In this paper, a comprehensive review of the artificial neural network (ANN) based model predictive control (MPC) system design is carried out followed by a case study in which ANN models of a ...residential house located in Ontario, Canada are developed and calibrated with the data measured from site. A new algorithm called best network after multiple iterations (BNMI) is introduced to help in determining the appropriate ANN architecture. The prediction performance of the developed models using BNMI algorithm was significantly better (between 6% and 59% better goodness of fit for various models) when compared to a previous study carried out by the authors which used the default single iteration ANN training algorithm of MATLAB®. The ANN models were further used to design the supervisory MPC for the residential HVAC system. The MPC generated the dynamic temperature set-point profiles of the zone air and buffer tank water which resulted in the operating cost reduction of the equipment without violating the thermal comfort constraints. When compared to the fixed set-point (FSP), MPC was able to save operating cost between 6% and 73% depending on the season.
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.
This paper aims to review Artificial neural networks, Multi-Layer Perceptron Neural network (MLP) and Convolutional Neural network (CNN) employed to detect breast malignancies for early diagnosis of ...breast cancer based on their accuracy in order to identify which method is better for the diagnosis of breast cell malignancies. Deep comparison of functioning of each network and its designing is performed and then analysis is done based on the accuracy of diagnosis and classification of breast malignancy by the network to decide which network outperforms the other. CNN is found to give slightly higher accuracy than MLP for diagnosis and detection of breast cancer. There still is the need to carefully analyse and perform a thorough research that uses both these methods on the same data set under same conditions in order identify the architecture that gives better accuracy.
A distributed optical fiber torsion sensor assisted by an artificial neural network (ANN) is designed based on the single stress-applying fiber (SSAF)-based Sagnac interferometer and demonstrated ...experimentally. A theoretical model is established to describe the piecewise torsion of the high birefringent fiber in the Sagnac loop, and the ANN algorithm is employed to demodulate the distributed torsion signals. The experimental results demonstrate the ability to simultaneously measure the torsion position and torsion angle when only one position along the fiber is subjected to torsion. The average R 2 and MAE of three predictions of the single torsion position are 0.984 and 0.55 cm, and those of the torsion angle are 0.998 and 1.98° for torsion angles from -120° to +120°. When two positions along the fiber are subjected to torsion, the R 2 and MAE of the torsion angle are 0.96/11.31° and 0.99/2.17° for torsion angles between -120° and +120°. The sensing system is demonstrated to demodulate the torsion of the wrist joint and elbow joint of the human arm. This promising strategy not only achieves the highest torsion position resolution and shortest response time, but also can be used to perform distributed torsion measurement and torsion direction recognition at the same time in addition to measuring the torsion at multiple positions, thereby showing great potential in applications such as robotic arms.
Optoelectronic synaptic devices, which combine the functions of photosensitivity and information processing, are essential for the development of artificial visual perception systems. Nevertheless, ...improving the paired pulse facilitation (PPF) index of optoelectronic synaptic devices, which is an urgent problem in the construction of high‐precision artificial visual perception systems, has received less attention so far. Herein, a light‐stimulated synaptic transistor (LSST) device with an ultra‐high PPF index (≈196%) is presented by introducing an ultra‐thin carrier regulator layer hexagonal boron nitride (h‐BN) into a classic graphene‐based hybrid transistor frame (graphene/CsPbBr3 quantum dots). Crucially, analysis of the rate‐limiting effect of h‐BN on photogenerated carriers reveals the mechanism behind the LSST ultra‐high PPF index. Furthermore, a two‐layer artificial neural network connected by LSST devices demonstrate ≈91.5% recognition accuracy of handwritten digits. This work provides an effective method for constructing artificial visual perception systems using a hybrid transistor frame in the future.
Optoelectronic synaptic devices with high paired pulse facilitation (PPF) index are essential for constructing high‐precision artificial visual perception systems. However, improving the PPF index of optoelectronic synaptic devices has received little attention. In this paper, a light‐stimulated synaptic transistor with an ultra‐high PPF index by introducing hexagonal boron nitride into a classic graphene‐based hybrid transistor framework is proposed.
A mechanics‐informed artificial neural network approach for learning constitutive laws governing complex, nonlinear, elastic materials from strain–stress data is proposed. The approach features a ...robust and accurate method for training a regression‐based model capable of capturing highly nonlinear strain–stress mappings, while preserving some fundamental principles of solid mechanics. In this sense, it is a structure‐preserving approach for constructing a data‐driven model featuring both the form‐agnostic advantage of purely phenomenological data‐driven regressions and the physical soundness of mechanistic models. The proposed methodology enforces desirable mathematical properties on the network architecture to guarantee the satisfaction of physical constraints such as objectivity, consistency (preservation of rigid body modes), dynamic stability, and material stability, which are important for successfully exploiting the resulting model in numerical simulations. Indeed, embedding such notions in a learning approach reduces a model's sensitivity to noise and promotes its robustness to inputs outside the training domain. The merits of the proposed learning approach are highlighted using several finite element analysis examples. Its potential for ensuring the computational tractability of multi‐scale applications is demonstrated with the acceleration of the nonlinear, dynamic, multi‐scale, fluid‐structure simulation of the supersonic inflation dynamics of a parachute system with a canopy made of a woven fabric.
We propose a novel context-dependent (CD) model for large-vocabulary speech recognition (LVSR) that leverages recent advances in using deep belief networks for phone recognition. We describe a ...pre-trained deep neural network hidden Markov model (DNN-HMM) hybrid architecture that trains the DNN to produce a distribution over senones (tied triphone states) as its output. The deep belief network pre-training algorithm is a robust and often helpful way to initialize deep neural networks generatively that can aid in optimization and reduce generalization error. We illustrate the key components of our model, describe the procedure for applying CD-DNN-HMMs to LVSR, and analyze the effects of various modeling choices on performance. Experiments on a challenging business search dataset demonstrate that CD-DNN-HMMs can significantly outperform the conventional context-dependent Gaussian mixture model (GMM)-HMMs, with an absolute sentence accuracy improvement of 5.8% and 9.2% (or relative error reduction of 16.0% and 23.2%) over the CD-GMM-HMMs trained using the minimum phone error rate (MPE) and maximum-likelihood (ML) criteria, respectively.
In order to improve the performance and reliability of the three-phase PWM rectifier in electric vehicle (EV) charging system, it is important to focus on the identification of the DC bus ...capacitance. The existing methods have the disadvantages such as a low identification accuracy, a high hardware dependency, and high costs. Therefore, the development of new identification methodologies could be the way out of the aforementioned disadvantages, in terms of advanced algorithms. In this paper, a DC bus capacitance identification method based on back propagation (BP) artificial neural network (ANN) algorithm is proposed. The capacitance can be accurately identified in the diode rectification stage, by training the neural network to extract the potential laws in the data, which only includes the Phase-a voltage and current, as well as the DC bus voltage ripple. The regression response is 0.99991. Finally, the experimental results show the accuracy and effectiveness of the proposed method. A simple and effective BP ANN is designed, and it can identify the capacitance at different grid voltages and DC bus loads. It has a high identification accuracy that the maximum identification error is less than 4.5%.