An enhanced design for a solar still desalination system which has been proposed in the previously conducted study of the research team is considered here, and the experimental data obtained during a ...year are employed to develop ANN models for that. Different types of artificial neural network (ANN), as one of the most popular machine learning approaches, are developed and compared together to find the best of them to predict the hourly produced distillate and water temperature in the basin, which are two key performance criteria of the system. Feedforward (FF), backpropagation (BP), and radial basis function (RBF) types of ANN are examined. According to the results, by having the coefficients of determination of 0.963111 and 0.977057, FF and RBF types are the best ANN structures for estimation of the hourly water production and water temperature in the basin, respectively. In addition, the annual error analysis done for the data not used to develop ANN models demonstrates that the average error in prediction of the hourly distillate production and water temperature in the basin varies from 9.03 and 5.13% in January (the highest values) to 4.06 and 2.07% in July (the lowest values), respectively. Moreover, the error for prediction of the daily water production is in the range of 2.41 to 5.84% in the year.
Memristive systems offer biomimetic functions that are being actively explored for energy‐efficient neuromorphic circuits. In addition to providing ultimate geometric scaling limits, 2D ...semiconductors enable unique gate‐tunable responses including the recent realization of hybrid memristor and transistor devices known as memtransistors. In particular, monolayer MoS2 memtransistors exhibit nonvolatile memristive switching where the resistance of each state is modulated by a gate terminal. Here, further control over the memtransistor neuromorphic response through the introduction of a second gate terminal is gained. The resulting dual‐gated memtransistors allow tunability over the learning rate for non‐Hebbian training where the long‐term potentiation and depression synaptic behavior is dictated by gate biases during the reading and writing processes. Furthermore, the electrostatic control provided by dual gates provides a compact solution to the sneak current problem in traditional memristor crossbar arrays. In this manner, dual gating facilitates the full utilization and integration of memtransistor functionality in highly scaled crossbar circuits. Furthermore, the tunability of long‐term potentiation yields improved linearity and symmetry of weight update rules that are utilized in simulated artificial neural networks to achieve a 94% recognition rate of hand‐written digits.
Dual‐gated MoS2 memtransistors enable artificial synapses in a novel crossbar architecture where one gate achieves tunable learning rates and the second gate overcomes the sneak current issue that plagues conventional memristor crossbar arrays. The linear and symmetric synaptic response of dual‐gated MoS2 memtransistors is used to demonstrate efficient training of an artificial neural network for potential hardware implementation.
Studying the dynamic viscosity (DV) is a key factor to determine the nanofluids’ hydrodynamic behavior (NFs). In this research, the effect of volume fraction (φ), shear rate (SR), and temperature (T) ...on the DV, and torque of SiO2 nanoparticles (NPs)/ Ethylene glycol (EG) nanofluid (NF) are studied with an artificial neural network (ANN). Different machine learning (ML) models are examined to predict the rheological properties, and then the best model is selected for prediction. The results show that the torque mostly increased linearly with the SR in all samples. The slope of this enhancing trend is higher for lower T. The Gaussian Process Regression (GPR) models with the Matérn covariance function provided the best results on both datasets to predict the DV. The correlation results provided by this method to predict the DV in terms of Pearson’s Linear Correlation Coefficient (PLCC), and Spearman’s Rank Order Correlation Coefficient (SROCC) were 0.999 and 1, respectively. R squared (R2) was 0.996 and, the Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) values of about 0.24 and 1.61 represented the accuracy and power of this method to predict the DV values unseen data by the model. The GPR torque predictor model performed very well by providing a correlation of about 0.98 and an RMSE of about 4. Matérn covariance functions that used separate length scales per predictor with ν=3/2 (ardmatern 32) and ν=5/2 (ardmatern52) were superior to other functions. All 100 models trained on each dataset were well-trained and quite reliable. The trained models were accurate enough to be used in related applications.
Haloketones (HKs) is one class of disinfection by-products (DBPs) which is genetically toxic and mutagenic. Monitoring HKs in drinking water is important for drinking water safety, yet it is a ...time-consuming and laborious job. Developing predictive models of HKs to estimate their occurrence in drinking water is a good alternative, but to date no study was available for HKs modeling. This study was to explore the feasibility of linear, log linear regression models, back propagation (BP) as well as radial basis function (RBF) artificial neural networks (ANNs) for predicting HKs occurrence (including dichloropropanone, trichloropropanone and total HKs) in real water supply systems. Results showed that the overall prediction ability of RBF and BP ANNs was better than linear/log linear models. Though the BP ANN showed excellent prediction performance in internal validation (N25 = 98–100%, R2 = 0.99–1.00), it could not well predict HKs occurrence in external validation (N25 = 62–69%, R2 = 0.202–0.848). Prediction ability of RBF ANN in external validation (N25 = 85%, R2 = 0.692–0.909) was quite good, which was comparable to that in internal validation (N25 = 74–88%, R2 = 0.799–0.870). These results demonstrated RBF ANN could well recognized the complex nonlinear relationship between HKs occurrence and the related water quality, and paved a new way for HKs prediction and monitoring in practice.
Display omitted
•Linear/log linear regression models cannot well predict haloketones (HKs) levels.•Back propagation (BP) is good to predict HKs in internal but bad in external validation.•Radial basis function artificial neural network (RBF ANN) well predicts HKs levels.•RBF ANN can well recognize complex relationships between HKs and water quality.
Short-term traffic flow prediction plays a key role of Intelligent Transportation System (ITS), which supports traffic planning, traffic management and control, roadway safety evaluation, energy ...consumption estimation, etc. The widely deployed traffic sensors provide us numerous and continuous traffic flow data, which may contain outlier samples due to expected sensor failures. The primary objective of the study was to evaluate the use of various smoothing models for cleaning anomaly in traffic flow data, which were further processed to predict short term traffic flow evolution with artificial neural network. The wavelet filter, moving average model, and Butterworth filter were carefully tested to smooth the collected loop detector data. Then, the artificial neural network was introduced to predict traffic flow at different time spans, which were quantitatively analyzed with commonly-used evaluation metrics. The findings of the study provide us efficient and accurate denoising approaches for short term traffic flow prediction.
Ever-changing variables in the electricity market require energy management systems (EMSs) to make optimal real-time decisions adaptively. Demand response (DR) is the latest approach being used to ...accelerate the efficiency and stability of power systems. This paper proposes an hour-ahead DR algorithm for home EMSs. To deal with the uncertainty in future prices, a steady price prediction model based on artificial neural network is presented. In cooperation with forecasted future prices, multi-agent reinforcement learning is adopted to make optimal decisions for different home appliances in a decentralized manner. To verify the performance of the proposed energy management scheme, simulations are conducted with non-shiftable, shiftable, and controllable loads. Experimental results demonstrate that the proposed DR algorithm can handle energy management for multiple appliances, minimize user energy bills, and dissatisfaction costs, and help the user to significantly reduce its electricity cost compared with a benchmark without DR.
This paper proposes the use of an artificial neural network (ANN) for solving one of the ongoing research challenges in finite set-model predictive control (FS-MPC) of power electronics converters, ...i.e., the automated selection of weighting factors in cost function. The first step in this approach is to simulate a detailed converter circuit model or run experiments numerous times using different weighting factor combinations. The key performance metrics e.g., average switching frequency (<inline-formula><tex-math notation="LaTeX">f_{{\rm sw}}</tex-math></inline-formula>) of the converter, total harmonic distortion, etc. are extracted from each simulation. This data is then used to train the ANN, which serves as a surrogate model of the converter that can provide fast and accurate estimates of the performance metrics for any weighting factor combination. Consequently, any arbitrary user-defined fitness function that combines the output metrics can be defined and the weighting factor combinations that optimize the given function can be explicitly found. The proposed methodology was verified on a practical weighting factor design problem in FS-MPC regulated voltage source converter for uninterruptible power supply system. Designed weighting factors for two exemplary fitness functions turned out to be robust to load variations and to yield close to expected performance when applied both to detailed simulation model (less than 3% error) and to experimental test bed (less than 10% error).
Bipolar DC microgrid (MG) based on two voltage levels with three wires has higher reliability and flexibility than unipolar DC MG. However, the voltages of bipolar buses are coupled and the voltage ...of the PN bus affects the voltages of the bipolar buses in bipolar DC MG. In this paper, a hierarchical control with voltage balancing and energy management based on the characteristics of bipolar DC MG is proposed. To perform distributed power sharing with coupled voltages, droop-based primary controls for three buses and the coupling relationships between three buses are analyzed. Furthermore, in secondary control, balancing and voltage restoration controls are proposed to compensate for voltage drops caused by the balanced and unbalanced loads. To design the proposed hierarchical control, the stability analysis is performed. Additionally, a tertiary control based on an artificial neural network (ANN) is proposed for state-of-charge (SoC) management of bipolar DC MG. Experimental results of the proposed hierarchical control are verified by a lab-scale bipolar DC MG and performance analysis is performed with experimental and ideal results.
This paper presents an investigation on the thermal conductivity of nanofluids using experimental data, neural networks, and correlation for modeling thermal conductivity. The thermal conductivity of ...Mg(OH)2 nanoparticles with mean diameter of 10nm dispersed in ethylene glycol was determined by using a KD2-pro thermal analyzer. Based on the experimental data at different solid volume fractions and temperatures, an experimental correlation is proposed in terms of volume fraction and temperature. Then, the model of relative thermal conductivity as a function of volume fraction and temperature was developed via neural network based on the measured data. A network with two hidden layers and 5 neurons in each layer has the lowest error and highest fitting coefficient. By comparing the performance of the neural network model and the correlation derived from empirical data, it was revealed that the neural network can more accurately predict the Mg(OH)2–EG nanofluids' thermal conductivity.