Regulating control of in-pipe intelligent isolation plugging tool based on adaptive dynamic programming

In-pipe intelligent isolation plugging tools (IPTs) are crucial in pipeline maintenance. During the plugging process, the flow field around the IPT changes drastically, resulting in vibration and instability of the plugging process. Therefore, three foldable spoilers were designed at the tail of the IPT to reduce the vibration of the IPT. First, a disturbing flow experiment of IPT with spoilers was designed. A mathematical model of the pneumatic spoiler control system was established to regulate the spoiler angles. Second, based on the experimental data, a Bi-LSTM (bidirectional long short-term memory) neural network predictor between the plugging states, the spoiler angles, and the pressure gradient was established. Then, an adaptive dynamic programming controller was designed to select the optimal control action for each plugging state, thereby reducing the pressure gradient. Finally, Python and Matlab/Simulink were used for simulation. The results showed that the controller could reduce the pressure gradient during the plugging process by an average of 25.94%, which alleviated the vibration of the IPT and achieved a smooth plugging operation.

Development of a relay-vector control system for a multi-phase semiconductor converter of electric energy

A system of relay-vector control of current in the circuit of a polyphase electric machine has been developed. For this, on the basis of the analysis of electromagnetic processes in a multiphase semiconductor converter of electrical energy, its discrete mathematical model was created, which takes into account the redistribution of electromagnetic energy by individual spatial harmonic components, depending on the number of phases. Using this mathematical model, a method for relay control of spatial harmonic components of the input current of the converter in the “tube” has been developed. The formation of polyharmonic currents in each of the phases, conjugated in shape and phase with the voltage supplying the converter at each control period, is carried out by means of the optimal voltage vector of the semiconductor switch. To select the optimal control action, the objective function of the minimum deviation of the projections of the base voltage vectors of the semiconductor switch for the j-th combination of the state of the keys from the calculated control action determined by the mathematical model is used. An objective function of this type allows one to take into account different values of the amplitudes of the base voltage vectors of the semiconductor switch in the transformed orthogonal coordinate systems. In this case, there is no need to predict changes in the instantaneous values of the input current for one or two periods ahead, which is ensured by a decrease in the number of iterations to determine the optimal control action. To check the developed provisions, a simulation model of a nine-phase semiconductor converter of electrical energy with a relay vector control system was created. The results of the study of the model confirmed the adequacy of the developed technical solutions, the use of which will ensure the most complete realization of the own advantages of a multiphase electric machine in order to generally improve the weight, size and energy indicators of the autonomous power supply system.

OPTIMIZATION OF RECTIFICATION PROCESS USING MOBILE CONTROL ACTION WITH ACCOUNT FOR CRITERION OF MAXIMIZING SEPARATION QUALITY

The use of mobile control action allows the improvement of technical-economical characteristics of the rectification process and allows for operation regimes that can’t be achieved with traditional control approaches. Mobility lies in the ability to choose the movement law of compound source and energy in the spatial region of apparatus. Mobile control over the rectification process can be realized by changing the column feed point. An optimal number of feed trays must be determined with consideration of cost and output performance, and also the quality of the target product. The work aimed to develop a method for calculating optimal control action, including mobile ones, on the rectification process with additional account for the criterion of maximizing quality of target product, and also, comparison of static column profiles that are optimal by different criteria. Mathematical modeling of the rectification column for separation of water-methanol mixture revealed that increasing quality requirements to target products decreases the number of the optimal feed tray. A method was described for process optimization by the normalized criterion that accounts for separation quality and power consumption. The method was used to determine optimal values of traditional (flows of heat into the column's cube and phlegm) and mobile (feed tray number) control actions that provide the best technical-economical parameters of the rectification column. A proof is presented for the existence and uniqueness of solutions for this optimization problem and the effectiveness of using mobile actions for different requirements to target. The optimal temperature profile of the culms was studied and their characteristic features that correspond to different specific and normalized optimization criteria were found

Hybrid Electric Vehicle Emissions Monitoring and Estimation using Artificial Neural Networks: Technical Note

Power is utilized as the prime fuel for hybrid and module electric vehicles in order to build the productivity of commercial vehicles. This paper forecasts the emission factors utilizing discrete Fourier transform, artificial neural networks and hybridization of back propagation algorithm. The DFT facilitates the extraction of the performance indicators which are otherwise called the features. The coefficients of the power spectrum denote the performance indicators. The ANN learns the pattern for emissions from HEVs using these performance indicators. This ANN based strategy offers an optimal control action to detect and reduce the exhaust gas emissions which are hazardous. These vehicles are provided with automated highway traffic Jam assist. Hence the forecast of these emissions offers increased efficiency of 90% to 100% thereby ensuring optimal operating condition for the hybrid vehicles.

Application and Evaluation of the Reinforcement Learning Approach to Eco-Driving at Intersections under Infrastructure-to-Vehicle Communications

Eco-driving behavior is able to improve vehicles’ fuel consumption efficiency and minimize exhaust emissions, especially with the presence of infrastructure-to-vehicle (I2V) communications for connected vehicles. Several techniques such as dynamic programming and neural networks have been proposed to study eco-driving behavior. However, most techniques need a complicated problem-solving process and cannot be applied to dynamic traffic conditions. Comparatively, reinforcement learning (RL) presents great potential for self-learning to take actions in a complicated environment to achieve the optimal mapping between traffic conditions and the corresponding optimal control action of a vehicle. In this paper, a vehicle was treated as an agent to select its maneuver, that is, acceleration, cruise speed, and deceleration, according to dynamic conditions while approaching a signalized intersection equipped with I2V communication. An improved cellular automation model was utilized as the simulation platform. Three parameters, including the distance between the vehicle and the intersection, signal status, and instant vehicle speeds, were selected to characterize real-time traffic state. The total CO2 emitted by the vehicle on the approach to the intersection serves as a measure of reward policy that informs the vehicle how good its operation was. The Q-learning algorithm was utilized to optimize vehicle driving behaviors for eco-driving. Vehicle exhaust emissions and traffic performance (travel time, stop duration, and stop rate) were evaluated in two cases: (1) an isolated intersection, and (2) a medium-scale realistic network. Simulation results showed that the eco-driving behavior obtained by RL can not only reduce emissions but also optimize traffic performance.

A Receding Horizon Switching Control Resilient to Communication Failures for Connected Vehicles

This paper focuses on networked control systems subject to network-induced constraints, namely transmission delays and packet dropping. The proposed framework is based on a switching control logic which selects the optimal control action in a finite set of strategies tailored to a specific scenario. The switching logic relies on a receding horizon optimization — which resembles model predictive control — and does not require any prior knowledge on the condition of the network. This strategy is tested on a platoon of connected vehicles engaged in cooperative adaptive cruise control which communicate over an imperfect DSRC network. The main objective consists in avoiding unsafe scenarios where the network is subject to the aforementioned failures; results show the proposed approach achieves the objective whereas a nominal controller would lead the platoon to crash.

Model Predictive Control System Design for Boiler Turbine Process

<p>MPC is a computer based technique that requires the process model to anticipate the future outputs of that process. An optimal control action is taken by MPC based on this prediction. The MPC is so popular since its control performance has been reported to be best among other conventional techniques to control the multivariable dynamical plants with various inputs and outputs constraints. In the present work the control of boiler turbine process with three manipulated variables namely fuel flow valve position, steam control valve position and feed water flow valve position and three controlled variables namely drum pressure, output power and drum water level deviation [8] has been attempted using MPC technique. Boiler turbine process is very complex and nonlinear multivariable process. A linearized model obtained using Taylor series expansion around operating point has been used.</p>

Synthesis of New Mechatronic Systems by Inverse Algorithm

nverse method algorithm for invention of mechatronic systems in vibrotechnics is used for robotic systems motion control synthesis. The main difference between this method and simple analysis method is that before synthesis of a real system optimal control task for abstract initial subsystem is solved. After calculations the optimal control law is found that allows to synthesise series of structural schemes for real systems on a basis of initial subsystem. It is shown that optimal control action corresponds to the case of boundary values of area limits. For realizing optimal control actions in general case a system of one degree of freedom needs feedback system with two adapters: one for measure displacement and second for measure velocity. It is shown that simple case exists of the control with only one adapter when motion changes directions. It means that control action is like negative dry friction and switch points are along zero velocity line.

Synthesis of Vibrator with Air or Water Flow Excitation

In the daily life and in using technologies people interact with continuous medium like air or water. In present article a motion of the vibrator with constant air or water flow excitation is observed. In the first part of the article a motion of the vibrator with constant air or water flow velocity excitation is investigated. The main idea is to find optimal control law for variation of additional area of vibrating object within certain limits. The criterion of optimization is the time required to move object from initial position to end position. For the solution of high-speed problem the maximum principle is used. It is shown that optimal control action is on boundaries of area limits. Examples of synthesis of real mechatronic systems are given.