Multi-time-scale input approaches for hourly-scale rainfall–runoff modeling based on recurrent neural networks

This study proposes two effective approaches to reduce the required computational time of the training process for time-series modeling through a recurrent neural network (RNN) using multi-time-scale time-series data as input. One approach provides coarse and fine temporal resolutions of the input time-series data to RNN in parallel. The other concatenates the coarse and fine temporal resolutions of the input time-series data over time before considering them as the input to RNN. In both approaches, first, the finer temporal resolution data are utilized to learn the fine temporal scale behavior of the target data. Then, coarser temporal resolution data are expected to capture long-duration dependencies between the input and target variables. The proposed approaches were implemented for hourly rainfall–runoff modeling at a snow-dominated watershed by employing a long short-term memory network, which is a type of RNN. Subsequently, the daily and hourly meteorological data were utilized as the input, and hourly flow discharge was considered as the target data. The results confirm that both of the proposed approaches can reduce the required computational time for the training of RNN significantly. Lastly, one of the proposed approaches improves the estimation accuracy considerably in addition to computational efficiency.

Multi-dimensional Taylor network adaptive predictive control for single-input single-output nonlinear systems with input time-delay

In this study, an adaptive predictive control approach based on the multi-dimensional Taylor network (MTN) is proposed for the real-time tracking control of single-input single-output nonlinear systems with input time-delay. Two MTNs are used to implement the accurate tracking control. First, to compensate for the influence of time-delay, MTN is taken as a predictor and the damped recursive least squares algorithm is used as its online learning algorithm. Second, a feed-forward MTN controller is developed on the basis of the proportional–integral–derivative controller, and the closed-loop errors between the reference input and the system output are directly chosen to be the MTN controller’s inputs. The back propagation algorithm is introduced for its learning which can update its weights online at stable learning rate by the errors caused by the system’s uncertain factors. Convergence and stability analysis are given to guarantee the performance of our proposed approach. Finally, two examples are given to verify the effectiveness of the proposed approach.

Observer-Based Coordinated Control for Blended Braking System with Actuator Delay

The coordinated control of a blended braking system is always a difficult task. In particular, blended braking control becomes more challenging when the braking actuator has an input time-delay and some states of the braking system cannot be measured. In order to improve the tracking performance, a coordinated control system was designed based on the input time-delay and state observation for a blended braking system comprising a motor braking system and friction braking system. The coordinated control consists of three parts: Sliding mode control, a multi-input single-output observer, and time-delay estimation-based Smith Predictor control. The sliding mode control is used to calculate the total command braking torque according to the desired braking performance and vehicle states. The multi-input single-output observer is used to simultaneously estimate the input time-delay and output braking torque of the friction braking system. With time-delay estimation-based Smith Predictor control, the friction braking system is able to effectively track the command braking torque of the friction braking system. The tracking of command braking torque is realized through the coordinated control of the motor braking system and friction braking system. In order to validate the effectiveness of the proposed approach, numerical simulations on a quarter-vehicle braking model were performed.

Uncertain Time Series Classification

Time series analysis has gained a lot of interest during the last decade with diverse applications in a large range of domains such as medicine, physic, and industry. The field of time series classification has been particularly active recently with the development of more and more efficient methods. However, the existing methods assume that the input time series is free of uncertainty. However, there are applications in which uncertainty is so important that it can not be neglected. This project aims to build efficient, robust, and interpretable classification methods for uncertain time series.

Observer-Based Leader-Following Consensus of General Linear Multiagent Systems Based on Novel Event Trigger Mechanism with Input Time Delay under Directed Graphs

This paper considers the tracking and containment consensus for the general linear systems with input time delays under directed communication networks. The distributed observer-based algorithm on the basis of event-triggering mechanism will be designed by using only neighboring agents information. In this way, we can save network resource effectively. The event-based protocol with input time delays will be proposed for the leader-follower systems. Appropriate feedback gain matrices and trigger parameters can be designed by using Lyapunov stability theory. Based on the designed control algorithm, if the feedback gain matrices and the event trigger are designed appropriately, the leader-follower general linear system can eventually reach tracking and containment consensus. Then, two simulation results are provided to demonstrate the practicability of the theoretical analysis.