The waterjet propulsion device, as an efficient power propulsion method, has been widely used in various types of ships. However, due to its complex structure, harsh working environment, and frequent failures caused b...
详细信息
In this paper, a parameter self-learning multivariable active disturbance rejection control (ADRC) algorithm is proposed for the Diesel engine air system equipped with a variable exhaust gas turbocharger (VGT), exhaus...
详细信息
ISBN:
(纸本)9798350321050
In this paper, a parameter self-learning multivariable active disturbance rejection control (ADRC) algorithm is proposed for the Diesel engine air system equipped with a variable exhaust gas turbocharger (VGT), exhaust gas recirculation (EGR), and intake throttle valve (TVA). Firstly, based on the principle of simplified Diesel engine operation, a three-in-three-out linear variable parameter air system prediction model is established, with the model deviation equivalent to the total disturbance. A multivariable extended state observer is employed for active observation to enhance the model's adaptability. Secondly, to address the issues of strong noise and variable signal-to-noise ratio of the air signal, the gain matrix of the extended state observer is dynamically adjusted to achieve a real-time trade-off between observation speed and disturbance fluctuation amplitude. Finally, in order to improve tracking accuracy while compensating for the total disturbance, extremum seeking is utilized to optimize the control input gain online and enhance the algorithm's adaptability to nonlinearities. The algorithm is verified on a Diesel engine stand, and compared with a PID controller with global parameter optimization, it achieves the same response speed while reducing the overshoot of intake manifold pressure and EGR rate tracking by 24.9% and 10.3%, respectively. The proposed algorithm's parameters can be automatically adjusted with the change of working conditions, avoiding the need for sectional calibration.
This paper proposes a collaborative iterative learningcontrol scheme with optimal leader path planning strategy. Due to the demonds on repetitive tasks and static references under traditional ILC framework, it cannot...
详细信息
In the era of IoT, efficient real-time anomaly detection is critical for preventing industrial incidents and ensuring operational integrity. This paper introduces ATC-AFAT (Adaptive Transformer-CNN Architecture Fusing...
详细信息
Path-tracking control is an integral part of motion planning in autonomous vehicles, where a control system on the vehicle will provide acceleration and steering angle commands to ensure accurate tracking of its longi...
详细信息
ISBN:
(纸本)9798350399462
Path-tracking control is an integral part of motion planning in autonomous vehicles, where a control system on the vehicle will provide acceleration and steering angle commands to ensure accurate tracking of its longitudinal and lateral movements in reference to a pre-defined trajectory. In this paper, a scenario and machine learning-based data-drivencontrol approach is proposed for a path-tracking controller. Firstly, a deep reinforcement learning (DRL) model is developed to facilitate the control of the vehicle's longitudinal speed. A deep deterministic policy gradient algorithm is employed to train the reinforcement learning model. The main objective of this model is to maintain a safe distance from a lead vehicle (if present) or track a velocity set by the driver. Secondly, a lateral steering controller is developed to control the steering angle of the vehicle with the main goal of following a reference trajectory. Finally, the longitudinal and lateral control models are coupled to obtain a complete path-tracking controller at a wide range of vehicle speeds. The state-of-the-art model-based path-tracking controller is also built (using the model predictive control and Stanley control) to evaluate the performance of the proposed model. The results showed that the performance of the proposed data-driven DRL control model is effective compared with model-based control approaches (in terms of the velocity error, lateral yaw angle error, and lateral distance error).
In this work, a data-driven virtual reference setting learning (DDVRSL) method is proposed to enhance the proportional-derivative (PD) feedback controller of the repetitive nonlinear system. First, an ideal nonlinear ...
详细信息
In this work, a data-driven virtual reference setting learning (DDVRSL) method is proposed to enhance the proportional-derivative (PD) feedback controller of the repetitive nonlinear system. First, an ideal nonlinear virtual reference setting learning law is presented in the outer loop of the control system to tune the reference setting. Such an ideal nonlinear learning law exists theoretically and is transferred to a linear parametric DDVRSL via iterative dynamic linearization (IDL). Next, an iterative adaptation law is proposed for the estimation of the parameters in the DDVRSL law subject to the nonlinear system which is also transferred into a linear form by using the IDL method. The iterative adaptation algorithm tunes the learning gains of DDVRSL law using input and output measurements, therefore improving the robust ability against uncertainties. The proposed DDVRSL-based PD control method does not require any exact mechanistic model knowledge. The convergence is proved via the contraction mapping principle, mathematical induction, and time-weighted norm. Further, the theoretical results are verified through simulations.
In order to optimize complex industrial processes, an accurate model is essential. The mainstream approach for complex industrial modeling is data-driven soft sensors. However, the accuracy of the established models i...
详细信息
ISBN:
(纸本)9798350321050
In order to optimize complex industrial processes, an accurate model is essential. The mainstream approach for complex industrial modeling is data-driven soft sensors. However, the accuracy of the established models is often low due to an insufficient amount of effective data, so the method of generating virtual samples has been proposed to achieve data augmentation, but the previous virtual sample generation methods have ignored the correlation between samples. To solve this problem, an effective virtual sample generation method based on Gibbs Sampling algorithm (GS-VSG) is proposed in this paper. In the proposed method, virtual input samples are first generated using the prior knowledge of the original data through the Gibbs Sampling method. Next, a generalized regression neural network (GRNN) model is constructed from the raw data, which is used to predict the output values of the virtual samples. Finally, the input and output parts of the virtual samples are combined to create a virtual sample set, which completes the extension of the original data set. To demonstrate the feasibility of the proposed GS-VSG method, numerical example and real industrial process dataset are used for simulation experiments. The results show that GS-VSG generated samples can improve the model accuracy and is a good technique for virtual sample generation.
A start-end frame pair and a motion pattern-based motion synthesis scheme can provide more control to the synthesis process and produce content-various motion sequences. However, the data preparation for the motion tr...
详细信息
A start-end frame pair and a motion pattern-based motion synthesis scheme can provide more control to the synthesis process and produce content-various motion sequences. However, the data preparation for the motion training is intractable, and concatenating feature spaces of the start-end frame pair and the motion pattern lacks theoretical rationality in previous works. In this article, we propose a deep learning framework that completes automatic data preparation and learns the nonlinear mapping from start-end frame pairs to motion patterns. The proposed model consists of three modules: action detection, motion extraction, and motion synthesis networks. The action detection network extends the deep subspace learning framework to a supervised version, i.e., uses the local self-expression (LSE) of the motion data to supervise feature learning and complement the classification error. A long short-term memory (LSTM)-based network is used to efficiently extract the motion patterns to address the speed deficiency reflected in the previous optimization-based method. A motion synthesis network consists of a group of LSTM-based blocks, where each of them is to learn the nonlinear relation between the start-end frame pairs and the motion patterns of a certain joint. The superior performances in action detection accuracy, motion pattern extraction efficiency, and motion synthesis quality show the effectiveness of each module in the proposed framework.
The application of shipboard microgrids (SMGs) makes it possible to effectively use renewable new energy on the shipboard platform. As renewable energy sources are connected to SMGs in the form of distributed generato...
详细信息
ISBN:
(纸本)9798350321050
The application of shipboard microgrids (SMGs) makes it possible to effectively use renewable new energy on the shipboard platform. As renewable energy sources are connected to SMGs in the form of distributed generators (DGs), the openness of the system increases and so does the risk of exposure to cyber attacks. In this paper, a resilient distributed secondary frequency control strategy for SMGs is constructed to resist false data injection (FDI) attacks. An attacker can tamper with the information in the communication links between the DGs of a SMG to prevent the DGs from outputting stable power, thereby causing oscillations in the entire SMG. To increase resilience to FDI attacks, the proposed resilient control strategy introduces a control network layer interconnected with the original data transmission layer to form a hierarchical communication network. By setting the SMG parameters, the proposed strategy can well reduce the negative effects of FDI attacks on DGs and ensure the stable operation of SMGs. Finally, the simulation results verify the effectiveness of the strategy.
Wind turbine condition monitoring has been extensively studied to reduce maintenance costs. Although there exist a vast amount of literature on anomaly detection for wind turbine, anomaly root cause analysis has not b...
详细信息
ISBN:
(纸本)9798350321050
Wind turbine condition monitoring has been extensively studied to reduce maintenance costs. Although there exist a vast amount of literature on anomaly detection for wind turbine, anomaly root cause analysis has not been fully addressed so far. To cope with this problem, we propose a denoising autoencoder (DAE) based anomaly detector and performs anomaly root cause analysis using sparse estimation. For anomaly detection, deep denoising autoencoder is learned with normal history data, with enhanced robustness compared to the conventional autoencoder. The reconstruction error from the DAE is further evaluated by the exponentially weighted moving average control chart (EWMA) to reduce the false positive rate. After anomaly detection, root cause analysis performs sparse fault estimation, with the assumption that a small number of observed variables are affected under the abnormal condition. The fault estimates are then leveraged to identify the variables most relevant to the underlying anomaly root causes. Real cases on a public dataset demonstrate the effectiveness of the proposed method.
暂无评论