Hybrid model for BOF oxygen blowing time prediction based on oxygen balance mechanism and deep neural network

The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based on oxygen balance mechanism (OBM) and deep neural network (DNN) was established for predicting oxygen blowing time in converter. A three-step method was utilized in the hybrid model. First, the oxygen consumption volume was predicted by the OBM model and DNN model, respectively. Second, a more accurate oxygen consumption volume was obtained by integrating the OBM model and DNN model. Finally, the converter oxygen blowing time was calculated according to the oxygen consumption volume and the oxygen supply intensity of each heat. The proposed hybrid model was verified using the actual data collected from an integrated steel plant in China, and compared with multiple linear regression model, OBM model, and neural network model including extreme learning machine, back propagation neural network, and DNN. The test results indicate that the hybrid model with a network structure of 3 hidden layer layers, 32-16-8 neurons per hidden layer, and 0.1 learning rate has the best prediction accuracy and stronger generalization ability compared with other models. The predicted hit ratio of oxygen consumption volume within the error±300 m^(3)is 96.67%;determination coefficient (R^(2)) and root mean square error (RMSE) are0.6984 and 150.03 m^(3), respectively. The oxygen blow time prediction hit ratio within the error±0.6 min is 89.50%;R2and RMSE are0.9486 and 0.3592 min, respectively. As a result, the proposed model can effectively predict the oxygen consumption volume and oxygen blowing time in the converter.

Activation Redistribution Based Hybrid Asymmetric Quantization Method of Neural Networks

The demand for adopting neural networks in resource-constrained embedded devices is continuously increasing.Quantization is one of the most promising solutions to reduce computational cost and memory storage on embedded devices.In order to reduce the complexity and overhead of deploying neural networks on Integeronly hardware,most current quantization methods use a symmetric quantization mapping strategy to quantize a floating-point neural network into an integer network.However,although symmetric quantization has the advantage of easier implementation,it is sub-optimal for cases where the range could be skewed and not symmetric.This often comes at the cost of lower accuracy.This paper proposed an activation redistribution-based hybrid asymmetric quantizationmethod for neural networks.The proposedmethod takes data distribution into consideration and can resolve the contradiction between the quantization accuracy and the ease of implementation,balance the trade-off between clipping range and quantization resolution,and thus improve the accuracy of the quantized neural network.The experimental results indicate that the accuracy of the proposed method is 2.02%and 5.52%higher than the traditional symmetric quantization method for classification and detection tasks,respectively.The proposed method paves the way for computationally intensive neural network models to be deployed on devices with limited computing resources.Codes will be available on https://github.com/ycjcy/Hybrid-Asymmetric-Quantization.

Simultaneous Identification of Thermophysical Properties of Semitransparent Media Using a Hybrid Model Based on Artificial Neural Network and Evolutionary Algorithm

A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductivity and effective absorption coefficient of semitransparent materials.For the direct model,the spherical harmonic method and the finite volume method are used to solve the coupled conduction-radiation heat transfer problem in an absorbing,emitting,and non-scattering 2D axisymmetric gray medium in the background of laser flash method.For the identification part,firstly,the temperature field and the incident radiation field in different positions are chosen as observables.Then,a traditional identification model based on PSO algorithm is established.Finally,multilayer ANNs are built to fit and replace the direct model in the traditional identification model to speed up the identification process.The results show that compared with the traditional identification model,the time cost of the hybrid identification model is reduced by about 1 000 times.Besides,the hybrid identification model remains a high level of accuracy even with measurement errors.

Design of a novel hybrid quantum deep neural network in INEQR images classification

We redesign the parameterized quantum circuit in the quantum deep neural network, construct a three-layer structure as the hidden layer, and then use classical optimization algorithms to train the parameterized quantum circuit, thereby propose a novel hybrid quantum deep neural network(HQDNN) used for image classification. After bilinear interpolation reduces the original image to a suitable size, an improved novel enhanced quantum representation(INEQR) is used to encode it into quantum states as the input of the HQDNN. Multi-layer parameterized quantum circuits are used as the main structure to implement feature extraction and classification. The output results of parameterized quantum circuits are converted into classical data through quantum measurements and then optimized on a classical computer. To verify the performance of the HQDNN, we conduct binary classification and three classification experiments on the MNIST(Modified National Institute of Standards and Technology) data set. In the first binary classification, the accuracy of 0 and 4 exceeds98%. Then we compare the performance of three classification with other algorithms, the results on two datasets show that the classification accuracy is higher than that of quantum deep neural network and general quantum convolutional neural network.

Analysis of learnability of a novel hybrid quantum-classical convolutional neural network in image classification

We design a new hybrid quantum-classical convolutional neural network(HQCCNN)model based on parameter quantum circuits.In this model,we use parameterized quantum circuits(PQCs)to redesign the convolutional layer in classical convolutional neural networks,forming a new quantum convolutional layer to achieve unitary transformation of quantum states,enabling the model to more accurately extract hidden information from images.At the same time,we combine the classical fully connected layer with PQCs to form a new hybrid quantum-classical fully connected layer to further improve the accuracy of classification.Finally,we use the MNIST dataset to test the potential of the HQCCNN.The results indicate that the HQCCNN has good performance in solving classification problems.In binary classification tasks,the classification accuracy of numbers 5 and 7 is as high as 99.71%.In multivariate classification,the accuracy rate also reaches 98.51%.Finally,we compare the performance of the HQCCNN with other models and find that the HQCCNN has better classification performance and convergence speed.

HQNN-SFOP:Hybrid Quantum Neural Networks with Signal Feature Overlay Projection for Drone Detection Using Radar Return Signals-A Simulation

With the wide application of drone technology,there is an increasing demand for the detection of radar return signals from drones.Existing detection methods mainly rely on time-frequency domain feature extraction and classical machine learning algorithms for image recognition.This method suffers from the problem of large dimensionality of image features,which leads to large input data size and noise affecting learning.Therefore,this paper proposes to extract signal time-domain statistical features for radar return signals from drones and reduce the feature dimension from 512×4 to 16 dimensions.However,the downscaled feature data makes the accuracy of traditional machine learning algorithms decrease,so we propose a new hybrid quantum neural network with signal feature overlay projection(HQNN-SFOP),which reduces the dimensionality of the signal by extracting the statistical features in the time domain of the signal,introduces the signal feature overlay projection to enhance the expression ability of quantum computation on the signal features,and introduces the quantum circuits to improve the neural network’s ability to obtain the inline relationship of features,thus improving the accuracy and migration generalization ability of drone detection.In order to validate the effectiveness of the proposed method,we experimented with the method using the MM model that combines the real parameters of five commercial drones and random drones parameters to generate data to simulate a realistic environment.The results show that the method based on statistical features in the time domain of the signal is able to extract features at smaller scales and obtain higher accuracy on a dataset with an SNR of 10 dB.On the time-domain feature data set,HQNNSFOP obtains the highest accuracy compared to other conventional methods.In addition,HQNN-SFOP has good migration generalization ability on five commercial drones and random drones data at different SNR conditions.Our method verifies the feasibility and effectiveness of signal detection methods based on quantum computation and experimentally demonstrates that the advantages of quantum computation for information processing are still valid in the field of signal processing,it provides a highly efficient method for the drone detection using radar return signals.

Gated Neural Network-Based Unsteady Aerodynamic Modeling for Large Angles of Attack

Modeling of unsteady aerodynamic loads at high angles of attack using a small amount of experimental or simulation data to construct predictive models for unknown states can greatly improve the efficiency of aircraft unsteady aerodynamic design and flight dynamics analysis.In this paper,aiming at the problems of poor generalization of traditional aerodynamic models and intelligent models,an intelligent aerodynamic modeling method based on gated neural units is proposed.The time memory characteristics of the gated neural unit is fully utilized,thus the nonlinear flow field characterization ability of the learning and training process is enhanced,and the generalization ability of the whole prediction model is improved.The prediction and verification of the model are carried out under the maneuvering flight condition of NACA0015 airfoil.The results show that the model has good adaptability.In the interpolation prediction,the maximum prediction error of the lift and drag coefficients and the moment coefficient does not exceed 10%,which can basically represent the variation characteristics of the entire flow field.In the construction of extrapolation models,the training model based on the strong nonlinear data has good accuracy for weak nonlinear prediction.Furthermore,the error is larger,even exceeding 20%,which indicates that the extrapolation and generalization capabilities need to be further optimized by integrating physical models.Compared with the conventional state space equation model,the proposed method can improve the extrapolation accuracy and efficiency by 78%and 60%,respectively,which demonstrates the applied potential of this method in aerodynamic modeling.

Data-Driven Modeling for Wind Turbine Blade Loads Based on Deep Neural Network

Blades are essential components of wind turbines.Reducing their fatigue loads during operation helps to extend their lifespan,but it is difficult to quickly and accurately calculate the fatigue loads of blades.To solve this problem,this paper innovatively designs a data-driven blade load modeling method based on a deep learning framework through mechanism analysis,feature selection,and model construction.In the mechanism analysis part,the generation mechanism of blade loads and the load theoretical calculationmethod based on material damage theory are analyzed,and four measurable operating state parameters related to blade loads are screened;in the feature extraction part,15 characteristic indicators of each screened parameter are extracted in the time and frequency domain,and feature selection is completed through correlation analysis with blade loads to determine the input parameters of data-driven modeling;in the model construction part,a deep neural network based on feedforward and feedback propagation is designed to construct the nonlinear coupling relationship between the unit operating parameter characteristics and blade loads.The results show that the proposed method mines the wind turbine operating state characteristics highly correlated with the blade load,such as the standard deviation of wind speed.The model built using these characteristics has reasonable calculation and fitting capabilities for the blade load and shows a better fitting level for untrained out-of-sample data than the traditional scheme.Based on the mean absolute percentage error calculation,the modeling accuracy of the two blade loads can reach more than 90%and 80%,respectively,providing a good foundation for the subsequent optimization control to suppress the blade load.

Dynamics Modeling and Robust Trajectory Tracking Control for a Class of Hybrid Humanoid Arm Based on Neural Network

In order to solve the problem of trajectory tracking for a class of novel serial-parallel hybrid humanoid arm（HHA）, which has parameters uncertainty, frictions, disturbance, abrasion and pulse forces derived from motors, a multistep dynamics modeling strategy is proposed and a robust controller based on neural network（NN）-adaptive algorithm is designed. At the first step of dynamics modeling, the dynamics model of the reduced HHA is established by Lagrange method. At the second step of dynamics modeling, the parameter uncertain part resulting mainly from the idealization of the HHA is learned by adaptive algorithm. In the trajectory tracking controller, the radial basis function（RBF） NN, whose optimal weights are learned online by adaptive algorithm, is used to learn the upper limit function of the total uncertainties including frictions, disturbances, abrasion and pulse forces. To a great extent, the conservatism of this robust trajectory tracking controller is reduced, and by this controller the HHA can impersonate mostly human actions. The proof and simulation results testify the validity of the adaptive strategy for parameter learning and the neural network-adaptive strategy for the trajectory tracking control.

Modeling and linearizing broad-band power amplifier based on real and complex-valued hybrid time-delay neural network

A new real and complex-valued hybrid time-delay neural network(TDNN)is proposed for modeling and linearizing the broad-band power amplifier(BPA).The neural network includes the generalized memory effect of input signals,complex-valued input signals and the fractional order of a complex-valued input signal module,and,thus,the modeling accuracy is improved significantly.A comparative study of the normalized mean square error(NMSE)of the real and complex-valued hybrid TDNN for different spread constants,memory depths,node numbers,and order numbers is studied so as to establish an optimal TDNN as an effective baseband model,suitable for modeling strong nonlinearity of the BPA.A 51-dBm BPA with a 25-MHz bandwidth mixed test signal is used to verify the effectiveness of the proposed model.Compared with the memory polynomial(MP)model and the real-valued TDNN,the real and complex-valued hybrid TDNN is highly effective,leading to an improvement of 5 dB in the NMSE.In addition,the real and complex-valued hybrid TDNN has an improvement of 0.6 dB over the generalized MP model in the NMSE.Also,it has better numerical stability.Moreover,the proposed TDNN presents a significant improvement over the real-valued TDNN and the MP models in suppressing out-of-band spectral regrowth.

Modeling of temperature-humidity for wood drying based on time-delay neural network

The temperature-humidity models of wood drying were developed based on Time-delay neural network and the identification structures of Time-delay neural network were given. The controlling model and the schedule model, which revealed the relation between controlling signal and temperature-humidity and the relation between wood moisture content and temperature-humidity of wood drying, were separately presented. The models were simulated by using the measured data of the experimental drying kiln. The numerical simulation results showed that the modeling method was feasible, and the models were effective.

Improved results on synchronization in arrays of coupled delayed neural networks with hybrid coupling

In order to investigate the influence of hybrid coupling on the synchronization of delayed neural networks, by choosing an improved delay-dependent Lyapunov-Krasovskii functional, one less conservative asymptotical criterion based on linear matrix inequality （LMI） is established. The Kronecker product and convex combination techniques are employed. Also the bounds of time-varying delays and delay derivatives are fully considered. By adjusting the inner coupling matrix parameters and using the Matlab LMI toolbox, the design and applications of addressed coupled networks can be realized. Finally, the efficiency and applicability of the proposed results are illustrated by a numerical example with simulations.

Behavioral modeling of RF power amplifiers with time-delay feed-forward neural networks

A novel behavioral model using three-layer time-delay feed-forward neural networks （TDFFNN）is adopted to model radio frequency （RF）power amplifiers exhibiting memory nonlinearities. In order to extract the parameters, the back- propagation algorithm is applied to train the proposed neural networks. The proposed model is verified by the typical odd- order-only memory polynomial model in simulation, and the performance is compared with different numbers of taped delay lines（TDLs） and perceptrons of the hidden layer. For validating the TDFFNN model by experiments, a digital test bench is set up to collect input and output data of power amplifiers at a 60 × 10^6 sample/s sampling rate. The 3.75 MHz 16-QAM signal generated in the vector signal generator（VSG） is chosen as the input signal, when measuring the dynamic AM/AM and AM/PM characteristics of power amplifiers. By comparisons and analyses, the presented model provides a good performance in convergence, accuracy and efficiency, which is approved by simulation results and experimental results in the time domain and frequency domain.

Identification of Hammerstein Model Using Hybrid Neural Networks

The identification problem of Hammerstein model with extension to the multi input multi output (MIMO) case is studied. The proposed identification method uses a hybrid neural network (HNN) which consists of a multi layer feed forward neural network (MFNN) in cascade with a linear neural network (LNN). A unified back propagation (BP) algorithm is proposed to estimate the weights and the biases of the MFNN and the LNN simultaneously. Numerical examples are provided to show the efficiency of the proposed method.

A New Modeling Method Based on Genetic Neural Network for Numeral Eddy Current Sensor

In this paper,we present a method used to the numeral eddy current sensor modeling based on genetic neural network to settle its nonlinear problem.The principle and algorithms of genetic neural network are introduced.In this method, the nonlinear model parameters of the numeral eddy current sensor are optimized by genetic neural network (GNN) according to measurement data.So the method remains both the global searching ability of genetic algorithm and the good local searching ability of neural network.The nonlinear model has the advantages of strong robustness,on-line scaling and high precision.The maximum nonlinearity error can be reduced to 0.037% using GNN.However,the maximum nonlinearity error is 0.075% using least square method (LMS).

A Novel On-Site-Real-Time Method for Identifying Characteristic Parameters Using Ultrasonic Echo Groups and Neural Network

On-site and real-time non-destructive measurement of elastic constants for materials of a component in a in-service structure is a challenge due to structural complexities,such as ambiguous boundary,variable thickness,nonuniform material properties.This work develops for the first time a method that uses ultrasound echo groups and artificial neural network(ANN)for reliable on-site real-time identification of material parameters.The use of echo groups allows the use of lower frequencies,and hence more accommodative to structural complexity.To train the ANNs,a numerical model is established that is capable of computing the waveform of ultrasonic echo groups for any given set of material properties of a given structure.The waveform of an ultrasonic echo groups at an interest location on the surface the structure with material parameters varying in a predefined range are then computed using the numerical model.This results in a set of dataset for training the ANN model.Once the ANN is trained,the material parameters can be identified simultaneously using the actual measured echo waveform as input to the ANN.Intensive tests have been conducted both numerically and experimentally to evaluate the effectiveness and accuracy of the currently proposed method.The results show that the maximum identification error of numerical example is less than 2%,and the maximum identification error of experimental test is less than 7%.Compared with currently prevailing methods and equipment,the proposefy the density and thickness,in addition to the elastic constants.Moreover,the reliability and accuracy of inverse prediction is significantly improved.Thus,it has broad applications and enables real-time field measurements,which has not been fulfilled by any other available methods or equipment.

Customized Convolutional Neural Network for Accurate Detection of Deep Fake Images in Video Collections

The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the CNN.The customized Convolutional Neural Network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its libraries.We used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were real.Ten seconds were allotted for each video.There were 318 videos used in all,199 of which were fake and 119 of which were real.Our proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and MLP-CNN.Furthermore,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and DST-Net.The novelty of this investigation is the development of a new Convolutional Neural Network(CNN)learning model that can accurately detect deep fake face photos.

Modeling of Ship Maneuvering Motion Using Neural Networks

In this paper, Neural Networks （NNs） are used in the modeling of ship maneuvering motion. A nonlinear response model and a linear hydrodynamic model of ship maneuvering motion are also investigated. The maneuverability indices and linear non-dimensional hydrodynamic derivatives in the models are identified by using two-layer feed forward NNs. The stability of parametric estimation is confirmed. Then, the ship maneuvering motion is predicted based on the obtained models. A comparison between the predicted results and the model test results demonstrates the validity of the proposed modeling method.

Hybrid Neural Network Model for RH Vacuum Refining Process Control

A hybrid neural network model,in which RH process(theoretical)model is combined organically with neural network(NN)and case-base reasoning(CBR),was established.The CBR method was used to select the operation mode and the RH operational guide parameters for different steel grades according to the initial conditions of molten steel,and a three-layer BP neural network was adopted to deal with nonlinear factors for improving and compensating the limitations of technological model for RH process control and end-point prediction.It was verified that the hybrid neural network is effective for improving the precision and calculation efficiency of the model.

Anaerobic tapered fluidized bed reactor for starch wastewater treatment and modeling using multilayer perceptron neural network

treatability of synthetic sago wastewater was investigated in a laboratory anaerobic tapered fluidized bed reactor （ATFBR） with a mesoporous granular activated carbon （GAC） as a support material. The experimental protocol was defined to examine the effect of the maximum organic loading rate （OLR）, hydraulic retention time （HRT）, the efficiency of the reactor and to report on its steady- state performance. The reactor was subjected to a steady-state operation over a range of OLR up to 85.44 kg COD/（m^3·d）. The COD removal efficiency was found to be 92% in the reactor while the biogas produced in the digester reached 25.38 m^3/（m^3·d） of the reactor. With the increase of OLR from 83.7 kg COD/（m^3·d）, the COD removal efficiency decreased. Also an artificial neural network （ANN） model using multilayer perceptron （MLP） has been developed for a system of two input variable and five output dependent variables. For the training of the input-output data, the experimental values obtained have been used. The output parameters predicted have been found to be much closer to the corresponding experimental ones and the model was validated for 30% of the untrained data. The mean square error （MSE） was found to be only 0.0146.