Model Predictive System Research Articles

Frequency experimental identification approach for single-phase induction motor common-mode parameters

Introduction. The presence of broad-spectrum and high-amplitude electromagnetic interference (EMI) within a single-phase induction motor (SPIM) drive poses a significant threat to both the system and other electronic equipment. High-frequency (HF) models of electrical motors play a critical role in overcoming these challenges, as they are essential for characterizing electromagnetic compatibility (EMC) in drives and designing effective EMI filters. The novelty of this study proposes an enhanced HF motor model based on transfer functions (TFs) to accurately represent the motor’s behavior at HFs for frequency-domain analyses in the range of 100 Hz to 30 MHz. Purpose. The equivalent HF model for a SPIM is discussed in this paper. The suggested equivalent circuit describes a motor’s common-mode (CM) properties. Methodology. HF model was developed by a frequency-domain analysis utilizing an experimental setup and MATLAB software. The motor impedance analysis is based on the measurement of variations in motor characteristics as a function of frequency in the CM setup. Originality. TF has been tuned using an asymptotic identification method of Bode to match the behavior of the real impedances of the motor parameters as a function of the frequency in the CM configuration. This tuned TFs are then synthesized into a comprehensive wideband EMC equivalent circuit model using the Foster network technique, which can be then simulated in any Spice-based simulator tools. Results. The proposed mathematical model was employed to conduct simulations, and the resulting predictions were validated against experimental data. CM response of the EMC equivalent circuit at low, medium, and HFs were compared between simulations and experimental measurements using Lt-Spice simulator software. Practical value. It is observed that results show satisfactory agreement with the measurements over a large frequency bandwidth [100 Hz–30 MHz], and the equivalent model of SPIM can be cascaded with other electronic and electrical modules to form a complete single-phase electric drive system model for fast analysis and prediction of system level EMI and electromagnetic sensitivity. References 37, table 5, figures 13.

Privacy-preserving State of Health prediction for electric vehicle batteries: A comprehensive review

This work presents an in-depth systematic literature review of privacy-preserving machine learning techniques for battery State of Health (SoH) prediction in electric vehicles (EVs). Our review methodically analyses a corpus of 43 research articles and publications spanning from 2012 to 2024 which provides a comprehensive landscape of the field’s evolution and current trends. This review covers a range of machine learning techniques and uniquely addresses first-of-its-kind privacy needs specific to SoH prediction for EVs, with a detailed examination of the integration of privacy-preserving methods. We also delve into the key challenges associated with data processing and feature engineering, and how these challenges are managed. The methodology employed includes not only the identification but also a thematic analysis of the literature, focusing on how these techniques balance data confidentiality with analytical performance. We proposed a privacy preserving system model for SoH prediction. The review is further enriched by various real-time applications and case studies, illustrating the practical implementation and efficacy of the discussed methods. This systematic approach provides a well-rounded view of the existing solutions and highlights gaps for future research, offering invaluable insights for both academic and industrial stakeholders in the domain of electric vehicle technology.

Priorities, opportunities, and challenges for integrating microorganisms into Earth system models for climate change prediction.

Climate change jeopardizes human health, global biodiversity, and sustainability of the biosphere. To make reliable predictions about climate change, scientists use Earth system models (ESMs) that integrate physical, chemical, and biological processes occurring on land, the oceans, and the atmosphere. Although critical for catalyzing coupled biogeochemical processes, microorganisms have traditionally been left out of ESMs. Here, we generate a "top 10" list of priorities, opportunities, and challenges for the explicit integration of microorganisms into ESMs. We discuss the need for coarse-graining microbial information into functionally relevant categories, as well as the capacity for microorganisms to rapidly evolve in response to climate-change drivers. Microbiologists are uniquely positioned to collect novel and valuable information necessary for next-generation ESMs, but this requires data harmonization and transdisciplinary collaboration to effectively guide adaptation strategies and mitigation policy.

Development and optimization of a prediction system model for mechanical properties in rotary friction-welded polyamide joints using the SVM approach and GA optimization

Development and optimization of a prediction system model for mechanical properties in rotary friction-welded polyamide joints using the SVM approach and GA optimization

Optimising building heat load prediction using advanced control strategies and Artificial Intelligence for HVAC system

Amid the dynamic challenges posed by the COVID-19 era, this study offers a nuanced exploration, delving into the complexities of optimising building heat load prediction. This study addresses the imperative challenge of optimising building heat load prediction by implementing advanced control strategies and integrating Artificial Intelligence (AI) into air conditioning systems. The study emphasises the need to design HVAC devices for minimal energy consumption without compromising comfort conditions. The study introduces an intelligent predictive adaptive neuro-fuzzy inference system (ANFIS) model that proves highly capable of accurately predicting HVAC performance outcomes while contributing to the development of a comprehensive dataset. The uncertainty percentage is evaluated across various membership functions, with the trapezoidal membership exhibiting the lowest error rate, followed by the Gaussian membership function. Weather parameters crucial to ventilation efficiency and heat load are examined, leading to the identification of an optimal combination involving 45 % relative humidity, 13 °C dry bulb temperature, and 5 km/h wind speed. The current system demonstrates significant efficiency improvements, with ventilation and heat load rates reaching 93 % and 97 %, respectively, compared to pre-COVID-19 conditions. The findings underscore the importance of considering these parameters in future HVAC designs, particularly in the context of COVID-19 guidelines (75 % and 79 %, respectively).

An Automated Prostate-cancer Prediction System (APPS) Based on Advanced DFO-ConGA2L Model using MRI Imaging Technique

The prostate cancer is a deadly form of cancer that assassinates a significant number of men due of its mediocre identification process. Images from people with cancer include important and intricate details that are difficult for conventional diagnostic methods to extract. This work establishes a novel Automated Prostate-cancer Prediction System (APPS) model for the goal of detecting and classifying prostate cancer utilizing MRI imaging sequences. The supplied medical image is normalized using a Coherence Diffusion Filtering (CDFilter) approach for improved quality and contrast. The appropriate properties are also extracted from the normalized image using the morphological and texture feature extraction approach, which helps to increase the classifier's accuracy. In order to train the classifier, the most important properties are also selected utilizing the cutting-edge Dragon Fly Optimized Feature Selection (DFO-FS) algorithm. Using this method greatly improves the classifier's overall disease diagnosis performance in less time and with faster processing. More specifically, the provided MRI input data are used to categorize the prostate cancer-affected and healthy tissues using the new Convoluted Gated Axial Attention Learning Model (ConGA2L) based on the selected features. This study compares and validates the performance of the APPS model by looking at several aspects using publicly available prostate cancer data.

Predictive direct control strategy of unified power quality conditioner based on power angle control

The unified power quality conditioner (UPQC), based on power angle control (PAC), addresses the power distribution issue and enhances equipment utilization between two active power filters (APF) of UPQC by employing conventional linear control algorithms that have complex control structures and exhibit challenges in adjusting controller parameters and control delays. This study proposes a UPQC predictive direct control strategy based on power angle control (PDCS-PAC). We combine the direct control strategy with the finite control set model predictive control (FCS-MPC) to establish the UPQC finite set model predictive direct control system model in the dq coordinate system. This approach simplifies the controller structure and alleviates the control algorithm’s complexity. Based on a detailed analysis of the PAC mechanism, an instantaneous power angle determination method is proposed based on the reactive power equalization technique, and a predictive direct control strategy given the current generation mechanism is constructed for the series and shunt sides of the UPQC, considering the active power balance of the UPQC system and the principle of constant load fundamental voltage amplitude. Finally, we construct a simulation platform and a laboratory prototype to validate the feasibility and efficacy of the proposed control strategy.

Data Mining for Quality Prediction in Software-as-A-Service Concept: A Case Study in Offset Printing Company

Purpose: This research aims to design a model of quality prediction system using data mining methods in the software-as-a-service (Saas) environment in order to facilitate manufacturers to be able to analyse process and product quality without software investment.
 Methodology/Approach: To develop the quality prediction model, this study utilized a data mining methodology to extract knowledge from historical data collected from the offset printing industry, focusing on manufacturing parameters. Four classification algorithms (Decision Tree, k-NN, Naive Bayes, Random Tree) were employed and compared to identify the most precise model specifically tailored for offset printing. Subsequently, the prediction model was integrated into a web-based system to enable quality prediction.
 Findings: This study demonstrates practicality of integrating quality prediction into the SaaS framework, specifically for offset printing. This integration is designed to predict how manufacturing control parameters, such as printing slope angle, engine temperature, paper size, ink density, and roller speed, relate to the occurrence of product defects such as crumpled paper and imprecise printing.
 Research Limitation/implication: Generalizability is constrained by its focus on the offset printing industry, and prediction accuracy relies on historical data, which can vary across manufacturing sectors, affecting model performance.
 Originality/Value of paper: This article presents the concept and practical implementation of utilizing data mining in a SaaS environment to enhance the quality of manufacturing, with a particular emphasis on the offset printing sector.

Performance of a hybrid gain ensemble data assimilation system based on the GRAPES_Meso model

In this paper, a hybrid gain data assimilation (HGDA) method was introduced into the mesoscale version of the Global/Regional Assimilation and Prediction System (GRAPES_Meso) model. To further improve the forecasting performance of the GRAPES_Meso model, a scheme combining the HGDA and multiscale incremental analysis update (IAU) methods was first proposed in this work. To evaluate the performance of the HGDA method in the GRAPES_Meso model, different initialization schemes, including the GRAPES three-dimensional variational (3DVAR), HGDA and HGDA multiscale IAU schemes, were compared for a tropical cyclone (TC) case (Lupit, 2021). The results showed that the HGDA scheme outperformed the GRAPES-3DVAR scheme in forecasting the TC position and intensity. Using the optimal relaxation times, the HGDA multiscale IAU scheme attained the best performance in forecasting the TC position, intensity and precipitation. In addition, 3-month quasioperational comparative experiments were conducted with different assimilation schemes. Rainfall validation showed that the HGDA multiscale IAU method yielded a higher threat score (TS) and equitable threat score (ETS) and a lower bias score than did the 3DVAR multiscale IAU method. Especially in the first 18 h of the forecast, the HGDA scheme could increase the TS and ETS values by 11% and 6%, respectively, compared to the control and 3DVAR experiments. The results demonstrated that the HGDA method resulted in better prediction performance of the GRAPES_Meso model than did the GRAPES-3DVAR method.

Soil-Derived Dust PM10 and PM2.5 Fractions in Southern Xinjiang, China, Using an Artificial Neural Network Model

Soil-derived dust emissions have been widely associated with health and environmental problems and should therefore be accurately and reliably estimated and assessed. Of these emissions, the inhalable PM10 and PM2.5 are difficult to estimate. Consequently, to calculate PM10 and PM2.5 emissions from soil erosion, an approach based on an artificial neural network (ANN) model which provides a multilayered, fully connected framework that relates input parameters and outcomes was proposed in this study. Owing to the difficulty in obtaining the actual emissions of soil-derived PM10 and PM2.5 over a broad area, the PM10 and PM2.5 simulated results of the ANN model were compared with the published results simulated by the widely used wind erosion prediction system (WEPS) model. The PM10 and PM2.5 emission results, based on the WEPS, agreed well with the field data, with R2 values of 0.93 and 0.97, respectively, indicating the potential for using the WEPS results as a reference for training the ANN model. The calculated r, RMSE and MAE for the results simulated by the WEPS and ANN were 0.78, 3.37 and 2.31 for PM10 and 0.79, 1.40 and 0.91 for PM2.5, respectively, throughout Southern Xinjiang. The uncertainty of the soil-derived PM10 and PM2.5 emissions at a 95% CI was (−66–106%) and (−75–108%), respectively, in 2016. The results indicated that by using parameters that affect soil erodibility, including the soil pH, soil cation exchange capacity, soil organic content, soil calcium carbonate, wind speed, precipitation and elevation as input factors, the ANN model could simulate soil-derived particle emissions in Southern Xinjiang. The results showed that when the study domain was reduced from the entire Southern Xinjiang region to its five administrative divisions, the performance of the ANN improved, producing average correlation coefficients of 0.88 and 0.87, respectively, for PM10 and PM2.5. The performances of the ANN differed by study period, with the best result obtained during the sand period (March to May) followed by the nonheating (June to October) and heating periods (November to February). Wind speed, precipitation and soil calcium carbonate were the predominant input factors affecting particle emissions from wind erosion sources. The results of this study can be used as a reference for the wind erosion prevention and soil conservation plans in Southern Xinjiang.

Fault prediction model in wind turbines using deep learning structure with enhanced optimisation algorithm

Digital Twin (DT) is used for lifetime monitoring of the drive train and can be a costly option. This proposal adopts the predictive modelling of wind turbines by digital twins by deep learning strategies. Initially, the data is acquired from publicly available wind turbine datasets. Next, the deep features and statistical features are extracted, and the autoencoder is adapted to get the deep features. Then, the Enhanced Marine Predators Algorithm (EMPA) is to select the optimal weighted fused features, where the EMPA would tune the weights used for fusion and the features selection. Finally, the predictive modelling is done via a newly recommended Adaptive Deep Temporal Convolution Network with an Attention Mechanism (ADTCN-AM). It is tuned for precise outcomes with the help of EMPA for forecasting the wind speed and predicting the generated power. The comparative performance analysis of the recently used wind prediction system model shows better efficient results.

Security control based on variable‐step predictive approach for networked control system with denial‐of‐service attacks

AbstractThis paper investigates the variable‐step predictive control problem for networked control system (NCS) with denial‐of‐service (DoS) attacks and model uncertainty. An event‐based variable‐step predictive scheme determined by accumulated error is firstly formulated to compensate the impact of DoS attacks. Based on the presence of DoS attacks and predictive control signals, NCS with DoS attacks is divided into three different operation modes and is described by switching system. With the above prediction scheme and system model, sufficient conditions are derived for ensuring the stability of the underlying system. Finally, an example is given to verify the validity of the theoretical results.

Hybrid forecasting: blending climate predictions with AI models

Abstract. Hybrid hydroclimatic forecasting systems employ data-driven (statistical or machine learning) methods to harness and integrate a broad variety of predictions from dynamical, physics-based models – such as numerical weather prediction, climate, land, hydrology, and Earth system models – into a final prediction product. They are recognized as a promising way of enhancing the prediction skill of meteorological and hydroclimatic variables and events, including rainfall, temperature, streamflow, floods, droughts, tropical cyclones, or atmospheric rivers. Hybrid forecasting methods are now receiving growing attention due to advances in weather and climate prediction systems at subseasonal to decadal scales, a better appreciation of the strengths of AI, and expanding access to computational resources and methods. Such systems are attractive because they may avoid the need to run a computationally expensive offline land model, can minimize the effect of biases that exist within dynamical outputs, benefit from the strengths of machine learning, and can learn from large datasets, while combining different sources of predictability with varying time horizons. Here we review recent developments in hybrid hydroclimatic forecasting and outline key challenges and opportunities for further research. These include obtaining physically explainable results, assimilating human influences from novel data sources, integrating new ensemble techniques to improve predictive skill, creating seamless prediction schemes that merge short to long lead times, incorporating initial land surface and ocean/ice conditions, acknowledging spatial variability in landscape and atmospheric forcing, and increasing the operational uptake of hybrid prediction schemes.

An adaptive neuro-fuzzy inference system white-box model for real-time multiphase flowing bottom-hole pressure prediction in wellbores

The majority of published empirical correlations and mechanistic models are unable to provide accurate flowing bottom-hole pressure (FBHP) predictions when real-time field well data are used. This is because the empirical correlations and the empirical closure correlations for the mechanistic models were developed with experimental datasets. In addition, most machine learning (ML) FBHP prediction models were constructed with real-time well data points and published without any visible mathematical equation. This makes it difficult for other readers to use these ML models since the datasets used in their development are not open-source. This study presents a white-box adaptive neuro-fuzzy inference system (ANFIS) model for real-time prediction of multiphase FBHP in wellbores. 1001 real well data points and 1001 normalized well data points were used in constructing twenty-eight different Takagi–Sugeno fuzzy inference systems (FIS) structures. The dataset was divided into two sets; 80% for training and 20% for testing. Statistical performance analysis showed that a FIS with a 0.3 range of influence and trained with a normalized dataset achieved the best FBHP prediction performance. The optimal ANFIS black-box model was then translated into the ANFIS white-box model with the Gaussian input and the linear output membership functions and the extracted tuned premise and consequence parameter sets. Trend analysis revealed that the novel ANFIS model correctly simulates the anticipated effect of input parameters on FBHP. In addition, graphical and statistical error analyses revealed that the novel ANFIS model performed better than published mechanistic models, empirical correlations, and machine learning models. New training datasets covering wider input parameter ranges should be added to the original training dataset to improve the model's range of applicability and accuracy.

Personalized Lane Change Planning and Control By Imitation Learning From Drivers

In this article, we propose a novel personalized planning and control approach for lane change assistance system which can efficiently learn a model prediction control (MPC)-based driver-specific lane-changing policy via end-to-end imitation learning from a few driver demonstrations. Specifically, we build a novel learnable predictive model of the vehicle-driver system and design an adaptable cost function for the MPC-based lane change controller. We then calculate the gradient of the imitation loss with respect to the personalization parameters of the model and cost function via differentiating the optimality conditions, and update those parameters to minimize the imitation loss in an end-to-end fashion. A semi-physical simulation on a driving simulator and a closed-loop test on a real vehicle are conducted to validate the learning ability and personalized control performance. The results show that 1) the proposed method can automatically implement both the generalized and the personalized lane change planning and control by learning from demonstration data; 2) the proposed controller can adapt to different driver-specific behaviors; and 3) the proposed approach outperforms the model-free learning approach in terms of imitation accuracy, interpretability, data efficiency, and generalized performance.

An integrated security approach for vehicular networks in smart cities

Fog computing, which is an extension of cloud computing is one of the cornerstone for Internet of Things, that witnessed rapid growth because of its ability to enhance several difficult problems such as network congestion, latency, and the lack of regional autonomy. However, privacy concerns and the resulting inefficiency are causing the performance of fog computing to suffer. While suffering from poisoning attacks, the vast majority of current works do not take into consideration of proper balance between them. Specifically, we present blockchain‐enabled secure federated learning in vehicle network (BSFLVN) system model for traffic flow prediction in urban computing to overcome the aforementioned difficulties and narrow the gap. When vehicle devices trade local learning updates, BSFLVN enables them to be exchanged with a blockchain‐based global learning model, which is confirmed by miners. To improve accuracy of classification we proposed federated learning‐based gated recurrent unit for local model update using FL‐GRNN algorithm and global model update using FL‐AGG algorithm. The BSFLVN, which is built on top of this, allows autonomous deep learning‐based GRU to take place without the need for a centralized authority to maintain the global model and coordinate by using the PoW consensus mechanism of blockchain. For preserving privacy and security of local and global model updates we employ the LDP mechanism. For the analysis of the latency performance of BSFLVN, as well as the derivation of the best block production rate we consider communication, consensus delays, and computing cost. The results of a thorough examination demonstrate that BSFLVN outperforms its competitors in terms of privacy protection, efficiency, and resistance to poisoning attacks, among other areas. Various deadline time iteration process is simulated for result evaluation using Fashion MINIST data in which over 93% of accuracy is obtained.

Hybrid bat–grasshopper and bat–modified multiverse optimization for solar photovoltaics maximum power generation

A hybrid BAT with Grasshopper (GH) algorithm and BAT-MMVO (Modified Multiverse Optimization) are exhibited for harvesting maximum power from photovoltaics (PV) using the Xilinx System Generator (XSG) implanted controller. Using a hybrid BAT-GH and BAT-MMVO algorithm, the proposed implanted controller finds the best switching pulse for the boost converter. The implanted controller, switching schemes, and the Photovoltaic (PV) supported boost converter were built using the XSG domain. The hardware implementation of the best two cases were done using a microcontroller in a smaller scale. This aims to gather the maximum amount of power by a PV array for solar irradiation and cell temperature under varied environmental situations. The PV structure in the XSG domain is used to construct the system model for prediction. The major emphasis of this work is to keep the difference of actual power and reference power as minimum. Finally, the implanted controller's performance is compared to that of other existing hybrid controllers. The performance of the proposed algorithm is found to yield good results in terms of power extraction. The theoretical and experimental results are presented. The computational efforts for the implementation of the algorithm are found to be less complex when compared to other existing methods.

Development of a Predictive System Model Using Big Data in the Transport Sector

This article discusses the possibility of creating a predictive system model using smart innovative technologies to generate a request for spare parts for the automotive industry using big data analysis, which is quite relevant for many transport, logistics and repair companies. The authors seek to generalize and systematize research in this area, with the possibility of integrating practical knowledge and big data for the implementation of urgent management and logistics tasks that will allow economic growth. In addition, the relevance of timely diagnostics and rapid leveling of vehicle defects is explored in light of current market conditions. Using data from the domestic market, a hypothesis has been proposed for specific parts and assemblies that may fail for a given car model. The top-selling models on the Russian second-hand market, consisting of 9 brands and 27 models from foreign manufacturers, were selected. An algorithm for analyzing the selected data set was developed, implemented using the Python programming language in Jupiter Notebook. Following a comprehensive investigation of the car's flaws, stacked diagrams were created to show the flaws, and the relevance of the 27 most popular model's flaws and their structural makeup were determined according to the country of origin. A model for predicting used car spare parts based on the results of the analysis of the structure of defects has been developed. The model combines data from revocable companies, feedback from car owners, maintenance services and component suppliers. Also, this article establishes the direction for future research in this area.

Horizontal Voting Ensemble Based Predictive Modeling System for Colon燙ancer

Colon cancer is the third most commonly diagnosed cancer in the world. Most colon AdenoCArcinoma (ACA) arises from pre-existing benign polyps in the mucosa of the bowel. Thus, detecting benign at the earliest helps reduce the mortality rate. In this work, a Predictive Modeling System (PMS) is developed for the classification of colon cancer using the Horizontal Voting Ensemble (HVE) method. Identifying different patterns in microscopic images is essential to an effective classification system. A twelve-layer deep learning architecture has been developed to extract these patterns. The developed HVE algorithm can increase the system’s performance according to the combined models from the last epochs of the proposed architecture. Ten thousand (10000) microscopic images are taken to test the classification performance of the proposed PMS with the HVE method. The microscopic images obtained from the colon tissues are classified into ACA or benign by the proposed PMS. Results prove that the proposed PMS has ~8% performance improvement over the architecture without using the HVE method. The proposed PMS for colon cancer reduces the misclassification rate and attains 99.2% of sensitivity and 99.4% of specificity. The overall accuracy of the proposed PMS is 99.3%, and without using the HVE method, it is only 91.3%.

Biases and teleconnections in the Met Office Global Coupled Model version 5.0 (GC5) – insights for seasonal prediction and Australia

The Australian Bureau of Meteorology (The Bureau) has been involved in the package testing and assessment process of the UK Met Office Global Coupled Model Version 5.0 (GC5) configuration. GC5 will underpin the Met Office’s next seasonal prediction system, global coupled numerical weather prediction (NWP) system and Earth System Model. It will also likely be the next version of The Bureau’s seasonal prediction system, and the version to replace the global atmosphere-only NWP system to be the first global coupled NWP system at The Bureau. The GC5 configuration includes a new sea-ice model and substantial updates to almost all areas of model physics. We have evaluated the present-day climate simulation, and compared it to observations and with previous versions GC4 and GC2. Our assessment focuses on the climate mean state and variabilities relevant to Australian seasonal prediction, including the El Niño–Southern Oscillation (ENSO), the Indian Ocean Dipole (IOD), the Southern Annular Mode and the Madden–Julian Oscillation. Notably, in comparison to its predecessor (GC4), GC5 shows significant improvements in the eastern Pacific mean state but a slight degradation in the Indian Ocean in terms of the mean state and variability. These and other results provide us with early insights of the potential performance of the next sub-seasonal or seasonal forecast system. Longstanding issues in the seasonal prediction system associated with the equatorial eastern Indian Ocean biases and an overactive ENSO and IOD will likely remain; however, improvements over the eastern equatorial Pacific in GC5 hold promise of improved prediction skill of ENSO and its teleconnections.