• Nuclear Engineering and Technology
• /
• v.54 no.9
• /
• pp.3283-3292
• /
• 2022

Based on the Deep Q-Network(DQN) algorithm of reinforcement learning, an active fault-tolerance method with incremental action is proposed for the control system with sensor faults of the once-through steam generator(OTSG). In this paper, we first establish the OTSG model as the interaction environment for the agent of reinforcement learning. The reinforcement learning agent chooses an action according to the system state obtained by the pressure sensor, the incremental action can gradually approach the optimal strategy for the current fault, and then the agent updates the network by different rewards obtained in the interaction process. In this way, we can transform the active fault tolerant control process of the OTSG to the reinforcement learning agent's decision-making process. The comparison experiments compared with the traditional reinforcement learning algorithm(RL) with fixed strategies show that the active fault-tolerant controller designed in this paper can accurately and rapidly control under sensor faults so that the pressure of the OTSG can be stabilized near the set-point value, and the OTSG can run normally and stably.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.620-626
• /
• 2004

For general nonlinear processes, it is difficult to control with a linear model-based control method and nonlinear controls are considered. Among the numerous approaches suggested, the most rigorous approach is to use dynamic optimization. Many general engineering problems like control, scheduling, planning etc. are expressed by functional optimization problem and most of them can be changed into dynamic programming (DP) problems. However the DP problems are used in just few cases because as the size of the problem grows, the dynamic programming approach is suffered from the burden of calculation which is called as 'curse of dimensionality'. In order to avoid this problem, the Neuro-Dynamic Programming (NDP) approach is proposed by Bertsekas and Tsitsiklis (1996). To get the solution of seriously nonlinear process control, the interest in NDP approach is enlarged and NDP algorithm is applied to diverse areas such as retailing, finance, inventory management, communication networks, etc. and it has been extended to chemical engineering parts. In the NDP approach, we select the optimal control input policy to minimize the value of cost which is calculated by the sum of current stage cost and future stages cost starting from the next state. The cost value is related with a weight square sum of error and input movement. During the calculation of optimal input policy, if the approximate cost function by using simulation data is utilized with Bellman iteration, the burden of calculation can be relieved and the curse of dimensionality problem of DP can be overcome. It is very important issue how to construct the cost-to-go function which has a good approximate performance. The neural network is one of the eager learning methods and it works as a global approximator to cost-to-go function. In this algorithm, the training of neural network is important and difficult part, and it gives significant effect on the performance of control. To avoid the difficulty in neural network training, the lazy learning method like k-nearest neighbor method can be exploited. The training is unnecessary for this method but requires more computation time and greater data storage. The pH neutralization process has long been taken as a representative benchmark problem of nonlin ar chemical process control due to its nonlinearity and time-varying nature. In this study, the NDP algorithm was applied to pH neutralization process. At first, the pH neutralization process control to use NDP algorithm was performed through simulations with various approximators. The global and local approximators are used for NDP calculation. After that, the verification of NDP in real system was made by pH neutralization experiment. The control results by NDP algorithm was compared with those by the PI controller which is traditionally used, in both simulations and experiments. From the comparison of results, the control by NDP algorithm showed faster and better control performance than PI controller. In addition to that, the control by NDP algorithm showed the good results when it applied to the cases with disturbances and multiple set point changes.

• Applied Chemistry for Engineering
• /
• v.16 no.2
• /
• pp.217-225
• /
• 2005

Because of the limitation of controllable operation variables for the wastewater treatment process with variable hydrodynamic flow patterns, it may preclude the use of this type of nutrient removal activated sludge process. As the operation variables, only temperature and dissolved oxygen (DO) have been used to operate the process. This study made an effort to improve treatment efficiency and operability of the process by the following methodologies: 1) process and operation data analysis using process simulation, 2) determination of optimal control logic or algorithm using a pilot-scaled experimental apparatus and its operations, and 3) application of experimental and simulation results to find the optimal process operation modes. In this study, it was found that the optimal operation mode named 'save mode' in the basis of process variables, such as the ammonia-nitrogen concentration of inlet flow, temperature and flow rate, can reduce the operation cost comparing with the present normal operation mode. And the stable conditions in nitrification were also shown by the proportional control of DO with the inlet air flow rate of blower and the mixing rate of mechanical aeration.

• International Journal of Precision Engineering and Manufacturing
• /
• v.9 no.1
• /
• pp.3-6
• /
• 2008

Electrical discharge machining (EDM) is one of the most widespread nonconventional machining processes. Recently, a low-power micro-EDM process was introduced using a cylindrical electrode. Since its development, micro-EDM has been applied effectively to micromachining, and because the device setup for this process is simple, it is suitable for a microfactory that minimizes machines to fabricate small products economically in one system. In the EDM process, however, the electrode is also removed along with the workpiece. Therefore, the electrode shape and length vary as machining progresses. In this paper, a control method using a high speed realtime voltage measurement is proposed to regulate the rate and amount of material removed. The proposed method is based on the assumption that the volume of the workpiece removed in a single discharge pulses is nearly constant. The discharge pulses are monitored and controlled to regulate the amount of material removed. For this purpose, we developed an algorithm and apparatus for counting the number of discharge pulses. Electrode wear compensation using pulse number information was applied to EDM milling in a microfactory, in which a slight tilt of the workpiece may occur. The proposed control method improves the machining quality and efficiency by eliminating the inaccuracies caused by electrode wear and workpiece tilt.

• Journal of the Korean Chemical Society
• /
• v.54 no.2
• /
• pp.181-182
• /
• 2010

• Journal of Mechanical Science and Technology
• /
• v.20 no.10
• /
• pp.1680-1690
• /
• 2006

As a promising and novel manufacturing technology, laser aided direct metal deposition (DMD) process produces near-net-shape functional metal parts directly from 3-D CAD models by repeating laser cladding layer by layer. The key of the build-up mechanism is the effective control of powder delivery and laser power to be irradiated into the melt-pool. A feedback control system using two sets of optical height sensors is designed for monitoring the melt-pool and real-time control of deposition dimension. With the feedback height control system, the dimensions of part can be controlled within designed tolerance maintaining real time control of each layer thickness. Clad nugget shapes reveal that the feedback control can affect the nugget size and morphology of microstructure. The pore/void level can be controlled by utilizing pulsed-mode laser and proper design of deposition tool-path. With the present configuration of the control system, it is believed that more innovation of the DMD process is possible to the deposition of layers in 3-D slice.

• Structural Engineering and Mechanics
• /
• v.82 no.4
• /
• pp.445-458
• /
• 2022

Some of the control systems used in engineering structures that use sensors and decision systems have some time delay reducing efficiency of the control system or even might make it unstable. In this research, in addition to considering the effect of the time delay in vibration control process, predictive control is used to compensate the time delay. A semi-active vibration control approach with the help of magneto-rheological dampers is implemented. In addition to using fuzzy inference system to determine the appropriate control voltage for MR damper, structural behavior prediction system and specifying future responses are also used such that the time delays occurring within control process are overcome. For this purpose, determination of prediction horizon is conducted for one, five, and ten steps ahead for single degree of freedom structures with periods ranging from 0.1 to 4 seconds, subjected to twenty earthquake excitations. The amount of time delay applied to the control system is 0.1 seconds. The obtained results indicate that for 0.1 second time delay, average prediction error values compared to the case without time delay is 3.47 percent. Having 0.1 second time delay in a semi-active control system reduces its efficiency by 11.46 percent; while after providing the control system with structure behavior prediction, the difference in the results for the control system without time delay is just 1.35 percent on average; indicating a 10.11 percent performance improvement for the control system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.268-271
• /
• 2004

This paper describes the development of a fuzzy logic control based on PID controller to improve the performances of the control system using conventional PID controller for the cascade process control systems. The structure of the proposed control system consists of two fuzzy-based PID controllers. One is used to eliminate the input disturbances of the inner loop and the other is used to regulate output response of the outer loop. The fuzzy PID design is derived from the linear-time continuous function of the conventional PID controller. The performance of the proposed controller is verified by MATLAB/SIMULINK simulation. Results of simulation studies demonstrates the outstanding of the control system using fuzzy-based PID controller in terms of reduced overshoot and fast response compared with the conventional PID controller.

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2445-2447
• /
• 2002

In this paper, CAN-based feedback control system is proposed for the pressurization system of korean high-speed train. The control performance of the system is evaluated. According to the requirement of the pressurization system A process model considering network delay and an adaptive PID control method based on the process model are proposed here. And it is shown that the proposed adaptive PID control method considering the network delay has on adequate feature compared to some other existing methods consequently it can be considered to be applied the pressurization system of korean high-speed train.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.11 no.18
• /
• pp.71-80
• /
• 1988

Process capability implies the qualitative capability of a process, and it is necessary to specify the process capability by quantification and to evaluate the level with the specified standardizaion. But the process capability index is currently used to evaluate the performance of quality control activity. without considering the characteristics of process structure or the economy of management. Here the researcher would like to redefine process capability and emphasize its index may be used as the measure of managerial assessment and the objective of process quality control in full consideration of the economic aspects of process characteristics. Too little or too much process capability causes a loss of or excess. The proper economic level of process capability varies to each process. The procedure of taking the optimum process capability index is derived from the expected profit function, whereas each method is studied in cases of normal process with one-sided specification and two-sided specification. In addition, the process capability index is presented as a method of quality assurance. And an example is exhibited on wrapping process of 'A' company. The results of this study are summarized at follows. First, though the norminalization of the process capability index is possible by the existing methods, the optimum process capability index can vary to the situation of each process. So, the optimum process capability index which is suggested in this dissertation should be used as the standard to assess process capability. Second, the process capability index can take its effect not just in indicating quality control or managerial records but also in the management of high qualify assurance.