Neural Network Modeling Approach Research Articles

Optimizing injection molding parameters to minimize and prediction potential for flashing defects

The injection molding process is a manufacturing process that can produce products in a short time in large quantities, in the injection molding process the factor of setting process parameters plays a significant role in product quality, so it requires special treatment. The purpose of this study is to find the optimal parameters in the injection moulding process of yogurth container lid with polypropylene material, so that the process can reduce the incidence of flashing defects that result in the emergence of initial waste in the industrial environment. The method used in this research is to create a Response Surface Methodology Box-Behnken Design (RSM - BBD) optimization model and an Artificial Neural Network (ANN) model approach in analyzing optimal parameters and predicting the appearance of flashing defects in a designed cycle. The results obtained from this research are the optimal parameters from the RSM and ANN model recommendations, namely the clamping force setting of 70 tons, holding time 0.1 seconds, and holding pressure. The ANN model provides the highest level of prediction accuracy with an R2 value of 100% and a prediction error rate of 7.9689E-09. In comparison, the RSM model obtains a prediction accuracy level with an R2 of 71% with an error rate of 0.24315.

Impulsive Control Discrete Fractional Neural Networks in Product Form Design: Practical Mittag-Leffler Stability Criteria

The planning, regulation and effectiveness of the product design process depend on various characteristics. Recently, bio-inspired collective intelligence approaches have been applied in this process in order to create more appealing product forms and optimize the design process. In fact, the use of neural network models in product form design analysis is a complex process, in which the type of network has to be determined, as well as the structure of the network layers and the neurons in them; the connection coefficients, inputs and outputs have to be explored; and the data have to be collected. In this paper, an impulsive discrete fractional neural network modeling approach is introduced for product design analysis. The proposed model extends and complements several existing integer-order neural network models to the generalized impulsive discrete fractional-order setting, which is a more flexible mechanism to study product form design. Since control and stability methods are fundamental in the construction and practical significance of a neural network model, appropriate impulsive controllers are designed, and practical Mittag-Leffler stability criteria are proposed. The Lyapunov function strategy is applied in providing the stability criteria and their efficiency is demonstrated via examples and a discussion. The established examples also illustrate the role of impulsive controllers in stabilizing the behavior of the neuronal states. The proposed modeling approach and the stability results are applicable to numerous industrial design tasks in which multi-agent systems are implemented.

Neural Network-based Pattern Recognition in the Framework of Edge Computing

Neural network (NN) model has been widely used in pattern recognition (PR), speech recognition, image processing and other fields, but its application in edge computing (EC) environment faces performance and energy consumption problems. This article first introduced the basic structure and training process of NN, including backpropagation algorithms. Then, this article presented a NN modeling approach based on EC, including NN model compression, distributed NN model and knowledge distillation approach. Finally, this article implemented a PR model for the MNIST (Mixed National Institute of Standards and Technology database) dataset and analyzed the experimental results. The experimental outcomes indicated that the presented approach can significantly enhance the performance of the NN model in the EC environment, while ensuring a high recognition accuracy. The NN modeling approach based on EC can reduce the amount of computation and storage of the NN, thus improving the operating efficiency of the NN in the EC environment by 6%-12%. The NN modeling approach based on EC can optimize the performance and efficiency of the NN model in the EC environment, and provide new ideas and approaches for the application of NN in the EC environment.

Estimation of cutting forces in CNC slot-milling of low-cost clay reinforced syntactic metal foams by artificial neural network modeling

PurposeThis study aims to elucidate the machining properties of low-cost expanded clay-reinforced syntactic foams by using different neural network models for the first time in the literature. The main goal of this endeavor is to create a casting machining-neural network modeling flow-line for real-time foam manufacturing in the industry.Design/methodology/approachSamples were manufactured via an industry-based die-casting technology. For the slot milling tests performed with different cutting speeds, depth of cut and lubrication conditions, a 3-axis computer numerical control (CNC) machine was used and the force data were collected through a digital dynamometer. These signals were used as input parameters in neural network modelings.FindingsAmong the algorithms, the scaled-conjugated-gradient (SCG) methodology was the weakest average results, whereas the Levenberg–Marquard (LM) approach was highly successful in foreseeing the cutting forces. As for the input variables, an increase in the depth of cut entailed the cutting forces, and this circumstance was more obvious at the higher cutting speeds.Research limitations/implicationsThe effect of milling parameters on the cutting forces of low-cost clay-filled metallic syntactics was examined, and the correct detection of these impacts is considerably prominent in this paper. On the other side, tool life and wear analyses can be studied in future investigations.Practical implicationsIt was indicated that the milling forces of the clay-added AA7075 syntactic foams, depending on the cutting parameters, can be anticipated through artificial neural network modeling.Social implicationsIt is hoped that analyzing the influence of the cutting parameters using neural network models on the slot milling forces of metallic syntactic foams (MSFs) will be notably useful for research and development (R&D) researchers and design engineers.Originality/valueThis work is the first investigation that focuses on the estimation of slot milling forces of the expanded clay-added AA7075 syntactic foams by using different artificial neural network modeling approaches.

Enhanced defluoridation by nano-crystalline alum-doped hydroxyapatite and artificial intelligence (AI) modeling approach

The study aimed to investigate the defluoridation capacity of nano-hydroxyapatite (HAP) [Ca10(PO4)6(OH)2] and alum-doped hydroxyapatite (AHAP) [Ca8Al(PO4)6.(OH)2] as an environmental friendly adsorbent. The physicochemical characteristics of both the material (HAP and AHAP) were examined using XRD, FE-SEM-EDS, and BET techniques. The batch adsorption study revealed a fluoride removal efficiency of up to 83% (AHAP) and 74% (HAP) under acidic conditions (pH-2). The doping of alum alters the surface chemistry and enhances the affinity of AHAP for fluoride adsorption. The pseudo-second-order kinetic (R2–0.9941) and Langmuir isotherm (R2–0.9425) models best describe the adsorption mechanism and behavior. The thermodynamic analysis indicated the spontaneous and endothermic nature of the adsorption process. The study also tested the applicability of the artificial neural network (ANN) modeling approach using MATLAB R2013a to simulate the simulated absorptive efficiency of AHAP. This study suggests that AHAP proved an effective adsorbent for defluoridation.

An IoT Real-Time Potable Water Quality Monitoring and Prediction Model Based on Cloud Computing Architecture.

In order to achieve the Sustainable Development Goals (SDG), it is imperative to ensure the safety of drinking water. The characteristics of each drinkable water, encompassing taste, aroma, and appearance, are unique. Inadequate water infrastructure and treatment can affect these features and may also threaten public health. This study utilizes the Internet of Things (IoT) in developing a monitoring system, particularly for water quality, to reduce the risk of contracting diseases. Water quality components data, such as water temperature, alkalinity or acidity, and contaminants, were obtained through a series of linked sensors. An Arduino microcontroller board acquired all the data and the Narrow Band-IoT (NB-IoT) transmitted them to the web server. Due to limited human resources to observe the water quality physically, the monitoring was complemented by real-time notifications alerts via a telephone text messaging application. The water quality data were monitored using Grafana in web mode, and the binary classifiers of machine learning techniques were applied to predict whether the water was drinkable or not based on the data collected, which were stored in a database. The non-decision tree, as well as the decision tree, were evaluated based on the improvements of the artificial intelligence framework. With a ratio of 60% for data training: at 20% for data validation, and 10% for data testing, the performance of the decision tree (DT) model was more prominent in comparison with the Gradient Boosting (GB), Random Forest (RF), Neural Network (NN), and Support Vector Machine (SVM) modeling approaches. Through the monitoring and prediction of results, the authorities can sample the water sources every two weeks.

Adsorption of lead ions from wastewater using electrospun zeolite/MWCNT nanofibers: kinetics, thermodynamics and modeling study.

Heavy metal contamination in water is a serious environmental issue due to the toxicity of metals like lead. This study developed zeolite and multi-walled carbon nanotube (MWCNT) incorporated polyacrylonitrile (PAN) nanofibers via needleless electrospinning and examined their potential for lead ion adsorption from aqueous solutions. The adsorption process was optimized using response surface methodology (RSM) and artificial neural network (ANN) modeling approaches. The adsorbent displayed efficient lead removal of 84.75% under optimum conditions (adsorbent dose (2.21 g), adsorption time (207 min), temperature (48 °C), and initial concentration (62 ppm)). Kinetic studies revealed that the adsorption followed pseudo-first-order kinetics governed by interparticle diffusion. Isotherm analysis indicated Langmuir monolayer adsorption with improved 5.90 mg g-1 capacity compared to pristine PAN nanofibers. Thermodynamic parameters suggested the adsorption was spontaneous and endothermic. This work demonstrates the promise of electrospun zeolite/MWCNT nanofibers as adsorbents for removing lead from wastewater.

Second-Order Sensitivity Neural Network Modeling Approach With Applications to Microwave Devices

Second-Order Sensitivity Neural Network Modeling Approach With Applications to Microwave Devices

Fusion of theory and data-driven model in hot plate rolling: A case study of rolling force prediction

As one of the most critical variables in the hot rolling process, the accuracy of rolling force prediction is directly associated with production stability and product quality. Purely data-driven approaches, however, are severely constrained by the quantity and quality of data, posing challenges for further enhancing the accuracy of rolling force prediction. In this paper, a theory fusion deep neural network (DNN) modelling approach was proposed and applied to the prediction of rolling force during hot plate rolling. In terms of model establishment, the novel NN structure was designed in consideration of the rolling mechanism, and senior variable inputs were added at shallow locations in the network to reduce the loss of critical information. In terms of model training, the method of using rolling theory to guide the initialization of the model was proposed to enable the model to learn the theoretical features more completely in the pre-training phase. Finally, a method to optimize the overall structure of the model using the sparrow search algorithm (SSA) was proposed to ensure the best prediction performance. The model was tested with the data in the developed platform, and the results indicated that the proposed method achieves the best accuracy and stability in this paper, and the response relationship between model inputs and output was consistent with existing theoretical knowledge. Thus, the model can be trusted and flexibly applied to the actual manufacturing processes.

Groundwater quality index development using the ANN model of Delhi Metropolitan City, India.

Groundwater is widely recognized as a vital source of fresh drinking water worldwide. However, the rapid, unregulated population growth and increased industrialization, coupled with a rise in human activities, have significantly harmed the quality of groundwater. Changes in the local topography and drainage systems in an area have negative impacts on both the quality and quantity of groundwater. This underscores the critical need to assess the susceptibility of groundwater to pollution and implement measures to mitigate these risks. The water quality index (WQI) is an approach that simulates the water quality at peculiar locations for a particular period of time. The artificial neural network (ANN) model approach is such an idealistic methodology that can be utilized for WQI development and provides better results for specific locations in optimum time. Therefore, the goal of the current study is to provide a unique way for using artificial neural networks (ANN) to characterize the groundwater quality of Delhi Metropolitan City, India. In order to make the water fit for residential and drinking use, the research also pinpoints the geographical variability and spots where the contaminated region has to be sufficiently cleaned. A minimum WQI of 41.51 was obtained at the Jagatpur location while a maximum value of 779.01 was at the Peeragarhi location. During the training phase, the results obtained using the ANN model were highly favorable, demonstrating a strong association with an R-value of 98.10%, thus highlighting the program's exceptional efficiency. However, in accordance with the correlation regression findings, the prediction outcomes of the ANN model in testing are observed to be an R-value of 99.99-100%. This study confirms the promise and advantages of employing advanced artificial intelligence in managing groundwater quality in the studied area.

Investigations on tool wear behavior in turning AISI 304 stainless steel: An empirical and neural network modeling approach

Machining with a cutting edge with extensive damage or a fractured cutting edge significantly influences the machining performance. Therefore, investigations on tool wear behavior, their forms, and wear mechanisms will be very helpful in the current environment of sustainable manufacturing. On the other hand, the machining economy is negatively impacted by replacing the tool well before its useful life. This proactive maintenance planning reduces the risk of sudden tool failure and potential workpiece damage. Accordingly, the current work creates empirical and ANN models to predict flank wear growth for turning AISI 304 stainless steel using a MTCVD-TiCN/Al2O3 coated carbide tool. The experiments were designed to cover a broad range of operating conditions to ensure the model's accuracy and applicability in practical machining scenarios. An ANN was modeled using a feedforward backpropagation machine learning technique. In this study, a higher prediction accuracy of 0.9975 was achieved with ANN model as compared to the empirical model. The most common wear mechanism observed is metal adhesion, followed by fracture due to the pulling away of adhered material. The developed models have been found to be valuable for optimizing cutting parameters and enhancing tool life in machining.

Obtaining an accurate prediction model for viscosity of a new nano-lubricant containing multi-walled carbon nanotube-titanium dioxide nanoparticles with oil SAE50

This study aims to investigate the viscosity behavior of multi-walled carbon nanotube (MWCNT) - titanium dioxide (TiO2) (40−60) - SAE50 oil nanofluid using an Artificial Neural Network (ANN) modeling approach. The main objective is to develop a highly accurate predictive model for viscosity by considering three input parameters: temperature, solid volume fraction (SVF), and shear rate (SR). Rheological measurements provide experimental data used to train and validate the ANN model. The ANN model's architecture, activation functions, and training algorithms are carefully chosen. Data are divided to three subsets including train, validation and test. ANN is trained using trainlm algorithm for 50 times to vanish the effect of random nature of ANN weight initialization. The trained ANN model is then utilized to predict the viscosity of the nanofluid under varying conditions. The results demonstrate the efficacy of the proposed ANN model in capturing the complex relationship between viscosity and the input parameters, providing accurate viscosity predictions for the MWCNT-TiO2-oil SAE50 nanofluid. Furthermore, the influence of temperature, SVF, and SR on viscosity is analyzed, offering valuable insights into the flow behavior of the nanofluid. According to the obtained results, the developed ANN model presents a reliable and efficient approach to estimate the viscosity of the MWCNT-TiO2-SAE50 oil nanofluid, eliminating the need for costly and extensive experimental measurements within the analyzed range. ANN could model the nanofluid viscosity with R2 = 0.9998 and MSE= 0.000189 that is quite acceptable. Also, the experimental data revealed that for the investigated nanofluid, temperature and shear rate have impressive effect on the viscosity (changing viscosity more than 100% for the analyzed margin), on the other hand, the nanoparticle volume fraction effect is much lower, to be more precise, increasing the nanoparticle percentage will increase the viscosity mean value around 30%.

Artificial Neural Network Approach for Modeling of Effect of Ultrasound on the Dissolution of Magnesia in Aqueous Carbon Dioxide

Artificial Neural Network Approach for Modeling of Effect of Ultrasound on the Dissolution of Magnesia in Aqueous Carbon Dioxide

Development of Predictive Model for Wax Formation in Deep-water Pipeline Using Machine learning

Wax deposition in deep sea pipelines can affect oil and gas production. It happens when the pipeline temperature drops below the wax appearance temperature, causing the wax to solidify and stick to the pipeline walls. This paper discusses the limitations of current models in predicting wax deposition in pipelines and proposes the development of more complex, intelligent models that are accurate, resilient, and adaptable to novel input-output scenarios. It also highlights various methods for preventing wax deposition, including the use of chemical inhibitors and thermal remediation techniques. The paper aims to develop a neural network modeling approach for predicting wax deposition potential in producing reservoirs to prevent accumulation before removal. The parameters that were used are wax molecule concentration gradient at pipe wall, temperature gradient at pipe wall, reported wax deposition rate, the pipe wall shear stress, and crude oil viscosity. The radial basis function neural network (RBFNN), is based on the machine learning technique. RBFNN is a good choice for building a predictive wax deposition rate model because it is highly accurate, robust to noise and outliers, computationally efficient, can model complex nonlinear relationships, suitable for real-time applications and requires less training data. The RBF neural network is constructed using MATLAB. The outcomes and experimental data are consistent with a 1.5 percent relative inaccuracy when compared to prior studies. The R^2 value was 0.9906, R value was 0.9953 and the RMSE value was 0.8598. The RBF neural network-based approach for predicting wax deposition rate was successful.

Optimization of sequential ultrasound-microwave assisted extraction of polyphenols-rich concrete from tuberose flowers through modelling

The polyphenols-rich concrete from tuberose flowers can be extracted by sequential ultrasound-microwave assisted extraction (UMAE). However, additional study is required to optimise the processing parameters of sequential UMAE of tuberose concrete. Therefore, in this work, we have focused on establishing the optimal conditions for sequential UMAE of concrete from tuberose flowers using the Response Surface Methodology (RSM) and Artificial Neural Network (ANN) model approach. The impact of different extraction conditions (microwave power (160–800 W), irradiation time (60–300 s), sonication intensity (200–600 W) and sonication time (360−840)) of sequential UMAE on the percent concrete yield from the fresh chopped tuberose flowers were investigated. The percent concrete yield (%), total phenols (mg/g) and antioxidant activity of concrete obtained were 92.28 ± 0.52%, 232.50 ± 0.46 mg/g and 54.48 ± 0.46%, respectively under optimized conditions of sonication power-300 W, microwave power-480 W, irradiation time-2.2 min and sonication time-10 min. The findings suggested that the RSM and ANN models may adequately describe the experimental data. However, ANN prediction is more accurate than the RSM model with a higher coefficient of determination (R2) (0.987 vs. 0.904) and lower mean squared error (1.385 vs. 1.65) and root mean squared error (1.177 vs. 1.284). Gas chromatography-mass spectrometry analyzed that the tuberose concrete was rich in benzyl benzoate (14.5%), trans-Farnesol (11.02%), indole (8.52%), eugenol (5.35%), isoeugenol (5.16%), methyl benzoate (2.17%), methyl anthranilate (2%).

A cell-level discriminative neural network model for diagnosis of blood cancers.

Precise identification of cancer cells in patient samples is essential for accurate diagnosis and clinical monitoring but has been a significant challenge in machine learning approaches for cancer precision medicine. In most scenarios, training data are only available with disease annotation at the subject or sample level. Traditional approaches separate the classification process into multiple steps that are optimized independently. Recent methods either focus on predicting sample-level diagnosis without identifying individual pathologic cells or are less effective for identifying heterogeneous cancer cell phenotypes. We developed a generalized end-to-end differentiable model, the Cell Scoring Neural Network (CSNN), which takes sample-level training data and predicts the diagnosis of the testing samples and the identity of the diagnostic cells in the sample, simultaneously. The cell-level density differences between samples are linked to the sample diagnosis, which allows the probabilities of individual cells being diagnostic to be calculated using backpropagation. We applied CSNN to two independent clinical flow cytometry datasets for leukemia diagnosis. In both qualitative and quantitative assessments, CSNN outperformed preexisting neural network modeling approaches for both cancer diagnosis and cell-level classification. Post hoc decision trees and 2D dot plots were generated for interpretation of the identified cancer cells, showing that the identified cell phenotypes match the cancer endotypes observed clinically in patient cohorts. Independent data clustering analysis confirmed the identified cancer cell populations. The source code of CSNN and datasets used in the experiments are publicly available on GitHub (http://github.com/erobl/csnn). Raw FCS files can be downloaded from FlowRepository (ID: FR-FCM-Z6YK).

Validation of a neural network based model to predict foF2

This work presents the application of Neural Networks (NNs) techniques to develop an empirical model for foF2, the critical frequency of the F2 ionospheric layer. Prediction of foF2 parameter is important because of the paucity of data in some areas of the globe (due to uneven distributions of ground- based measuring equipment) and, also, because of the roles it plays in high frequency communications and navigation purposes. Hourly values of foF2 corresponding to the period 1985–2007 and obtained from 105 World-wide distributed ionospheric stations, have been considered in this work. A statistical analysis of the difference between NN model-derived and the corresponding experimental foF2 values was carried out for eleven (11) selected ionospheric stations during periods of very high (year 2000), relatively low (year 2006) and very low (year 2008) solar activity. In particular, the ionospheric behavior during the years 2000 and 2008 appeared to be very challenging to be captured for any empirical model. For comparison purposes, the same kind of statistical analysis was performed with foF2 values as obtained from the International Reference Ionosphere (IRI) model and from NeQuick 2 model. Results of the statistical comparison confirmed that the neural network modelling approach is suitable to describe in a climatological way the main characteristics of the ionosphere F2 layer peak frequency, also over the extended geographic region where the additional sensor stations were located. The results obtained also indicate that the NN predictions and NeQuick 2 algorithm driven by solar flux (F10.7) index have similar performance.

Predicting 10-year breast cancer mortality risk in the general female population in England: a model development and validation study

Identifying female individuals at highest risk of developing life-threatening breast cancers could inform novel stratified early detection and prevention strategies to reduce breast cancer mortality, rather than only considering cancer incidence. We aimed to develop a prognostic model that accurately predicts the 10-year risk of breast cancer mortality in female individuals without breast cancer at baseline. In this model development and validation study, we used an open cohort study from the QResearch primary care database, which was linked to secondary care and national cancer and mortality registers in England, UK. The data extracted were from female individuals aged 20-90 years without previous breast cancer or ductal carcinoma in situ who entered the cohort between Jan 1, 2000, and Dec 31, 2020. The primary outcome was breast cancer-related death, which was assessed in the full dataset. Cox proportional hazards, competing risks regression, XGBoost, and neural network modelling approaches were used to predict the risk of breast cancer death within 10 years using routinely collected health-care data. Death due to causes other than breast cancer was the competing risk. Internal-external validation was used to evaluate prognostic model performance (using Harrell's C, calibration slope, and calibration in the large), performance heterogeneity, and transportability. Internal-external validation involved dataset partitioning by time period and geographical region. Decision curve analysis was used to assess clinical utility. We identified data for 11 626 969 female individuals, with 70 095 574 person-years of follow-up. There were 142 712 (1·2%) diagnoses of breast cancer, 24 043 (0·2%) breast cancer-related deaths, and 696 106 (6·0%) deaths from other causes. Meta-analysis pooled estimates of Harrell's C were highest for the competing risks model (0·932, 95% CI 0·917-0·946). The competing risks model was well calibrated overall (slope 1·011, 95% CI 0·978-1·044), and across different ethnic groups. Decision curve analysis suggested favourable clinical utility across all age groups. The XGBoost and neural network models had variable performance across age and ethnic groups. A model that predicts the combined risk of developing and then dying from breast cancer at the population level could inform stratified screening or chemoprevention strategies. Further evaluation of the competing risks model should comprise effect and health economic assessment of model-informed strategies. Cancer Research UK.

Quantification of contamination, ecological risk index, and health risk assessment of groundwater using artificial neural network and multi-linear regression modeling approaches within Egbema, Nigeria

Quantification of contamination, ecological risk index, and health risk assessment of groundwater using artificial neural network and multi-linear regression modeling approaches within Egbema, Nigeria

Exploring the Effectiveness of Deep Learning in Analyzing Review Sentiment

This study aimed to analyze sentiment in office product reviews by using word embedding with three neural network modeling approaches: Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU). Office product review data is taken from Amazon's reviews of office products covering a wide range of sentiments. Word embedding converts text into a numerical vector representation for neural network processing. Experimental comparison of this model reveals that CNN achieves the highest accuracy, 77.99%. The CNN model effectively extracts significant features from review text, improving sentiment classification performance. Although the LSTM and GRU models show satisfactory results, they do not match CNN performance. These findings demonstrate the effectiveness of word embedding and neural networks for sentiment analysis in office product reviews. This provides valuable insights for companies to improve their products based on user feedback from online reviews. Additionally, this research serves as a foundation for further advances in sentiment analysis across a wide range of other products and services