Parallel Hybrid Research Articles

Assessing the potential and energy distribution calibration of ethanol-biodiesel based RCCI mode of compression ignition engine in a plugin parallel hybrid electric vehicle

The focus of this research is to develop the resilient powertrain to combat the enforcement of stringent emission regulations and elevate its feasibility to power with the sustainable fuels to support the fuel crisis. The current solution in the reliable and adaptability point of view is the low temperature combustion engine-based hybrid electric powertrain powered with sustainable fuel is the better choice. The present work proposes the concept of an ethanol-biodiesel fuel based RCCI plugin parallel hybrid electric vehicles (PHEVs). The significant examination of this work in the aspects of optimal torque structure and injector control parameter calibration. The calibration of the RCCI engine torque structure operation is performed based on the multi-objective constraints of variance of indicated mean effective pressure and the maximum rate of pressure rise for the combustion stability. While the equivalence ratio and combustion temperature with emphasis on limiting the amount of NOx and soot emissions. The maximum ethanol energy share proportion of 66.98% has been achieved. The RCCI engine is most frequently operating in the torque zone of 10 Nm and then 17.81 Nm while the BLDC motor is most frequently operated in the range of 55 Nm even at max torque of 60 Nm. When comparing to a standard diesel hybrid setup, the ethanol-biodiesel fuelled RCCI setup has a 18%–19% reduction in harmful NOx emissions, with an equivalent decrease of 22.7% in fuel economy. This is achieved by only having a 13.4% more CO emission while a minimal increase in soot emission throughout the overall course of the driving cycle. The result of this work shows evidence that implementing an ethanol-biodiesel fuelled RCCI engine in a parallel hybrid configuration achieves a significant reduction in NOx emissions while achieving the performance targets and managing the fuel and battery energy utilization over a driving cycle efficiently.

Short-term power load forecasting based on hybrid feature extraction and parallel BiLSTM network

Electricity is a vital resource for societal and economic activities. Accurate electricity load forecasting can effectively reduce costs and enhance energy efficiency. Nevertheless, current research has limitations in effectively extracting and utilizing load forecasting information. This encompasses both undiscovered latent features and models that have not effectively captured long-term dependencies. To address these issues, this paper proposes a novel network architecture, which utilizes a hybrid feature extraction strategy and integrates machine learning methods with deep learning techniques. This method employs a hybrid feature extraction strategy composed of gradient-boosted regression trees, Fisher Score, and mutual information to achieve comprehensive feature representation. The network architecture utilizes a multi-head convolutional neural network and a bi-directional long short-term memory (BiLSTM) with lag parameters. This architecture can simultaneously learn multiple levels and aspects of features, further enhancing the BiLSTM model’s ability to capture long-term dependencies. Through multiple experiments conducted on datasets from Maine, Singapore, New South Wales, Australia, and European countries, our method outperformed the comparison models in three out of the five datasets.

Adoptability assessment of HCDI and RCCI modes in plug-in parallel hybrid electric vehicles using sustainable fuels and model-based torque structure calibration strategies

In this research, a comparative analysis of plug-in hybrid electric vehicle (PHEV) engine was conducted with two advanced low temperature combustion (LTC) techniques viz. Homogeneous charge with direct injection (HCDI) and reactivity-controlled compression ignition (RCCI), utilizing alternative fuels diethyl ether (DEE) and ethanol. This was attempted to exhibit the promising potential of LTC based PHEV to achieve the highest efficiency and low emissions. The experimental results disclosed that DEE powered HCDI can achieve superior thermal efficiency with an impressive peak torque of 14 Nm. On the other hand, ethanol powered RCCI produced a peak torque of 17.5 Nm with remarkable emission reduction characteristics, especially CO2. It was vindicated that HCDI-PHEV outperformed the RCCI-PHEV in terms of fuel economy despite both HCDI and RCCI being lower than the conventional diesel PHEV. The NOx emissions from HCDI were almost negligible. About 20 % lower nitrogen oxide (NOx) emissions were recorded for RCCI respectively as compared to diesel (36 g/s). HCDI and RCCI showcased about 2 and 1.3 times higher soot emissions than diesel (7.12 g/s). Fuel economy was improved by 15 % and 43 % respectively under HCDI and RCCI modes over the conventional diesel mode of PHEV operation. When the PHEV was operated continuously for about 3.5 h, the battery's SOC dropped from 80 % to 45 % under diesel operation, whereas it only reached 50 % and 60 % under RCCI and HCDI mode operation. Low fuel consumption characteristics, acceptable torque production capabilities and ultralow NOx reduction potential established HCDI as the preferable choice for PHEV over RCCI.

Fault diagnosis of photovoltaic array with multi-module fusion under hyperparameter optimization

Photovoltaic (PV) arrays’ random and intermittent output characteristics impact power system safety. To improve the performance of the PV array fault diagnosis model, a novel online fault monitoring technique is introduced. (1) Fault diagnostic model construction: Significant differences in PV arrays’ I-V and P-V curves under various fault conditions led to constructing a 3D channel feature map based on I, V, and P features. (2) Multi-source information fusion network (MSIFN): this multi-module fusion model includes a time–frequency domain fusion module (TDFM), a multi-feature shuffle expansion convolution module (MSECM), a parameter-free parallel hybrid attention enhancement module, and a multi-scale mixed pooling fusion classification module (MMPCM). (3) Multi-strategy fusion whale optimization algorithm (MSFWOA): addressing the original WOA’s deficiencies, we designed time control, parameter modification, and greedy control strategies based on lens imaging to optimize MSIFN’s hyper-parameters. Experimental results show that the MSFWOA-MSIFN model excels in PV array fault diagnosis (Paccuracy=Pprecision=Precall = 99.92 %). In three types of noise experiments with 15 dB, 25 dB, and 30 dB, the average performance index remained above 99 %. In practical experiments, the average performance indices werePaccuracy = 97.53 %, Pprecision = 97.32 %, andPrecall = 97.41 %, further demonstrating its excellent diagnostic performance. This model effectively diagnoses various faults in PV arrays, providing scientific and theoretical support for PV system operations.

Feature Fusion Image Dehazing Network Based on Hybrid Parallel Attention

Feature Fusion Image Dehazing Network Based on Hybrid Parallel Attention

Energy-saving mechanism of series–parallel hybrid transmissions — A dynamic programming method based on matrix operations

The economic evaluation of hybrid transmission is a complicated numerical calculation problem in the finite time domain. Currently, employing traditional dynamic programming methods to evaluate a single design scheme consumes a lot of time, making it arduous to effectively compare performance disparities across various design schemes. This paper introduces a dynamic programming method based on matrix operations, enabling the determination of maximum energy-saving potential in hybrid transmission while reducing the evaluation time for a single design scheme from hours to less than 10 s. It unifies the design variables, constraints, and optimization objectives for multi-gear and multi-mode series–parallel hybrid transmissions (MGMM-SPHTs) during economic evaluation. By solving the performance of tens of thousands of design schemes, it is found that increasing the number of engine direct drive gears from 1 to 2 enhances the economy and power performance of series–parallel hybrid transmissions. For the optimal design scheme of Type-B vehicles, this enhancement results in a 1.712% increase in energy-saving efficiency and a 30.5% increment in power performance. Furthermore, this paper elucidates the adaptive relationship between MGMM-SPHTs and different vehicle types, revealing the energy-saving mechanisms under varied design schemes. This paper holds the promise of offering theoretical underpinnings and methodological instruments for selecting technical routes and optimizing design parameters for MGMM-SPHTs.

Hybrid modelling of nitrogen removal by biofiltration using high-frequent operational data

ABSTRACT In this research, a parallel hybrid model is presented for the simulation of nitrogen removal by submerged biofiltration of a very large-size wastewater treatment plant. This hybrid model consists of a machine learning model and a mechanistic model that are combined to produce accurate predictions of water quality variables. The models are calibrated/validated using detailed and quality-controlled operational data collected over a period of 3.5 months in 2020. The mechanistic model applied is a modified activated sludge model that describes the biological, physical and chemical processes taking place in a biofilm reactor based on the domain knowledge of these processes. A three-layer feed-forward artificial neural network with a rectified linear activation function that aims to reduce the mechanistic model's residual error and then correct its output. The results show how the hybrid model outperforms and significantly reduces the size of the mechanistic model's prediction errors of the effluent nitrate concentration from a relative mean error of 12% for the mechanistic model to 2% for the hybrid model during training. The error on nitrate simulations increases to 8% during hybrid model testing, still significantly lower than the error of the mechanistic model. These results support future operational applications of hybrid biofilm models.

A Hybrid Parallel Computing Architecture Based on CNN and Transformer for Music Genre Classification

Music genre classification (MGC) is the basis for the efficient organization, retrieval, and recommendation of music resources, so it has important research value. Convolutional neural networks (CNNs) have been widely used in MGC and achieved excellent results. However, CNNs cannot model global features well due to the influence of the local receptive field; these global features are crucial for classifying music signals with temporal properties. Transformers can capture long-range dependencies within an image thanks to adopting the self-attention mechanism. Nevertheless, there are still performance and computational cost gaps between Transformers and existing CNNs. In this paper, we propose a hybrid architecture (CNN-TE) based on CNN and Transformer encoder for MGC. Specifically, we convert the audio signals into mel spectrograms and feed them into a hybrid model for training. Our model employs a CNN to initially capture low-level and localized features from the spectrogram. Subsequently, these features are processed by a Transformer encoder, which models them globally to extract high-level and abstract semantic information. This refined information is then classified using a multi-layer perceptron. Our experiments demonstrate that this approach surpasses many existing CNN architectures when tested on the GTZAN and FMA datasets. Notably, it achieves these results with fewer parameters and a faster inference speed.

A novel EMS design framework for SPHTs based on instantaneous layer, driving event layer, and driving cycle layer

To effectively harness the energy-saving potential of series–parallel hybrid transmissions (SPHTs) with multiple gears and modes and to enhance the driving cycle adaptability of the rule-based energy management strategy (RB EMS), this study establishes a novel EMS design framework for SPHTs at three levels: the instantaneous, the driving event, and the driving cycle layers. Firstly, an equivalent fuel factor based on the principles of energy conservation and calorific value measurements is constructed, the energy consumption of different working modes and torque combinations under different instantaneous power units is determined, and the decision conditions of working modes are determined. Secondly, the energy consumption of engine and motor torque combination under constant speed, acceleration and deceleration driving events is compared, and the torque distribution feature of multi-power sources is determined. Thirdly, a driving cycle distribution factor is introduced and calculated using vehicle navigation map information, which can adjust the gear switching condition of parallel driving mode online. Based on above, an RB EMS adjusted with driving cycles (ADC-RB EMS) is proposed. The effectiveness of the proposed strategy is then verified through real-world vehicle tests. The fuel consumption performance of this strategy falls between the RB EMS and the dynamic programming (DP) strategy. According to the fuel consumption results, the RB EMS consumes an additional 0.35 L/100 km of fuel, while the DP strategy saves only 3.66% more energy compared to this strategy. The application potential of driving cycle distribution factor in instantaneous optimal control is tested. Compared with ADC-RB and CD-CS, the fuel saving rate is 1.71% and 5.67% respectively, which proves the energy saving performance of A-ECMS. This study provides a development direction for improving the energy saving effect of the RB EMS.

Optimal Rule-Interposing Reinforcement Learning-Based Energy Management of Series—Parallel-Connected Hybrid Electric Vehicles

P2–P3 series–parallel hybrid electric vehicles exhibit complex configurations with multiple power sources and operational modes, presenting a difficulty in developing efficient energy management strategies. This paper takes a P2–P3 series–parallel hybrid power system-KunTye 2DHT system as the research object and proposes a deep reinforcement learning framework based on pre-optimized energy management to improve the energy consumption performance of the hybrid electric vehicles. Firstly, a control-oriented model is established based on its system configuration and characteristics. Then, the optimal distribution of the motor energy under different operating modes is pre-optimized, which aims to reduce the energy management task’s dimensionality by equating two motors as an equivalent motor. Subsequently, based on real-time traffic information under connected conditions, deep reinforcement learning is utilized to optimize the optimal operating modes of the hybrid system and the optimal distribution between the engine and equivalent motors. Combining the pre-optimized results, the optimal energy distribution between the engine and the two motors in the system is achieved. Finally, performance comparisons are made between the predictive control and the traditional Dynamic Programming and Adaptive Equivalent Consumption Minimization Strategy, revealing the proposed optimization algorithm’s promising potential in reducing fuel consumption.

Modelling and Design Optimization of a Novel Compliant XY Positioner for Vibration-Assisted CNC Milling

Vibration-assisted machining, known as hybrid processing technology, offers several benefits over conventional machining methods. However, developing mechanical structure designs to generate a non-resonant frequency source remains challenging. The objective of this study is to propose a novel design for an XY flexure positioner by combining the pseudo-rigid-body model with the Lagrange technique, finite element analysis and Crayfish optimization algorithm. Firstly, the mechanism was designed by combining a hybrid amplifier and parallel driving mechanism integrated with right circular hinges to increase the natural frequency and precision for potential application to VAM CNC milling. Then, the analytical model was established by the pseudo-rigid-body and Lagrange method. Next, the theoretical result was verified by finite element analysis. The first natural frequency results of theory and FEM methods were found at 990.74 Hz and 1058.5 Hz, respectively. The error between the two methods was 6.4%, demonstrating a reliable modeling approach. Based on the analytical equations, the Crayfish optimization algorithm was utilized for optimizing the main design variables of the mechanism. Next, the prototype was fabricated. The results showed that the experimental and simulated frequencies were 1127.62 Hz and 1216.6 Hz, with an error between the two methods of 7.31%. Finally, the workpiece was installed on the prototype and a real vibration-assisted CNC milling process was carried out in the frequency range [700 Hz, 1000 Hz]. The best surface roughness of the specimen was achieved at a frequency of 900 Hz with a Ra of 0.287 µm. This demonstrates that the proposed XY mechanism is an effective structure for generating a non-resonant frequency source for vibration-assisted machining.

Addressing cost barriers to healthy eating with Eat Well, a prescription produce subsidy, for patients with diabetes and at risk for food insecurity: Study protocol for a type 1 hybrid effectiveness-implementation pragmatic randomized controlled trial

BackgroundPatients with diabetes at risk of food insecurity face cost barriers to healthy eating and, as a result, poor health outcomes. Population health management strategies are needed to improve food security in real-world health system settings. We seek to test the effect of a prescription produce program, ‘Eat Well’ on cardiometabolic health and healthcare utilization. We will also assess the implementation of an automated, affirmative outreach strategy. MethodsWe will recruit approximately 2400 patients from an integrated academic health system in the southeastern United States as part of a two-arm parallel hybrid type 1 pragmatic randomized controlled trial. Patients with diabetes, at risk for food insecurity, and a recent hemoglobin A1c reading will be eligible to participate. The intervention arm receives, ‘Eat Well’, which provides a debit card with $80 (added monthly) for 12 months valid for fresh, frozen, or canned fruits and vegetables across grocery retailers. The control arm does not. Both arms receive educational resources with diabetes nutrition and self-management materials, and information on existing care management resources. Using an intent-to-treat analysis, primary outcomes include hemoglobin A1C levels and emergency department visits in the 12 months following enrollment. Reach and fidelity data will be collected to assess implementation. DiscussionAddressing food insecurity, particularly among those at heightened cardiometabolic risk, is critical to equitable and effective population health management. Pragmatic trials provide important insights into the effectiveness and implementation of ‘Eat Well’ and approaches like it in real-world settings. RegistrationClinicalTrials.gov Identifier: NCT05896644; Clinical Trial Registration Date: 2023-06-09.

A Multidimensional Communication Scheduling Method for Hybrid Parallel DNN Training

A Multidimensional Communication Scheduling Method for Hybrid Parallel DNN Training

Enhanced hybrid energy storage system combining battery and supercapacitor to extend nanosatellite lifespan

The power limitations of nanosatellites, particularly during peak demand periods such as data transmission and maneuvering, hinder their operational capabilities. Traditional Electrical Power Subsystems relying solely on batteries face challenges in delivering the necessary power density and maintaining battery life, especially during eclipses. This study proposes an innovative Hybrid Energy Storage System for a 3U nanosatellite, integrating high-energy-density batteries with high-power-density supercapacitors, using an active parallel hybrid topology with two bidirectional converters and an optimal power management strategy. Using MATLAB and Simulink models, the study optimizes the Hybrid Energy Storage System by focusing on minimizing the capacity rate and depth of discharge to extend battery life. Simulation results show a 53.42% reduction in depth of discharge compared to a battery-only system, indicating a significant extension of battery life. Additionally, the proposed system allows for a minimal 2.08% increase in overall mass while maintaining enhanced performance. This research fills a critical gap in the literature by exploring active Hybrid Energy Storage System topologies for spacecraft applications, beyond the traditional passive and semi-active configurations. The innovative power management strategy ensures efficient energy utilization, significantly enhancing the reliability and efficiency of nanosatellite missions. The findings offer a practical solution to improve mission performance and extend the operational lifespan of nanosatellites, paving the way for more robust and capable small satellite deployments.

Numerical Analysis of Optimal Hybridization in Parallel Hybrid Electric Powertrains for Tracked Vehicles

Numerical Analysis of Optimal Hybridization in Parallel Hybrid Electric Powertrains for Tracked Vehicles

PD-DETR: towards efficient parallel hybrid matching with transformer for photovoltaic cell defects detection

Defect detection for photovoltaic (PV) cell images is a challenging task due to the small size of the defect features and the complexity of the background characteristics. Modern detectors rely mostly on proxy learning objectives for prediction and on manual post-processing components. One-to-one set matching is a critical design for DEtection TRansformer (DETR) in order to provide end-to-end capability, so that does not need a hand-crafted Efficient Non-Maximum Suppression NMS. In order to detect PV cell defects faster and better, a technology called the PV cell Defects DEtection Transformer (PD-DETR) is proposed. To address the issue of slow convergence caused by DETR’s direct translation of image feature mapping into target detection results, we created a hybrid feature module. To achieve a balance between performance and computation, the image features are passed through a scoring network and dilated convolution, respectively, to obtain the foreground fine feature and contour high-frequency feature. The two features are then adaptively intercepted and fused. The capacity of the model to detect small-scale defects under complex background conditions is improved by the addition of high-frequency information. Furthermore, too few positive queries will be assigned to the defect target via one-to-one set matching, which will result in sparse supervision of the encoder and impair the decoder’s ability of attention learning. Consequently, we enhanced the detection effect by combining the original DETR with the one-to-many matching branch. Specifically, two Faster RCNN detection heads were added during training. To maintain the end-to-end benefits of DETR, inference is still performed using the original one-to-one set matching. Our model implements 64.7% AP on the PVEL-AD dataset.

Integrated Optimization of Component Parameters and Energy Management Strategies for A Series–Parallel Hybrid Electric Vehicle

Integrated Optimization of Component Parameters and Energy Management Strategies for A Series–Parallel Hybrid Electric Vehicle

A multi-objective trajectory planning approach for vibration suppression of a series–parallel hybrid flexible welding manipulator

Although the series–parallel hybrid welding manipulator has advantages over the traditional series manipulator, its must run continuously and smoothly according to a specific trajectory at the rated velocity. Considering a flexible manipulator with a complex series–parallel hybrid structure as the research object, this paper proposes a multi-objective approach to indirectly suppress the vibration. In view of the complex flexible mechanism with a multi-kinematic pair arrangement and a multi-motor drive, a system comprehensive elastodynamics model is established, and the effectiveness of the model is verified through the hammer test method. To achieve synchronous and coordinated planning of the end position and attitude, the spatial arc welding trajectory is planned on the basis of the synchronous planning controller and the dual-S velocity profile interpolation function. Then, a multi-objective optimization model considering the travel time, energy consumption and terminal amplitude fluctuations is proposed, the trajectory planning problem is transformed into a parameter optimization problem in the interpolation function, and then the elite non-dominated sorting genetic algorithm (NSGA-II) is employed to determine the optimal trajectory. The optimal trajectory thus obtained effectively suppresses the vibration of the system. Finally, compared with the classic fifth-degree polynomial trajectory planning method, the system vibration suppression effect is significant, which verifies the effectiveness and feasibility of the proposed method and provides a theoretical basis for further realizing real-time control.

Energy management strategy of series–parallel hybrid transmission integrating map information and personalized driving characteristics

The integration of multi-source intelligent and connected information during a driving trip, along with its online application to globally optimized energy management strategies, has emerged as a crucial technical approach for enhancing the energy-saving effectiveness of hybrid transmissions. However, the action mode of such information and the optimization calculation efficiency of existing dynamic programming (DP) methods limit the online application of the aforementioned strategies with global optimization capabilities. To address these problems, the present study proposes a hierarchical energy management strategy that follows the reference trajectory of the battery state of charge (SoC) and comprehensively considers the multi-source information on the driving trip. First, a global speed prediction model based on personalized driving characteristics is proposed to obtain an accurate driving cycle input for the space-domain DP method. Second, the aforementioned tasks as well as the working-mode decision of the hybrid transmission and the multi-power-source torque distribution calculation tasks are deployed in the dual-core controller. Finally, the hierarchical energy management strategy is verified via vehicle testing. Compared with the DP strategy, the proposed strategy has an energy-saving potential of 4.17% that is yet to be realized. Furthermore, compared with the charge-depleting and charge-sustaining (CD–CS) strategy, the proposed strategy reduces fuel consumption by 0.38 L per 100 km, and its energy-saving effect is significant. This study is the first to apply the DP method to the vehicle controller, thereby facilitating the online application of energy management strategies with global optimization capabilities.

Energy price prediction based on decomposed price dynamics: A parallel neural network approach

The growing uncertainties of the world due to geographic tensions, and weather conditions challenge the traditional method to achieve a reliable price prediction of energy future for both asset pricing and risk management. Following the initial success of deep learning models in energy price prediction, we attempt to establish a better architecture of neural networks to improve the prediction accuracy. We propose a novel Parallel Hybrid Neural Network (PHNN) model that utilizes independent sub-networks to effectively capture the distinct features of various sequences. Empirical results demonstrate that the PHNN model exhibits a significant performance enhancement of 16.68%, 14.09%, and 2.34% over the EMD–LSTM, the informer model, and the single LSTM model, respectively. In particular, the PHNN outperforms the single LSTM, which is trained on the same inputs, by 2.34% overall while by a remarkable 4.11% during event periods. This suggests that the PHNN derives notable benefits from its distinct architecture, particularly during the initial phase of extreme events characterized by significant price trend changes. Additionally, the study explores the potential benefits of incorporating additional event-tracking indicators for energy futures price forecasting. However, the findings suggest that these indicators may not consistently provide effective complementary information.