Set Of Input-output Data Research Articles

Micro engraving on Ti-6Al-4V using fiber laser for orthopedic implant-A study

The demand for production of fine micro-grooves with least heat-affected zone (HAZ), recast layer thickness, microcrack, and microcavity are increasing as Ti6Al4V is a readily used orthopedic implant material. This study presents a groove quality optimiser called response surface methodology (RSM) for fiber laser micro engraving on Ti6Al4V to improve microgroove quality and functionality. The critical process factors’ (number of laser beam passes, scan speed, and pulse frequency) for each response characteristic are identified through the RSM optimiser by analysing the experimental data sets. The optimised data sets are beneficial in maintaining groove quality characteristics (width, depth, HAZ, recast layer thickness, and microhardness). Number of passes and scanning speed has been recognised as crucial process parameters that primarily regulate the groove response characteristics. A 3-20-5 neural network (NN) model is developed and trained through the experimental input–output data sets. Performance of 3-20-5 model is found as 1.63e-27, and regression score is significantly closer to 1. It has been recognised that ANN model predicts more accurate results with a low error percentage than RSM model even when the input factor level settings are beyond the defined boundary. Under these experimental settings, the microgroove characteristics are enhanced in terms of low HAZ, recast layer thickness, microhardness, and spatter. X-ray diffraction analysis (XRD) is also performed on base metal and grooved surfaces to determine diffraction peaks, crystallite phase composition, size, and lattice strain. XRD analysis revealed the presence of both HCP-α-Ti and BCC-β-Ti in both base metal grooved surfaces.

Power peaking factor prediction using ANFIS method

Power peaking factors (PPF) is an important parameter for safe and efficient reactor operation. There are several methods to calculate the PPF at TRIGA research reactors such as MCNP and TRIGLAV codes. However, these methods are time-consuming and required high specifications of a computer system. To overcome these limitations, artificial intelligence was introduced for parameter prediction. Previous studies applied the neural network method to predict the PPF, but the publications using the ANFIS method are not well developed yet. In this paper, the prediction of PPF using the ANFIS was conducted. Two input variables, control rod position, and neutron flux were collected while the PPF was calculated using TRIGLAV code as the data output. These input-output datasets were used for ANFIS model generation, training, and testing. In this study, four ANFIS model with two types of input space partitioning methods shows good predictive performances with R2 values in the range of 96%–97%, reveals the strong relationship between the predicted and actual PPF values. The RMSE calculated also near zero. From this statistical analysis, it is proven that the ANFIS could predict the PPF accurately and can be used as an alternative method to develop a real-time monitoring system at TRIGA research reactors.

Gradient‐based recursive parameter estimation for a periodically nonuniformly sampled‐data Hammerstein–Wiener system based on the key‐term separation

SummaryThe identification of the Hammerstein–Wiener (H‐W) systems based on the nonuniform input–output dataset remains a challenging problem. This article studies the identification problem of a periodically nonuniformly sampled‐data H‐W system. In addition, the product terms of the parameters in the H‐W system are inevitable. In order to solve the problem, the key‐term separation is applied and two algorithms are proposed. One is the key‐term‐based forgetting factor stochastic gradient (KT‐FFSG) algorithm based on the gradient search. The other is the key‐term‐based hierarchical forgetting factor stochastic gradient (KT‐HFFSG) algorithm. Compared with the KT‐FFSG algorithm, the KT‐HFFSG algorithm gives more accurate estimates. The simulation results indicate that the proposed algorithms are effective.

Parameter identification of pulsed eddy current testing equivalent circuit model and its application to defect evaluation

The equivalent circuit model of pulsed eddy current testing (PECT) has simple mathematics but its applications are limited to qualitative analysis such as principle illustration and signal interpretation. In this paper, the parameters of equivalent circuit model are estimated using system identification method and quantitative relationships are found between some of the parameters and the size of the defect. The equivalent circuit equations were solved from the perspective of system analysis to yield the system transfer function. An m-sequence of 10 order was selected to excite the system and the probe current was used as the output. A set of experiment input-output data for system identification were obtained by performing experiments on two aluminium alloy 6061 slabs, one of which was machined with five slots of different widths, and the other one was machined with five depth-varied slots. The equivalent circuit parameters were finally estimated based on the identified transfer function parameters. It is found that the values of resistance and self-inductance of the secondary windings decrease greatly and monotonically with the increase of the slot width or depth. The self-inductance is more sensitive to the slot size variation than the resistance. Both of them have the potential to serve as the signal feature for defect evaluation in PECT applications.

Online parameter estimation under non-persistent excitations for high-rate dynamic systems

High-rate dynamic systems are defined as systems experiencing dynamic events of typical amplitudes higher than 100 gn for a duration of less than 100 ms. They are characterized by 1) large uncertainties on the external loads; 2) high levels of nonstationarity and heavy disturbance; and 3) generation of unmodeled dynamics from changes in mechanical configuration. To fully enable these systems, feedback capabilities must be developed. This includes computationally fast software and low latency hardware. This paper presents a pure time-based online parameter estimation algorithm for high-rate dynamic systems with real-time applicability. The algorithm is based on a model reference adaptive system architecture consisting of a reference system and an adaptive model. The adaptive model is built on a reduced order physical representation of the system and uncertainties are linearized. Uncertain coefficients are adapted leveraging instantaneous measurements and historical input–output data sets, termed history stack data, based on concurrent learning theory for coping with the lack of persistent excitation. The history stack is sequentially modified based on a singular value maximizing algorithm to accelerate convergence. The algorithm is numerically verified and experimentally validated on a testbed consisting of a cantilever beam with a moving cart. Numerical verifications show that the algorithm provides fast and accurate convergence when concurrent learning is used. Experimental validations show that the algorithm can successfully identify static positions of the cart, and can also track its movement relatively well, with large chattering and overshoots during travel time. The average computation speed of the algorithm per sample step, implemented in MATLAB, is 93 μs. It is envisioned that the implementation of the algorithm on an FPGA, along with refined coding, will greatly reduce computation time.

Observer-Based Enhanced ANFIS Control for a Quadrotor UAV

This paper introduces a new approach for optimizing the Adaptive Network Fuzzy Inference System (ANFIS) with the (metaheuristic) particle swarm optimization (PSO) algorithm to solve a trajectory tracking problem for a UAV quadrotor system. In this work, the input-output dataset is collected from the quadrotor's time response from a Proportional Integral Derivative (PID) controller. Then, before its use in the ANFIS algorithm, the collected dataset is optimized using the PSO algorithm. Moreover, an integral control action is integrated into the proposed ANFIS controller to ensure disturbance rejection. A suitable high gain observer is utilized in estimating unmeasured states for translational and rotational motions of the quadrotor system. Compared to a conventional ANFIS and traditional PID controllers, the results of two simulation tests demonstrate the efficiency and robustness of the proposed new output-feedback PSO-ANFIS controller.

Fuzzy rule-based model for outlier detection in a Topical Negative Pressure Wound Therapy Device

This paper proposes a novel method for offline outlier detection in nonlinear dynamical systems using an input–output dataset of a Topical Negative Pressure Wound Therapy Device, NPWT. The fundamental characteristics of an NPWT describe a chaotic system whose states vary over time and may result in unpredictable and possibly anomalous divergent behavior in the presence of perturbations and other unmodeled system dynamics, despite a quasi-stable controller. Bacterial Memetic Algorithm, BMA, is used to generate fuzzy rule-based models of the input–output dataset. The error definition in the fuzzy rule extraction features a novel application of the Canberra Distance. The optimal number of rules for identifying the outliers, validated against both artificial and real system datasets, is calculated from the sample of inferred fuzzy models. The optimal number of rules is two in both cases based on the maximum average-error-drop. Using three or more rules results in better error performance; however, the algorithm learns the nuances of the outlier patterns instead. Novel methods for creating the outlier list and determining the optimal number of rules for the outlier detection problem are proposed.

Future changes in consumption: The income effect on greenhouse gas emissions

Abstract The scale and patterns of household consumption are important determinants of environmental impacts. Whilst affluence has been shown to have a strong correlation with environmental impact, they do not necessarily grow at the same rate. Given the apparent contradiction between the sustainable development goals of economic growth and environmental protection, it is important to understand the effect of rising affluence and concurrent changing consumption patterns on future environmental impacts. Here we develop an econometric demand model based on the data available from a global multiregional input-output dataset. We model future household consumption following scenarios of population and GDP growth for 49 individual regions. The greenhouse gas (GHG) emissions resulting from the future household demand is then explored both with and without consideration of the change in expenditure over time on different consumption categories. Compared to a baseline scenario where final demand grows in line with the 2011 average consumption pattern up until 2030, we find that changing consumer preferences with increasing affluence has a small negative effect on global cumulative GHG emissions. The differences are more profound on both a regional and a product level. For the demand model scenario, we find the largest decrease in GHG emissions for the BRICS and other developing countries, while emissions in North America and the EU remain unchanged. Decreased spending and resulting emissions on food are cancelled out by increased spending and emissions on transportation. Despite relatively small global differences between the scenarios, the regional and sectoral wedges indicate that there is a large untapped potential in environmental policies and lifestyle changes that can complement the technological transition towards a low-emitting society.

Data-Driven Predictive Control for Linear Parameter-Varying Systems

Based on the extension of the behavioral theory and the Fundamental Lemma for Linear Parameter-Varying (LPV) systems, this paper introduces a Data-driven Predictive Control (DPC) scheme capable to ensure reference tracking and satisfaction of Input-Output (IO) constraints for an unknown system under the conditions that (i) the system can be represented in an LPV form and (ii) an informative data-set containing measured IO and scheduling trajectories of the system is available. It is shown that if the data set satisfies a persistence of excitation condition, then a data-driven LPV predictor of future trajectories of the system can be constructed from the IO data set and online measured data. The approach represents the first step towards a DPC solution for nonlinear and time-varying systems due to the potential of the LPV framework to represent them. Two illustrative examples, including reference tracking control of a nonlinear system, are provided to demonstrate that the data-based LPV-DPC scheme, achieves similar performance as LPV model-based predictive control.

CGE modeling with disaggregated pollution treatment sectors for assessing China's environmental tax policies

This research involved constructing a computable general equilibrium (CGE) model for assessing China's latest environmental tax policies. Most environmental CGE models link pollutant emissions to the standard CGE model only by pollution coefficients per unit of sectoral output, and the emission reduction process is not included within production structures. We constructed separate pollution treatment sectors for solid waste management, wastewater management, and waste gas management to describe the pollution treatment processes and identify how policies affect production activities. We compiled the satellite accounts of 18 pollutants from the China Environmentally Extended Input-Output (CEEIO) dataset covering primary gas, water, and solid pollutants and disaggregated the electricity sector into six different production technologies: hydroelectricity, coal power, gas electricity, oil electricity, nuclear power, and renewable energies. We drew two primary conclusions from the simulation results. First, the environmental policies examined could help reduce the emissions of most kinds of pollutants, but also negatively affect GDP. GDP loss by 2030 would be 0.03% in the low environmental tax scenario (LowET), 0.06% in the high environmental tax scenario (HighET), 0.16% in the low environmental tax and low carbon tax scenario (LowETC), and 0.34% in the high environmental tax and high carbon tax scenario (HighETC). SO2 emissions would decrease by 17.4%, 21.0%, 19.3% and 24.5%, respectively, and CO2 emissions would reduce by 0.9%, 1.7%, 5.8% and 11.0%. Second, despite the minor changes in the economic impacts, the effectiveness in pollution treatment of environmental tax policies is underestimated if the pollution treatment sectors are disaggregated in the CGE model. Take the SO2 for an example. The calculated SO2 reductions will increase from 8.95% to 24.46% after disaggregating the pollution treatment sectors in HighETC scenarios.

Predicting thrust of aircraft using artificial neural networks

PurposeThe purpose of this study is to make artificial neural network (ANN)-based prediction about thrust using the flight control parameters of aircrafts.Design/methodology/approachIn today’s transportation, airplanes have an important place because of their safety, quality and speed. One of the most important parameters affecting the secure flying of aircrafts is the thrust value of aircraft engines. Determining the optimum thrust value should be investigated. If thrust value is less than optimum level, the flight safety runs a risk. Otherwise, fuel consumption goes high and some unwanted vibrations occur that cause uncomfortable flight. In this study, multi-layer perceptron ANNs, which are one of the intelligent optimization methods and frequently used in the literature, are preferred to predict the optimum thrust value during take-off, cruise and landing. The actual flight data, which is taken from the black box of an Airbus A319 aircraft, is used to train ANN models using back propagation algorithms. Velocity, altitude and ambient temperature values of the aircraft are selected as inputs and the thrust value is selected as output. During the training process of ANN, eight different training algorithms with different structures are used to figure out optimum ANN model with minimum error.FindingsDifferent ANN models were trained using eight different training algorithms. The ANN model with minimum error has multi-layer perceptron structure, which is trained using Levenberg–Marquardt (LM) algorithm.Research limitations/implicationsTo obtain the ANN structure with minimum error training, process takes more than a day depending on the capacity of a computer for LM training algorithm. But after training process, the trained ANN model produces sufficient output in a few milliseconds.Practical implicationsTotally 15,670 input-output data sets are obtained from an Airbus A319 aircraft. 12,889 of them are used as training data and the rest of the data sets, selected randomly are used as test data. Test data sets are never used in training phase, and the obtained results show that the ANN model successfully predicts thrust value using unseen input data.Social implicationsThe ANN could be used as an alternative method to predict other flight control parameters of aircrafts.Originality/valueTo the best of authors’ knowledge, this study is the first example in literature to predict the thrust value of the aircraft using ANN.

Fragility of a multilayer network of intranational supply chains

Supply chains enable the flow of goods and services within economic systems. When mapped for the entire economy and geographic locations of a country, supply chains form a spatial web of interactions among suppliers and buyers. One way to characterize supply chains is through multiregional input-output linkages. Using a multiregional input-output dataset, we build the multilayer network of supply chains in the United States. Together with a network cascade model, the multilayer network is used to explore the propagation of economic shocks along intranational supply chains. We find that the effect of economic shocks, measured using the avalanche size or total number of collapsed nodes, varies widely depending on the geographic location and economic sector of origin of a shock. The response of the supply chains to shocks reveals a threshold-like behavior. Below a certain failure or fragility level, the avalanche size increases relatively quickly for any node in the network. Based on this result, we find that the most fragile regions tend to be located in the central United States, which are regions that tend to specialize in food production and manufacturing. The most fragile layers are chemical and pharmaceutical products, services and food-related products, which are all sectors that have been disrupted by the Coronavirus Disease 2019 (COVID-19) pandemic in the United States. The fragility risk, measured by the intersection of the fragility level of a node and its exposure to shocks, varies across regions and sectors. This suggests that interventions aiming to make the supply-chain network more robust to shocks are likely needed at multiple levels of network aggregation.

Neural-fuzzy controller configuration design for an electro-optical line of sight stabilization system

This paper presents a Neural-fuzzy model structure to improve the disturbance attenuation performance of a gimballed Line of Sight (LOS) stabilization system. Initially, a Fuzzy Logic Controller (FLC) based on prior qualitative information about system dynamics and linguistic performance criteria is developed. Next, proposed Neural-fuzzy model architecture is constructed, which overcome the difficulties and limitations of each isolated methodology. The Neural-fuzzy architecture is developed based on input-output data-sets available from FLC. Fuzzy curve approach is used to determine significant inputs, number of rules, initialization of connecting layers weights, and hence the model structure. Both the controller configurations are tested based on critical performance characteristics such as stability of the loop, responsiveness of the loop and insensitivity to disturbances. Finally, the comparative analysis suggests that the proposed Neural-fuzzy controller completely outperforms the FLC configuration and hence, can be very effective for more precise pointing applications.

Estimation of Small Unmanned Aerial Vehicle Lateral Dynamic Model with System Identification Approaches

Modeling of unmanned aerial vehicle (UAV) with system identification is very important in terms of its model-based effective control. The modeling of UAV is required for aircraft crashes, analyzing autonomous aircrafts, preventing external disturbances, pre-flight analysis. However, since UAV has nonlinear inherent dynamics including inherent chaoticity and fractality, it becomes difficult to obtain a mathematical model under external disturbance. In this study, some of the inherent nonlinear dynamics of UAV are linearized and the model of UAV is obtained by system identification approaches under external disturbance. The linearized lateral dynamics of a fixed wing UAV is used in this study. Further, the flight motion equations applied to fixed wing UAV have been utilized for obtaining the coefficients of lateral model for straight and level flight. The roll angles are calculated using transfer functions for aileron, rudder and deflections inputs. The autoregressive exogenous (ARX), autoregressive moving average with exogenous (ARMAX) and output error (OE) parametric system identification approaches are performed to estimate UAV lateral dynamic system response as using empirical input-output data sets. The accuracy of parametric model estimation and model degrees are compared for different external disturbance effects.

Physics-guided convolutional neural network (PhyCNN) for data-driven seismic response modeling

Accurate prediction of building’s response subjected to earthquakes makes possible to evaluate building performance. To this end, we leverage the recent advances in deep learning and develop a physics-guided convolutional neural network (PhyCNN) for data-driven structural seismic response modeling. The concept is to train a deep PhyCNN model based on limited seismic input–output datasets (e.g., from simulation or sensing) and physics constraints, and thus establish a surrogate model for structural response prediction. Available physics (e.g., the law of dynamics) can provide constraints to the network outputs, alleviate overfitting issues, reduce the need of big training datasets, and thus improve the robustness of the trained model for more reliable prediction. The surrogate model is then utilized for fragility analysis given certain limit state criteria. In addition, an unsupervised learning algorithm based on K-means clustering is also proposed to partition the datasets to training, validation and prediction categories, so as to maximize the use of limited datasets. The performance of PhyCNN is demonstrated through both numerical and experimental examples. Convincing results illustrate that PhyCNN is capable of accurately predicting building’s seismic response in a data-driven fashion without the need of a physics-based analytical/numerical model. The PhyCNN paradigm also outperforms non-physics-guided neural networks.

Estimating domestic content in China’s exports: Accounting for a dual-trade regime

This paper identifies the heterogeneity issue as a key challenge that is central to but not fully addressed when measuring global value chains. To resolve this issue, we propose an extended input-output model that is consistent with the theoretical framework of heterogeneous firms. Empirically, we use China as a prominent example of a country that is engaged in both normal trade and the processing trade under a dual-trade regime, and we synthesize methods for constructing China’s extended input-output dataset for the period 1997 to 2015. Our results show that when alternative generic datasets are used, this is likely to result in overestimating the domestic content in China’s exports by as much as 44%, compared to a model that uses an extended database that incorporates production heterogeneity, as does the one in this study. This paper’s proposed methodology and rich dataset may be useful to a wider range of empirical applications.

Rising Protectionism and Global Value Chains: Quantifying the General Equilibrium Effects

Quantifying the effects of trade policy in the age of 'global value chains' (GVCs) requires an enhanced analytical framework that takes the observed international input-output relations in due account. However, existing quantitative general equilibrium models generally assume that industry-level bilateral final and intermediate trade shares are identical, and that the allocation of imported inputs across sectors is the same as the allocation of domestic inputs. This amounts to applying two proportionality assumptions, one at the border to split final goods and inputs, and another behind the border to allocate inputs across industries. In practice, neither assumption holds in available input-output data sets. To overcome this limitation of existing models, we consider a richer input-output structure across countries and sectors that we can match with the actual structure reported in input-output tables. This allows us to investigate the relation between the effects of changes in trade policies and GVCs. When we apply the enhanced quantitative general equilibrium model to the assessment of the effects of Brexit, we find trade and welfare losses that are substantially larger than those obtained by previous models. This is due to the close integration of UK-EU production networks and implies that denser GVCs amplify the adverse effects of protectionist trade policies.

Rising Protectionism and Global Value Chains: Quantifying the General Equilibrium Effects

Quantifying the effects of trade policy in the age of ’global value chains’ (GVCs) requires an enhanced analytical framework that takes the observed international input-output relations in due account. However, existing quantitative general equilibrium models generally assume that industrylevel bilateral final and intermediate trade shares are identical, and that the allocation of imported inputs across sectors is the same as the allocation of domestic inputs. This amounts to applying two proportionality assumptions, one at the border to split final goods and inputs, and another behind the border to allocate inputs across industries. In practice, neither assumption holds in available inputoutput data sets. To overcome this limitation of existing models, we consider a richer input-output structure across countries and sectors that we can match with the actual structure reported in inputoutput tables. This allows us to investigate the relation between the effects of changes in trade policies and GVCs. When we apply the enhanced quantitative general equilibrium model to the assessment of the effects of Brexit, we find trade and welfare losses that are substantially larger than those obtained by previous models. This is due to the close integration of UK-EU production networks and implies that denser GVCs amplify the adverse effects of protectionist trade policies.

Modelling and Simulation of a Fuzzy System for Site-Specific Nitrogen Fertilization

Increasing environmental concerns are a driving force in the search for ways to improve the efficiency of mineral nitrogen (N) fertilization. Spectral sensors to determine the crop’s supply status are among the most mature precision agriculture technologies to adapt the N dose site-specifically to the crop’s need. By using artificial intelligence techniques like expert systems based on fuzzy set theory, the algorithms of such sensor systems could be adapted by the farmer to the highly varying conditions among the specific fertilization dates. This paper is dealing with the development of a fuzzy logic based model of the commercial Yara N-Sensor’s dosing algorithms. Simulations for several sets of input-output data acquired in field experiments showed high accordance with the behaviour of the N-Sensor system with good adaptability to different calibrations.

The Role of Global Production Networks in Indonesian Exports

This study looks into Indonesia’s participation in fragmented structures within the Global Value Chain. By using a global input-output dataset and splitting gross exports into distinctive elements of value-added, the study measures vertical specialization of Indonesia against its four largest trading partners (NAFTA, East Asia, European Union and ASEAN) covering 29 countries for three periods: 1997, 2004 and 2012. Value-added is computed according to the initial source country and in the last destination. The paper also compares Indonesia to its ASEAN partners. The results show that Indonesia moved from exporting 50% of its value-added through finished products in 1997 to being a supplier of intermediates goods in 2012 (nearly 60% of its value-added). Foreign inputs in Indonesian exports account for 12%, a lower share versus ASEAN regional partners (35%) who are more vertically integrated. A total of 21% of Indonesian goods will be further exported to third countries. The degree of vertical integration in Indonesia in 2012 is 32.3%, up from 26% in 1997. Indonesia advanced in integration with East Asia and ASEAN countries (region), while it lowered its share of value-added traded with the North America and the Europe. Indonesia gained more than any other ASEAN partner in intra-regional trade