Search Results (18)

Background and Objective: Temperature management is key for reliable operation of permanent magnet synchronous motors (PMSMs). The lumped-parameter thermal network (LPTN) is fast and interpretable but struggles with nonlinear behavior under high power density. We propose OLTEM, a physics-informed deep model that combines LPTN with a thermal neural network (TNN) to improve prediction accuracy while keeping physical meaning. Methods: OLTEM embeds LPTN into a recurrent state-space formulation and learns three parameter sets: thermal conductance, inverse thermal capacitance, and power loss. Two additions are introduced: (i) a state-conditioned squeeze-and-excitation (SC-SE) attention that adapts feature weights using the current temperature state, and (ii) an enhanced power-loss sub-network that uses a deep MLP with SC-SE and non-negativity constraints. The model is trained and evaluated on the public Electric Motor Temperature dataset (Paderborn University/Kaggle). Performance is measured by mean squared error (MSE) and maximum absolute error across permanent-magnet, stator-yoke, stator-tooth, and stator-winding temperatures. Results: OLTEM tracks fast thermal transients and yields lower MSE than both the baseline TNN and a CNN–RNN model for all four components. On a held-out generalization set, MSE remains below 4.0 °C² and the maximum absolute error is about 4.3–8.2 °C. Ablation shows that removing either SC-SE or the enhanced power-loss module degrades accuracy, confirming their complementary roles. Conclusions: By combining physics with learned attention and loss modeling, OLTEM improves PMSM temperature prediction while preserving interpretability. This approach can support motor thermal design and control; future work will study transfer to other machines and further reduce short-term errors during abrupt operating changes. Full article

The propulsion system is a critical component of medium–low-speed maglev trains and the single-sided linear induction motor (SLIM) has been adopted to generate thrust. However, the SLIM operates periodically in maglev trains. The temperature of the secondary plate of the SLIM rises significantly due to eddy currents when the train enters and leaves the station, where large slip occurs. Subsequently, the temperature decreases through natural cooling during the shift interval time. This periodic operating condition is rarely addressed in the existing literature and warrants attention, as the temperature accumulates over successive periods, potentially resulting in thermal damage and thrust variation. Furthermore, the conductivity of plate varies significantly in the process, which affects the losses and thrust, requiring a coupled analysis. To investigate the temperature variation patterns, this paper proposes a coupled model integrating the lumped parameter thermal network (LPTN) and the equivalent circuit (EC) of the SLIM. Given the unique structure of the F-shaped rail, the LPTN mesh is well designed to account for the skin effect. Three experiments and a finite element method (FEM)-based analysis were conducted to validate the proposed model. Finally, optimizations were performed with respect to different shift interval time, plate materials, and carriage numbers. The impact of temperature on thrust is also discussed. The results indicate that the minimum shift interval time and maximum carriage number are 70.7 s and 9, respectively, with thrust increasing by 22.0% and 22.0%. Furthermore, the use of copper as the plate material can reduce the maximum temperature by 22.01% while decreasing propulsion thrust by 26.1%. Full article

This paper proposes a dual-mode thermal analysis framework for the composite cage rotor bearingless induction motor (CCR-BIM), which combines lumped parameter thermal network (LPTN) and finite element thermal model (FETM) methods with experimental verification. The CCR-BIM, an advanced motor design combining torque and suspension windings within a single stator core, offers significant advantages in high-speed and high-precision applications. However, accurate thermal management remains a critical challenge due to its complex structure and increased losses. An LPTN model tailored to the unique thermal characteristics of the CCR-BIM is proposed, and detailed FETM simulations and experimental tests are validated. The LPTN model employs a meshing method to discretize the motor into orthogonal thermal nodes, enabling the rapid and accurate calculation of steady-state temperatures. The FETM further verifies the LPTN results by simulating the transient and steady-state temperature fields. Experimental validation using a 2 kW CCR-BIM test platform confirms the effectiveness of both models, with temperature predictions closely matching measured values. This study provides a reliable thermal analysis method for CCR-BIM. Full article

A conventional dual-winding (DW) motor has two internal windings consisting of a master part and a slave part, each connected to a different electronic control unit (ECU) to realize a redundant system. However, existing DW motors have a problem related to heat generation in both the healthy mode and the faulty mode of the motor operation. In the healthy mode, unexpected overloads can cause both windings to burn out simultaneously due to equal heat distribution. If the current sensor fails to measure correctly, the motor may exceed the designed current density of 4.7 [Arms/mm²] under air-cooling conditions, further increasing burnout risk. External factors such as excessive load cycles or extreme heat conditions can further exacerbate this issue. In the faulty mode, the motor requires double the current to generate maximum torque, leading to rapid temperature increases and a high risk of overheating. To address these challenges, this paper proposes the design of a thermal fault-tolerant asymmetric dual-winding (ADW) motor, which improves heat management in both healthy and faulty modes for autonomous vehicles. A lumped-parameter thermal network (LPTN) with a piecewise stator-housing model (PSMs) was employed to evaluate the coil temperature during faulty operation. An optimal design approach, incorporating kriging modeling, Design of Experiments (DOE), and a genetic algorithm (GA), was also utilized. The results confirm that the proposed ADW motor design effectively reduces the risk of simultaneous burnout in the healthy mode and overheating in the faulty mode, offering a robust solution for autonomous vehicle applications. Full article

The thermal management of a driving motor is related to the performance and economy of the vehicle. The lumped-parameter thermal network (LPTN) method can provide a model basis for motor temperature-rise control and effectively shorten the development cycle of motor thermal performance design. In this study, an 80 kw water-cooled permanent magnet synchronous motor was used and the accurate thermal model of a motor was built using the LPTN. On the basis of the accurate thermal model, the simplified thermal model of a motor was obtained by reducing the complexity of the model. The temperature-rise test of the end winding and magnetic steel of the motor was carried out under some working conditions. The test conditions were selected according to continuous external characteristics and operating characteristics of the motor. Compared with the experimental results, the temperature-rise error of the two thermal models was less than 5%. The temperature-rise error of the simplified thermal model was less than 3% compared with the accurate thermal model. Therefore, the simplified thermal model can be used to quickly predict the temperature rise of the motor. Full article

The quality of aerial remote sensing imaging is heavily impacted by the thermal distortions in optical cameras caused by temperature fluctuations. This paper introduces a lumped parameter thermal network (LPTN) model for the optical system of aerial cameras, aiming to serve as a guideline for their thermal design. By optimizing the thermal resistances associated with convection and radiation while considering the camera’s unique internal architecture, this model endeavors to improve the accuracy of temperature predictions. Additionally, the proposed LPTN framework enables the establishment of a heat leakage network, which offers a detailed examination of heat leakage paths and rates. This analysis offers valuable insights into the thermal performance of the camera, thereby guiding the refinement of heating zones and the development of effective active control strategies. Operating at a total power consumption of 26 W, the thermal system adheres to the low-power limit. Experimental data from thermal tests indicate that the temperatures within the optical system are maintained consistently between 19 °C and 22 °C throughout the flight, with temperature gradients remaining below 3 °C, satisfying the temperature requirements. The proposed LPTN model exhibits swiftness and efficacy in determining thermal characteristics, significantly facilitating the thermal design process and ensuring optimal power allocation for aerial cameras. Full article

Maintaining optimal temperatures in the critical parts of an induction traction motor is crucial for railway propulsion systems. A reduced-order lumped-parameter thermal network (LPTN) model enables computably inexpensive, accurate temperature estimation; however, it requires empirically based parameter estimation exercises. The calibration process is typically performed in labs in a controlled experimental setting, which is associated with a lot of supervised human efforts. However, the exploration of machine learning (ML) techniques in varied domains has enabled the model parameterization in the drive system outside the laboratory settings. This paper presents an innovative use of a multi-agent reinforcement learning (MARL) approach for the parametrization of an LPTN model. First, a set of reinforcement learning agents are trained to estimate the optimized thermal parameters using the simulated data in several driving cycles (DCs). The selection of a reinforcement learning agent and the level of neurons in the RL model is made based on variability of the driving cycle data. Furthermore, transfer learning is performed on a new driving cycle data collected on the measurement setup. Statistical analysis and clustering techniques are proposed for the selection of an RL agent that has been pre-trained on the historical data. It is established that by synergizing within reinforcement learning techniques, it is possible to refine and adjust the RL learning models to effectively capture the complexities of thermal dynamics. The proposed MARL framework shows its capability to accurately reflect the motor’s thermal behavior under various driving conditions. The transfer learning usage in the proposed approach could yield significant improvement in the accuracy of temperature prediction in the new driving cycles data. This approach is proposed with the aim of developing more adaptive and efficient thermal management strategies for railway propulsion systems. Full article

This paper investigates the loss and thermal characteristics of a three-phase 10 kW flux-switching permanent magnet (FSPM) machine, which is used as an integrated starter generator (ISG) for hybrid electric vehicles (HEVs). In this paper, an improved method considering both DC-bias component and minor hysteresis loops in iron flux-density distribution is proposed to calculate core loss more precisely. Then, a lumped parameter thermal network (LPTN) model is constructed to predict transient thermal behavior of the FSPM machine, which takes into consideration various losses as heat sources determined from predictions and experiments. Meanwhile, a simplified one-dimensional (1D) steady heat conduction (1D-SHC) model with two heat sources in cylindrical coordinates is also proposed to predict the thermal behavior. To verify the two methods above, transient and steady thermal analyses of the FSPM machine were performed by computational fluid dynamics (CFD) based on the losses mentioned above. Finally, the predicted results from both LPTN and 1D-SHC were verified by the experiments on a prototyped FSPM machine. Full article

To further increase the torque/power density of a permanent magnet synchronous machine (PMSM) employed for a port traction electric vehicle, improving the thermal dissipation capacity of the cooling system used in the PMSM has become more and more important. This paper focuses on the thermal analysis of a water-cooling 200 kW PMSM for a port traction electric vehicle. First, the size parameters of the machine and the thermal property parameters of the materials used for each component are given. Based on the heat transfer theory, a fast evaluation method for a transient temperature rise in the water-cooling machine under multiple operating conditions is proposed. A lumped parameter thermal network (LPTN) model is established, and the temperature distributions of the machine at different operating conditions are analyzed. Second, under the same conditions, based on computational fluid dynamics (CFD), a three-dimensional (3D) CFD model is constructed. The influence of different cooling structures on temperature distribution is studied. The validity of the proposed fast evaluation method for a transient temperature rise in water-cooling machines under multiple operating conditions is verified. Finally, the results of the CFD and LPTN calculation are verified by experiments; the maximum temperature deviation of the rated speed/rated power operating condition is 8.5%. This paper provides a reference for the design and analysis of port traction electric vehicle machines. Full article

This paper proposes a simplified lumped parameter thermal network (LPTN) model for thermal analysis under the inter-turn short-circuit (SC) faults of a five-phase fault-tolerant permanent magnet (PM) motor for electric vehicles. The proposed model can consider circumferential heat transfer, variable copper loss, and uneven loss distribution. Firstly, an analytical calculation formula of inter-turn SC current is proposed to separate the copper loss of SC turns from electromagnetic simulation, and the accuracy of the formula is verified by finite element analysis (FEA). Secondly, a simplified LPTN model is proposed, the calculation formulas of the thermal resistance are given, and the simplified principle is explained. By comparing the results of different simplifications, it is found that the error between the simplified model and the original model is small. Finally, the proposed model is verified by experiments. The results show that the simplified model can achieve not only a high calculation speed but also a high accuracy. Moreover, the proposed model is applicable to all cases of asymmetrical temperature distribution. Full article

The axial-flux permanent magnet (AFPM) machines with yokeless and segmented armature (YASA) topology are suitable for in-wheel traction systems due to the high power density and efficiency. To guarantee the reliable operation of the YASA machines, an accurate thermal analysis should be undertaken in detail during the electrical machine design phase. The technical contribution of this paper is to establish a detailed thermal analysis model of the YASA machine by the lumped parameter thermal network (LPTN) method. Compared with the computational fluid dynamics (CFD) method and the finite element (FE) method, the LPTN method can obtain an accurate temperature distribution with low time consumption. Firstly, the LPTN model of each component of the YASA machine is constructed with technical details. Secondly, the losses of the YASA machine are obtained by the electromagnetic FE analysis. Then, the temperature distribution of the machine can be calculated by the LPTN model and loss information. Finally, a prototype of the YASA machine is manufactured and its temperature distribution under different operating conditions is tested by TT-K-30 thermocouple temperature sensors. The experimental data matches the LPTN results well. Full article

Electric vehicle (EV) generators have characteristics of small volume and high power density, which leads to high temperature rise. The temperature rise will directly influence the service life and reliability of the generator, so thermal analysis of EV generators is necessary in machine design. This paper carries out thermal analysis of a dual-axis-direction hybrid excitation generator (DHEG) used in EVs. The lumped parameter thermal network (LPTN) method is used to build the three-dimensional thermal model of DHEG. Compared with finite element analysis, LPTN can significantly reduce the simulation time while ensuring a good accuracy. Then, the influence of heat dissipation rib on DHEG temperature rise is studied. The results prove that adding heat dissipation rib on the enclosure surface can effectively reduce the maximum temperature of DHEG. Full article

A 40 kW–4000 rpm interior permanent magnet synchronous machine (IPMSM) applied to an electric vehicle (EV) is introduced as the study object in this paper. The main work of this paper is theoretical derivation and validation of the first-order and multi-order transient lumped-parameter thermal network (LPTN) for the development of a fast thermal model. Based on the first-order LPTN built, the study finds that the heat transfer coefficient of fluid and thickness of the air gap layer are the main influencing factors for the final temperature and time of reaching the steady state. The larger the heat transfer coefficient of fluid is, the lower the steady node temperature is. The smaller the air layer thickness is, the lower the steady node temperature is. The multi-order LPTN theory is further deduced based on the extension of the first-order LPTN. For the constant load and rectangular periodic load, transient node temperatures of the IPMSM are obtained by modeling and solving the first order inhomogeneous differential equations. Temperature rise curves and efficiency maps of the IPMSM under load conditions are realized on a dynamometer platform. The FLUKE infrared-thermal imager and the thermocouple PTC100 are used to validate the mentioned method. The experiment shows that the LPTN of the IPMSM can accurately predict the node temperature. Full article

Thermal analysis represents a key factor in electrical machine design due to the impact of temperature increase on insulation lifetime. In this context, there has been a wide investigation on thermal modeling, particularly for machines used in harsh working conditions. In this perspective, brake-by-wire (BBW) systems represent one of the most challenging applications for electrical machines used for automotive smart actuators. Indeed, electro-actuated braking systems are required to repeatedly operate the electric machine in high overload conditions in order to limit the actuator response time, as well as to enhance gravimetric and volumetric specific performance indexes. Moreover, BBW systems often impose unconventional supply conditions to the electric machine, consisting of dc currents in three-phase windings to keep the rotor fixed during the braking intervals. However, a dc supply leads to uneven temperature distributions in the machine, and simplified thermal models may not accurately represent the temperature variations for the different machine parts. Considering such unconventional supply conditions, this paper initially investigates the applicability of a conventional lumped-parameters thermal network (LPTN) based on symmetry assumptions for the heat paths and suitable for surface-mounted PM synchronous machines used in BBW systems. An extensive test campaign consisting of pulses and load cycle tests representative of the real machine operations was conducted on a prototype equipped with several temperature sensors. The comparison between measurements and predicted average temperatures, together with insights on the unbalanced heat distribution under the dc supply obtained by means of finite element analyses (FEA), paved the way for the proposal of a phase-split LPTN with optimized parameters. The paper also includes a critical analysis of the optimized parameters, proposing a simplified, phase-split lumped-parameters thermal model suitable to predict the temperature variations in the different machine parts for PM synchronous electric machines used in BBW systems. Full article

The operational reliability and high efficiency of modern electrical machines depend on the ability to transfer heat in the construction parts of the machine. Therefore, many authors study various thermal models and work on the development of effective heat dissipation. New insights and methods lead to improved techniques for the thermal design of electrical machines. This paper presents an experimentally validated thermal model of a permanent magnet synchronous motor (PMSM) with an improved slot winding model. It also deals with various approaches to homogenization and equivalent material properties of a tooth-coil winding sub-model. First, an algorithm for building a lumped-parameter thermal network (LPTN) of PMSM is described and its properties and problems are discussed. Subsequently, a sub-model of a slot with a winding based on the finite element method (FEM) is introduced. This sub-model is able to generate different conductor distributions based on probabilistic methods for a specified fill factor. This allows the verification of various homogenization approaches and at the same time it is a tool that automatically calculates thermal resistances for the LPTN. Full article