Prediction of flow pattern of gas–liquid flow through circular microchannel using probabilistic neural network

In this study the transient analysis of a laminar liquid flow in a three-dimensional microchannel of varying rectangular cross-section was numerically investigated. The imposed heat fluxes on the microchannel upper and bottom wall, the Joule heating due to an applied electric potential at the microchannel inlet and outlet, the electroosmosis, the pressure-driven flow, and the liquid temperature-dependent thermophysical properties were accounted for. The time-dependent liquid flow velocity profile and the time-dependent liquid temperature distribution were obtained respectively solving the Navier-Stokes equations and the energy equations for a laminar incompressible liquid flow using a computational fluid dynamics code. The effects of the microchannel divergence angle and the microchannel dimensions on the liquid flow and the heat transfer in the microchannel were analyzed. Results obtained show significant influences of the pressure difference between the microchannel inlet and outlet, the imposed heat flux, and the microchannel inlet width on the transient and steady states of the liquid flow velocity and the liquid temperature distribution. A comparison of the results of the developed model with those achieved considering the liquid constant thermophysical properties and those obtained from a microchannel of a constant cross-section was made.

Study on the identification of resistance of rice blast based on near infrared spectroscopy

Sentence alignment using P-NNT and GMM

Surrounding rock squeezing deformation is a common and prominent hazard in tunnel engineering projects, which often induces the shield jamming disaster during the TBM tunneling process. Based on the 139 groups of historical squeezing deformation cases, this study developed a hybrid PCA-IWGO-PNN model for squeezing classification. According to the influencing factors and characteristics of squeezing deformation, the strength-stress ratio, tunnel burial depth, tunnel equivalent diameter, rock mass quality index, and support stiffness were selected to establish the prediction index system of squeezing level. Because the probabilistic neural network (PNN) requires that the input variables are independent, principal component analysis (PCA) was used to preprocess the original data to eliminate the correlation between prediction indexes and achieve dimensionality reduction. The spread coefficient was the critical hyper-parameter in the PNN, and the improved gray wolf optimization (IGWO) algorithm was used to realize its efficient automatic optimization. Then, the PNN model was applied to engineering practice. Only 1 of 20 test samples was misjudged, achieving the 95% prediction accuracy. Finally, the comparison analysis with the artificial neural network (ANN) model, support vector machine (SVM) model, and random forest (RF) model was conducted. Among them, the PNN model achieved the highest prediction accuracy, followed by the artificial neural network (85%), RF (85%), and SVM (80%). In addition, the PNN model had the fastest running speed, which only consumed 5.6350 s, while the running time of ANN, SVM, and RF was 8.8340, 6.2290, and 6.9260 s, respectively. The hybrid PCA-IWGO-PNN model developed in this research provides an effective method for surrounding rock squeezing classification, and it has superiorities in both prediction accuracy and running speed.

Simplified techniques based on in situ testing methods are commonly used to assess seismic liquefaction potential. Many of these simplified methods are based on finding the liquefaction boundary separating two categories (the occurrence or non-occurrence of liquefaction) through the analysis of liquefaction case histories. As the liquefaction classification problem is highly nonlinear in nature, it is difficult to develop a comprehensive model taking into account all the independent variables, such as the seismic and soil properties, using conventional modeling techniques. Hence, in many of the conventional methods that have been proposed, simplified assumptions have been made. In this study, a probabilistic neural network (PNN) approach based on the Bayesian classifier method is used to evaluate seismic liquefaction potential based on actual field records. Two separate analyses are performed, one based on cone penetration test data and one based on shear wave velocity data. The PNN model effectively explores the relationship between the independent and dependent variables without any assumptions about the relationship between the various variables. Through the iterative presentation of the data (the learning phase), this study serves to demonstrate that the PNN can "discover" the intrinsic relationship between the seismic and soil parameters and the liquefaction potential. Comparisons indicate that the PNN models perform far better than the conventional methods in predicting the occurrence or non-occurrence of liquefaction.Key words: cone penetration test, neural networks, prediction, probabilistic neural network, sand, seismic liquefaction, shear wave velocity.

In this paper we address the problem of face detection and recognition of grey scale frontal view images. We propose a face recognition system based on probabilistic neural networks (PNN) architecture. The system is implemented using voronoi/ delaunay tessellations and template matching. Images are segmented successfully into homogeneous regions by virtue of voronoi diagram properties. Face verification is achieved using matching scores computed by correlating edge gradients of reference images. The advantage of classification using PNN models is its short training time. The correlation based template matching guarantees good classification results.

The development of computer technology has made intelligence a way to solve problems in many industries. There are some problems in political teaching in colleges and universities, and colleges and universities urgently need to build an ecological political teaching system, and the conceptual neuron network model can be a means of realization. A conceptual neuron network is a branch of artificial intelligence technology that can help the system perform accurate discriminant analysis. This article takes the current situation of ideological and political education in colleges and universities as the research background, and tries to establish an artificial intelligence network research learning platform based on the depth of college political culture. This article introduces the probabilistic neural network, and uses the neural network to build a system that can reflect the defects of school politics teaching and propose solutions to the defects. Finally, it is verified by MATLAB that the artificial intelligence prediction based on the probabilistic neural network has good convergence and fault tolerance. And data processing capabilities. The construction of this system allows universities to clearly observe the parts of political education that need to be strengthened through data, which is conducive to the improvement of political education.

Evaluation of service quality (SQ) based on user preferences has become a primary concern for the transportation authorities. The most significant attributes of public transportation systems are revealed through service quality analysis. This information serves as valuable input in constantly updating the quality of public transportation services. An appropriate tool is therefore mandatory in this regard. This paper represents a comparative study on the bus SQ prediction capabilities of three effective Artificial Neural Network (ANN) approaches, namely: Generalized Regression Neural Network (GRNN), Probabilistic Neural Network (PNN) and Pattern Recognition Neural Network (PRNN). To calibrate the parameters of the developed ANN models, data on users’ perception toward bus services of Dhaka city, Bangladesh, have been used. Taking the public opinion as baseline, GRNN and PNN have proven to be better prediction models since both have achieved higher accuracy compared to PRNN. Among 22 selected SQ attributes, the most significant attributes have been ranked according to their influence on the users’ decision making process. According to the GRNN and PNN models, punctuality and reliability, service frequency, seat availability and commuting experience are found to be the most significant attributes, which support the user-stated preferences.

As the growth of the operating life and the influence of the environment, the hydrophobic of transformer composite insulator bushing will decline and pollution flashover accident happened easily, which can affect the safe operation of lines. This paper using machine vision to monitor the transformer composite insulator bushing surface, first, recognition and preprocessing the images of hydrophobic of composite insulator bushing, then extracting the characteristic value, finally, using probability neural network (PNN) to evaluate the hydrophobic of the transformer composite insulator bushing, after a large number of samples training, PNN model can accurately distinguish the hydrophobic level of bushing composite insulator bushing, which has great significance for monitoring composite insulator reliably.

Two‐dimensional compressible momentum equations were solved by a perturbation analysis and the PISO algorithm to investigate the effects of compressibility and rarefaction on the local flow resistance of isothermal gas flow in circular microchannels. The computations were performed for a wide range of Reynolds numbers and inlet Mach numbers. The explicit expression of the normalized local Fanning friction factor along the microchannel was derived in the present paper. The results reveal that the local Fanning friction factor is a function of the inlet Mach number, the Reynolds number and the length‐diameter ratio of the channel. For larger Reynolds and inlet Mach numbers, the friction coefficient in the microchannel is higher than the value in a macrotube, and the gas flow in the microchannel is dominated only by compressibility. For smaller Reynolds and inlet Mach numbers, the Fanning friction factor of gas flow in the microchannel is lower than that in a circular tube of conventional size due to slip flow at the wall and thus, rarefaction has a significant effect on the fluid flow characteristics in a microchannel.

Microchannel heat sinks with two-phase flow can satisfy the increasing heat removal requirements of modern micro electronic devices. One of the important aspects associated with two- phase flows in microchannels is to study the bubble behavior. However, in the literature most of the reports present data of only a single channel. This does not account for flow mixing and hydrodynamic instability that occurs in parallel microchannels, connected by common inlet and outlet collectors. In the present study, experiments were performed for air- water and steam- water flow in parallel triangular microchannels with a base of 200–300 µ m. The experimental study is based on systematic measurements of temperature and flow pattern by infrared radiometry and high-speed digital video imaging. In air-water flow, different flow patterns were observed simultaneously in the various microchannels at a fixed values of water and gas flow rates. In steam-water flow, instability in uniformly heated microchannels was observed. This work develops a practical modeling approach for two-phase microchannel heat sinks and considers discrepancy between flow patterns of air- water and steam- water flow in microchannels.

The present study records an attempt to train artificial neural networks (ANNs) to develop an objective flow pattern indicator for air–water flows on the basis of the vast amount of data available in the literature. The technique should be capable of predicting the flow patterns as well as the intermediate bands of transition from known input variables such as the superficial velocity of the two phases, the pipe diameter, and its inclination. For this, the study tried three different types of ANN. The most commonly used feed‐forward back‐propagation (FFBP) technique accurately yields the flow patterns but fails when the transition regions are incorporated. The radial basis function network gives better predictions than those by FFBP but fails under certain flow conditions. The probabilistic neural network (PNN), based on Bayes–Parzen classification theory, gives accurate predictions of flow patterns for different pipe diameters and inclinations. It has been validated with both experimental and theoretical models available in the literature. It has next been used to generate generalized flow pattern maps for different pipe diameters and orientations. These maps reveal certain interesting features regarding the existence of flow patterns under different input conditions. PNN predicts the disappearance of the smooth stratified flow with slight inclinations from the horizontal orientation and the existence of churn flow only near the vertical orientation. © 2006 American Institute of Chemical Engineers AIChE J, 2006

Flow regime identification in the subsea jumper based on electrical capacitance tomography and convolution neural network

The vibration signals of rolling bearing are often highly nonstationary and nonlinear, and consequently it is not accurate to extract and identify the characteristics of these signals by the traditional methods. In order to improve the performance on the feature extraction from bearing signals and the accuracy of the diagnosis, it requires effective signal processing and diagnose algorithms. In this paper, a new fault diagnosis algorithm which combines complementary ensemble empirical mode decomposition (CEEMD), probabilistic neural network (PNN) and particle swarm optimization (PSO) algorithm optimized by improved linear decreasing weight (LDW) algorithm is proposed. In this method, firstly the vibration signals are decomposed into a number of Intrinsic Mode Functions (IMFs) by the CEEMD algorithm since it has good adaptive ability to nonstable signals and can effectively extract fault features. Then the improved LDWPSO algorithm is introduced to solve the problem that the selection of smoothing factor in PNN model is arbitrary and uncertain. Finally, train and diagnose the fault types of rolling bearing using the LDWPSO-PNN model. The proposed method is verified by the experimental datasets. The results indicate that the method can extract the feature vectors of the vibration signals and distinguish them effectively.

Assessment of the State of Quality in Garments Applying Data Mining Mechanisms: A Case Study in the Apparel Industry