RESUMEN
Under the trend of vehicle intelligentization, many electrical control functions and control methods have been proposed to improve vehicle comfort and safety, among which the Adaptive Cruise Control (ACC) system is a typical example. However, the tracking performance, comfort and control robustness of the ACC system need more attention under uncertain environments and changing motion states. Therefore, this paper proposes a hierarchical control strategy, including a dynamic normal wheel load observer, a Fuzzy Model Predictive Controller and an integral-separate PID executive layer controller. Firstly, a deep learning-based dynamic normal wheel load observer is added to the perception layer of the conventional ACC system and the observer output is used as a prerequisite for brake torque allocation. Secondly, a Fuzzy Model Predictive Control (fuzzy-MPC) method is adopted in the ACC system controller design, which establishes performance indicators, including tracking performance and comfort, as objective functions, dynamically adjusts their weights and determines constraint conditions based on safety indicators to adapt to continuously changing driving scenarios. Finally, the executive controller adopts the integral-separate PID method to follow the vehicle's longitudinal motion commands, thus improving the system's response speed and execution accuracy. A rule-based ABS control method was also developed to further improve the driving safety of vehicles under different road conditions. The proposed strategy has been simulated and validated in different typical driving scenarios and the results show that the proposed method provides better tracking accuracy and stability than traditional techniques.
Asunto(s)
Movimiento (Física) , Tiempo de ReacciónRESUMEN
The mechanical coupling of multiple powertrain components makes the energy management of 4-wheel-drive (4WD) plug-in fuel cell electric vehicles (PFCEVs) relatively complex. Optimizing energy management strategies (EMSs) for this complex system is essential, aiming at improving the vehicle economy and the adaptability of operating conditions. Accordingly, a novel adaptive equivalent consumption minimization strategy (A-ECMS) based on the dragonfly algorithm (DA) is proposed to achieve coordinated control of the powertrain components, front and rear motors, as well as the fuel cell system and the battery. To begin with, the equivalent consumption minimization strategy (ECMS) with extraordinary instantaneous optimization ability is used to distribute the vehicle demand power into the front and rear motor power, considering the different motor characteristics. Subsequently, under the proposed novel hierarchical energy management framework, the well-designed A-ECMS based on DA empowers PFCEVs with significant energy-saving advantages and adaptability to operating conditions, which are achieved by precise power distribution considering the operating characteristics of the fuel cell system and battery. These provide state-of-the-art energy-saving abilities for the multi-degree-of-freedom systems of PFCEVs. Lastly, a series of detailed evaluations are performed through simulations to validate the improved performance of A-ECMS. The corresponding results highlight the optimal control performance in the energy-saving performance of A-ECMS.
RESUMEN
Existing data-driven technology for prediction of state of health (SOH) has insufficient feature extraction capability and limited application scope. To deal with this challenge, this paper proposes a battery SOH prediction model based on multi-feature fusion. The model is based on a convolutional neural network (CNN) and a long short-term memory network (LSTM). The CNN can learn the cycle features in the battery data, the LSTM can learn the aging features of the battery over time, and regression prediction can be made through the full-connection layer (FC). In addition, for the aging differences caused by different battery operating conditions, this paper introduces transfer learning (TL) to improve the prediction effect. Across cycle data of the same battery under 12 different charging conditions, the fusion model in this paper shows higher prediction accuracy than with either LSTM and CNN in isolation, reducing RMSPE by 0.21% and 0.19%, respectively.
Asunto(s)
Aprendizaje Automático , Redes Neurales de la ComputaciónRESUMEN
A battery's charging data include the timing information with respect to the charge. However, the existing State of Health (SOH) prediction methods rarely consider this information. This paper proposes a dilated convolution-based SOH prediction model to verify the influence of charging timing information on SOH prediction results. The model uses holes to fill in the standard convolutional kernel in order to expand the receptive field without adding parameters, thereby obtaining a wider range of charging timing information. Experimental data from six batteries of the same battery type were used to verify the model's effectiveness under different experimental conditions. The proposed method is able to accurately predict the battery SOH value in any range of voltage input through cross-validation, and the SDE (standard deviation of the error) is at least 0.28% lower than other methods. In addition, the influence of the position and length of the range of input voltage on the model's prediction ability is studied as well. The results of our analysis show that the proposed method is robust to different sampling positions and different sampling lengths of input data, which solves the problem of the original data being difficult to obtain due to the uncertainty of charging-discharging behaviour in actual operation.
Asunto(s)
Líquidos Corporales , Litio , Suministros de Energía Eléctrica , Iones , AlgoritmosRESUMEN
Energy management strategies are vitally important to give full play to the energy-saving of the four-wheel drive electric vehicle (4WD EV). The cooperative output of multi-power components is involved in the process of driving and braking energy recovery of 4WD EV. This paper proposes a novel energy management strategy of dual equivalent consumption minimization strategy (D-ECMS) to improve the economy of the vehicle. According to the different driving and braking states of the vehicle, D-ECMS can realize the proportional control of the energy cooperative output among the multi-power components. Under the premise of satisfying the dynamic performance of the vehicle, the operating points of the power components are distributed more in the high-efficiency range, and the economy and driving range of the vehicle are optimized. In order to achieve the effectiveness of D-ECMS, MATLAB/Simulink is used to realize the simulation of the vehicle. Compared with the rule-based strategy, the economy of D-ECMS increased by 4.35%.
RESUMEN
An energy management strategy is a key technology used to exploit the energy-saving potential of a plug-in hybrid electric vehicle. This paper proposes the environmental perceiver-based equivalent consumption minimization strategy (EP-ECMS) for parallel plug-in hybrid vehicles. In this method, the traffic characteristic information obtained from the intelligent traffic system is used to guide the adjustment of the equivalence factor, improving the environmental adaptiveness of the equivalent consumption minimization strategy (ECMS). Two main works have been completed. First, a high-accuracy environmental perceiver was developed based on a graph convolutional network (GCN) and attention mechanism to complete the traffic state recognition of all graph regions based on historical information. Moreover, it provides the grade of the corresponding region where the vehicle is located (for the ECMS). Secondly, in the offline process, the search for the optimal equivalent factor is completed by using the Harris hawk optimization algorithm based on the representative working conditions under various grades. Based on the identified traffic grades in the online process, the optimized equivalence factor tables are checked for energy management control. The simulation results show that the improved EP-ECMS can achieve 7.25% energy consumption optimization compared with the traditional ECMS.
Asunto(s)
Algoritmos , Electricidad , Simulación por ComputadorRESUMEN
Energy management strategies are vitally important to give full play to energy-saving four-wheel-drive plug-in hybrid electric vehicles (4WD PHEV). This paper proposes a novel dual-adaptive equivalent consumption minimization strategy (DA-ECMS) for the complex multi-energy system in the 4WD PHEV. In this strategy, management of the multi-energy system is optimized by introducing the categories of future driving conditions to adjust the equivalent factors and improving the adaptability and economy of driving conditions. Firstly, a self-organizing neural network (SOM) and grey wolf optimizer (GWO) are adopted to classify the driving condition categories and optimize the multi-dimensional equivalent factors offline. Secondly, SOM is adopted to identify driving condition categories and the multi-dimensional equivalent factors are matched. Finally, the DA-ECMS completes the multi-energy optimization management of the front axle multi-energy sources and the electric driving system and releases the energy-saving potential of the 4WD PHEV. Simulation results show that, compared with the rule-based strategy, the economy in the DA-ECMS is improved by 13.31%.
Asunto(s)
Conducción de Automóvil , Vehículos a Motor , Simulación por Computador , Electricidad , Emisiones de Vehículos/análisisRESUMEN
With the development of technology, speed prediction has become an important part of intelligent vehicle control strategies. However, the time-varying and nonlinear nature of vehicle speed increases the complexity and difficulty of prediction. Therefore, a CNN-based neural network architecture with two channel input (DICNN) is proposed in this paper. With two inputs and four channels, DICNN can predict the speed changes in the next 5 s by extracting the temporal information of 10 vehicle signals and the driver's intention. The prediction performances of DICNN are firstly examined. The best RMSE, MAE, ME and R2 are obtained compared with a Markov chain combined with Monte Carlo (MCMC) simulation, a support vector machine (SVM) and a single input CNN (SICNN). Secondly, equivalent fuel consumption minimization strategies (ECMS) combining different vehicle speed prediction methods are constructed. After verification by simulation, the equivalent fuel consumption of the simulation increases by only 4.89% compared with dynamic-programming-based energy management strategy and decreased by 5.40% compared with the speed prediction method with low accuracy.
Asunto(s)
Redes Neurales de la Computación , Máquina de Vectores de SoporteRESUMEN
Vehicle speed prediction can obtain the future driving status of a vehicle in advance, which helps to make better decisions for energy management strategies. We propose a novel deep learning neural network architecture for vehicle speed prediction, called VSNet, by combining convolutional neural network (CNN) and long-short term memory network (LSTM). VSNet adopts a fake image composed of 15 vehicle signals in the past 15 s as model input to predict the vehicle speed in the next 5 s. Different from the traditional series or parallel structure, VSNet is structured with CNN and LSTM in series and then in parallel with two other CNNs of different convolutional kernel sizes. The unique architecture allows for better fitting of highly nonlinear relationships. The prediction performance of VSNet is first examined. The prediction results show a RMSE range of 0.519-2.681 and a R2 range of 0.997-0.929 for the future 5 s. Finally, an energy management strategy combined with VSNet and model predictive control (MPC) is simulated. The equivalent fuel consumption of the simulation increases by only 4.74% compared with DP-based energy management strategy and decreased by 2.82% compared with the speed prediction method with low accuracy.
RESUMEN
Cognitive decline is a central feature in the aging process. Previous studies have indicated an association between depressive symptoms and cognitive decline in Caucasian populations. However, few studies have examined the effect of changes in depression on the trajectory of cognitive decline. Here, we included 580 participants with normal cognitive ability and complete cognitive and depression data from the Rugao Longevity and Ageing Study (RuLAS). We explored the relationship between depressive symptoms and cognitive decline in these participants. We examined how the change in depressive symptoms affected the trajectory in the HDS-R (the Revised Hasegawa Dementia Scale) scores by comparing cognition function in both the depression deterioration group and the depression steady group by using a linear mixed model. The results indicated that those with deteriorating depression tended to have faster cognitive declines than those with steady depression, indicated by the significance of the interaction term of GDS (Geriatric Depression Scale) groups and time (unadjusted model, ß = - 0.673, p < 0.001). The results remained significant after adding demographic covariates. Moreover, we found that those with the worst depressive symptoms at baseline had the worst cognition in subsequent years (GDS = 0 group vs. GDS ≥ group in the unadjusted model: ß = - 1.522, p < 0.003), while the slope of change was not significantly different among groups (GDS = 0 group × time vs. GDS > =4 group × time in the unadjusted model: ß = - 0.045, p = 0.857). Therefore, we found that depressive symptom deterioration was significantly associated with faster cognitive decline. Medical interventions for depression may decrease the number of older Chinese individuals who experience early-stage cognitive decline.
Asunto(s)
Disfunción Cognitiva , Depresión , Anciano , Envejecimiento , Cognición , Disfunción Cognitiva/epidemiología , Depresión/epidemiología , Humanos , LongevidadRESUMEN
P2X receptors are ligand-gated ion channels that can bind with the adenosine triphosphate (ATP) and have diverse functional roles in neuropathic pain, inflammation, special sense, and so on. In this study, 180 putative P2X genes, including 176 members in 32 animal species and 4 members in 3 species of lower plants, were identified. These genes were divided into 13 groups, including 7 groups in vertebrates and 6 groups in invertebrates and lower plants, through phylogenetic analysis. Their gene organization and motif composition are conserved in most predicted P2X members, while group-specific features were also found. Moreover, synteny relationships of the putative P2X genes in vertebrates are conserved while simultaneously experiencing a series of gene insertion, inversion, and transposition. Recombination signals were detected in almost all of the vertebrates and invertebrates, suggesting that intragenic recombination may play a significant role in the evolution of P2X genes. Selection analysis also identified some positively selected sites that acted on the evolution of most of the predicted P2X proteins. The phenomenon of alternative splicing occurred commonly in the putative P2X genes of vertebrates. This article explored in depth the evolutional relationship among different subtypes of P2X genes in animal and plants and might serve as a solid foundation for deciphering their functions in further studies.
Asunto(s)
Receptores Purinérgicos P2X/genética , Animales , Filogenia , Proteínas de Plantas/genéticaRESUMEN
Degeneration of the retina is intrinsically associated with the pathogenesis and progression of neurodegenerative diseases. However, the cellular and molecular mechanisms underlying the association between neurodegeneration and retinal degeneration are still under exploration due to the complexity of the connectivity network of the nervous system. In this study, RNA-seq data from the brains of model retinitis pigmentosa (RP) mice and previously studied Parkinson's disease (PD) mice were analyzed to explore the commonalities between retinal degenerative and neurodegenerative diseases. Differentially expressed genes in RP were compared with neurodegenerative disease-related genes and intersecting genes were identified, including Cnr1 and Septin14. These genes were verified by quantitative real-time reverse transcription PCR and Western blotting experiments. The key proteins CNR1 and SEPTIN14 were found to be potential cotherapeutic targets for retinal degeneration and neurodegenerative disease. In conclusion, understanding the commonalities between retinal degenerative diseases and neurodegenerative processes in the brain will not only facilitate the interpretation of the underlying pathomechanisms but also contribute to early diagnosis and the development of new therapeutic strategies.
RESUMEN
The escalating environmental concerns and energy crisis caused by internal combustion engines (ICE) have become unacceptable under environmental regulations and the energy crisis. As a promising alternative solution, multi-power source electric vehicles (MPS-EVs) integrate various clean energy systems to enhance the powertrain efficiency. The energy management strategy (EMS) is plays a pivotal role for MPS-EVs to maximize efficiency, fuel economy, and range. Reinforcement Learning (RL) has emerged as an effective methodology for EMS development, attracting continuous attention and research. However, a systematic analysis of the design elements of RL-based EMS is currently lacking. This paper addresses this gap by presenting a comprehensive analysis of current research on RL-based EMS (RL-EMS) and summarizing its design elements. This paper first summarizes the previous applications of RL in EMS from five aspects: algorithm, perception scheme, decision scheme, reward function, and innovative training method. It highlights the contributions of advanced algorithms to training effectiveness, provides a detailed analysis of perception and control schemes, classifies different reward function settings, and elucidates the roles of innovative training methods. Finally, by comparing the development routes of RL and RL-EMS, this paper identifies the gap between advanced RL solutions and existing RL-EMS. Potential development directions are suggested for implementing advanced artificial intelligence (AI) solutions in EMS.
RESUMEN
Staining frozen sections is often required to distinguish cell types for spatial transcriptomic studies of the brain. The impact of the staining methods on the RNA integrity of the cells becomes one of the limitations of spatial transcriptome technology with microdissection. However, there is a lack of systematic comparisons of different staining modalities for the pretreatment of frozen sections of brain tissue as well as their effects on transcriptome sequencing results. In this study, four different staining methods were analyzed for their effect on RNA integrity in frozen sections of brain tissue. Subsequently, differences in RNA quality in frozen sections under different staining conditions and their impact on transcriptome sequencing results were assessed by RNA-seq. As one of the most commonly used methods for staining pathological sections, HE staining seriously affects the RNA quality of frozen sections of brain tissue. In contrast, the homemade cresyl violet staining method developed in this study has the advantages of short staining time, low cost, and less RNA degradation. The homemade cresyl violet staining proposed in this study can be applied instead of HE staining as an advance staining step for transcriptome studies in frozen sections of brain tissue. In the future, this staining method may be suitable for wide application in brain-related studies of frozen tissue sections. Moreover, it is expected to become a routine step for staining cells before sampling in brain science.
Asunto(s)
Encéfalo , Secciones por Congelación , Coloración y Etiquetado , Animales , Encéfalo/metabolismo , Coloración y Etiquetado/métodos , Secciones por Congelación/métodos , Crioultramicrotomía/métodos , Ratones , Transcriptoma , Masculino , ARN/análisis , Benzoxazinas , Ratones Endogámicos C57BL , OxazinasRESUMEN
Common genetic association models for structured populations, including principal component analysis (PCA) and linear mixed-effects models (LMMs), model the correlation structure between individuals using population kinship matrices, also known as genetic relatedness matrices. However, the most common kinship estimators can have severe biases that were only recently determined. Here we characterize the effect of these kinship biases on genetic association. We employ a large simulated admixed family and genotypes from the 1000 Genomes Project, both with simulated traits, to evaluate key kinship estimators. Remarkably, we find practically invariant association statistics for kinship matrices of different bias types (matching all other features). We then prove using statistical theory and linear algebra that LMM association tests are invariant to these kinship biases, and PCA approximately so. Our proof shows that the intercept and relatedness effect coefficients compensate for the kinship bias, an argument that extends to generalized linear models. As a corollary, association testing is also invariant to changing the reference ancestral population of the kinship matrix. Lastly, we observed that all kinship estimators, except for popkin ratio-of-means, can give improper non-positive semidefinite matrices, which can be problematic although some LMMs handle them surprisingly well, and condition numbers can be used to choose kinship estimators. Overall, we find that existing association studies are robust to kinship estimation bias, and our calculations may help improve association methods by taking advantage of this unexpected robustness, as well as help determine the effects of kinship bias in related problems.
Asunto(s)
Modelos Genéticos , Grupos de Población , Humanos , Grupos de Población/genética , Genotipo , Modelos Lineales , Fenotipo , SesgoRESUMEN
A number of methods have been proposed for causal effect estimation, yet few have demonstrated efficacy in handling data with complex structures, such as images. To fill this gap, we propose Causal Multi-task Deep Ensemble (CMDE), a novel framework that learns both shared and group-specific information from the study population. We provide proofs demonstrating equivalency of CDME to a multi-task Gaussian process (GP) with a coregionalization kernel a priori. Compared to multi-task GP, CMDE efficiently handles high-dimensional and multi-modal covariates and provides pointwise uncertainty estimates of causal effects. We evaluate our method across various types of datasets and tasks and find that CMDE outperforms state-of-the-art methods on a majority of these tasks.
RESUMEN
A self-supporting composite electrode material with a unique three-dimensional structure was synthesized by in-situ growth of nanoscale NiMnLDH-Co(OH)2 on a nickel foam substrate via hydrothermal electrodeposition. The 3D layer of NiMnLDH-Co(OH)2 provided abundant reactive sites for electrochemical reactions, ensuring a solid and conductive skeleton for charge transfer and resulting in significant enhancement of electrochemical performance. The composite material showed a strong synergistic effect between the small nano-sheet Co(OH)2 and NiMnLDH, which promoted reaction kinetics, while the nickel foam substrate acted as a structural conductivity agent, stabilizer, and good conductive medium. The composite electrode showed impressive electrochemical performance, achieving a specific capacitance of 1870F g-1 at 1 A g-1 and retaining 87% capacitance after 3000 charge-discharge cycles, even at a high current density of 10 A g-1. Moreover, the resulting NiMnLDH-Co(OH)2//AC asymmetric supercapacitor (ASC) demonstrated remarkable specific energy of 58.2 Wh kg-1 at a specific power of 1200 W kg-1, along with outstanding cycle stability (89% capacitance retention after 5000 cycles at 10 A g-1). More importantly, DFT calculations reveal that NiMnLDH-Co(OH)2 facilitates charge transfer, accelerating surface redox reactions and increasing specific capacitance. This study presents a promising approach towards designing and developing advanced electrode materials for high-performance supercapacitors.
RESUMEN
Severe weather conditions pose a significant challenge for computer vision algorithms in autonomous driving applications, particularly regarding robustness. Image rain-removal algorithms have emerged as a potential solution by leveraging the power of neural networks to restore rain-free backgrounds in images. However, existing research overlooks the vulnerability concerns in neural networks, which exposes a potential threat to the intelligent perception of autonomous vehicles in rainy conditions. This paper proposes a universal rain-removal attack (URA) that exploits the vulnerability of image rain-removal algorithms. By generating a non-additive spatial perturbation, URA significantly diminishes scene restoration similarity and image quality. The imperceptible and generic perturbation employed by URA makes it a crucial tool for vulnerability detection in image rain-removal algorithms and a potential real-world AI attack method. Experimental results demonstrate that URA can reduce scene repair capability by 39.5% and image generation quality by 26.4%, effectively targeting state-of-the-art rain-removal algorithms.