Search

• A novel magnetorheological fluid damper inverse model is constructed based on the radial basis function neural network. • The filter performance function is employed in the semi-active suspension system as the reference state. • A unified frame is developed to study the semi-active suspension system with various disturbances. The magnetorheological fluid semi-active suspension system has been widely employed in vehicles. In general, the output force of the magnetorheological fluid damper varies with service time and temperature, which will cause the controller performance to degrade or even fail. To conquer this problem, this study proposes a compensatory backstepping strategy for the magnetorheological fluid suspension system. First, the normalized phenomenological model is introduced to simulate the nonlinear characteristics of the magnetorheological fluid damper. Second, the adaptive radial-basis function neural network is employed to construct the inverse model of the magnetorheological fluid damper. Next, the reference state is calculated by the filter performance function to trade off the vehicle handling stability and ride comfort. Finally, the voltage-force compensator is constructed to improve the robustness of the controller under input time delay, external noise disturbance, and actuator failures. Furthermore, the performances of the magnetorheological fluid damper, inverse magnetorheological fluid model, and compensatory backstepping controller are simulated under bump and random excitations. It is found that the proposed compensatory backstepping controller shows good improvement in the semi-active suspension system with time delay, noise disturbance, and actuator failure. [ABSTRACT FROM AUTHOR]

This paper investigates the adaptive event-triggered dynamic output feedback control problem for vehicle active suspension systems with nonlinearity and uncertainty based on interval type-2 fuzzy method. Firstly, considering the dynamic behaviors of the spring and shock absorber are highly nonlinear, a fuzzy suspension model is established to capture the nonlinearity and uncertainty of the suspension systems based on interval type-2 Takagi-Sugeno fuzzy rules. Secondly, in order to decrease the transmission burden, an event-triggered mechanism is employed to decide whether the sampled signal is transmitted or not with an adaptive triggering threshold. Thirdly, by combining the fuzzy dynamic output feedback control law with event-triggered mechanism, a co-design method of fuzzy controller and event generator is proposed to improve the suspension performances and save network resources simultaneously. Finally, experimental tests under multiple pavement are implemented to verify that the proposed method can improve the performance of ride comfort and reduce communication burden simultaneously, despite the existence of unmeasurable states and nonlinearities. [ABSTRACT FROM AUTHOR]

As a key environment perception technology of autonomous driving or driver assistance systems, lane detection is to ensure vehicles to drive safely in corresponding lane. However, existing lane detection algorithms for two-lane detection focus on using various filtering methods to reduce the impact of useless information, resulting in low accuracy and low efficiency. In this paper, a novel Adaptive Region of Interest (A-ROI) extraction method is proposed to improve the accuracy and real-time performance of the two-lane detection algorithm. Three key technologies are introduced to solve the problems. First, A-ROI, which only focuses on the lane where the vehicle is located, is applied to the Bird's-Eye-View image obtained by using Inverse Perspective Mapping (IPM). Next, based on Bayesian framework and Likelihood models, a lane feature extraction method with a lane-like feature filter is used for edge detection. Finally, an improved Random Sample Consensus (RANSAC) algorithm is introduced by using a filter that can remove noisy lane data. The performance of the proposed A-ROI method together with the improved lane detection method is evaluated via simulation of various scenarios. Experimental results show the proposed method has better accuracy and real-time performance than the traditional lane detection methods. [ABSTRACT FROM AUTHOR]

Self-supervised learning methods have been proved effective in the task of real-time stereo depth estimation with the requirement of lower memory space and less computational cost. In this paper, a light-weight adaptive network (LWANet) is proposed by combining the self-supervised learning method to perform online adaptive stereo depth estimation for low computation cost and low GPU memory space. Instead of a regular 3D convolution, the pseudo 3D convolution is employed in the proposed light-weight network to aggregate the cost volume for achieving a better balance between the accuracy and the computational cost. Moreover, based on U-Net architecture, the downsample feature extractor is combined with a refined convolutional spatial propagation network (CSPN) to further refine the estimation accuracy with little memory space and computational cost. Extensive experiments demonstrate that the proposed LWANet effectively alleviates the domain shift problem by online updating the neural network, which is suitable for embedded devices such as NVIDIA Jetson TX2. The relevant codes are available at https://github.com/GANWANSHUI/LWANet [ABSTRACT FROM AUTHOR]

For the purpose of improving the lateral stability in the path following process for the distributed drive electric vehicles subject to multiple actuator/sensor faults, a new fault diagnosis and fault tolerant control method is proposed in this paper through the integration of the active front steering (AFS) and direct yaw-moment control (DYC). Firstly, considering the actuator/sensor faults and parameter uncertainties together, a Takagi–Sugeno fuzzy model is established to describe the integrated AFS/DYC system with nonlinear dynamics. Secondly, because the fault information plays a key role in the fault tolerant control, a fuzzy estimation observer is presented to diagnose actuator/sensor faults online. Thirdly, considering the high cost of the measurement sensors for lateral speed, it is hard to measure the complete state of the vehicle. Thus, in the frame of dynamic output feedback structure, a fuzzy fault tolerant control method is proposed to improve the path following performance and guarantee the dynamic stability. Finally, the hardware-in-the-loop experimental results of two typical driving maneuvers show that the proposed control method has a superior performance in the improvement of the driving stability and active safety. [ABSTRACT FROM AUTHOR]

Active front steering (AFS) can enhance the vehicle yaw stability. However, the control of vehicle yaw rate is very challenging due to (1) the unmodelled nonlinearity and uncertainties in vehicle dynamics; (2) timely response in control scheme. These two issues can be simultaneously alleviated through a random projection neural network (RPNN) for its high model generalisation and fast computational speed. However, typical RPNN cannot be directly applied to adaptive control applications. Therefore, a new RPNN-based adaptive neural control method is proposed, which is equipped with a newly designed adaptation law based on the theorem of Lyapunov stability. To test the performance of the proposed control method, simulations were carried out using a validated vehicle model. The simulation results show that, compared to conventional backpropagation neural network (BPNN) based controller, the proposed RPNN-based adaptive controller can reduce the response time and attenuate oscillatory steering in the case of cornering manoeuvre under fast variant vehicle speed. The results also demonstrate that the proposed RPNN-based adaptive controller outperforms the state-of-the-art fuzzy logic controller and the error feedback controller in multiple aspects including tracking nominal vehicle yaw rate, desired sideslip angle and intended path, showing its significance in vehicle yaw stability control. [ABSTRACT FROM AUTHOR]

The assessment of vehicle dynamic comfort to human body vibration varies from person to person. Even though the dynamic comfort rating can be obtained by placing measurement devices over the cabin, passengers may have dissimilar sensations. For many car manufacturers, both subject and objective measurements are used together at development of new cars. To effectively assess the dynamic comfort of vehicle, this research explores the correlation between the objective measurement of the whole body vibration, hand-transmitted vibration and subjective assessment. The whole body vibration is measured from the backrest, seat surface and vehicle floor, whereas the hand-transmitted vibration is measured from the steering wheel. Four different vehicles are driven at various speeds on five types of pavements. Both simple linear regression and polynomial regression models based on Stevens's power law from psychophysics are built to correlate the subjective and objective data. The regression results show that (1) the seat surface is more reliable than other positions for assessing the human body vibration; (2) the hand transmitted vibration on rough roads is more trustful for dynamic comfort evaluation than on smooth roads; (3) the overall dynamic comfort value is the most reliable index for dynamic comfort evaluation. [ABSTRACT FROM AUTHOR]

The automotive engine idle speed control problem is a compromise among low engine speed for fuel saving, minimum emissions and disturbance rejection ability to prevent engine stall. However, idle speed regulation is very challenging due to the presence of high nonlinearity and aging-caused uncertainties in the engine dynamics. Therefore, the engine idle speed system is a typical uncertain nonlinear system. To address the problems of inherent nonlinearity and uncertainties in idle speed regulation, an extreme learning machine (ELM)-based adaptive neural control algorithm is proposed for tracking the target idle speed adaptively. The purpose of ELM is to rapidly deal with the uncertain nonlinear engine system. Since the original ELM is not designed for adaptive control, a new adaptation law is designed to update the weights of ELM in the sense of Lyapunov stability. Experiment is conducted to validate the performance of the proposed control method. Experimental result indicates that the ELM-based adaptive neural control outperforms the classical proportional–integral–derivative (PID), fuzzy-PID and back-propagation-neural-network-based controllers in terms of tracking performance under the variation of engine load. [ABSTRACT FROM AUTHOR]

Summary: This paper proposes a new integrated vehicle dynamics management for enhancing the yaw stability and wheel slip regulation of the distributed‐drive electric vehicle with active front steering. To cope with the unknown nonlinear tire dynamics with uncertain disturbances in integrated control problem of vehicle dynamics, a neuro‐adaptive predictive control is therefore proposed for multiobjective coordination of constrained systems with unknown nonlinearity. Unknown nonlinearity with unmodeled dynamics is modeled using a random projection neural network via adaptive machine learning, where a new adaptation law is designed in premise of Lyapunov stability. Given the computational efficiency, a neurodynamic method is extended to solve the constrained programming problem with unknown nonlinearity. To test the performance of the proposed control method, simulations were conducted using a validated vehicle model. Simulation results show that the proposed neuro‐adaptive predictive controller outperforms the classical model predictive controller in tracking nominal wheel slip ratio, desired vehicle yaw rate and sideslip angle, showing its significance in vehicle yaw stability enhancement and wheels slip regulation. [ABSTRACT FROM AUTHOR]

Highlights • The vehicle nonlinear characteristics are considered by using the T-S fuzzy approach. • A new sliding mode control strategy is proposed based on the T-S fuzzy approach. • The effective region is considered for the bounded sector zone of the AFS system. • A model parameter observer is designed to obtain the real-time cornering stiffness. Abstract Active front steering (AFS) has drawn considerable attention due to its superiority in improving the vehicle safety. This paper proposes a new Takagi-Sugeno (T-S) fuzzy based sliding mode control (SMC) strategy for the AFS system to improve the cornering stability of vehicles. Different from the conventional SMC strategy, the control law of the proposed control strategy is designed based on the T-S fuzzy approach which deals with the nonlinearity of the tire in a simplified but effective way. In the design of the control strategy, the bounded sector zone in the T-S fuzzy approach is determined based on the working region of the AFS system, and a model parameter observer is constructed to obtain the real-time cornering stiffness of the vehicle. To evaluate the cornering performance, simulations are conducted via open-loop and closed-loop tests. Simulation results show that the proposed T-S fuzzy based SMC strategy, which considers the nonlinearity of the tire and multi-objective control, is able to improve the cornering stability of the vehicle as compared with the conventional SMC strategy. [ABSTRACT FROM AUTHOR]

Highlights • Compensation system based regulating mechanism with grey neural network or fuzzy neural network for nonlinear hydraulic adjustable damper. • Particle swarm optimization optimized sliding mode control method for multi-objective control of semi-active suspension systems. • Online hardware-in-the-loop test on quarter car test rig for practical application of vehicle semi-active suspension systems. Abstract In recent, the development of the automotive semi-active suspension (SAS) system with the nonlinear hydraulic adjustable damper (HAD) has attracted widely attention due to its superiorities of low energy consumption, fast response, durable, reliable and simple structure. Many existing SAS researches focus on control algorithms for limited objectives and assume the control signal is the damping force, but very few of them discusses how to realize the calculated damping force. To solve this problem, the unknown regulating mechanism of the nonlinear HAD should be modeled and a complex multi-objective control of the SAS system should be designed. Aiming at modeling the regulating mechanism of the nonlinear HAD, this work constructs a novel compensation system by using fuzzy neural network or grey neural network algorithm in order to realize the desired damping force by regulating the stepper motor angle adaptively. Meanwhile, a new multi-objective control strategy, particle swarm optimization based sliding mode control method, is originally proposed to calculate the desired damping force to achieve exact damping force control of the SAS system. To realize the practical application of the SAS system with the nonlinear HAD, an online hardware-in-the-loop test is conducted on a quarter car test rig. Numerical and experimental results illustrate that the modeled regulating mechanism of the nonlinear HAD and the proposed multi-objective control of SAS system are effective to improve the vertical performance of the vehicle and feasible in practical applications. [ABSTRACT FROM AUTHOR]

The semi-active suspension (SAS) system has been one of the most attractive topics due to its simplicity and effectiveness in the control of vehicle dynamics. This research proposes a cuckoo search optimized proportional-integral-derivative (CS-PID) strategy for the damping force control of the semi-acive suspension system in order to improve vehicle ride quality. Firstly, a quarter-car suspension model with air spring and variable hydraulic damper (VHD) is developed. By constructing the detailed analytical model and describing the working process, the regulating mechanism and external characteristics of the VHD are presented. Subsequently, the CS-PID strategy is designed to generate the desired damping force according to the vehicle states in real-time, followed with the evaluation of the proposed strategy. Finally, the experimental tests are carried out to verify the accuracy of the VHD model and examine the feasibility of the proposed strategy. The numerical simulation reveal that the proposed control strategy is effective in improving the vehicle performance and the experimental results show that the CS-PID strategy can be successfully implemented in the suspension system for practical use. [ABSTRACT FROM AUTHOR]

Abstract As an effective approach of suppressing vibrations, the constrained layer damping (CLD) has drawn wide attention from the automotive and aerospace industries. However, most of the existing investigations focus on the beam structures with CLD and few studies have been done on the plate structures with CLD. Considering the practical applications, this work studies the finite element (FE) modeling of plate structures with CLD by considering the shear and extension strains in all of three layers. To reduce the computational cost and ensure the accuracy, a simplified single-layer equivalent method is originally proposed to model the plate structure with CLD based on the equivalent material properties. In this method, the equivalent material properties are obtained by defining a new equation which includes the equivalent bending stiffness. By nonlinear regression of these responses at resonance frequencies, the equivalent bending stiffness can be obtained, and the plate structure with CLD can be regarded as a regular single-layer plate for modeling. The simulation result shows that the proposed simplified single-layer equivalent method using single-layer equivalent material properties is efficient and accurate for modeling plate structures with CLD. [ABSTRACT FROM AUTHOR]

Intelligent fault diagnosis of rotating machinery is vital for industries to improve fault prediction performance and reduce the maintenance cost. The new fault diagnostic framework is proposed which consists of three stages: (1) signal processing and feature extraction, (2) fault diagnosis by combining the classification results through a probabilistic ensemble method, and (3) parameter optimization and performance evaluation. In the first stage, ensemble empirical mode decomposition (EEMD) decomposes the acquired signal into a suite of intrinsic mode functions (IMF) which encounters redundant components and large data problems. To eliminate the redundant IMF and select fault feature from residual IMF, correlation coefficient (CC) and singular value decomposition (SVD) method are applied respectively. In the second stage, to improve the performance of fault diagnosis based on single classifier and increase the number of detectable fault, a new probabilistic committee machine (PCM) method is proposed, in which multiple pairwise-coupled sparse Bayesian extreme learning machines (PCSBELM) are individually trained using air ration, ignition pattern and engine sound signal. In addition, each classifier is assigned with an optimal weight in accordance with their reliability and accuracy so that a reliable and widely-covered fault diagnostic result can be obtained from the weighted combination of the members. To verify the effectiveness of the proposed fault diagnostic framework, it is applied to automotive engine fault detection. The evaluation results show the proposed framework is superior to the existing single classifier in terms of both single- and simultaneous-faults in automotive engine. [ABSTRACT FROM AUTHOR]

Dual-injection engines, which allow real-time control and injection of two different fuels, are capable of varying the ratio of biofuel blends at different engine operating conditions for optimal engine performance. However, while many experiments have been carried out on these engines to demonstrate their advantages, very few studies have focused on the corresponding air–fuel ratio (AFR) control strategy. In order to achieve stable engine operation, it is essential to maintain transient AFR during the change of fuel blend ratio. Therefore, this study proposes an adaptive controller for AFR control of dual-injection engines. The proposed controller is designed based on a recently developed machine learning method called extreme learning machine, and its stability is verified with Lyapunov analysis. Simulations have been performed on an industry-level engine simulation software to verify the controller. Since dual-injection engines are not available in the market, a spark-ignition engine has been retrofitted for dual-injection operation so that the proposed controller can be implemented and evaluated experimentally. Both simulation and experiment results show that the proposed controller can effectively regulate the AFR to desired level. The results also show that the proposed controller outperforms the engine built-in AFR controller, indicating its significance for dual-injection engines. [ABSTRACT FROM AUTHOR]

An online extreme learning machine (ELM) based modeling and optimization approach for point-by-point engine calibration is proposed to improve the efficiency of conventional model-based calibration approach. Instead of building hundreds of local engine models for every engine operating point, only one ELM model is necessary for the whole process. This ELM model is firstly constructed for a starting operating point, and calibration of this starting point is conducted by determining the optimal parameters of the model. This ELM model is then re-used as a base model for a nearby target operating point, and optimization is performed on the model to search for its best parameters. With a design of experiment strategy on the best parameters obtained, new measurements from the target operating point can be collected and used to update the model. By repeating the optimization and model update procedures, the optimal parameters for the target point can be found after several iterations. By using the model of this target point as the base model for another nearby operating point and repeating the same process again, calibration for all the operating points can be done online efficiently. The contribution of the proposed method is to save the number of experiments in the calibration process. To verify the effectiveness of the proposed approach, experiments on a commercial engine simulation software have been conducted. Three variants of online ELM are utilized in the model update process for comparison. The results show that engine calibration can be carried out with much fewer measurements and time using the proposed approach, and the initial training free online ELM is the most efficient online modeling method for this application. [ABSTRACT FROM AUTHOR]

Summary: It is well known that the map‐based control can reduce the computational burden of the automotive on‐board controller. This paper proposes an output‐feedback model‐reference adaptive control algorithm to calibrate the map‐based anti‐jerk controller for electromechanical clutch engagement. The algorithm can be used to adaptively construct a data‐driven fuzzy rule base without resorting to manual tuning, so that it can overcome the problem of conventional knowledge‐based fuzzy logic design, which involves strenuous parameter‐tuning work in the construction of calibration maps. To accurately define the consequent of each fuzzy rule for anti‐jerk control, an output feedback law for computing the reference trajectory of clutch engagement is developed to eliminate the discontinuous slip‐stick transition, whereas an adaptive controller is designed to track the reference trajectory and compensate the nonlinearity. The convergence of the proposed output‐feedback model‐reference adaptive control algorithm is analyzed. Simulation results indicate that the proposed method can successfully reduce the excessive vehicle jerk and frictional energy dissipation during clutch engagement as compared with the conventional knowledge‐based fuzzy logic controller without fine tuning. [ABSTRACT FROM AUTHOR]

The continuously variable transmission (CVT) is one of the prevailing automotive transmissions. Nowadays, the most popular design is Van Doorne's CVT with single metal pushing V-belt. However, it is only applicable to low-power passenger cars because of its low torque capacity. To overcome this limitation of traditional single-belt Van Doorne's CVT, this research proposes a novel parallel Van Doorne's dual-belt CVT system which can be applied to heavy-duty vehicles. As the first attempt, an analytical model for both torque capacity and power efficiency based on effective radii instead of traditional working radii for the single-belt CVT is developed for this novel CVT system, and this newly developed model is experimentally validated. Evaluation result reveals that the new analytical model based on effective radii is more accurate than that based on working radii. Experimental and simulation results show that the proposed dual-belt CVT system can greatly improve the torque capacity as compared with the single-belt CVT. Moreover, the newly proposed analytical model can provide a foundation for further study of multi-belt CVTs. [ABSTRACT FROM AUTHOR]

Although many combinations of biofuel blends are available in the market, it is more beneficial to vary the ratio of biofuel blends at different engine operating conditions for optimal engine performance. Dual-injection engines have the potential to implement such function. However, while optimal engine calibration is critical for achieving high performance, the use of two injection systems, together with other modern engine technologies, leads the calibration of the dual-injection engines to a very complicated task. Traditional trial-and-error-based calibration approach can no longer be adopted as it would be time-, fuel- and labor-consuming. Therefore, a new and fast calibration method based on sparse Bayesian extreme learning machine (SBELM) and metaheuristic optimization is proposed to optimize the dual-injection engines operating with biofuels. A dual-injection spark-ignition engine fueled with ethanol and gasoline is employed for demonstration purpose. The engine response for various parameters is firstly acquired, and an engine model is then constructed using SBELM. With the engine model, the optimal engine settings are determined based on recently proposed metaheuristic optimization methods. Experimental results validate the optimal settings obtained with the proposed methodology, indicating that the use of machine learning and metaheuristic optimization for dual-injection engine calibration is effective and promising. [ABSTRACT FROM AUTHOR]

This paper proposes a novel integrated controller with three-layer hierarchical structure to coordinate the interactions among active suspension system (ASS), active front steering (AFS) and direct yaw moment control (DYC). First of all, a 14-degree-of-freedom nonlinear vehicle dynamic model is constructed. Then, an upper layer is designed to calculate the total corrected moment for ASS and intermediate layer based on linear moment distribution. By considering the working regions of the AFS and DYC, the intermediate layer is functionalised to determine the trigger signal for the lower layer with corresponding weights. The lower layer is utilised to separately trace the desired value of each local controller and achieve the local control objectives of each subsystem. Simulation results show that the proposed three-layer hierarchical structure is effective in handling the working region of the AFS and DYC, while the quasi-experimental result shows that the proposed integrated controller is able to improve the lateral and vertical dynamics of the vehicle effectively as compared with a conventional electronic stability controller. [ABSTRACT FROM PUBLISHER]

The automotive engine is prone to various faults due to its complex structure and running conditions. Development of a fast response and accurate intelligent system for fault diagnosis of automotive engines is therefore greatly urged. The engine fault diagnosis faces challenges because of the existence of simultaneous-faults which are multiple single-faults appear concurrently. Another challenge is the high cost in acquiring the exponentially increased simultaneous-fault signals. Traditional signal-based engine fault diagnostic systems may not give reliable diagnostic results because they usually rely on single classifier and one kind of engine signal. To enhance the reliability of fault diagnosis and the number of detectable faults, this research proposes a new diagnostic framework namely probabilistic committee machine (PCM). The framework combines feature extraction (empirical mode decomposition and sample entropy), a parameter optimization algorithm, and multiple sparse Bayesian extreme learning machines (SBELM) to form an intelligent diagnostic framework. Multiple SBELM networks are built to form different domain committee members. The members are individually trained using air ratio, ignition pattern and engine sound signals. The diagnostic result from each fault detection member is then combined by using a new probabilistic ensemble method, which can improve the overall diagnostic accuracy and increase the number of detectable faults as compared to individual classifier. Experimental results show the proposed framework is superior to the existing single probabilistic classifier. Moreover, the proposed system can diagnose both single and simultaneous-faults for automotive engines while the system is trained by single-fault patterns only. [ABSTRACT FROM AUTHOR]

Semiactive suspension (SAS) system has been widely used for its outstanding performance in offering competent ride quality, road holding, and handling capacity. However, the road friendliness is also one of the crucial factors that should be attached in the design of the SAS system for heavy-duty vehicles. In this study, a fuzzy controlled hybrid-acceleration driven damper (ADD) and ground hook- (GH-) control strategy is proposed for SAS system of heavy-duty vehicles. Firstly, a quarter-vehicle model with SAS system is constructed. Then, aiming to improve the ride quality and road friendliness, a hybrid-ADD and GH-control strategy is proposed under the coordination of the fuzzy controller. Numerical results show that the ride quality and road friendliness of the SAS system with the proposed control strategy outperform those with traditional hybrid-sky hook and ground hook-control strategy. It is also verified that the proposed strategy is superior to the sole ADD approach and sole ground hook approach in improving the vehicle overall performance. [ABSTRACT FROM AUTHOR]

A novel dual-belt Van Doorne’s continuous variable transmission (DBVCVT) system, which is applicable to heavy-duty vehicles, has been previously proposed by the authors in order to improve the low torque capacity of traditional single-belt CVT. This DBVCVT is a novel design among continuously variable transmissions and is necessary to be prototyped for experimental study, and the analytical dynamic model for this DBVCVT also needs to be experimentally validated. So, this work originally fabricated a prototype of DBVCVT and integrates this prototype to a light-load hardware-in-the-loop test rig by replacing the engine and load equipment with the AC motor and magnetic powder dynamometer. Moreover, with the use of this newly developed test rig, this work implements the experimental study of this DBVCVT for the first time. The comparison of experimental and simulation results validates the previously proposed analytical model for DBVCVT, and some basic characteristics of the DBVCVT in terms of the reliability, speed ratio, and transmission efficiency are also experimentally studied. In all, this developed test rig with the analytical model lays the foundation for further study on this novel DBVCVT. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have received increased attention in endoscopic images due to their outstanding advantages. Clinically, some gastric polyps are related to gastric cancer, and accurate identification and timely removal are critical. CNN-based semantic segmentation can delineate each polyp region precisely, which is beneficial to endoscopists in the diagnosis and treatment of gastric polyps. At present, just a few studies have used CNN to automatically diagnose gastric polyps, and studies on their semantic segmentation are lacking. Therefore, we contribute pioneering research on gastric polyp segmentation in endoscopic images based on CNN. Seven classical semantic segmentation models, including U-Net, UNet++, DeepLabv3, DeepLabv3+, Pyramid Attention Network (PAN), LinkNet, and Muti-scale Attention Net (MA-Net), with the encoders of ResNet50, MobineNetV2, or EfficientNet-B1, are constructed and compared based on the collected dataset. The integrated evaluation approach to ascertaining the optimal CNN model combining both subjective considerations and objective information is proposed since the selection from several CNN models is difficult in a complex problem with conflicting multiple criteria. UNet++ with the MobineNet v2 encoder obtains the best scores in the proposed integrated evaluation method and is selected to build the automated polyp-segmentation system. This study discovered that the semantic segmentation model has a high clinical value in the diagnosis of gastric polyps, and the integrated evaluation approach can provide an impartial and objective tool for the selection of numerous models. Our study can further advance the development of endoscopic gastrointestinal disease identification techniques, and the proposed evaluation technique has implications for mathematical model-based selection methods for clinical technologies. [ABSTRACT FROM AUTHOR]

Summary: This article is concerned with the problem of robust fuzzy fault tolerant control for the nonlinear active suspension system via adaptive hybrid triggered scheme. To describe the system with high nonlinearity, a Takagi‐Sugeno fuzzy approach is applied by weighting a series of linear subsystems. During the design of the controller, the actuator failure is taken into consideration. To ease the network communication pressure, a novel adaptive hybrid triggered scheme is proposed for the suspension system. By applying a Bessel‐Legendre inequality and a Jensen's inequality together, the control algorithm can be derived in the form of linear matrix inequalities with less conservatism. Finally, compared with the existing sampled‐data H∞$$ {H}_{\infty } $$ control and adaptive event triggered H∞$$ {H}_{\infty } $$ control, numerical simulations are performed to demonstrate the effectiveness and superiority of the proposed controller. [ABSTRACT FROM AUTHOR]

The lifetime and efficiency of diesel particulate filters (DPFs) strongly depend on the proper and periodic cleaning and servicing. Unfortunately, in some cases, inappropriate methods are applied to clean the DPFs, e.g., using air compressors without proper disposal procedures which can have negative impacts on human health, the environment, and DPF's efficiency. However, there is no information available about the properties of this kind of PM. This research is therefore presented to explore the physicochemical and toxicity properties of aged PM trapped in a DPF (using compressed air for PM sampling) employing STEM, SEM, EDS, Organic Carbon Analyzer, TGA/DSC, and Raman Spectrometer for investigating the physicochemical properties, and assays of cell viability, cellular reactive oxygen species (ROS), interleukin-6, and tumor necrosis factor-alpha (TNF-α) for investigating the toxicity properties. Also, analyses from fresh PM samples from the diesel vehicle at two engine speeds are presented. It is found that at a certain/fixed PM number/mass for all three samples tested, the PM from DPF compared with the fresh PM can have both positive (particularly having the lowest water-soluble total carbon ratio) and negative impacts on human health (particularly having the highest cell death rate of 13.4%, ROS, and TNF-α) and the environment. [Display omitted] • Exploring physicochemical and cell toxicity properties of particulate matter (PM). • Examining PM trapped in a diesel particulate filter (DPF) and from a diesel engine. • Particles are in 32.3 nm and agglomerates are mostly big (even > 10 µm) in DPF. • PM of DPF has 25.1% non-volatile substances with ignition temperature of 550–600 °C. • One mg PM of DPF causes a cell death rate of 13.4% and 4.75 fold change in ROS. [ABSTRACT FROM AUTHOR]

While many standards have been stipulated to control vehicular emissions, current inspection program for examining the engine health of in-use vehicles is practically ineffective and time-consuming. In particular, in-use vehicles are only required for inspection yearly, but huge amount of emissions may have been produced from malfunctioned engines daily. A new wireless inspection and notification system (WINS) is therefore proposed to monitor the vehicle engine health on the street in situ . The principle of WINS is to wirelessly examine some of the engine parameters through radio frequency identification (RFID) and traffic lights. RFID tags are installed on vehicles to collect the engine health information, whereas RFID interrogators are installed on traffic lights for wireless data transmission. Experiments were carried out to evaluate the effectiveness of the proposed WINS, and the results show that the proposed WINS is more convenient and economical than traditional vehicle inspection system. Moreover, as there are more than hundreds of traffic lights in the traffic network of a city, a maximum spanning tree (MAXST) algorithm is proposed to determine the suitable number of RFID devices required in the network so that the implementation cost, system loading and missing rate can be optimized. Different from the typical spanning tree algorithm in operational research, the MAXST algorithm has a domain-specific rule and weight calculation method for this application. To verify the methodology, simulations on the traffic networks of Shenzhen, New York and London were conducted. Results show that only 25–40% of traffic lights of the traffic networks are necessary for installation of RFID interrogators, with a rate of 2–7% that the vehicle owners may be able to escape the location of RFID interrogators. [ABSTRACT FROM AUTHOR]

Effective air-ratio control is desirable to maintain the best engine performance. However, traditional air-ratio control assumes the lambda sensor located at the tail pipe works properly and relies strongly on the air-ratio feedback signal measured by the lambda sensor. When the sensor is warming up during cold start or under failure, the traditional air-ratio control no longer works. To address this issue, this paper utilizes an advanced modelling technique, kernel extreme learning machine (ELM), to build a backup air-ratio model. With the prediction from the model, a limited air-ratio control performance can be maintained even when the lambda sensor does not work. Such strategy is realized as fault tolerance control. In order to verify the effectiveness of the proposed fault tolerance air-ratio control strategy, a model predictive control scheme is constructed based on the kernel ELM backup air-ratio model and implemented on a real engine. Experimental results show that the proposed controller can regulate the air-ratio to specific target values within a satisfactory tolerance under external disturbance and the absence of air-ratio feedback signal from the lambda sensor. This implies that the proposed fault tolerance air-ratio control is a promising scheme to maintain air-ratio control performance when the lambda sensor is under failure or warming up. [ABSTRACT FROM AUTHOR]

This study presents the optimization of biodiesel engine performance that can achieve the goal of fewer emissions, low fuel cost and wide engine operating range. A new biodiesel engine modeling and optimization framework based on extreme learning machine (ELM) is proposed. As an accurate model is required for effective optimization result, kernel-based ELM (K-ELM) is used instead of basic ELM because K-ELM can provide better generalization performance, and the randomness of basic ELM does not occur in K-ELM. By using K-ELM, a biodiesel engine model is first created based on experimental data. Logarithmic transformation of dependent variables is used to alleviate the problems of data scarcity and data exponentiality simultaneously. With the K-ELM engine model, cuckoo search (CS) is then employed to determine the optimal biodiesel ratio. A flexible objective function is designed so that various user-defined constraints can be applied. As an illustrative study, the fuel price in Macau is used to perform the optimization. To verify the modeling and optimization framework, the K-ELM model is compared with a least-squares support vector machine (LS-SVM) model, and the CS optimization result is compared with particle swarm optimization and experimental results. The evaluation result shows that K-ELM can achieve comparable performance to LS-SVM, resulting in a reliable prediction result for optimization. It also shows that the optimization results based on CS is effective. [ABSTRACT FROM AUTHOR]

Abstract: Real-time fault diagnostic system is very important to maintain the operation of the gas turbine generator system (GTGS) in power plants, where any abnormal situation will interrupt the electricity supply. The GTGS is complicated and has many types of component faults. To prevent from interruption of electricity supply, a reliable and quick response framework for real-time fault diagnosis of the GTGS is necessary. As the architecture and the learning algorithm of extreme learning machine (ELM) are simple and effective respectively, ELM can identify faults quickly and precisely as compared with traditional identification techniques such as support vector machines (SVM). This paper therefore proposes a new application of ELM for building a real-time fault diagnostic system in which data pre-processing techniques are integrated. In terms of data pre-processing, wavelet packet transform and time-domain statistical features are proposed for extraction of vibration signal features. Kernel principal component analysis is then applied to further reduce the redundant features in order to shorten the fault identification time and improve accuracy. To evaluate the system performance, a comparison between ELM and the prevailing SVM on the fault detection was conducted. Experimental results show that the proposed diagnostic framework can detect component faults much faster than SVM, while ELM is competitive with SVM in accuracy. This paper is also the first in the literature that explores the superiority of the fault identification time of ELM. [Copyright &y& Elsevier]

As an effective and efficient discriminative learning method, the broad learning system (BLS) has received increasing attention due to its outstanding performance without large computational resources. The standard BLS is derived under the minimum mean square error (MMSE) criterion, while MMSE is with poor performance when dealing with imbalanced data. However, imbalanced data are widely encountered in real-world applications. To address this issue, a novel cost-sensitive BLS algorithm (CS-BLS) is proposed. In the CS-BLS, many variations can be adopted, and CS-BLS with weighted cross-entropy is analyzed in this paper. Weighted penalty factors are used in CS-BLS to constrain the contribution of each sample in different classes. The samples in minor classes are allocated higher weights to increase their contributions. Four different weight calculation methods are adopted to the CS-BLS, and thus, four CS-BLS methods are proposed: Log-CS-BLS, Lin-CS-BLS, Sqr-CS-BLS, and EN-CS-BLS. Experiments based on artificially imbalanced datasets of MNIST and small NORB are firstly conducted and compared with the standard BLS. The results show that the proposed CS-BLS methods have better generalization and robustness than the standard BLS. Then, experiments on a real ultrasound breast image dataset are conducted, and the results demonstrate that the proposed CS-BLS methods are effective in actual medical diagnosis. [ABSTRACT FROM AUTHOR]

Simultaneous-fault diagnosis is a common problem in many applications and well-studied for time-independent patterns. However, most practical applications are of the type of time-dependent patterns. In our study of simultaneous-fault diagnosis for time-dependent patterns, two key issues are identified: 1) the features of the multiple single faults are mixed or combined into one pattern which makes accurate diagnosis difficult, 2) the acquisition of a large sample data set of simultaneous faults is costly because of high number of combinations of single faults, resulting in many possible classes of simultaneous-fault training patterns. Under the assumption that the time-frequency features of a simultaneous fault are similar to that of its constituent single faults, these issues can be effectively resolved using our proposed framework combining feature extraction, pairwise probabilistic multi-label classification, and decision threshold optimization. This framework has been applied and verified in automotive engine-ignition system diagnosis based on time-dependent ignition patterns as a test case. Experimental results show that the proposed framework can successfully resolve the issues. [ABSTRACT FROM PUBLISHER]

Abstract: This study aims to determine optimal biodiesel ratio that can achieve the goals of fewer emissions, reasonable fuel economy and wide engine operating range. Different advanced machine learning techniques, namely ELM (extreme learning machine), LS-SVM (least-squares support vector machine) and RBFNN (radial-basis function neural network), are used to create engine models based on experimental data. Logarithmic transformation of dependent variables is used to alleviate the problems of data scarcity and data exponentiality simultaneously. Based on the engine models, two optimization methods, namely SA (simulated annealing) and PSO (particle swarm optimization), are employed and a flexible objective function is designed to determine the optimal biodiesel ratio subject to various user-defined constraints. A case study is presented to verify the modeling and optimization framework. Moreover, two comparisons are conducted, where one is among the modeling techniques and the other is among the optimization techniques. Experimental results show that, in terms of the model accuracy and training time, ELM with the logarithmic transformation is better than LS-SVM and RBFNN with/without the logarithmic transformation. The results also show that PSO outperforms SA in terms of fitness and standard deviation, with an acceptable computational time. [Copyright &y& Elsevier]

Abstract: Modern automotive engines are controlled by an electronic control unit (ECU), and engine power performance is significantly affected by the selection of both ECU parameters and engine components. The engine performance tuning is usually done by a trial-and-error method. In the current literature, very little research has considered the selection of engine parts because engine parts are complicated objects that are usually represented as nominal data. These data are meaningless values in terms of computation. This paper presents a novel multiple-input/output least-squares support vector machine plus one-of-n remapping method for modelling engine power performance using both numerical (ECU parameters) and nominal data (candidate engine parts). The Quasi-Newton method, a genetic algorithm and particle swarm optimisation are then applied to the engine model to determine the optimal engine setup automatically. A simple binary code synthesis rule is also proposed to optimise the nominal variable. Both experimental and simulation results show that the proposed methodology can successfully yield an optimal engine setup. [Copyright &y& Elsevier]

Hysteresis nonlinearity degrades the positioning accuracy of a piezostage and requires a suppression for precision micro-/nanopositioning applications. This paper proposes two new approaches to modeling and compensating the rate-dependent hysteresis of a piezostage driven by piezoelectric stack actuators. By formulating the hysteresis modeling as an online nonlinear regression problem, online least squares support vector machine (SVM) (LS-SVM) and online relevance vector machine (RVM) models are proposed to capture the hysteretic behavior. Both hysteresis models are capable of updating continually with subsequent samples. After a comparative study on modeling performances, an inverse model-based feedforward combined with proportional–integral–derivative feedback control is presented to alleviate the hysteresis effect. Experimental results show that the LS-SVM model-based control scheme is over 86% more accurate than the RVM model-based one in the motion tracking task, whereas the latter is 14 times faster than the former in terms of updating time. Moreover, both LS-SVM and RVM model-based control schemes can suppress the rate-dependent hysteresis to a negligible level, which validates the feasibility and effectiveness of the proposed approaches. [ABSTRACT FROM AUTHOR]

Abstract: Hysteresis effect degrades the positioning accuracy of a piezostage, and hence the nonlinearity has to be suppressed for ultrahigh-precision positioning applications. This paper extends least squares support vector machines (LS-SVM) to the domain of hysteresis modeling and compensation for a piezostage driven by piezoelectric stack actuators. A LS-SVM model is proposed and trained by introducing the current input value and input variation rate as the input data set to formulate a one-to-one mapping. By adopting the radial basis function (RBF) as kernel function, the LS-SVM model only has two free hyperparameters, which are optimally tuned by resorting to Bayesian inference framework. The effectiveness of the presented model is verified as compared with two state-of-the-art approaches, namely, Bouc–Wen model and modified Prandtl–Ishlinskii (MPI) model. In addition, the LS-SVM inverse model based feedforward control combined with an incremental proportional–integral–derivative (PID) feedback control is designed to compensate the hysteresis nonlinearity. Experimental results show that the LS-SVM model based hybrid control scheme is superior to the Bouc–Wen model and MPI model based ones as well as either of the stand-alone controllers. The rate-dependent hysteresis is suppressed to a negligible level, which validates the effectiveness of the constructed controller. Owing to a simple procedure, the proposed LS-SVM based approach can be applied to modeling and control of other types of hysteretic systems as well. [Copyright &y& Elsevier]

Abstract: Whenever there is any fault in an automotive engine ignition system or changes of an engine condition, an automotive mechanic can conventionally perform an analysis on the ignition pattern of the engine to examine symptoms, based on specific domain knowledge (domain features of an ignition pattern). In this paper, case-based reasoning (CBR) approach is presented to help solve human diagnosis problem using not only the domain features but also the extracted features of signals captured using a computer-linked automotive scope meter. CBR expert system has the advantage that it provides user with multiple possible diagnoses, instead of a single most probable diagnosis provided by traditional network-based classifiers such as multi-layer perceptions (MLP) and support vector machines (SVM). In addition, CBR overcomes the problem of incremental and decremental knowledge update as required by both MLP and SVM. Although CBR is effective, its application for high dimensional domains is inefficient because every instance in a case library must be compared during reasoning. To overcome this inefficiency, a combination of preprocessing methods, such as wavelet packet transforms (WPT), kernel principal component analysis (KPCA) and kernel K-means (KKM) is proposed. Considering the ignition signals captured by a scope meter are very similar, WPT is used for feature extraction so that the ignition signals can be compared with the extracted features. However, there exist many redundant points in the extracted features, which may degrade the diagnosis performance. Therefore, KPCA is employed to perform a dimension reduction. In addition, the number of cases in a case library can be controlled through clustering; KKM is adopted for this purpose. In this paper, several diagnosis methods are also used for comparison including MLP, SVM and CBR. Experimental results showed that CBR using WPT and KKM generated the highest accuracy and fitted better the requirements of the expert system. [Copyright &y& Elsevier]

Urinary tract infection (UTI) is among the most common bacterial infections and poses a significant healthcare burden. The standard culture-based diagnosis of UTI has a typical delay of two to three days. In the absence of definitive microbiological diagnosis at the point of care, physicians frequently initiate empirical broad-spectrum antibiotic treatment, and this has contributed to the emergence of resistant pathogens. Biosensors are emerging as a powerful diagnostic platform for infectious diseases. Paralleling how blood glucose sensors revolutionized the management of diabetes, and how pregnancy tests are now conducted in the home, biosensors are poised to improve UTI diagnosis significantly. Biosensors are amenable to integration with microfluidic technology for point-of-care (POC) applications. This review focuses on promising biosensor technology for UTI diagnosis, including pathogen identification and antimicrobial susceptibility testing, and hurdles to be surpassed in the translation of biosensor technology from bench to bedside. [ABSTRACT FROM AUTHOR]

Abstract: Cellular processes are regulated by various mechanical and physical factors in their local microenvironment such as geometric confinements, cell–substrate interactions, and cell–cell contact. Systematic elucidation of these regulatory mechanisms is crucial for fundamental understanding of cell biology and for rational design of biomedical devices and regenerative medicine. Here, we report a generally applicable plasma lithography technique, which performs selective surface functionalization on large substrate areas, for achieving long-term, stable confinements with length scales from 100 nm to 1 cm toward the investigation of cell–microenvironment interactions. In particular, we applied plasma lithography for cellular confinement of neuroblastomas, myoblasts, endothelial cells, and mammary gland epithelial cells, and examined the motion of mouse embryonic fibroblasts in directionality-confined environments for studying the effect of confinements on migratory behavior. In conjunction with live cell imaging, the distance traveled, velocity, and angular motion of individual cells and collective cell migration behaviors were measured in confined environments with dimensions comparable to a cell. A critical length scale that a cell could conceivably occupy and migrate to was also identified by investigating the behaviors of cells using confined environments with subcellular length scales. [ABSTRACT FROM AUTHOR]

Abstract: The automotive engine performance is greatly affected by the calibration of its electronic control unit (ECU). The method for ECU calibration is traditionally done by trial-and-error. This traditional method consumes a large amount of time and money. To resolve this problem, case-based reasoning (CBR) is employed, so that an existing and effective ECU setup can be adapted to fit another similar class of engines. The adaptation procedure is done through a more sophisticated step called case-based adaptation (CBA) (). CBA is an effective knowledge management tool, which can interactively learn the expert adaptation knowledge. The paper briefly reviews the methodologies of CBR and CBA. Then the application to ECU calibration is described via a case study. With CBR and CBA, the efficiency of calibrating an ECU can be enhanced. A prototype system has also been developed to verify the usefulness of CBR in ECU calibration. [Copyright &y& Elsevier]

Abstract: Automotive engine power and torque are significantly affected with effective tune-up. Current practice of engine tune-up relies on the experience of the automotive engineer. The engine tune-up is usually done by trial-and-error method, and then the vehicle engine is run on the dynamometer to show the actual engine output power and torque. Obviously, the current practice costs a large amount of time and money, and may even fail to tune up the engine optimally because a formal power and torque model of the engine has not been determined yet. With an emerging technique, least squares support vector machines (LS-SVM), the approximated power and torque model of a vehicle engine can be determined by training the sample data acquired from the dynamometer. The number of dynamometer tests for an engine tune-up can therefore be reduced because the estimated engine power and torque functions can replace the dynamometer tests to a certain extent. Besides, Bayesian framework is also applied to infer the hyperparameters used in LS-SVM so as to eliminate the work of cross-validation, and this leads to a significant reduction in training time. In this paper, the construction, validation and accuracy of the functions are discussed. The study shows that the predicted results using the estimated model from LS-SVM are good agreement with the actual test results. To illustrate the significance of the LS-SVM methodology, the results are also compared with that regressed using a multilayer feed forward neural networks. [Copyright &y& Elsevier]

We have studied the behavior of failure in lifetime acceleration test of TMR prototype with performance meeting 100 Gb/in2 recording. The failure mode is identified to be same as extrinsic breakdown of the AlOx barrier, while failure due to magnetic change is not observed. The extrinsic breakdown is further found to be the increase in pinhole conduction in the barrier, involving thermal energy from ambient and read current. Results also suggest the existence of a critical voltage below which pinhole is not enlarged. Furthermore, we will discuss our hypothesis in the formation of pinholes and the role of charge traps in the barrier. Finally, we will discuss a method for screening out heads with relatively short lifetime, which is feasible for mass production. The screening allows a guarantee of lifetime well enough for drive application. [ABSTRACT FROM AUTHOR]

Precise measurement of the mechanical properties of a cell provides useful information about its structural organization and physiological state. It is interesting to understand the effect of individual components on the mechanical properties of the entire cell. In this study, we investigate the influence of the cytoskeletal actin on the viscoelastic properties of a cell. Actin-specific agents, including latrunculin A and jasplakinolide, are used to alter the organization of the cytoskeletal actin. Brassica oleracea protoplasts are treated with the drugs and deformed under an external electric potential. The relaxation processes of single protoplasts after electrodeformation are measured. The data are analyzed by a model-independent spectrum recovery algorithm. Two distinct characteristic time constants are obtained from the relaxation spectra. Treatment with latrunculin A increases both of the relaxation time constants. The longest relaxation times for control, latrunculin A treated, and jasplakinolide treated cells are determined to be 0.28, 1.0, and 0.21 s, respectively. [Copyright &y& Elsevier]

The literature reveals that fossil fuels will continue to be the main energy source for transportation fleets up to 2050, despite their non-renewability and the emissions of pollutants resulting from their use. Until the full adoption of non-fossil and zero-emission vehicles (e.g., electric vehicles), the application of renewable liquid fuels could be the best choice due to the latter's positive effects such as reduced consumption of fossil fuels and reduced emissions of pollutants. Alcohols, among others, have been widely tested as alternative fuels in diesel engines, however, there is no comprehensive information about their impacts on particulate matter (PM) which has a direct influence on human health, the environment, and emission catalyst's efficiency. This review comprehensively explores the impact of lower/higher alcohols, from methanol to decanol, in dual-fuel mode on the PM physicochemical properties emitted from diesel engines under different alcohol ratios and operating conditions. It is observed that alcohols change the PM physical properties by reducing primary particle size/number, radius of gyration, fractal dimension, and fringe length and increasing fringe separation distance and tortuosity compared to those of diesel PM. Regarding the chemical properties, alcohols reduce polycyclic aromatic hydrocarbons, benzo[a]pyrene equivalent, organic carbon (OC), elemental carbon (EC), ions, and soot ignition temperature and increase OC/EC ratio and soot oxidation reactivity. Thus, each 10% of alcohol, by volume, has the potential to reduce PM mass, number, and size by about 17, 20, and 10%, while lower alcohols and blended mode have more impact than higher alcohols and fumigation mode, respectively. [Display omitted] • Impact of alcohols on particulate matter (PM) properties from CI engines are reviewed. • PM structure and chemical properties have strong effect on PM mass, number, and size. • Alcohol fuels can significantly change the physicochemical properties of diesel PM. • Lower alcohols have more impact than higher alcohols on PM properties. • Alcohols in blended format have more impact than fumigated format on PM reduction. [ABSTRACT FROM AUTHOR]

This paper presents a novel observer-based gain-scheduling path following control algorithm for autonomous electric vehicles subject to time delay. Firstly, the lateral dynamic model of the autonomous electric vehicle is constructed by a polytope with four vertices, in which the issues of the time-varying longitudinal velocity and nonlinear tyre dynamics are accurately described. Secondly, taking the time delay encountered in the process of signal transmission into consideration, the observer-based path following controller is proposed by using easily measured vehicle states. In the algorithm, the observer and controller gains are gain scheduled according to the actual longitudinal velocity. Thirdly, based on Lyapunov stability theory, an appropriate Lyapunov–Krasovskii functional is constructed to derive sufficient conditions of the controller, which is effective to ensure the asymptotical stability of the closed-loop path following error system with a guaranteed H ∞ performance. Specially, for ease of computation, the sufficient conditions of controller design are developed in terms of a set of linear matrix inequalities. Finally, numerical simulations are implemented to illustrate the efficiency and superiority of the proposed method in comparison with the existing method. [ABSTRACT FROM AUTHOR]