance of the resulting Lorentz force profile and should be considered first to improve reproducibility.

Optimization Coupling Approach for/with Non-Static Point Based CAT-models

This paper proposes a concept to optimize tolerance synthesis process. Tolerance synthesis is getting more and more important to limit inaccuracies of the product during the manufacturing process. Today tolerance synthesis is used to assign the “right tolerance range” to the called out geometrical and dimensional tolerances. This can be achieved using tolerance analysis tools. However to reach the defined target value (e.g. maximum allowed deviation of a gap-/ flushness- measurement) there are multiple input parameters available towards the tolerance simulation model, which can be modified to a certain range. To address these issues, the approach in this paper is showing a way to couple an optimization tool to a CAT-simulation. This approach shall consider all the input parameters in a tolerance simulation model to stand out from existing tolerance optimization approaches. Also a unique feature of the approach is using a non-static simulation deck for the coupled tolerance analysis. This means all the tolerance simulation models are generated subjected to the deviating input parameters defined by the optimization tool. The optimization tool then uses the results of the CAT-simulations to calculate the response surface model. Using an optimization algorithm on this response surface model (RSM) helps to find an optimal set of parameters to reach the required quality features. Thus the tolerance planning engineer can give a well-founded feedback to the departments involved.

Decision support system for temperature monitoring in beehives

European honeybee colonies are the most important pollinator insects and source of honey and other useful products. Honeybee colonies today face new diseases and pests as well as pollution which threaten their survival and endanger whole food production which relies on honey bee pollination. Internet of Things (IoT) technology enables integration of wireless sensors inside beehives to enable remote monitoring of various beehive parameters from remote location using Internet. Detection of certain critical events in beehive is hard to be explicitly program due to complex dependence between multiple input parameters. Machine learning algorithms give computers the ability to learn to detect these events without being explicitly programmed. Detection of these event from streams of data collected from IoT sensors is possible using Complex Event Processing (CEP) which applies machine induced knowledge do detect and warn beekeepers about certain events in beehive.

Visual parameter optimisation for biomedical image processing.

BackgroundBiomedical image processing methods require users to optimise input parameters to ensure high-quality output. This presents two challenges. First, it is difficult to optimise multiple input parameters for multiple input images. Second, it is difficult to achieve an understanding of underlying algorithms, in particular, relationships between input and output.ResultsWe present a visualisation method that transforms users' ability to understand algorithm behaviour by integrating input and output, and by supporting exploration of their relationships. We discuss its application to a colour deconvolution technique for stained histology images and show how it enabled a domain expert to identify suitable parameter values for the deconvolution of two types of images, and metrics to quantify deconvolution performance. It also enabled a breakthrough in understanding by invalidating an underlying assumption about the algorithm.ConclusionsThe visualisation method presented here provides analysis capability for multiple inputs and outputs in biomedical image processing that is not supported by previous analysis software. The analysis supported by our method is not feasible with conventional trial-and-error approaches.