Search

• A novel water transparency calculation algorithm is introduced, employing deep neural network and image processing technology. This algorithm obviates the need for a water gauge, allowing the calculation of water transparency solely through the analysisof Secchi disk videos. Notably, it demonstrates heightened detection efficiency and success rates. • An enhanced Siamese tracker, termed SiamDCFF (Siamese tracker based on dual correlation feature fusion), is proposed for Secchi disk recognition. Distinguishing features of SiamDCFF include a dual correlation module and a feature fusion module. On the Secchi disk dataset, SiamDCFF achieves the highest success rate, outperforming other methods detailed in this paper. • The simplified 3D-ResNet [41] is leveraged to assess the state of the Secchi disk, transforming the critical position determination problem into an optimization challenge. The objective function involves maximizing the number of visible and invisible Secchi disk images on both sides of the critical position. This method facilitates adaptive critical position determination. • A novel Gated Recurrent Unit based on auto-regression (ARGRU) is proposed, taking into account the motion characteristics of the Secchi disk. ARGRU achieves a higher success detection rate for water transparency compared to the water gauge recognition method. Notably, ARGRU outperforms RNN [42], GRU, and LSTM [43] on the dataset presented in this paper. Water transparency is traditionally assessed through visual inspection using a lowered Secchi disk (SD) into the water, with the disappearance depth of the SD recorded as the measure of transparency. However, manual and visually-dependent frequency measurements of the SD render this process labor-intensive and time-consuming. This paper presents a comprehensive machine-vision-based algorithm designed for the automatic computation of water transparency using Secchi disk videos. The algorithm leverages multiple deep neural networks, including an enhanced Siamese tracking model, a 3D-ResNet, and an improved GRU network. Trained models directly identify the SD in the video, calculating water transparency by processing pixel information. Experimental results demonstrate the algorithm's efficacy in estimating water transparency across diverse natural environments, achieving commendable accuracy (MAE = 3.6 cm MSE = 21.5 cm RMSE = 4.6 cm), rapid processing speed (average 6.87 s), and robust stability. In comparison with the former water-gauge-based algorithm, our proposed algorithm exhibits heightened efficiency and a superior detection success rate. [ABSTRACT FROM AUTHOR]

• This paper suggests a grating Moiré fringe-based error correction approach that uses an artificial neural network (ANN) and the quartile method (QM). • The approach uses QM for data cleaning operations to eliminate outliers and creates the ANN model with a structure of fully connected layer-normalization layer-fully connected layer for regression training in order to achieve lightweight and stability. • The proposed QM-ANN error correction model's mean absolute error (MAE) can reach 3.3 nm once the QM data has been cleaned and the ANN model has been trained. Many interference factors of the complex and changeable working environment of the grating sensor are the main factors affecting the accuracy; a grating Moiré fringe error correction model based on the quartile method (QM) and artificial neural network (ANN) is proposed in this paper. Firstly, the grating sensor's signals in the working process are collected, and three kinds of interference signals (temperature, humidity and vibration) from the grating sensor working environment are collected simultaneously. Secondly, the QM is used to detect outliers from the collected data and delete data outliers directly. Subsequently, the processed data are input into the ANN model for training. The model is lightweight and stable, because it adopts the cascaded structure of full connection layer-normalization layer-full connection layer, which does not need deploy the complex convolution layer module etc. Finally, the corrected data are output after being processed by the QM-ANN error correction model. The experimental results show that the mean absolute error (MAE) of the proposed QM-ANN error correction model is better than QM-convolutional neural network (CNN), QM-long short-term memory (LSTM) and ANN, CNN, LSTM models without QM. It shows that the proposed model has better robustness and practicability. [ABSTRACT FROM AUTHOR]

Highlights • Method simulates effects of launch conditions on rail-gun current and armature speed. • The input five parameters are closely related to the rail-gun launchment. • Three neural networks predict the rail-gun current and armature speed with low error. • General Regression neural network is optimal on error, time cost, parameter design. Abstract In this paper, based on the advantages of artificial neural network, such as good tolerance of data noise, strong ability of nonlinear mapping, multi-dimensional input variables, fast operation, low error, etc., a method of using artificial neural network for data prediction is proposed for the research of rail-gun. The results show that it is feasible to use the Back Propagation Neural Network, the Radial Basis Function Neural Network and the General Regression Neural Network to realize the method of prediction and simulation of the rail-gun current and the armature speed curve through relevant parameters. The General Regression Neural Network has superiority in error performance and time cost of neural network training and simulation. [ABSTRACT FROM AUTHOR]

Gearboxes have a significant influence on the durability and reliability of a power transmission system. Currently, extensive research studies are being carried out to increase the reliability of gearboxes working in the energy industry, especially with a focus on planetary gears in wind turbines and bucket wheel excavators. In this paper, a signal pre-processing algorithm designed for condition monitoring of planetary gears working in non-stationary operation is presented. The algorithm is dedicated for hardware implementation on Field Programmable Gate Arrays (FPGAs). The purpose of the algorithm is to estimate the features of a vibration signal that are related to failures, e.g. misalignment and unbalance. These features can serve as the components of an input vector for a neural classifier. The approach proposed here has several important benefits: it is resistant to small speed fluctuations up to 7%, it can be performed in real-time conditions and its implementation does not require many resources of FPGAs. [ABSTRACT FROM AUTHOR]

• Electrical power output of power plants is predicted with high accuracy. • Electrostatic discharge algorithm is for the first time used for this aim. • Regular MLPs are compared to ESDA- and ASO-optimized versions. • ESDA-MLP is the most efficient model. • An explicit predictive formula is derived for convenient early prediction. Combined cycle power plants (CCPP) are among the most sophisticated, yet efficient, systems for producing electrical energy. Hence, simulating their performance has been an engineering hotspot toward sustainable developments. This paper employs novel soft computing methods for predicting electrical power (P E) output of CCPPs. To this end, a metaheuristic technique called electrostatic discharge algorithm (ESDA) is coupled with an artificial neural network (ANN) to create the proposed hybrid. Its performance is compared to several conventionally trained ANNs to investigate the effect of hybridization. By considering the influence of ambient temperature, exhaust vacuum, atmospheric pressure, and relative humidity, the P E is predicted through a 4 × 9 × 1 network. Among the conventional trainers, Levenberg-Marquardt emerged as the most promising one. However, the ESDA outperformed this algorithm in both training and testing phases. Accordingly, the used metaheuristic optimization could improve the robustness of the regular ANN in surmounting computational drawbacks. The ESDA-ANN is, therefore, introduced as a reliable predictive tool for the P E modeling, and the corresponding predictive formula is presented in the last part of this research. [ABSTRACT FROM AUTHOR]

This article deals with classification problems involving unequal probabilities in each class and discusses metrics to systems that use multilayer perceptrons neural networks (MLP) for the task of classifying new patterns. In addition we propose three new pruning methods that were compared to other seven existing methods in the literature for MLP networks. All pruning algorithms presented in this paper have been modified by the authors to do pruning of neurons, in order to produce fully connected MLP networks but being small in its intermediary layer. Experiments were carried out involving the E. coli unbalanced classification problem and ten pruning methods. The proposed methods had obtained good results, actually, better results than another pruning methods previously defined at the MLP neural network area. [ABSTRACT FROM AUTHOR]

Abstract: Qualitative identification of THz spectra of illicit drugs using self-organization feature map (SOM) artificial neural network has been demonstrated. In this paper, investigation results show that SOM has quantitatively identified drug mixtures successfully. Based on Beer’s law THz spectra data of various drug proportions were made for training dates. After analyzing the clustering algorithm of SOM, we introduced a parameter named shortest distance as a quantitative criterion for identification result. By this parameter, an automatic recognition algorithm has been developed and successfully applied to the content identification of experimental samples. Combined with our previous work, the SOM neural network can be an integrated and effective method in the identification the THz spectra of illicit drugs. [Copyright &y& Elsevier]

• The hybrid model is established for predicting MEC. • Mh, UCS, YM, Pr and SF-a are the influencing factors in sequence. • The main factors are explained by grinding mechanism and fracture mechanics. Modeling of stone processing, especially the sawability of stones (SS) has been studied extensively over the last decade. Artificial neural network (ANN) is an effective method to deal with complex engineering problems. However, ANN has some limitations such as trapped in local minima and cannot analyze the sensitivity of parameters. To fill the gaps, the primary objectives of this paper are to optimize ANN by genetic algorithm (GA) and introduce mean impact value (MIV) algorithm for parametric sensitivity analysis. Therefore, a hybrid model was proposed for predicting SS based on BP neural network (BPNN), MIV algorithm, and GA. Further, the main factors that affect SS were analyzed based on the grinding mechanism and fracture mechanics. The proposed model is not only meaningful to analyze SS, but provides a novel foundation for studying other stone procedures in future. [ABSTRACT FROM AUTHOR]

In this paper, we develop an algorithm (hereby referred to as the S-function generator: SFG) for the automatic generation of dynamic S-function blocks which can be used for geometrical error compensation of precision machines. The function block is composed of neural network approximations of the geometrical errors of the machines which will serve as the basis for error compensation. It is generated automatically based on only raw calibration data obtained from a laser interferometer and simple user specifications in terms of approximation accuracy requirements. No coding is necessary on the part of the user. This tremendously simplifies the use of the functional error compensation approach which has clear advantages over a traditional look-up table approach. The SFG has been applied to the compensation of two XY tables and the evaluation tests show that the overall geometrical errors can be significantly reduced. [Copyright &y& Elsevier]