Feed-forward Back-propagation Network Research Articles

Utilizing neural networks and genetic algorithms in AI-assisted CFD for optimizing PCM-based thermal energy storage units with extended surfaces

Phase Change Materials (PCMs) offer significant benefits for applications such as electronic cooling and Thermal Energy Storage (TES) due to their high energy storage capacity and stability. However, their limited thermal conductivity restricts widespread utilization. To address this limitation, the use of fins has become a common technique to enhance heat transfer. Optimizing fin lengths and locations is challenging, as they affect natural convection. This study aims to develop a model using a feed-forward back-propagation network, trained on simulation data, for designing a TES unit. A design matrix, incorporating factors such as fin lengths and heights, is obtained through response surface methodology. Single- and multi-objective Genetic Algorithms (GAs) are employed to seek optimal solutions, considering Complete Melting Time (CMT) and total fin length. The results demonstrate the excellent performance of the network model, with an error of less than 2.98%. The single-objective GA yields a minimum CMT. In a finless enclosure, the CMT is 338.5% higher compared to the single-objective configuration. The multi-objective GA, using Euclidean distance specified from the Pareto front to balance weight and material costs, results in a CMT that is 192% higher compared to the single-objective optimization but with a total fin length that is 286% shorter. While these improvements are significant, it is important to note that fins can increase material and manufacturing costs, as well as the overall unit weight. This artificial intelligence-computational fluid dynamics method not only predicts TES unit performance but also reduces computational costs in designing an optimal TES unit.

Tuning the Proportional-Integral-Derivative Control Parameters of Unmanned Aerial Vehicles Using Artificial Neural Networks for Point-to-Point Trajectory Approach.

Nowadays, trajectory control is a significant issue for unmanned micro aerial vehicles (MAVs) due to large disturbances such as wind and storms. Trajectory control is typically implemented using a proportional-integral-derivative (PID) controller. In order to achieve high accuracy in trajectory tracking, it is essential to set the PID gain parameters to optimum values. For this reason, separate gain values are set for roll, pitch and yaw movements before autonomous flight in quadrotor systems. Traditionally, this adjustment is performed manually or automatically in autotune mode. Given the constraints of narrow orchard corridors, the use of manual or autotune mode is neither practical nor effective, as the quadrotor system has to fly in narrow apple orchard corridors covered with hail nets. These reasons require the development of an innovative solution specific to quadrotor vehicles designed for constrained areas such as apple orchards. This paper recognizes the need for effective trajectory control in quadrotors and proposes a novel neural network-based approach to tuning the optimal PID control parameters. This new approach not only improves trajectory control efficiency but also addresses the unique challenges posed by environments with constrained locational characteristics. Flight simulations using the proposed neural network models have demonstrated successful trajectory tracking performance and highlighted the superiority of the feed-forward back propagation network (FFBPN), especially in latitude tracking within 7.52745 × 10-5 RMSE trajectory error. Simulation results support the high performance of the proposed approach for the development of automatic flight capabilities in challenging environments.

Non-speech emotion recognition based on back propagation feed forward networks

Non-speech emotion recognition involves identifying emotions conveyed through non-verbal vocalizations such as laughter, crying, and other sound signals, which play a crucial role in emotional expression and transmission. This paper employs a nine-category discrete emotion model encompassing happy, sad, angry, peaceful, fearful, loving, hateful, brave, and neutral. A proprietary non-speech dataset comprising 2337 instances was utilized, with 384-dimensional feature vectors extracted. The traditional Backpropagation Neural Network (BPNN) algorithm achieved a recognition rate of 87.7% on the non-speech dataset. In contrast, the proposed Whale Optimization Algorithm - Backpropagation Neural Network (WOA-BPNN) algorithm, applied to a self-made non-speech dataset, demonstrated a remarkable accuracy of 98.6%. Notably, even without facial emotional cues, non-speech sounds effectively convey dynamic information, and the proposed algorithm excels in their recognition. The study underscores the importance of non-speech emotional signals in communication, especially with the continuous advancement of artificial intelligence technology. The abstract thus encapsulates the paper’s focus on leveraging AI algorithms for high-precision non-speech emotion recognition.

Predicted evaporation in Basrah using artificial neural networks

Abstract Accurate evaporation estimation is crucial for managing hydrologic, hydraulic, and agricultural systems, among many other applications of water resources. Empirical formulae for estimating evaporation exist, but their performance is not always sufficient due to the intricacy of the process and its nonlinear connection with other elements of the hydrological cycle. For this reason, a model of artificial neural networks was developed to estimate the daily potential evaporation in the southern Iraqi city of Basrah. A feedforward backpropagation (BP) network with a single hidden layer has been used to construct the mode. Different networks with various neuron counts were assessed. The developed models have been trained, tested, and validated using daily observations of the average rainfall, wind speed, average temperature, average relative humidity, and evaporation. The final evaporation was predicted using an artificial neural network (ANN) model. The proposed model was found to be more suitable to describe evaporation in any region of the world based on the values of the error analysis and the coefficient of determination, according to the ANN model. The Levenberg–Marquardt algorithm (LMA) was determined to have the lowest mean-squared error (MSE) and highest value of the coefficient of correlation (R) of the six proposed BP algorithms. The LMA’s hidden layer’s ideal neuron count was 30 neurons, with an MSE of 0.00288 and R 2 = 99. As a result, ANN displayed excellent performance in terms of evaporation prediction value. The study’s findings highlight the significance of predicting evaporation as the main metric for evaluating the effects of climate change on water resources.

Predicting intrauterine growth restriction: a pilot study with feed-forward back propagation network

Predicting intrauterine growth restriction: a pilot study with feed-forward back propagation network

Residual networks for text-independent speaker identification: Unleashing the power of residual learning

The human voice, a dynamic signal, conveys valuable information for speaker identification, encompassing gender, age, emotions, and language. In the biometrics industry, identifying voices in real-time amidst diverse accents, tones, and noisy backgrounds is a challenging task. Voice biometry, a complex aspect of speaker identification, is gaining importance in various applications, such as user authentication, attendance systems, forensics, and banking operations, as it eliminates the need for traditional credentials like cards or passwords. Recent advancements in Human–Computer Interaction technology have made conversational tasks technically feasible. Deep Neural Learning approaches, especially Convolutional Deep Neural Networks (CDNN), have emerged as a powerful tool in the field of speech processing, surpassing traditional Speaker Identification methods. This paper introduces a novel approach using 1-Dimensional Convolutional Residual Blocks for audio classification and Speaker Identification, specifically focusing on speaker recognition from spoken Hindi language. The proposed Residual architecture significantly enhances speaker identification, even in low Signal Noise Ratio environments, achieving an impressive accuracy rate of 86.02%. This outperforms traditional Gaussian Mixture Model (GMM) and Feed Forward Back-propagation Network (FFBN) model for the same set of speakers. Future research directions may explore the classification of audio and speaker identification using various acoustic features derived from speech signals.

Modelling and evaluation of the post-hardness and forming limit diagram in the single point incremental hole flanging (SPIHF) process using ANN, FEM and experimental

In the single point incremental hole flanging (SPIHF) process, a sheet material with pre-cut holes is deformed using the SPIF technique to generate a flange, making it an effective approach for low volume manufacturing and quick prototyping. In the case of the SPIHF technique, the post-forming hardness property, the forming limit diagram (FLD), and spring-back phenomena are not completely evaluated. To this end, this paper employs experimental investigation and numerical validation to analyse the impact of SPIHF process parameters like tool diameter, feed rate, spindle speed, and initial hole diameter on these aspects for the truncated incrementally formed components made from AA1060 aluminium alloy and DC01 carbon steel. The plasticity behaviour of both sheet metals was simulated using the Workbench LS-DYNA model and ANSYS software version 18. Additionally, Cowper Symonds power-law hardening was added to the model to account for material properties. The average post-hardness of AA1060 and DC01 was evaluated using an SPIHF prediction model based on the performance of an artificial neural network (ANN). This ANN model was developed using a feed-forward back-propagation network trained using the Levenberg-Marquardt approach. The ANNs 4-n-1 were created by varying the transfer functions and the number of hidden neurons. Greater spindle speed and bigger pre-cut holes were shown to significantly increase the post-formed hardness of the truncated components, whereas the converse was seen when using a higher feed rate and a larger tool diameter. In addition, the FLD and spring-back improved dramatically with larger hole diameters. Employing correlation coefficient (R) and mean square error (MSE) as validation measures, it was shown that the established ANN models accurately predicted the SPIHF process response. Both the DC01 and AA1060 neural network models with a 4-8-1 network architecture performed very well, with MSE and R values of 0.0000105 and 1 for DC01 and 0.02613 and 0.99982 for AA1061.

A Meander Delay System Design Using Caps-Triple GAN Optimized with the Remora Optimization Algorithm for IOT Application

In this manuscript, a Meander Delay System design using Caps-Triple GAN optimized with the Remora Optimization Algorithm (ROA) is proposed for the Internet of Things (IoT) application. For designing the Meander Microstrip Delay Line (MMDL) Antenna, the Capsule Triple generative adversarial network (Caps-Triple GAN) is used. The Caps-Triple GAN error and delay parameters are optimized using the ROA. Hence, the designed MMDL Antenna is available in the IoT application. The proposed method is executed in the commercial Sonnet software package. The performance of the proposed method is examined under performance metrics, such as delay time with resistance characteristic, one-step delay time resistance characteristic, delay time, one-step delay time, error, and speed. The prediction results of the proposed MMDL-CAPS-Triple GAN-ROA method predict lower delay times of 14.77%, 15.89%, and 11.50%, higher speed of 32.57%, 16.25%, and 8.44% compared with the existing methods, such as Prediction of the meander delay system parameters for internet-of-things devices utilizing a Pareto-optimal artificial neural network and multiple linear regression (MDS-ANN-MLR), Predicting the frequency characteristics of hybrid meander systems utilizing the feed-forward back propagation network (MDS-FFBPN), Frequency Characteristic Analysis of Meander Structures with Different Connecting Electrodes (MDS-MoM), respectively.

Rule-Based Non-Intrusive Load Monitoring Using Steady-State Current Waveform Features.

Monitoring electricity energy usage can help to reduce power consumption considerably. Among load monitoring techniques, non-intrusive load monitoring (NILM) provides a cost-efficient solution to identify individual load consumption details from the aggregate voltage and current measurements. Existing load monitoring techniques often require large datasets or use complex algorithms to obtain acceptable performance. In this paper, a NILM technique using six non-redundant current waveform features with rule-based set theory (CRuST) is proposed. The architecture consists of an event detection stage followed by preprocessing and framing of the current signal, feature extraction, and finally, the load identification stage. During the event detection stage, a change in connected loads is ascertained using current waveform features. Once an event is detected, the aggregate current is processed and framed to obtain the event-causing load current. From the obtained load current, the six features are extracted. Furthermore, the load identification stage determines the event-causing load, utilizing the features extracted and the appliance model. The results of the CRuST NILM are evaluated using performance metrics for different scenarios, and it is observed to provide more than 96% accuracy for all test cases. The CRuST NILM is also observed to have superior performance compared to the feed-forward back-propagation network model and a few other existing NILM techniques.

Multivariate Simultaneous Determination of Some PAHs in Persian Gulf Oil-Contaminated Algae and Water Samples Using Miniaturized Triton X-100-Mediated Fe3O4 Nanoadsorbent and UV-Vis Detection

This research shows the development of a miniaturized solid-phase extraction method with UV-Vis detection for simultaneous determination of dibenzofuran, fluoranthene and phenanthrene using chemometrics approaches. After synthesis of Fe3O4 nanoparticles (Fe3O4 NPs), the surface of the nanoparticles was modified by Triton X100 coating. The influence of extraction solvent and volume, concentration of Triton X100, extraction time, and sample pH were studied and optimized. Due to high spectral overlapping, resolving ternary mixtures for simultaneous determination of targets with classical analytical methods is impossible. Therefore, the recorded UV-Vis spectra were transformed using continuous wavelet transform and then subjected to artificial neural networks (ANNs). The Db4 mother wavelet was used as the better mother wavelet. For simultaneous detection of analytes, a comparison of feed-forward back-propagation and radial basis function networks was accomplished. The calibration graphs showed linearity in the ranges of 2.4–250 ng mL−1, 50–3750 ng mL−1, and 48–5000 ng mL−1 with a limit of detection of 0.58, 9.5 ng mL−1, and 12.5 ng mL−1 under optimal conditions for phenanthrene, fluoranthene, and dibenzofuran, respectively. The limit of quantitation was achieved at 3.52 ng mL−1, 16.35 ng mL−1, and 31.3 ng mL−1 for phenanthrene, fluoranthene and dibenzofuran, respectively. The method involving TX-100-coated Fe3O4 NPs in a liquid sample phase for analyte extraction, followed by ethanol desorption and UV-Vis detection, was successfully applied for the determination of polycyclic aromatic hydrocarbons in oil-field water and algae samples.

Efficient training of two ANNs using four meta-heuristic algorithms for predicting the FRP strength

In recent years, artificial neural network (ANN) is one of the popular and effective machine learning models that can be used to accurately predict fiber reinforced polymer (FRP) strength. However, the ANN structure and parameters are usually are chosen by experience. In this study, the aim is to use the combination of meta-heuristic algorithm with two different types of artificial neural network structure to optimize the parameters of the feed forward backpropagation and radial basis function networks. In this paper, Particle swarm optimization (PSO), Genetic algorithm (GA), Colliding bodies optimization (CBO), Enhanced colliding bodies optimization (ECBO) algorithms are used to combine with ANNs.A total of 223 test data on Carbon FRP (CFRP) collected from the available literature were used to generate training and test data sets. Various validation criteria such as mean square error, root mean square error and correlation coefficient (R) are used to validate the models. These models consider the effects of concrete compressive strength, concrete sample diameter, concrete sample length, fiber elastic modulus, fiber thickness, fiber strength on the ultimate strength of FRP-concrete.It is shown that ECBO algorithm provide better results and higher accuracy. Also, the comparison of the results of using two neural networks, feed forward backpropagation (FFB) and radial basis function (RBF), indicates that the lower error percentage and more accurate results are related to the FFB neural networks combined with ECBO.

Artificial neural network model for strength predictions of CFST columns strengthened with CFRP

This paper presents an optimised Artificial Neural Network (ANN) model for predicting the ultimate axial strengths of concentrically loaded Concrete-Filled Steel Tubular (CFST) short and slender columns strengthened with Carbon Fibre-Reinforced Polymer (CFRP). Since experimental data on CFRP strengthened CFST columns is limited, an accurate Finite Element (FE) model is developed and used to provide additional numerical data. A multi-layered feed-forward back-propagation network is proposed, optimised, and trained using the results of 76 experimental tests and 450 generated FE models. The accuracy of the ANN model is assessed through comparing its computed results with experimental data. A reliability analysis is performed using Monte Carlo Simulation (MCS) to evaluate the safety of the solutions computed by the ANN model. ANN-based equations and Graphical User Interface (GUI) are developed based on the trained ANN model for the determination of the ultimate axial strengths of CFST columns. The results show that the developed ANN model is capable of accurately predicting the ultimate axial strengths of CFRP strengthened CFST columns with a high degree of accuracy.

Enhancing sensor linearity through the translinear circuit implementation of piecewise and neural network models

<abstract><p>The performance of the control system relies on the linearity of the sensor, which can be influenced by various factors such as aging and alterations in material properties. However, current sensor linearization techniques, such as utilizing neural networks and piecewise regression models in the digital domain, suffer from issues like errors, excessive power consumption, and slow response times. To address these constraints, this investigation employs a translinear based analog circuit to realize neural networks and piecewise regression models for the purpose of linearizing the selected sensors. A conventional feed-forward back propagation network is constructed and trained using the Levenberg-Marquardt algorithm. The developed linearization algorithm is implemented using a translinear circuit, where the trained weights, biases, and sensor output are fed as input current sources into the current-mode circuit. Further in this work, the piecewise regression model is designed and implemented using a translinear circuit and the breakpoint is determined using 'R' language. The simulation results indicate that the implementation of the current-mode circuit with metal-oxide-semiconductor field-effect transistors (MOSFETs) for the neural network algorithm leads to a substantial reduction in full-scale error as compared to the piecewise current mode model. Additionally, a performance analysis was conducted to compare the utilization of current-mode circuits with digital approaches for the linearization of sensors. The proposed translinear implementation surpasses the other researcher's work by delivering notable results. It showcases a significant improvement in linearity, ranging from 60% to 80%, for the selected sensors. Furthermore, the proposed implementation excels not only in linearity but also in terms of both response speed and power consumption. The improvement in the linearity of the sensor can be enhanced further by replacing the MOSFETs with bipolar transistors or any versatile materials such as gallium arsenide or gallium nitride-based transistors.</p></abstract>

Optimization of Grinding Parameters of Tool Steel by the Soft Computing Technique.

Grinding is one of the most complex and accurate machining processes, and the efficiency of the grinding wheel depends significantly on its surface properties. This work aims to propose an algorithmic manner that reduces the cost and time to conduct grinding of an optimized DIN 1.2080 tool steel (SPK) using a soft computing technique to obtain the best combination of input parameters including depth of cut (20, 40, 60 μm), wheel speed (15, 20, 25 m/s), feed rate (100, 300, 500 mm/s), and incidence angle (0, 30, 45 de grees) with respect to output parameters consisting of average surface roughness and specific grinding energy. According to the input parameters and their levels, an experiment using fractional factorial design of experiment (RFDOE) was designed. Later on, two parallel feed-forward backpropagation (FFBPNN) networks with similar topology made up of 4, 11, and 1 units in their input, hidden, and output layers are trained, respectively. After sensitivity analyses of networks for determination of the relative importance of input variables, a genetic algorithm (GA) adopting linear programming (LP) based on Euclidean distance is coupled to networks to seek out the best combinations of input parameters that result in minimum average surface roughness and minimum specific grinding energy. The findings revealed that RFDOE provides valid data for training FFBP networks with a total goodness value of more than 1.99 in both cases. The sensitivity analyses showed that feed rate (38.97%) and incidence angle (33.94%) contribute the most in the case of average surface roughness and specific grinding energy networks, respectively. Despite the similar surface quality based on scanning electron microscopy (SEM), the optimization resulted in an optimized condition of the depth of cut of 25.23 μm, wheel speed of 15.02 mm/s, feed rate of 369.45 mm/s, and incidence angle of 44.98 de grees, which had a lower cost value (0.0146) than the optimum one (0.0953). Thus, this study highlights that RFDOE with a hybrid optimization using FFBP networks-GA/LP can effectively minimize both average surface roughness and specific grinding energy of SPK.

Optimization and prediction of incremental sheet forming parameters of Titanium grade 5 sheet using a response surface methodology and artificial neural network

Single point incremental forming (SPIF) is an advanced, flexible, and cost-effective approach for producing complicated sheet metal objects quickly. Because of its low equipment cost, the process is best suited toward low or medium quantity batch production as the conventional stamping method remains cost-effective only for mass manufacture. During SPIF formation of titanium grade 5 materials, a response surface methodology and artificial neural network (ANN) model was created to optimize and estimate wall angle (Ømax) and average surface roughness ( Ra). The ANN model is developed using feed forward back propagation networks. Various combinations of transfer functions and number of neurons were used to create the ANNs (3- n-1, 3- n-2). The confirmation runs have been used to ensure that the ANN anticipated and practical findings have been in agreement. The generated ANN model (3- n-1) was capable of accurately forecasting the results of the experiment, with an overall R-value and Mean Square Error (MSE) of 0.99987 and 0.010905 for Ra, and 0.99999 and 0.00700 for wall angle. The best 3- n-2 models has an average R-value of 0.99992 and MSE of 0.05532, respectively. As a consequence of rapid ANN modeling technique, it became discovered that technical effort inside the SPIF process could be decreased.

Predicting the Chemical Attributes of Fresh Citrus Fruits Using Artificial Neural Network and Linear Regression Models

Different chemical attributes, measured via total soluble solids (TSS), acidity, vitamin C (VitC), total sugars (Tsugar), and reducing sugars (Rsugar), were determined for three groups of citrus fruits (i.e., orange, mandarin, and acid); each group contains two cultivars. Artificial neural network (ANN) and multiple linear regression (MLR) models were developed for TSS, acidity, VitC, Tsugar, and Rsugar from fresh citrus fruits by applying different independent variables, namely the dimensions of the fruits (length (FL) and diameter (FD)), fruit weight (FW), yield/tree, and soil electrical conductivity (EC). The results of ANN application showed that a feed-forward back-propagation network type with four input neurons (Yield/tree, FW, FL, and FD) and eight neurons in one hidden layer provided successful modeling efficiencies for TSS, acidity, VitC, Tsugar, and Rsugar. The effect of the EC variable was not significant. The hyperbolic tangent of both the hidden layer and the output layer of the developed ANN model was chosen as the activation function. Based on statistical criteria, the ANN developed in this study performed better than the MLR model in predicting the chemical attributes of fresh citrus fruits. The root mean square error of TSS, acidity, VitC, Tsugar, and Rsugar ranged from 0.064 to 0.453 and 0.068 to 0.634, respectively, for the ANN model, and 0.568 to 4.768 and 0.550 to 4.830, respectively, for the MLR model using training and testing datasets. In addition, the relative errors obtained through the ANN approach provided high model predictability and feasibility. In chemical attribute modeling, the FD and FL variables exhibited high contribution ratios, resulting in a reliable predictive model. The developed ANN model generally showed a good level of accuracy when estimating the chemical attributes of fresh citrus fruit.

Acid-activated Hibiscus sabdariffa seed pods biochar for the adsorption of Chloroquine phosphate: Prediction of adsorption efficiency via machine learning approach.

• Acid treated agrowaste was used for Chloroquine removal. • Maximum monolayer adsorption capacity for the system was 161.29 mg/g. • The mechanism of adsorption was predominantly chemisorption. • Freundlich and Pseudo Second Order models best described the adsorption system. • ANN model predicted the adsorption behaviour of CQ onto the prepared adsorbent. A constant increase in the release of pollutants into the environment poses a threat as this practice continually degrades water quality. One of the proffered solutions is the adsorption of pollutants onto adsorbents. The present study emphasized the performance of Hibiscus sabdariffa seed pods (HSP1) for removing Chloroquine phosphate (CQ) from aqueous media via adsorption. A machine learning tool (Artificial Neural Network, ANN) was used to predict the efficiency of CQ removal onto the prepared biochar. Different operational parameters were investigated for their influence and impact on CQ adsorption. HSP1 was also characterized using different physicochemical and spectrophotometric techniques. HSP1 remarkably displayed an outstanding performance for the elimination of CQ with a q max of 161.29 mg/g and percentage removal of 96.01%. The experimental data are well predicted by Pseudo Second Order (PSO) and Freundlich isotherm, indicating multilayer adsorption. The practicability and spontaneity of the adsorption process were confirmed through thermodynamic studies. A three-layer feedforward backpropagation network for the adsorption data was established using the Levenberg Marquardt training algorithm. The ANN model with structure 5-14-1, with Mean Square Error (8.01) and R 2 value (0.9823) was able to envisage good removal efficiency. It was concluded that the ANN model could predict the adsorption behavior of CQ on HSP1.

Machine Learning-Based Fragility Assessment of Reinforced Concrete Buildings.

In the past, large earthquakes caused the collapse of infrastructure and killed thousands of people in Pakistan, a seismically active region. Therefore, the seismic assessment of infrastructure is a dire need that can be done using the fragility analysis. This study focuses on the fragility analysis of school buildings in Muzaffarabad district, seismic zone-4 of Pakistan. Fragility curves were developed using incremental dynamic analysis (IDA); however, the numerical analysis is computationally time-consuming and expensive. Therefore, soft computing techniques such as Artificial Neural Network (ANN) and Gene Expression Programming (GEP) were employed as alternative methods to establish the fragility curves for the prediction of seismic performance. The optimized ANN model [5-25-1] was used. The feedforward backpropagation network was considered in this study. To achieve a reliable model, 70% of the data was selected for training and 15% for validation and 15% of data was used for testing the model. Similarly, the GEP model was also employed to predict the fragility curves. The results of both ANN and GEP were compared based on the coefficient of determination, R 2. The ANN model accurately predicts the global drift values with R 2 equal to 0.938 compared to the GEP model having R 2 equal to 0.87.

Modeling of sugarcane bagasse conversion to levulinic acid using response surface methodology (RSM), artificial neural networks (ANN), and fuzzy inference system (FIS): A comparative evaluation

Levulinic acid is recognized as a prominent value-added chemical that can be obtained from bioresources and has versatile industrial applications. This work reports bioprocess modeling of levulinic acid synthesis from sugarcane bagasse employing response surface methodology and artificial intelligence techniques, including artificial neural network and fuzzy inference system approaches. The influence of process parameters, namely reaction temperature, concentration of levulinic acid and reaction time on the production of levulinic acid was investigated. The levulinic acid production values predicted by empirical models were compared with experimentally acquired data. The predictive capability of various models was appraised by computing statistical indices. The artificial neural network model was determined to be the best predictive model with the highest coefficient of determination value of 0.96 and the lowest error values (root mean square error = 0.272, mean absolute error = 0.072 and mean absolute percentage deviation = 2 %). The feedforward back propagation network with 3–10-1 architecture was employed to model the production of levulinic acid. The process optimization was performed using the desirability function approach. The bagasse, on treatment under optimum conditions, with 1 M sulphuric acid at 190 °C for 15 min yielded 5.40 mg/mL levulinic acid accounting for 77.1 % process efficiency. The utilization of waste biomass sugarcane bagasse would offer a sustainable approach for the production of platform chemical levulinic acid.

Artificial neural network investigation of injectability and percolation of highly filled β -Tricalcium phosphate suspensions

Over the past few decades, calcium phosphate cement has been used successfully for bone reconstruction applications. As percutaneous surgical methods have developed, there is an increased interest in calcium phosphate cement injection behavior. The aim of this study is to minimize percolation (liquid phase migration under pressure) and maximize injectability (ratio of the extruded part to whole) of highly filled β-tri calcium phosphate (β-TCP) suspensions by varying capillary flow process parameters with an artificial neural network (ANN) approach. The effects of hydroxyethyl cellulose (HEC) and polyethylene glycol (PEG-400) were also studied as binder additives for injectable β-tri calcium phosphate pastes. Prepared suspensions were investigated by capillary and small amplitude oscillatory rheometry. The study predicted experimental input and output data by using Backpropagation Neural networks via the Levenberg-Marquardt algorithm. The ANN model was developed by feed-forward back propagation network and predict percolation (%) and injectability (%). A great agreement was observed between the predicted values by the ANN model and the experimental data for injectability (%) and percolation (regression coefficients) of 0.9984 and 0.9982 respectively. The results depict that ANNs can improve the accuracy of injectability and percolation results which can be used to optimize process and additive parameters for injectable bone cements and pastes. 2 wt% HEC was determined as the most effective factor to improve the rheological properties of highly filled β-TCP pastes which could be injected as much as 99.21 % at a rate of 15 mm/min through dies with L/D ratio of 15. Their percolation value was calculated as 0.82 %. Lubricative effect of PEG-400 additive with 2 wt% HEC to reduce injection force was also demonstrated.