Torque Prediction Research Articles

Dynamic Formulation of the Double Multiple Stream Tube Model of Offshore Vertical Axis Wind Turbines

Abstract The paper proposes a novel algorithm to simulate Vertical Axis Wind Turbines in floating motion based on a low-fidelity approach. The conventional Double Multiple Stream Tube Model is formulated as a steady state model to deal with the inherent unsteady aerodynamics of VAWTs. The Double Multiple Stream Tube Model makes use of an average contribution of the blade passages over a revolution to solve the Blade Element Momentum equation. The model reduces the dependence of the solution (the induction field) to a space variable. Floating Vertical Axis Wind Turbines undergoes a variation of aerodynamic quantities according to wave periods, also different from the rotor period. This paper provides a new formulation of the Double Multiple Stream Tube Model to solve the turbine rotation in time and space, introducing the variation of the platform velocity and a revised approach to the downstream actuator disc. The most impactful parameter is found to be the wave frequency: wave periods at full-scale are lower than the ones of the turbine rotor, featuring optimal operating points at low tip speed ratios. The increase of the wave frequency highlights the differences of the average torque prediction for a single blade up to 10% between the unsteady and the standard formulation. In this context, the development of fast low-fidelity computational tools play a key role in the assessment of the preliminary designs of Floating Offshore Vertical Axis Wind Turbines and it will be used to optimise the aerodynamic design of the laboratory scaled model under surge motion.

Neutral-Connect Control in a Two-Speed Transmission Based on Demand Torque Prediction Using a Time Series Deep Learning Model

Neutral-Connect Control in a Two-Speed Transmission Based on Demand Torque Prediction Using a Time Series Deep Learning Model

Numerical Analysis of A Two-Phase Turbine: A Comparative Study Between Barotropic and Mixture Models

Abstract Two-phase turbines offer the potential to significantly enhance the performance of power generation and refrigeration systems. However, their development has been hindered by comparatively lower efficiencies resulting from additional loss mechanisms absent in single-phase turbines. To date, most multiphase CFD studies on turbomachinery have focused on condensation in the final stages of steam turbines, and on cavitation in hydraulic pumps and turbines. These applications, however, are not representative of the conditions in two-phase turbines, where a liquid-dominated mixture undergoes a large expansion ratio, leading to a significant increase in the gas phase volume fraction throughout the entire flow. This paper aims to identify a suitable modeling methodology for two-phase turbines. Our evaluation is centered around two models: the mixture model and the barotropic model. The validity and accuracy of these two modeling approaches is assessed using existing experimental data from a single-stage impulse turbine operating with several mixtures of water and nitrogen as working fluid. The results indicate that both the mixture and barotropic models are consistent and accurately predict the nozzle mass flow rate, yet, both models systematically overpredict the nozzle exit velocity and rotor torque. Adding correction terms for windage and unsteady pumping losses significantly improves the torque predictions, bringing them within the uncertainty range of the experimental data. In addition, refining the models to account for the effect of slip presents a promising avenue to enhance the prediction of nozzle exit velocity and overall performance of two-phase turbines.

Enhancing temperature and torque prediction in permanent magnet synchronous motors using deep learning neural networks and BiLSTM RNNs

This study aims to develop an effective method for predicting the temperature and torque of Permanent Magnet Synchronous Motors (PMSMs) using deep learning techniques, which is crucial for optimizing motor performance and ensuring longevity, particularly in the automotive industry. Various Neural Network (NN) architectures, including a Recurrent Neural Network (RNN) with a Bidirectional Long Short-Term Memory (BiLSTM) unit, were employed to model the complex relationships between motor parameters, such as stator winding, current, torque, and permanent magnet temperature. The findings demonstrate that an NN with two hidden layers (64 and 32 neurons) achieved an R2 score of 0.99 for both torque and temperature prediction, while the BiLSTM network effectively modeled temporal dynamics, leading to high-fidelity rotor temperature predictions. This research provides a novel application of BiLSTM RNNs in accurately predicting PMSM temperatures, offering valuable insights for industries reliant on these motors. Integrating these models into motor control systems can enhance operational efficiency, reduce overheating risks, and extend motor lifespan, contributing to energy savings and environmental sustainability by lowering energy consumption and reducing waste.

Industrial robot energy consumption model identification: A coupling model-driven and data-driven paradigm

Due to wide distribution and low energy efficiency, the energy-saving in industrial robots (IRs) is attracting extensive attention. Accurate energy consumption (EC) models of IRs lay the foundation for energy-saving. However, most dynamic and electrical parameters of IRs are not disclosed by manufacturers, which leads to the invalidity of most model-based EC prediction methods. To bridge this gap, a mechanism-data hybrid-driven method is proposed to predict the EC of IRs in this paper. First, a joint torque prediction model integrating a hybrid-driven parameter identification is developed based on deep reinforcement learning (DRL). The framework for DRL-based parameter identification is constructed through tailored design of interfaces and training mechanisms, wherein the DRL agent can learn to identify the dynamic parameters from the trajectory database. And a deep neural network based on long short-term memory (LSTM) is proposed to predict the EC of IRs according to the joint torques and velocities. The nonlinear item, which is not modeled in the robot dynamic equation, are also encapsulated in the deep neural network with one-dimensional convolutional neural network (1D-CNN) layers to improve the prediction accuracy. To validate the accuracy and efficacy of the proposed method, experiments are conducted on a KUKA KR60-3 industrial robot with different loads. The results demonstrate that the proposed method can predict EC with a mean absolute percentage error of less than 2% under a fixed load and less than 3% under loads not used for agent training.

Adaptive EC-GPR: a hybrid torque prediction model for mobile robots with unknown terrain disturbances

Adaptive EC-GPR: a hybrid torque prediction model for mobile robots with unknown terrain disturbances

Improved Parametric Representation of IM From FEM for More Accurate Torque Predictions: Simulations and Experimental Validations

Improved Parametric Representation of IM From FEM for More Accurate Torque Predictions: Simulations and Experimental Validations

Experimental investigation of predictive control for PMSM-based wind turbine generation system

The theoretical analysis of permanent magnet synchronous machine (PMSM)-based wind turbine generation system was presented by many researchers; nevertheless, although the practical setup is still quite difficult, it is more valid. Moreover, the main challenge facing wind power systems is figuring out how to extract the most energy from varying wind speeds. Since wind turbine maintenance is hard and expensive, using wind speed sensors is a challenging operation. Therefore, this research suggests an effective and practical control system based on the Model Predictive Control Scheme (MPCS) for both the grid-side converter (GSC) and the machine-side converter (MSC) to optimize power extraction from wind energy. Detailed exploration of the MPCS for the PMSM and predictive power control (PPC) for the GSC involves stages such as flux estimation, torque prediction, and cost function minimization. The results obtained validate the higher performance of MPCS in comparison to the direct torque control (DTC) method. Furthermore, excellent tracking with high accuracy is achieved in relation to simulation and experimental data. Additionally, an evaluation indices based on root mean square error (RMSE) and gross system efficiency are used for wind turbine performance. These indices are used to show that, the feasibility of the MPCS approach compared with DTC under the same WT conditions. This approach offers a promising avenue for cost-effective wind energy conversion. The control systems were designed and implemented utilizing a DSPACE 1104 card. Experimental results confirm the effectiveness of the proposed mechanism in achieving maximum power point tracking (MPPT).

Prediction and Dynamic Simulation Verification of Output Characteristics of Radial Piston Motors Based on Neural Networks

Radial piston motors are executive components in hydraulic systems, tasked with providing appropriate torque and speed according to load requirements in practical applications. The purpose of this study is to predict the output torque of radial piston hydraulic motors and confirm their suitable operating conditions. Efficiency determination experiments were conducted on physical models, yielding thirty sets of performance data. Torque (output torque) and mechanical efficiency from the experimental data were selected as prediction targets and fitted using two methods: multiple linear regression and neural networks. A dynamic simulation model was built using Adams2020 software to obtain theoretical torque values, enabling the verification of the alignment between the predicted values and simulation results. The results indicate that the error between the theoretical torque of the dynamic model and the physical experiments is 1.9%, with the error of the neural network predictions being within 2%. The dynamic simulation model can yield highly accurate theoretical torque values, providing a reference for the external load of hydraulic motors; additionally, neural networks offer accurate predictions of output torque, thus reducing experimental testing costs.

Value of different preoperative bone evaluation methods in predicting intraoperative screw insertion torque: a prospective clinical comparative trial

BACKGROUND CONTEXTEstablishing good screw-bone structural stability is conducive to reducing the risk of postoperative screw loosening. Screw insertion torque is an objective index for evaluating screw-bone structural stability. Therefore, accurate prediction of screw insertion torque can improve the preoperative evaluation of patients, optimize the surgical plan, and improve the surgical effect. At present, the correlation between different bone assessment methods and screw insertion torque is unclear. PURPOSEThe aim of this study was to evaluate the correlation between different bone assessment methods and screw insertion torque and to optimize the predictive performance of screw insertion torque through mathematical modeling combined with different radiology methods. DESIGNProspective cross-sectional study. PATIENT SAMPLESSeventy-seven patients with preoperatively available DXA, CT and MRI data who underwent spinal fixation surgeries between October 2022 and September 2023 and 357 sets of screw data were included in this analysis. OUTCOME MEASURESSpinal, vertebrae-specific and screw trajectory's BMD were measured preoperatively by different imaging modalities. Intraoperative screw insertion torque was measured using an electronic torque wrench. METHODSPearson linear correlation, scatter plots and univariate linear regression were used to evaluate the correlation between different bone evaluation methods and screw insertion torque. Different bone evaluation methods were fitted into the prediction model of screw torque and the related equations were obtained. RESULTSScrew insertion torque had the strongest positive correlation with the volumetric bone mineral density (vBMD) of the screw trajectory (Pedicle screw insertion torque (PSIT): R = 0.618, p<.001; Terminal screw insertion torque (TSIT): R = 0.735, p<.001). A weak negative correlation was found between the screw insertion torque and level specific vertebral bone quality (VBQ) (PSIT: R = -0.178, p=.001; TSIT: R = -0.147, p=.006). We also found that the PSIT was strongly correlated with the TSIT (R = 0.812, p<.001). CONCLUSIONSCompared to other bone quality assessment methods, screw trajectory vBMD may be better predict the magnitude of screw insertion torque. In addition, we further optimized preoperative assessments by constructing a mathematical model to better predict screw insertion torque. In conclusion, clinicians should select appropriate preoperative bone quality assessment methods, identify potential low-torque patients, optimize surgical plans, and ultimately improve screw insertion accuracy and reduce postoperative screw loosening rate.

Analysis of secondary makeup characteristics of drill collar joint and prediction of downhole equivalent impact torque of Well SDTK1

Based on the three-dimensional elastic-plastic finite element analysis of the 8” (203.2 mm) drill collar joint, this paper studies the mechanical characteristics of the pin and box of NC56 drill collar joints under complex load conditions, as well as the downhole secondary makeup features, and calculates the downhole equivalent impact torque with the relative offset at the shoulder of internal and external threads. On the basis of verifying the correctness of the calculation results by using measured results in Well GT1, the prediction model of the downhole equivalent impact torque is formed and applied in the first extra-deep well with a depth over 10 000 m in China (Well SDTK1). The results indicate that under complex loads, the stress distribution in drill collar joints is uneven, with relatively higher von Mises stress at the shoulder and the threads close to the shoulder. For 203.2 mm drill collar joints pre-tightened according to the make-up torque recommended by American Petroleum Institute standards, when the downhole equivalent impact torque exceeds 65 kN·m, the preload balance of the joint is disrupted, leading to secondary make-up of the joint. As the downhole equivalent impact torque increases, the relative offset at the shoulder of internal and external threads increases. The calculation results reveal that there exists significant downhole impact torque in Well SDTK1 with complex loading environment. It is necessary to use double shoulder collar joints to improve the impact torque resistance of the joint or optimize the operating parameters to reduce the downhole impact torque, and effectively prevent drilling tool failure.

Prediction of the friction torque of scaled blade bearings in a test rig using machine learning

Blade bearing friction torque is a required parameter for the design of a pitch actuator, and deviations from a bearing’s initial torque can be utilized for condition monitoring of the bearing. The torque of large-scale bearings can, however, be difficult to predict due to quality fluctuations in the production of these large-scale components. Therefore, this paper employs machine learning approaches to predict the torque of a given set of bearings in a controlled test environment based on measurement data from that same set of bearings. Possible applications of the model include use for condition monitoring by checking for deviations from the bearing’s initial behavior.

Methodology for the assessment of the friction torque of ball slewing bearings considering preload scatter

This manuscript presents an innovative methodology for the assessment of the friction torque of ball slewing bearings. The methodology aims to overcome the limitations of state-of-the-art approaches, especially when the friction torque is conditioned by the preload of the balls. To this end, the authors propose to simulate the preload scatter when solving the load distribution problem, prior to the friction torque calculation. This preload scatter allows to simulate a progressive transition of the balls from a four-point contact state to a two-point contact one. By implementing this capability into an analytical model, the authors achieve a successful correlation with experimental results. Nonetheless, depending on the stiffness of the structures to which the bearing is assembled, it is demonstrated that the rigid ring assumption can lead to inaccurate friction torque results when a tilting moment is applied. The methodology described in this research work is meant to have a practical application. Therefore, the manuscript provides guidelines about how to use and tune the analytical model to get a reliable friction torque prediction tool.

Physics based models for characterization of machining performance – A critical review

This paper presents a comprehensive review of the concept of machinability by considering the dynamic, tribological, and thermo-mechanical interactions encountered at the tool-chip-machined surface interfaces. The paper provides a demonstration of the capabilities and gaps of the physics-based models for the characterization of the machining performance and the prediction of machinability of difficult-to-cut materials, including additively manufactured (AM) materials, nanocrystalline (NC) materials, fibre reinforced polymers (FRP), metal matrix composites reinforced with ceramic hard particles (MMC), and ceramic matrix composites (CMC). The utilization of efficient computation methods for accurate prediction of force, torque, power consumption, cutting temperature, deflection errors, vibration amplitudes, chatter stability, and thermomechanical interactions in the tool-workpiece system is discussed. The development of thermally-activated dissolution-diffusion wear models to describe the chemical reactions at the tool-chip-workpiece contact interfaces is also presented. These predictions are critical for identifying multi-objectives optimal machining conditions. The integration of predictive machining models within the framework of digital twins in cyber-physical spaces, for in-process monitoring and adaptive control, is demonstrated. Future research for developing new models that can characterize the machinability of AM and NC materials, by considering the effects of varying material microstructure and anisotropy, is presented for conventional and micro-machining operations.

Soft ground micro TBM jack speed and torque prediction using machine learning models through operator data and micro TBM-log data synchronization

Tunnel Boring Machines (TBMs) are pivotal in underground projects like subways, highways, and water supply tunnels. Predicting and monitoring jack speed and torque is crucial for optimizing TBM excavation efficiency. Conventionally, skilled operators manually adjust numerous tunnelling parameters to regulate the machine's progress. In contrast, machine learning (ML) algorithms offer a promising avenue where computers learn from operator actions to establish parameter relationships autonomously. This study introduces an innovative approach to enhancing operator monitoring and TBM data comprehension. A robust correlation between TBM operator behaviour and TBM logged data is established by leveraging an Optuna-assisted ML methodology—the research light on the intricate dynamics influencing TBM advance rate parameters. Operational data is collected from micro slurry tunnel boring machine (MSTBM) umbrella support excavations. The proposed framework harnesses Optuna, an advanced hyperparameter optimization platform, to dynamically refine jack speed and torque settings. Through meticulous analysis of the interplay between TBM operator decisions and real-time logged data, the AI model discerns patterns, empowering informed decision-making. Using Optuna, a range of models, including random forest (RF), K-nearest neighbours (kNN), decision tree (DT), XGBoost, Support Vector Machine (SVM), and Artificial Neural Network (ANN) were automatically compared and tuned. The best model's (RF) performance is evaluated through a correlation coefficient (R2) of 96%, mean squared error (MSE) of 119.7, and mean absolute error (MAE) of 4.42 for jack speed decision making while 83% of R2, MSE of 0.62, and MAE of 0.42 for the torque decision making. This intelligent model can assist the TBM operator in making decisions about TBM control.

Loose bolt localization and torque prediction in a bolted joint using lamb waves and explainable artificial intelligence

With the increasing application of artificial intelligence (AI) techniques in the field of structural health monitoring (SHM), there is a growing interest in explaining the decision-making of the black-box models in deep learning-based SHM methods. In this work, we take explainability a step further by using it to improve the performance of AI models. In this work, the results of explainable artificial intelligence (XAI) algorithms are used to reduce the input size of a one-dimensional convolutional neural network (1D-CNN), hence simplifying the CNN structure. To select the most accurate XAI algorithm for this purpose, we propose a new evaluation method, feature sensitivity (FS). Utilizing XAI and FS, a reduced dimension 1D-CNN regression model (FS-X1D-CNN) is proposed to locate and predict the torque of loose bolts in a 16-bolt connected aluminum plate under varying temperature conditions. The results were compared with 1D CNN with raw input vector (RI-1D-CNN) and deep autoencoders-1D-CNN (DAE-1D-CNN). It is shown that FS-X1D-CNN achieves the highest prediction accuracy with 5.95 mm in localization and 0.54 Nm in torque prediction, and converges 10 times faster than RI-1D-CNN and 15 times faster than DAE-1D-CNN, while only using a single lamb wave signal path.

Image-Based Approach Applied to Load Torque Estimation in Three-Phase Induction Motors.

This paper presents a novel method for load torque estimation in three-phase induction motors using air gap flux measurement and the conversion of this type of time-domain signal into grayscale images for further processing as inputs for an inception-type convolutional neural network. The magnetic flux was measured employing a Hall effect sensor installed inside the machine, near the stator slots, and above the stator windings. In this case, the sensor was able to measure a resultant magnetic flux density, having both rotor and stator magnetic flux contributions. The present methodology does not require motor parameters for torque prediction. The proposed approach successfully estimated load torque using three optimizers across almost the entire motor load operational range, spanning from 1.5% to 93.9% of the rated load. Four model configurations achieved a mean absolute percentage error (MAPE) less than or equal to 3.7%. Specifically, two models for a 40 × 50 pixel image achieved MAPE of 3.7% and 3%, one model for a 40 × 25 pixel image achieved a MAPE of 3.5%, and one model for a 50 × 80 pixel image achieved a MAPE of 3.3%. This research has been experimentally validated with a 7.5 kW squirrel cage induction machine.

Application of Machine Learning Models in Coaxial Bioreactors: Classification and Torque Prediction

Coaxial bioreactors are known for effectively dispersing gas inside non-Newtonian fluids. However, due to their design complexity, many aspects of their design and function, including the relationship between hydrodynamics and bioreactor efficiency, remain unexplored. Nowadays, various numerical models, such as computational fluid dynamics (CFD) and artificial intelligence models, provide exceptional opportunities to investigate the performance of coaxial bioreactors. For the first time, this study applied various machine learning models, both classifiers and regressors, to predict the torque generated by a coaxial bioreactor. In this regard, 500 CFD simulations at different aeration rates, central impeller speeds, anchor impeller speeds, and rotating modes were conducted. The results obtained from the CFD simulations were used to train and test the machine learning models. Careful feature scaling and k-fold cross-validation were performed to enhance all models’ performance and prevent overfitting. A key finding of the study was the importance of selecting the right features for the model. It turns out that just by knowing the speed of the central impeller and the torque generated by the coaxial bioreactor, the rotating mode can be labelled with perfect accuracy using k-nearest neighbors (kNN) or support vector machine models. Moreover, regression models, including multi-layer perceptron, kNN, and random forest, were examined to predict the torque of the coaxial impellers. The results showed that the random forest model outperformed all other models. Finally, the feature importance analysis indicated that the rotating mode was the most significant parameter in determining the torque value.

A novel decomposition and hybrid transfer learning-based method for multi-step cutterhead torque prediction of shield machine

As a core operating parameter of shield machine, the high-precision multi-step prediction of cutterhead torque can effectively help the driver adjust the operating parameters in advance to ensure the safe operation of shield machine. Due to data distribution discrepancy, it is challenging to accurately predict the cutterhead torque under different geological conditions. Currently, the existing methods cannot precisely predict cutterhead torque in cross domain. In order to accurately predict the cutterhead torque under different geological environments, we propose a novel decomposition and hybrid transfer learning-based method for multi-step cutterhead torque transfer prediction. First, original cutterhead torque signal is decomposed into some sub-signals by variational mode decomposition (VMD), which can effectively reduce the complexity. Then hybrid transfer learning-based method (HTLM) is established to predict each sub-signal and add the prediction results to realize multi-step cutterhead torque prediction in cross domain. HTLM has three network branches. The first one is that multi-layer GRU network is used to extract time-varying characteristics of source domain data. The second is that the automatic encoder is used to extract the deep common features between source domain and target domain. The third is the adversarial network and the maximum mean discrepancy (MMD) metric for domain adaptation. Then, the extracted features are integrated to predict the cutterhead torque in cross domain. To verify the proposed VMD-HTLM, several transfer prediction experiments were carried out. From the first step to fifth step transfer prediction, the proposed method achieved higher prediction accuracy than existing methods. Especially in the fifth step, the accuracy of proposed method is on average 7.09 % higher than existing methods, the RMSE and the MAE decreased on average 40.00 % and 39.92 %, respectively. Furthermore, the average accuracy of proposed method is 93.79 %, 93.58 %, 93.55 %, 92.25 % and 91.79 % from first step to fifth step, respectively. Hence, the proposed VMD-HTLM can accurately predict the cutterhead torque under different geological conditions.

Rotor Performance Predictions for Urban Air Mobility: Single vs. Coaxial Rigid Rotors

This work details the development and validation of a methodology for high-resolution rotor models used in hybrid Blade Element Momentum Theory Unsteady Reynolds Averaged Navier–Stokes (BEMT-URANS) CFD. The methodology is shown to accurately predict single and coaxial rotor performance in a fraction of the time required by conventional CFD methods. The methodology has three key features: (1) a high-resolution BEMT rotor model enabling large reductions in grid size, (2) a discretized set of momentum sources to interface between the BEMT rotor model and the structured URANS flow solver, and (3) leveraging of the first two features to enable highly parallelized GPU-accelerated multirotor CFD simulations. The hybrid approach retains high-fidelity rotor inflow, wake propagation, and rotor–rotor interactional effects at a several orders of magnitude lower computational cost compared to conventional blade-resolved CFD while retaining high accuracy on steady rotor performance metrics. Rotor performance predictions of thrust and torque for both single and coaxial rotor configurations are compared to test the data that the authors obtained at the NASA Langley 14- by 22-ft. Subsonic Tunnel Facility. Simulations were run with both fully turbulent and free-transition airfoil performance tables to quantify the associated uncertainty. Single rotor thrust and torque were predicted on average within 4%. Coaxial thrust and power were predicted within an average of 5%. A vortex ring state (VRS) shielding phenomenon for coaxial rotor systems is also presented and discussed. The results support that this hybrid BEMT-URANS CFD methodology can be highly parallelized on GPU machines to obtain accurate rotor performance predictions across the full spectrum of possible UAM flight conditions in a fraction of the time required by conventional higher-fidelity methods. This strategy can be used to rapidly create look-up tables with hundreds to thousands of flight conditions using a three-dimensional multirotor CFD for UAM.