The success of DNA amplification in Polymerase Chain Reaction (PCR) devices inherently depends on the rapid and absolute zero-overshoot temperature control of thermoelectric cooler (TEC) systems. In the literature, metaheuristic algorithms employed for proportional–integral–derivative (PID) tuning typically operate within unconstrained search spaces, relying exclusively on time-domain error metrics like ITAE. This conventional approach causes ‘gradient blindness’ and neglects frequency-domain robustness, resulting in excessive temperature overshoots that violate biological safety limits and lead to enzyme denaturation. To solve this problem, we propose a hybrid frequency-time domain optimization framework. Utilizing a first order plus dead-time (FOPDT) model for TEC dynamics, the PID search space is analytically restricted via Ziegler–Nichol’s stability boundaries. Furthermore, Phase Margin (PM ≥ 45°) and absolute zero-overshoot conditions are integrated into the objective function as a strict penalty mechanism. Evaluations conducted with five distinct metaheuristic algorithms (PSO, GWO, WOA, ABC, and ACO) prove that while traditional unconstrained methods yield overshoots up to 19.04%, the proposed architecture successfully confines all optimization agents to a globally stable region, enabling specific algorithms like ABC, PSO, and WOA to achieve exactly 0.00% overshoot. Validated across a realistic multi-step PCR cycle (95–55–75 °C), the developed robust controller settles into the denaturation phase with a 0.00 °C peak error, guaranteeing biological sample safety and delivering a reliable control framework for rapid-cycle PCR platforms.
This study proposes a sequential Hybrid GP-ANN architecture based on the concept of autonomous feature engineering for multi-output performance prediction of single-phase induction motors, serving as a high-fidelity surrogate model ready for digital twin integration. The required high-resolution motor dataset (88,375 samples) was generated using a parametric sweep approach with Ansys RMxprt. In the proposed architecture, Genetic Programming (GP) is not positioned as a final predictor but as an analytical filter that discovers hidden physical relationships in raw input data and converts them into super features, thereby structurally eliminating the polynomial explosion risk and scale sensitivity that arise when raw data are modelled directly. The nonlinear physical relationships discovered autonomously by GP are added to the network input matrix as mathematical vectors, breaking the black-box structure of standard artificial neural networks and transforming it into a physics-inspired grey-box model. The nonlinear terms discovered by GP are fed into the network after independent Z-score normalisation to preserve gradient stability. To comprehensively evaluate this framework, its predictive performance is benchmarked against industry-standard machine learning algorithms, including Random Forest (RF), Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost). Results on variation-based unseen test data show that the hybrid model achieves competitive prediction accuracy relative to XGBoost—matching or exceeding it for Output Torque and Input Current, and remaining broadly comparable for Output Power, though XGBoost achieves substantially lower RMSE for Efficiency and Power Factor—while additionally offering transparent mathematical traceability, reducing error rates (RMSE) by 42.1% to 66.1% per parameter compared to the standard ANN. The model achieves an score of 0.9879 for the power factor parameter, where conventional approaches struggle. To rigorously validate the interpretability of this grey-box architecture, a global Permutation Feature Importance (PFI) analysis was conducted, showing that the GP-derived super features collectively account for 61.46% of the decision logic, outweighing the combined contribution of the raw inputs (38.54%). Furthermore, the autonomous feature engineering layer is found to reduce the learning burden on the ANN, allowing it to converge to a substantially lower error floor within the same fixed epoch budget. With an online inference time below 0.02 ms, the proposed architecture offers a robust methodological infrastructure for sustainable motor digital twins through a balanced trade-off between prediction accuracy and computational efficiency.
Hoods are the most important devices used in our kitchens that contribute to the ventilation of the environment. 95% of the electric motors used in hoods are single-phase asynchronous motors. There are many domestic and foreign electric motor manufacturers producing for the hood industry. Supplier selection in companies producing hoods is vital and critical for sustainable production. It is extremely important to make the right decision in the purchasing process of the supplied products. While the decisions taken can sometimes be clearly separated from each other, sometimes they can be intertwined and interconnected. Multi criteria decision making techniques are used when making decisions that cannot be clearly separated or explained with numerical data. The aim of this study was to determine the most suitable Supplier for the built-in appliance company operating in the Turkiye/Amasya region by using fuzzyTOPSIS method in the supply of 1-phase asynchronous motors used in hoods. After 5 experts working in the company were determined as decision makers, 4 criteria were determined: quality, system capacity, finance and logistics performance. The best supplier selection among 6 different suppliers was made using this method. For the first time, a solution proposal was presented with the fuzzyTOPSIS technique for the 1-phase induction motor supplier selection and a contribution was made to the literature.
30 June 2026 in Journal of Computational Bioengineering and Clinical Medicine
Pulse oximeters are critical clinical devices widely used for the non-invasive monitoring of peripheral oxygen saturation (SpO₂). However, low peripheral perfusion and reduced tissue temperature significantly reduce measurement accuracy, particularly in patients who remain immobile for extended periods, and in some cases prevent measurements from being taken at all. In clinical practice, passive heating methods are typically used to address this issue; however, these approaches are uncontrolled and limited in terms of reproducibility. In this study, a controlled hand-heating system was designed and developed to improve pulse oximeter measurements under low-perfusion conditions. The system provides homogeneous heating of the hand’s upper and lower surfaces using low-power resistive heaters. A three-dimensional heater geometry was designed, the resistor placement was optimized, and a prototype was manufactured. Subsequently, a First-Order Plus Dead Time (FOPDT) transfer function was derived using experimental temperature-time data (33.9 °C initial, 46.9 °C steady-state temperature) obtained from the prototype’s open-loop step response. Particle Swarm Optimization (PSO) and Artificial Bee Colony (ABC) algorithms were compared and competed against each other in the optimization of a filtered PID controller architecture capable of maintaining hand temperature exactly at 36.0 °C body temperature with system identification and zero overshoot. While both algorithms showed a similar convergence error ("RMSE"≈0.81 °C), the PSO algorithm demonstrated absolute stability in parameter estimation with a standard deviation of 0.0000. When subjected to a sudden -1.5 °C load disturbance applied at t=400. seconds to simulate clinical disturbance scenarios, the optimized controllers were observed to rapidly recover the temperature with an instantaneous power increase and stabilize it back to 36.0 °C within seconds. The controlled thermal intervention system developed offers an approach for ensuring the stable thermal perfusion conditions required for pulse oximetry measurements, and the design and simulation results demonstrate that the system is configured to operate within its safety limits.