Backpropagation Research Articles

Hemodynamic effects of bifurcation and stenosis geometry on carotid arteries with different degrees of stenosis.

Carotid artery stenosis (CAS) is a key factor in pathological conditions, such as thrombosis, which is closely linked to hemodynamic parameters. Existing research often focuses on analyzing the influence of geometric characteristics at the stenosis site, making it difficult to predict the effects of overall vascular geometry on hemodynamic parameters. The objective of this study is to comprehensively examine the influence of geometric morphology at different degrees of carotid artery stenosis and at bifurcation sites on hemodynamic parameters. A three-dimensional model is established using computed tomography angiography (CTA) images, and eight geometric parameters of each patient are measured by MIMICS. Then, Computational fluid dynamics (CFD) is utilized to investigate 60 patients with varying degrees of stenosis (10% to 95%). Time and grid tests are conducted to optimize settings, and results are validated through comparison with reference calculations. Subsequently, correlation analysis using SPSS is performed to examine the relationship between the eight geometric parameters and four hemodynamic parameters. In MATLAB, prediction models for the four hemodynamic parameters are developed using Back Propagation neural networks (BPNN) and multiple linear regression. The BPNN model significantly outperforms the multiple linear regression model, reducing MAE, MSE, and RMSE by 91.7%, 93.9%, and 75.5%, respectively, and increasing R² from 19.0% to 88.0%. This greatly improves fitting accuracy and reduces errors. This study elucidates the correlation and patterns of geometric parameters of vascular stenosis and bifurcation in evaluating hemodynamic parameters of CAS. This study opens up new avenues for improving the diagnosis, treatment, and clinical management strategies of CAS.

Research on Deflection Risk Assessment for Steel Box Girder Bridges Based on GA-BP Neural Network

Steel box girder bridges constitute a pivotal structural component in modern bridge engineering, confronting intricate mechanical environments and dynamic conditions during construction, with a particularly notable risk of deflection. Risk assessments predominantly rely on traditional mechanical analyses and empirical judgments, which need help to fully capture the dynamic construction changes and latent risks. This study introduces an innovative risk assessment methodology grounded in finite element analysis (FEA) and optimized by a genetic algorithm-enhanced back propagation neural network (GA-BP) to address these limitations. This approach entails constructing an FEA model to precisely simulate and predict the mechanical behavior during the construction phase, with field data validation ensuring the model’s accuracy. The GA-BP assessment model is established by further incorporating the genetic algorithm to optimize the BP neural network, enabling comprehensive, systematic, and efficient risk assessment. Through practical application case studies, this methodology demonstrates the ability to accurately identify the critical risk factors influencing deflection during the construction phase of steel box girder bridges, providing a scientific basis for construction control. This research holds significant theoretical value and practical significance, and it offers a scientific foundation for risk management, construction optimization, and safety assurance in future bridge engineering projects, thereby enhancing the overall quality and safety of bridges.

Prediction of Agricultural Carbon Emission Based on Improved BP Neural Network with Optimized Sparrow Search Algorithm

The accurate forecasting of agricultural carbon emissions is essential for formulating strategies to achieve carbon peak and neutrality objectives within the agricultural sector. However, existing methodologies for predicting agricultural carbon emissions have notable limitations. To address these shortcomings, Shanghai farm was considered as a case study to conduct research utilizing a neural network approach. Agricultural carbon emissions from the Shanghai farm from 2011 to 2021 were computed using the emission-factor method. Subsequently, a Back Propagation （BP） neural network model was developed to predict carbon emissions, employing the GDP of the planting, animal husbandry, and fishery sectors as input variables. The model was further improved through the application of an optimized sparrow search algorithm, which was then employed to forecast the future carbon emissions of the farm. The results show that the BP neural network improved via the optimized sparrow search algorithm demonstrated a prediction accuracy of 96.14%, a root mean square error （RMSE） of 12 100 t·a-1 and a correlation coefficient （R2） of 0.995 2. These metrics underscored the superior performance of the enhanced model. Compared with the multiple running results of pre-improved models, the neural network improved by the optimized sparrow search algorithm enhanced both the accuracy and stability of carbon emission prediction significantly, with the prediction accuracy consistently approaching approximately 95%, the root mean square error remaining below 20 000 t·a-1, and the correlation coefficient exceeding 0.99. Predictive analysis of future carbon emissions from the Shanghai farm indicated a predominant contribution from the animal husbandry sector to the total carbon emissions, suggesting that effective management of the scale of animal husbandry operations could significantly mitigate overall carbon emissions.

Application Analysis of Big Data-Driven Algorithm Music Creation Generation System

In the field of music, music generation systems based on big data-driven algorithms have become an important research direction. This paper aims to explore the application of big data-driven algorithmic music generation systems in music creation and music education. Through the statistical analysis of the user’s operation record of the music, and the prediction of the artist’s music listening volume in the next stage, it can be judged that the artist’s music listening volume is the highest in a period of time, these artists, as music ambassadors of their respective eras, not only represent a sound, but are also leaders and promoters of music trends. In order to more accurately grasp and predict the dynamics of the music market, especially the popularity of specific artists, this paper proposes an innovative data analysis method that combines quadratic exponential smoothing, autoregressive moving average (ARIMA) model, and BP (backpropagation) neural network model. Quadratic exponential smoothing is a time series prediction technique that predicts future trends by smoothing historical data. This method is particularly effective in handling data with obvious trend and seasonal characteristics, and is also applicable for predicting the number of artist auditions in the music industry. It can help us capture long-term trends in the popularity of artists and provide a basis for prediction. This paper discusses the application prospect of a music generation system driven by big data algorithms in music creation and music education.

Crushing Force Prediction Method of Controlled-Release Fertilizer Based on Particle Phenotype

This study proposed a method to predict the crushing force of controlled-release fertilizer granules based on their phenotypic characteristics to prevent coating damage during production, transport, and fertilization, which could affect nutrient diffusion rates. The phenotypic features, including sphericity, particle size, and texture, of three commonly used controlled-release fertilizers were obtained using machine vision, while the crushing force was measured using a universal testing machine. A principal component analysis was applied for data reduction, and the optimal parameters for the support vector machine (SVM) were selected using particle swarm optimization (PSO) combined with k-fold cross-validation. A particle swarm optimization–support vector machine (PSO-SVM) model was then developed to predict the crushing force based on fertilizer shape features. Compared with the traditional method, the innovation of this paper is that a non-destructive prediction method is proposed, which enables high-precision predictions of the crushing force by integrating multi-dimensional phenotypic features and an intelligent optimization algorithm. Comparative tests with a random forest regression, the K-nearest neighbor, a back propagation (BP) neural network, and a long short-term memory (LSTM) neural network have demonstrated that the PSO-SVM model outperforms these methods in terms of mean absolute error, root mean square error, and correlation coefficient, underscoring its effectiveness. The proportion of predictions within the −10% to +10% error range reached 0.82, 0.82, and 0.86 for the three fertilizers, confirming the high reliability and accuracy of the PSO-SVM method for non-destructive testing.

Construction of a back propagation neural network model for predicting urosepsis after flexible ureteroscopic lithotripsy based on heparin-binding protein and C-reactive protein levels.

To analyze the association of serum heparin-binding protein (HBP) and C-reactive protein (CRP) levels with urosepsis following flexible ureteroscopic lithotripsy (FURL) and to construct a back propagation neural network prediction model. A total of 428 patients with kidney stones who underwent FURL were enrolled. Patients were divided into sepsis group (n=42) and control group (n=386) according to whether post-operative urosepsis developed. Logistic regression analysis was used to determine the risk factors and interactions of post-FURL urosepsis. A Logistic regression model and a neural network model were developed for predicting post-FURL urosepsis following FURL, and their predictive performance was evaluated using ROC curves. Univariate analysis showed that stone surgery history, gender, urine culture, stone diameter, diabetes, operation time, white blood cell (WBC), platelet, CRP, and HBP levels were significantly associated with post-FURL urosepsis (P<0.05). Multivariate analysis identified positive urine culture, CRP, and HBP levels as independent risk factors for post-FURL urosepsis (P<0.05). Interaction analysis revealed that CRP and HBP showed both additive (RERI=8.453, 95%CI: 2.645-16.282; AP=0.696, 95%CI: 0.131-1.273; S=3.369, 95%CI: 1.176-7.632) and multiplicative (OR=1.754, 95%CI: 1.218-3.650) interactions, while CRP and urine culture demonstrated multiplicative interaction (OR=2.449, 95%CI: 1.525-3.825). The neural network model showed superior predictive performance compared to the Logistic regression model. CRP and HBP levels are independent risk factors for post-FURL urosepsis. The neural network model based on CRP and HBP exhibits higher predictive accuracy than the Logistic regression model, which may provide a reliable risk assessment tool for early discrimination and intervention of post-FURL urosepsis.

Intelligent Office Lighting Control Using Natural Light and a GA-BP Neural Network-Based System

Intelligent lighting control systems are essential for regulating office illumination. Both illuminance levels and uniformity are important factors influencing the comfort of the office lighting environment. Thus, designing automatic control systems to regulate lighting is essential. This study addresses the issue of natural glare by proposing a method that uses a genetic algorithm (GA) to optimize a backpropagation (BP) neural network model. The model predicts the angle of window slats, with the Sun altitude and azimuth angles as inputs, and the slat angle as the output. For artificial lighting control, a linear function is proposed to manage the relationship between work plane illuminance, natural light intensity, occupancy rates, adjacent luminaire illuminance, and the dimming factor (K). The optimal K value for each luminaire is determined using the least squares method in MATLAB. The intelligent lighting system transmits dimming factors via a ZigBee tree network structure to achieve target illuminance levels. The system’s effectiveness is validated through simulations in DIAlux software, demonstrating that the workplace illuminance in occupied areas reaches 500 lx, while, in unoccupied areas, it reaches 300 lx, with an illuminance uniformity greater than 0.7. This addresses the issue of low illuminance uniformity during daytime. Additionally, the lighting power densities (LPDs) of 1.53 W/m2 and 3.8 W/m2 are well below the specified threshold of 6 W/m2, indicating significant energy savings while maintaining compliance with office lighting standards.

The data mining and high-performance network model of tourism electronic word of mouth for analysis of factors influencing tourists’ purchasing behavior

This study establishes a deep learning model for personalized travel recommendations based on factors that affect tourists’ purchases to provide users with more accurate and personalized travel recommendations. Firstly, Natural Language Processing (NLP) technology is used to process and emotionally analyze tourism review information, dividing it into positive, negative, or neutral to understand tourists’ attitudes towards purchasing products and services. Secondly, a High-Performance Network (HPN) model is constructed based on factors that affect tourists’ purchases. The relationship among tourists, products, and word of mouth (WOM) is represented as a complex network to analyze and predict event occurrence patterns and influencing factors in tourism electronic word-of-mouth (EWOM) data. The construction of the model considers various factors, such as the spread of WOM, the impact of price, etc., to reveal the complex relationships among tourists, WOM, products, etc. Finally, the Recurrent Neural Network (RNN) model is combined with the Backpropagation (BP) model, the time series data is processed with the help of the gated recurrent unit, and the HPN model is trained and evaluated. The Yelp dataset is employed to verify the accuracy and feasibility of the model, which contains the score and review data of many tourist destinations. The results reveal that price, WOM, and destination are one of the main factors influencing tourists’ purchasing behavior, with WOM being the most significant. Positive WOM reviews remarkably increase product sales, while negative WOM has the opposite effect. The minimum expectation for age, occupation, education, personal monthly income, and tourists’ willingness to purchase is 0.00, and the minimum expectation for gender factors is 0.31. The RNN-BP hybrid model has higher accuracy and predictive ability, which is 1.73% and 2.30% more accurate than single models and traditional machine learning predictive models. In short, this study contributes to a better understanding travelers’ needs and preferences to optimize products and services and improve market competitiveness. In addition, the methods and models of this study can also be applied in EWOM data mining in other fields.

Evaluation and Prediction of Water Resources Carrying Capacity in Dongting Lake Area Based on County Unit and DWM-BP Neural Network Model

Evaluation of water resource carrying capacity is one of the methods used to measure the degree of realization of resource and environmental planning. This study takes 26 county-level units in the Dongting Lake area of Hunan Province as the evaluation object and screens 22 indicators for the evaluation of water resource carrying capacity. The comprehensive weight of the water resources carrying capacity of the Dongting Lake area is calculated using double weight methods (DWM) based on the analytical hierarchy process (AHP) and the entropy weighting method. And then, the back propagation (BP) neural network is used to predict the evolution of the alarm situation of the water resources carrying capacity. The results show the following: (1) In terms of time trend, the water resources carrying capacity of Dongting Lake area is generally stable and is between overload and critical state, but the change trends of water resources carrying capacity of each county are very different; (2) in terms of spatial distribution, the water resources carrying capacity in the western and southern regions of the Dongting Lake area is relatively high, while that in the Yueyang urban area in the eastern region is relatively low, showing a pattern of “high in the west and low in the east”; (3) among the criterion layers, the water resources support force has the highest weight and the smallest change, and the economic support force has the largest change in weight. The decline of water resources carrying capacity is closely related to the speed of economic development; (4) by 2025, the water resources carrying capacity of Nanxian County, Hanshou County, and Xiangyin County will be significantly increased from overload to critical state, and Dingcheng District will gradually turn from critical to overloaded status. This study is the first attempt to evaluate and predict the water resources carrying capacity of the Dongting Lake area at the county level so that the evaluation results are more applicable to grass-roots administrative units with decision-making power. The double-weighting method is used to determine the weights of the indicators so that the evaluation results can be more accurate.

Real-time 3D MR guided radiation therapy through orthogonal MR imaging and manifold learning.

In magnetic resonance image (MRI)-guided radiotherapy (MRgRT), 2D rapid imaging is commonly used to track moving targets with high temporal frequency to minimize gating latency. However, anatomical motion is not constrained to 2D, and a portion of the target may be missed during treatment if 3D motion is not evaluated. While some MRgRT systems attempt to capture 3D motion by sequentially tracking motion in 2D orthogonal imaging planes, this approach assesses 3D motion via independent 2D measurements at alternating instances, lacking a simultaneous 3D motion assessment in both imaging planes. We hypothesized that a motion model could be derived from prior 2D orthogonal imaging to estimate 3D motion in both planes simultaneously. We present a manifold learning technique to estimate 3D motion from 2D orthogonal imaging. Five healthy volunteers were scanned under an IRB-approved protocol using a 3.0 T Siemens Skyra simulator. Images of the liver dome were acquired during free breathing (FB) with a 2.6mm × 2.6mm in-plane resolution for approximately 10min in alternating sagittal and coronal planes at ∼5 frames per second. The motion model was derived using a combined manifold learning and alignment approach based on locally linear embedding (LLE). The model utilized the spatially overlapping MRI signal shared by both imaging planes to group together images that had similar signals, enabling motion estimation in both planes simultaneously. The model's motion estimates were compared to the ground truth motion derived in each newly acquired image using deformable registration. A simulated target was defined on the dome of the liver and used to evaluate model performance. The Dice similarity coefficient and distance between the model-tracked and image-tracked contour centroids were evaluated. Motion modeling error was estimated in the orthogonal plane by back-propagating the motion to the currently imaged plane and by interpolating the motion between image acquisitions where ground truth motion was available. The motion observed in the healthy volunteer studies ranged from 12.6 to 38.7mm. On average, the model demonstrated sub-millimeter precision and>0.95 Dice coefficient compared to the ground truth motion observed in the currently imaged plane. The average Dice coefficient and centroid distance between the model-tracked and ground truth target contours were 0.96±0.03 and 0.26mm±0.27mm respectively across all volunteer studies. The out-of-plane centroid motion error was estimated to be 0.85mm±1.07mm and 1.26mm±1.38mm using the back-propagation (BP) and interpolation error estimation methods. The healthy volunteer studies indicate promising results using the proposed motion modeling technique. Out-of-plane modeling error was estimated to be higher but still demonstrated sub-voxel motion accuracy.

State-of-charge estimation based on improved back-propagation neural network for lithium-ion batteries in energy storage power stations

This paper develops a novel approach for the state of charge (SOC) estimation of Lithium-ion batteries in energy storage power stations, leveraging an improved back-propagation (BP) neural network optimized by an immune genetic algorithm (IGA). Addressing the paramount importance of accurate SOC estimation for enhancing battery management systems, this work proposes a methodological enhancement aimed at refining estimation precision and operational efficiency. First, the mechanisms of temperature, current, and voltage impacts on SOC are revealed, which serve as the inputs of the neural network. Second, the improved BP neural network’s structure and optimization through an IGA are designed, emphasizing the mitigation of traditional BP neural networks’ limitations including slow convergence speed and complex parameterization. Through an extensive experimental setup, the proposed model is validated against standard BP neural networks across various discharge experiments at different temperatures and discharge currents. Results prove that the estimation accuracy of the proposed method reaches as high as 98.15% and faster converges compared to the traditional BP network, thereby being valuable practically.

Research on prediction of high energy microseismic events in rock burst mines based on BP neural network

In response to the frequent occurrence of high-energy microseismic events in coal mines in China, a back propagation neural network (BPNN) prediction model based on surface subsidence data has been proposed to provide a basis for safely and efficiently predicting coal mine disasters. Theoretical research on the relationship between surface displacement, mining disturbance, and high-energy microseismic event levels has demonstrated a significant correlation among these factors. When there is a sudden increase or decrease in surface displacement or mining disturbance, the advancing working face typically exhibits dynamic characteristics. Therefore, feature parameters relevant to predicting high-energy microseismic event levels were selected as input variables for the BPNN model. Raw data from 88 sets of microseismic events in the 301 working face of the third mining area of a certain coal mine in Inner Mongolia were extracted. First, outlier preprocessing was conducted to obtain a complete dataset, which is then divided into a training set and a testing set. The BPNN model was trained with the training set and subsequently tested to evaluate its predictive performance. Finally, by comparing several model evaluation metrics, it was found that the BPNN model outperforms other common models in predicting high-energy events. The overall prediction accuracy is 86.4%, and the root mean square error (RMSE) is 0.45, indicating that the BPNN-based prediction model for high-energy microseismic events in coal mines is feasible.

Thickness monitoring of threshing mixture on the oscillating plate of corn grain harvester

Cleaning is a critical operation in the corn grain harvesting process, and the operation is seriously affected by the uneven distribution of the threshing mixture on the oscillating plate. To monitor the thickness of the threshing mixture on the oscillating plate of the corn grain harvester, in this study, we adopted the lever principle to design a corn threshing mixture thickness monitoring device based on the piezoresistive effect and theoretically analyzed the lever impact mechanics. The factors affecting the force on the sensor of the monitoring device are the vibration frequency of the oscillating plate, the thickness of the threshing mixture, and grain moisture content, which were obtained through theoretical analysis. The operational performance of the corn threshing mixture thickness monitoring device was assessed through a set of single-factor experiments, revealing the influence laws of three factors on the impact voltage: vibration frequency, thickness of the threshing mixture, and grain moisture content. A back-propagation (BP)11Back-propagation (BP) neural network prediction model was established using an orthogonal experiment with impact voltage, vibration frequency, and grain moisture content as input layers and the thickness of the corn threshing mixture as the output layer. An STM32 microcontroller was used as the primary control unit to build a thickness monitoring data acquisition and processing system that could process and operate the impact voltage collected by the pressure sensor and the vibration frequency signal collected by a Hall sensor. The data were wirelessly transmitted to a PC to predict the thickness of the threshing mixture by using the trained BP neural network. The experimental results of monitoring the variation in corn threshing mixture thickness demonstrated that the device could effectively monitor changes in thickness. The monitoring accuracy of the monitoring device was found to be over 90%, and the system can be used for monitoring the threshing mixture thickness on the oscillating plate of the corn grain harvester.

Artificial Intelligence without Restriction Surpassing Human Intelligence with Probability One: Theoretical Insight into Secrets of the Brain with AI Twins of the Brain

Artificial Intelligence (AI) has apparently become one of the most important techniques discovered by humans in history while the human brain is widely recognized as one of the most complex systems in the universe. One fundamental critical question which would affect human sustainability remains open: Will artificial intelligence (AI) evolve to surpass human intelligence in the future? This paper shows that in theory new AI twins with fresh cellular level of AI techniques for neuroscience could approximate the brain and its functioning systems (e.g. perception and cognition functions) with any expected small error and AI without restrictions could surpass human intelligence with probability one in the end. This paper indirectly proves the validity of the conjecture made by Frank Rosenblatt 70 years ago about the potential capabilities of AI, especially in the realm of artificial neural networks. This paper also gives the answer to the two widely discussed fundamental questions: 1) whether AI could have potentials of discovering new principles in nature; 2) whether error backpropagation (BP) algorithm commonly and efficiently used in tuning parameters in AI applications is also adopted in the brain. Intelligence is just one of fortuitous but sophisticated creations of the nature which has not been fully discovered. Like mathematics and physics, with no restrictions artificial intelligence would lead to a new subject with its self-contained systems and principles. We anticipate that this paper opens new doors for 1) AI twins and other AI techniques to be used in cellular level of efficient neuroscience dynamic analysis, functioning analysis of the brain and brain illness solutions; 2) new worldwide collaborative scheme for interdisciplinary teams concurrently working on and modelling different types of neurons and synapses and different level of functioning subsystems of the brain with AI techniques; 3) development of low energy of AI techniques with the aid of fundamental neuroscience properties; and 4) new controllable, explainable and safe AI techniques with reasoning capabilities of discovering principles in nature.

Study on quantitative interpretation of uranium spectral gamma-ray logging based on machine learning algorithm

Spectral gamma-ray logging stands out as an efficacious methodology in the exploration of uranium(U). In order to address the challenges associated with low statistical efficacy in spectral analysis and mitigate the impact of spectral drift, machine learning algorithms such as Back Propagation (BP) neural network, Generalized Regression Neural Network (GRNN), and Support Vector Machine (SVM) have been employed for the quantitative interpretation of uranium. A method rooted in machine learning algorithms for energy spectral analysis has been proposed, catering to the analysis of high-speed spectra logging and gamma-ray spectra characterized by spectral drift. Examinations conducted on standard model wells containing uranium revealed that the BP neural network exhibited commendable accuracy in uranium interpretation, achieving quantification accuracy rates of 86.986 % and 93.478 % for low-grade and medium-high-grade uranium ores in the Testing Set, respectively. Notably, marginal variations in the model's quantification errors were observed under diverse logging speeds and spectral drift conditions, underscoring the capacity of gamma-ray spectral quantitative interpretation through machine learning algorithms to effectively surmount the impacts of logging speed and spectral drift. This machine learning-based approach to energy spectral analysis proved instrumental in enhancing traditional logging speeds to 6 m/min, presenting a novel perspective for the quantitative interpretation of uranium spectral gamma-ray logging at heightened logging speeds.

Optimizing CNC turning of AISI D3 tool steel using Al₂O₃/graphene nanofluid and machine learning algorithms

Turning AISI (American Iron and Steel Institute) D3 tool steel can be challenging due to a lack of optimal process parameters and proper coolant application to achieve high surface quality and temperature control. Machine learning helps in predicting the optimal parameters, whereas nanofluids enhance cooling efficiency while preserving both the tool and the workpiece. This work intends to utilize advanced machine learning approaches to optimize process parameters with the application of hybrid nanofluids (Al2O3/graphene) during the CNC turning of AISI D3. The Response Surface Methodology (RSM), Back Propagation (BP) neural networks, and Genetic Algorithms (GA) will be utilized to model and predict optimal turning parameters to enhance surface quality and manage tool tip temperature. The experiments ranged the cutting speed, nanofluid concentration, depth of cut, and feed rate from 150 to 180 m/min, 0.3 to 0.9 wt.%, 0.5 to 0.9 mm, and 0.03-0.07 mm/rev. RSM and ANN analyses showed that cutting speed and feed rate had a significant effect on surface quality, contributing 11.5% and 10.5%, respectively, whereas the nanofluid affected tool tip temperature by 42.5%. The GA determined that the optimal cutting speed became 150 m/min, the feed rate was 0.05 mm/rev, the cutting depth was 0.6 mm, and the nanofluid concentration was 0.8%. At temperatures ranging from 23.01°C to 28.41°C, these conditions produced a desirable surface roughness of 0.16 to 0.45 μm. The findings emphasize the benefits of utilizing Al2O3/graphene nanofluid and machine learning algorithms in CNC turning to improve surface roughness and control temperature.

Performance prediction of 304 L stainless steel based on machine learning

With the development of testing technology and data mining methodologies, machine learning (ML) has been widely applied for predicting the performance of materials in various systems including stainless steel with improved performance. To address the limitations of traditional experimental and statistical methods in predicting the thermal deformation of materials, a predictive machine learning model was developed based on the data obtained from thermal simulation compression tests. Specifically, the Arrhenius and the Modified Johnson-Cook (J-C) Constitutive Model were developed utilizing experimental data to initially predict the rheological behavior of 1.52% Cu-304L stainless steel. Then, a physical metallurgy (PM)-guided Back Propagation (BP) model was developed, and Genetic Algorithm (GA), Whale Optimization Algorithm (WOA), and Mind Evolutionary Algorithm (MEA) were incorporated into the model for optimization purposes, respectively. Finally, the results indicate that the PM-MEA-BP model exhibits superior predictive performance, accurately forecasting the texture evolution of 304L stainless steel with random crystal orientation under rolling deformation conditions. Additionally, the present work also clearly demonstrated that the model not only satisfies precision requirement but also has certain guiding significance for optimizing process parameters and forecasting the microstructure and properties of stainless steel.

Machine learning-based performance prediction for energy storage medium-deep borehole ground source heat pump systems

With the rapid development of artificial intelligence, data-driven prediction models play an important role in energy demand forecasting and performance prediction. This study established performance prediction models for medium-deep borehole ground source heat pump (MDB-GSHP) systems to predict the coefficient of performance (COP) of GSHP, utilizing back propagation neural network (BPNN), extreme learning machine (ELM), support vector machine (SVM), and particle swarm optimization-support vector machine (PSO-SVM) method that optimizes the penalty parameter (C), insensitive loss parameter (ε), and kernel parameter (γ) of SVM using PSO. Operational data were collected through field experiments, and typical parameters were selected as features to establish the feature set. The feature set was then optimized using Pearson correlation analysis and recursive feature elimination (RFE), resulting in the creation of five distinct feature sets. Error analysis and trend evaluation results indicate that the combined feature set (FS5), which incorporates the advantages of multiple feature selection methods, demonstrates the best performance. The PSO-SVM model exhibits outstanding performance under various input conditions, achieving an accuracy of over 90% within the error range. When using FS5, the PSO-SVM model achieves a mean absolute percentage error (MAPE) of 0.037, mean absolute error (MAE) of 0.103, root mean square error (RMSE) of 0.125, coefficient of multiple determinations (R2) of 0.970, and explained variance score (EVS) of 0.967, showcasing excellent predictive performance. The research results can provide a basis for the formulation of storage-related operational parameters and the optimization of system operation for energy storage in MDB-GSHP heating systems.

Intensified customer churn Prediction: Connectivity with weighted Multi-Layer Perceptron and Enhanced Multipath Back Propagation

In the telecommunication industry, forecasting customer turnover in telecom networks is crucial for maintaining customers and increasing profits. The proposed model explores the importance of predicting churn, emphasizing its financial impact and strategic significance for telecommunications companies. Manual methods for predicting churn are restricted due to their dependence on basic models and human opinion, leading to less than ideal precision and effectiveness. Artificial Intelligence (AI)-based methods have arisen as promising solutions in light of these limitations. Nevertheless, existing AI methods frequently encounter issues like over-fitting, restricted interpretability, and suboptimal generalization. The presented system introduces a novel technique, named “MBP-WMLP” abbreviated as Multipath Back Propagation with Weighted MLP, to improve prediction accuracy in telecommunication networks. The respective approach utilizes a specialized multi-layer perceptron (MLP) structure with weights, designed for managing the intricacies of telecommunications data. Moreover, an improved multipath back-propagation method is presented to improve the optimization of model training and convergence. The projected model combines weighted MLP and enhanced multipath back-propagation to achieve better prediction accuracy, increased interpretability, and improved generalization capabilities. Furthermore, the proposed technique will be applied for authentic Telco customer churn datasets containing sanitized customer activity features and churn labels indicating subscription cancellations for creating predictive models. The projected approach is intended to show potential for improving customer loyalty tactics and boosting profits for telecom companies in a more competitive market environment.

Machine learning-based prediction of CoCrFeNiMo0.2 high-entropy alloy weld bead dimensions in wire arc additive manufacturing

Wire arc additive manufacturing (WAAM) is a promising method to fabricate large-sized components. By adjusting WAAM process parameters, dimensions of WAAM-produced weld beads can be optimized. To this end, the current study adopted the cold metal transition (CMT) process to produce different-sized beads of CoCrFeNiMo0.2 high-entropy alloy (HEA), varying WAAM parameters and linking them with the formed bead dimensions and bead-substrate contact angles. Three machine learning algorithms, namely back propagation neural network (BPNN), support vector regression (SVR), and random forest regression (RFR), were used to predict bead dimensions and contact angles under various WAAM parameters. The BPNN model has great prediction performance in the height of beads. The SVR model has the highest accuracy in predicting the width and cross-sectional area of beads. The RFR outperforms the other two models in contact angles prediction. This work not only provides a reference for the WAAM of high-entropy alloys, but also provides new ideas for predicting bead size in WAAM.