Real-time Control Method Research Articles

Online Monitoring and Control of Butt-Welded Joint Penetration during GMAW

Butt welding is an important link to ensure welding quality, and the penetration state of the weld is the main criterion to achieve this. Online monitoring and control of the penetration state of welded joints is an important measure to ensure welding quality. The molten pool image is monitored by a visual sensor in the gas metal arc welding (GMAW) process, and the bottom molten pool width is predicted by the regression network model. Combined with the real-time control method, the welding current is changed to monitor and control the bottom weld width in real time. Butt-welding experiments with different groove angles verified that the proposed method could achieve satisfactory control accuracy and generalization ability. For butt-welding experiments with constant groove angles of 30° and 45°, the MAE of the controlled backside melt width to the target values was 0.2603 mm and 0.2620 mm. Therefore, it provides a feasible method for the online control of weld penetration.

Neural Network-Based Confinement Mode Prediction for Real-Time Disruption Avoidance

Reliable disruption avoidance techniques are critical for the development of safe and economically viable fusion reactors. This incipient need has driven the fusion community to spend substantial effort to develop machine learning (ML) models that aim to assist in this area. One area of concern is a sudden loss in global confinement associated with an unintended back-transition from H-mode confinement to L-mode confinement (“H–L back-transition”), which can sometimes lead to a disruption and increased risk of damage to a reactor-grade fusion device. A recent experiment on DIII-D demonstrated a real-time control method able to steer away from such unwanted back transitions. The present confinement mode of the plasma was inferred in real-time using a temporal convolutional neural network that outputs a continuous scalar estimate suitable for input to a closed-loop controller. This scalar estimate was then regulated to a value consistent with H-mode by adjusting power associated with the ratio of the plasma pressure to magnetic pressure ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\beta _{N}$ </tex-math></inline-formula> ). The model was trained on hundreds of thousands of discrete time steps of expert-labeled data of periods of H-mode and L-mode confinement, taken from hundreds of DIII-D tokamak discharges. This work presents these experimental results, including the method of collecting expert-labeled H- and L-mode confinement data, and the ML model performance and efficacy on the mode prediction task. In addition, the first application of this tool for H–L back-transition prevention is demonstrated in this experiment. Details are presented on the training of the neural network model, including concerns such as hyperparameter tuning and the network architecture. In addition, the methodology for embedding the neural network into the control system for real-time inference and closed-loop control is discussed.

A prior knowledge-embedded reinforcement learning method for real-time active power corrective control in complex power systems

With the increasing uncertainty and complexity of modern power grids, the real-time active power corrective control problem becomes intractable, bringing significant challenges to the stable operation of future power systems. To promote effective and efficient active power corrective control, a prior knowledge-embedded reinforcement learning method is proposed in this paper, to improve the performance of the deep reinforcement learning agent while maintaining the real-time control manner. The system-level feature is first established based on prior knowledge and cooperating with the equipment-level features, to provide a thorough description of the power network states. A global-local network structure is then constructed to integrate the two-level information accordingly by introducing the graph pooling method. Based on the multi-level representation of power system states, the Deep Q-learning from Demonstrations method is adopted to guide the deep reinforcement learning agent to learn from the expert policy along with the interactive improving process. Considering the infrequent corrective control actions in practice, the double-prioritized training mechanism combined with the λ-return is further developed to help the agent lay emphasis on learning from critical control experience. Simulation results demonstrate that the proposed method prevails over the conventional deep reinforcement learning methods in training efficiency and control effects, and has the potential to solve the complex active power corrective control problem in the future.

Real-time shimming with FID navigators.

To implement a method for real-time field control using rapid FID navigator (FIDnav) measurements and evaluate the efficacy of the proposed approach for mitigating dynamic field perturbations and improving -weighted image quality. FIDnavs were embedded in a gradient echo sequence and a subject-specific linear calibration model was generated on the scanner to facilitate rapid shim updates in response to measured FIDnav signals. To confirm the accuracy of FID-navigated field updates, phantom and volunteer scans were performed with online updates of the scanner B0 shim settings. To evaluate improvement in -weighted image quality with real-time shimming, 10 volunteers were scanned at 3T while performing deep-breathing and nose-touching tasks designed to modulate the B0 field. Quantitative image quality metrics were compared with and without FID-navigated field control. An additional volunteer was scanned at 7T to evaluate performance at ultra-high field. Applying measured FIDnav shim updates successfully compensated for applied global and linear field offsets in phantoms and across all volunteers. FID-navigated real-time shimming led to a substantial reduction in field fluctuations and a consequent improvement in -weighted image quality in volunteers performing deep-breathing and nose-touching tasks, with 7.57% ± 6.01% and 8.21% ± 10.90% improvement in peak SNR and structural similarity, respectively. FIDnavs facilitate rapid measurement and application of field coefficients for slice-wise B0 shimming. The proposed approach can successfully counteract spatiotemporal field perturbations and substantially improves -weighted image quality, which is important for a variety of clinical and research applications, particularly at ultra-high field.

Physics-Informed Evolutionary Strategy Based Control for Mitigating Delayed Voltage Recovery

In this work we propose a novel data-driven, real-time power system voltage control method based on the physics-informed guided meta evolutionary strategy (ES). The main objective is to quickly provide an adaptive control strategy to mitigate the fault-induced delayed voltage recovery (FIDVR) problem. Reinforcement learning methods have been developed for the same or similar challenging control problems, but they suffer from training inefficiency and lack of robustness for “corner or unseen” scenarios. On the other hand, extensive physical knowledge has been developed in power systems but little has been leveraged in learning-based approaches. To address these challenges, we introduce the trainable action mask technique for flexibly embedding physical knowledge into RL models to rule out unnecessary or unfavorable actions, and achieve notable improvements in sample efficiency, control performance and robustness. Furthermore, our method leverages past learning experience to derive surrogate gradient to guide and accelerate the exploration process in training. Case studies on the IEEE 300-bus system and comparisons with other state-of-the-art benchmark methods demonstrate effectiveness and advantages of our method.

A real-time combined quality control method for GNSS precise positioning in harsh environments

Global Navigation Satellite System (GNSS) precise positioning can be significantly affected by severe multipath effects and outliers in harsh environments, and highly relies on quality control strategies. Previous studies mainly focus on the posterior residuals to check and exclude the outliers in GNSS observations, limited work emphasizes the combined quality control method considering both the prior and posterior knowledge simultaneously. This paper proposed a real-time combined quality control method to process the multipath effects and outliers in harsh environments simultaneously. Specifically, in the prior stage, a modified multipath processing strategy is proposed for both phase and code observations, then a modified detection, identification, and adaptation (DIA) method considering the maximum times of data snooping is studied in the posterior stage. Two dedicated experiments in real harsh environments were carried out to evaluate the performance of the proposed combined quality control method. For the static experiment, the proposed method exhibits smaller positioning errors, the best positioning accuracy, and the highest availability in this study. Specifically, the proposed method exhibits an improved percentage of 55.4 %, 56.3 %, and 59.7 % for positioning accuracy compared to those without the quality control method in the E, N, and U directions, respectively. Besides, the proposed method can further improve the performance of ambiguity resolution with an improved percentage of 32.2 %. For the kinematic experiment, the three-dimensional positioning accuracy of the proposed method is 0.577 m, which exhibits a 40.0 % improvement compared to those without the quality control method. Also, the proposed method exhibits better performance under relatively strong multipath effects. In this sense, the proposed real-time combined quality control method is highly appreciated in terms of positioning availability, accuracy, and ambiguity resolution for GNSS precise positioning, especially in harsh environments.

The Investigation of Novel Dynamic Packing Technology for Injection Molded Part Quality Control and Its Production Stability by Using Real-Time PVT Control Method

Injection molding is an effective mass production process for plastic, partly due to a number of advantages such as complex shape moldability, material selectivity, and a rapid process cycle. However, highly labor-based conventional production restrains the development of the industry. Experience-driven molding setups are used to trial the mold process, and also for quality checking the molded part for mass production. There is no effective solution for maintaining the production stability and defect-free adjustment. This study aimed to establish scientific packing pressure setup technology to optimize the molded part quality and the stability of consecutive production. The dynamic packing pressure setup technology for molded part quality and the process stability were investigated. This not only achieves the optimization of the packing pressure setup, but the stabilization of quality in mass production. Four major qualities were discussed in this study including tensile strength, regional deviation on shrinkage, total shrinkage, and warpage. The qualities improved by up to 3.9%, 92.9%, 41.9%, and 9.2%, respectively. A series of pilot runs of 300 cycles for two packing pressure control methods were tested to investigate the stability of the qualities. Dynamic packing pressure control improved the weight replication by 54%, reduced total shrinkage by 23%, and improved the warpage by 12%.

Research and verification on aero-propulsion system acceleration control under supersonic state

Under supersonic acceleration flight, the traditional passive control method brings about acceleration performance deterioration, due to the bad matching between inlet and engine. Accordingly, a real-time optimization control method of the integrated propulsion system is proposed. In the article, the effect of a supersonic inlet on propulsion system performance is analyzed, and an onboard model of the integrated propulsion system is built to calculate the installed parameters. An improved trust region algorithm is adopted to optimize the inlet ramp angle in real time. Besides, digital simulation and hardware-in-the-loop simulation are carried out. The digital simulation result shows that compared with conventional inlet passive control, the acceleration time of the propulsion system is reduced by 8.59%. The result of the hardware-in-the-loop simulation indicates that the proposed method has high real-time performance simultaneously, which proves the engineering application value.

A Comprehensive Robust Techno-Economic Analysis and Sizing Tool for the Small-Scale PV and BESS

Battery energy storage systems (BESS) are receiving great attention due to their ability in maximizing self-consumption and energy arbitrage. However, in many countries, BESS profitability is still questionable without subsidy due to their high capital costs. This paper proposes an open-source generic tool to provide comprehensive techno-economic analysis on the small-scale PV/BESS. The proposed tool utilizes real-time BESS control method that has been validated using real experimental measurements in addition to integrating a reliable degradation model to determine the loss in savings due to capacity degradation. The profitability is investigated by conducting different cost-benefit analyses for the PV and BESS. An optimization layer is introduced to find the optimal PV/BESS sizes that boost investment profitability by maximizing the net present value. A detailed case study is presented for a household in the U.K. under three different tariff structures that consider practical parameters and assumptions. Furthermore, sensitivity analyses are performed to evaluate the impact of the cost-benefit analysis assumptions on the PV/BESS sizing and profitability. Finally, the BESS investment viability is investigated over the next few years for different investment expectations to answer the question of when the BESS should be installed to be a viable economic-attractive option in the U.K.

A TM-Based Adaptive Learning Data-Model for Trajectory Tracking and Real-Time Control of a Class of Nonlinear Systems

In this paper, a Takenaka-Malmquist (TM) basis function based equivalent data-model is established by an adaptive rational decomposition for the finite-time interval trajectory tracking control and real-time control of a class of nonlinear systems in the frequency domain. This data model can adaptively learn and match the control process of nonlinear systems. As a result, the proposed trajectory tracking as well as real-time control method can reflect the feature of adaptive learning in order-by-order decomposition, and the feasibility of the proposed method is guaranteed by the convergence of adaptive decomposition by TM basis function under the maximum selection principle (MSP) in Hardy space H^2(\mathbbD). Compared with the traditional model-free control method, this data learning model which matches the control process has obvious advantages in the system model expression and control accuracy. Simulation results at the end of this paper show the effectiveness of the proposed method.

Metabolism-based ventilation monitoring and control method for COVID-19 risk mitigation in gymnasiums and alike places.

Gymnasiums, fitness rooms and alike places offer exercise services to citizens, which play positive roles in promoting health and enhancing human immunity. Due to the high metabolic rates during exercises, supplying sufficient ventilation in these places is essential and extremely important especially given the risk of infectious respiratory diseases like COVID-19. Traditional ventilation control methods rely on a single CO2 sensor (often placed at return air duct), which is often difficult to reflect the human metabolic rates accurately, and thus can hardly control the infection risk instantly. Thus, to ensure a safe and healthy environment in places with high metabolism, a real-time metabolism-based ventilation control method is proposed. A computer vision algorithm is developed to monitor human activities (regarding human motion amplitude and speed) and an artificial neural network is established for metabolic prediction. Case studies show that the proposed metabolism-based ventilation control method can reduce the infection probability down to 4.3-6.3% while saving 13% of energy in comparison with the strategy of fixed-fresh-air ventilation. In the development of healthy and sustainable society, gymnasiums and alike exercise places are essential and the proposed ventilation control method is a promising solution to decrease the risk of COVID-19 while preserving features of energy saving and carbon emission reduction.

Data-driven real-time control method for process equipment in flow shop towards product quality improvement

Real-time control of complex process equipment is a crucial aspect for product quality assurance in the flow shop. However, there are two bottleneck problems, including the inaccurate quality prediction and the unstable process control, which would lead to poor product quality. To solve these problems, a data-driven real-time product quality prediction and control method for the process equipment is elaborated in this paper. First, to improve the prediction accuracy, a delay-mean rule is designed to eliminate the negative effects of time lag focused on the modeling data. Second, a variable optimization method based on the improved simulated annealing algorithm and a time window is proposed to enhance the stability of control. Finally, a case study regarding the real-time control for a dryer equipment is used to verify the proposed method.

Real-Time Monitoring and Control of Ultra-Fast Laser Engraving Process Utilizing Spectrometer

The objective of this study was to develop a novel real-time monitoring and control method for ultra-fast laser scribing processes utilizing spectrometer. Adjustment of laser process parameters such as laser power with high precision in real-time is critical in the laser engraving process due to the premium quality and speed requirements of the process. An online monitoring system was established using the Ocean Optics spectrometer, IPG ytterbium pulsed laser, and PXIe-8880 industrial computer. An algorithm for real-time control of the laser scribing process was developed based on the monitoring outcomes using LabVIEWⓇ software. Experimental methods were performed to evaluate the reliability of the developed monitoring system and control algorithm. The sensitivity of the spectrometer was assessed by changing laser power, pulse length, and focal point position. A workpiece consisting of two different metals, including stainless steel SS304L and steel S355, was used to evaluate the performance of the developed algorithm when scribing moved from one material to another. Instant accurate setting of the laser power based on the variations in intensities of metals from 750 AU to 1400 AU validated the reliability of the algorithm.

Demonstration of Real-Time Motion Control Method for Access Edge Computing in PONs

In the remote motion control of IoT devices, the delay adversely affects control performance. In our access edge concept, in which motion control is performed from a central office, the delay becomes large due to Dynamic Bandwidth Allocation (DBA) when the Passive Optical Network (PON) is adopted as the access system. No existing motion control method considers the delay changes of the DBA algorithm. We rectify this omission by proposing a novel real-time and high-precision motion control method that links the PON device and the controller. The proposed method can improve the control performance while maintaining the bandwidth utilization efficiency without changing the DBA delay specified to meet the requirements. In the proposed method, the delay in the PON system is calculated by using a delay model based on the setting parameter received from the communication device, and is used for delay compensation control. An experiment shows that, unlike the conventional method which becomes unstable and fails to realize control, the proposed method achieves high resolution control within 4 s, which demonstrates the feasibility of motion control for factory automation using edge computing in PON systems.

Control Method of Cyborg Insect inspired by Biological Behaviors

This paper propose real time control method of cyborg insect inspired by biological behaviors. In experiments, we successfully demonstrated navigating an individual insect using IMU data based on machine learning analysis with minimum electrical stimulation.

Investigation of Control Method for Connected-Automated Vehicle to Multiplex Dedicated Bus Lane

Dedicated bus lanes (DBLs) have been widely utilized to ensure public transport priority. To improve overall road efficiency, various control methods of multiplexing DBL are developed and discussed. In this study, we focus on the control method which is based on the connected-automated vehicle (CAV) technology, and the proposed method is validated by using microscopic traffic simulation. The simulation results show that two proposed control methods of multiplexing DBL can reduce the average delay and the average number of stops and increase the travel speed. In comparison, the real-time control method based on the CAV technology offers better effects than the improved signal light control method.

Expandable quantum deep width learning-based distributed voltage control for smart grids with high penetration of distributed energy resources

With numerous distributed energy resources accessed to smart grids, the randomness of distributed generators exacerbates the risk of voltage violations in the smart grid. To reduce the risk of voltage violations caused by distributed energy resources, this paper designs a real-time distributed voltage control method for smart grids to replace the centralized voltage control method of smart grids. In the designed real-time distributed voltage control method, the adjacent regional controllers communicate with each other to realize the optimal global control of the voltage of the entire smart grid without the need for a central controller. To study the reactive states of distributed energy resources access to smart grids on the voltage of smart grids, this paper proposes a three-state energy voltage model. To match the expandable distributed voltage control method for smart grids, this paper proposes the expandable quantum deep width learning algorithm. By combining the proposed algorithm with the designed real-time distributed voltage control method, the proposed algorithm has strong expandability and can match the distributed voltage control problem of smart grids. Finally, the effectiveness and expandability of the proposed algorithm and the designed real-time distributed voltage control method are demonstrated under four complex systems. The integral squared time-weighted absolute error index value of the expandable quantum deep width learning is less than or equal to 6.461.

Motion recommendation for online character control

Reinforcement learning (RL) has been proven effective in many scenarios, including environment exploration and motion planning. However, its application in data-driven character control has produced relatively simple motion results compared to recent approaches that have used large complex motion data without RL. In this paper, we provide a real-time motion control method that can generate high-quality and complex motion results from various sets of unstructured data while retaining the advantage of using RL, which is the discovery of optimal behaviors by trial and error. We demonstrate the results for a character achieving different tasks, from simple direction control to complex avoidance of moving obstacles. Our system works equally well on biped/quadruped characters, with motion data ranging from 1 to 48 minutes, without any manual intervention. To achieve this, we exploit a finite set of discrete actions, where each action represents full-body future motion features. We first define a subset of actions that can be selected in each state and store these pieces of information in databases during the preprocessing step. The use of this subset of actions enables the effective learning of control policy even from a large set of motion data. To achieve interactive performance at run-time, we adopt a proposal network and a k-nearest neighbor action sampler.

데이터센터 에너지 효율화를 위한 급기팬 온라인 예측제어

It is important to minimize electric energy consumption of a data center that uses enormous electricity for maintaining an adequate indoor temperature. Most data centers have applied the outdoor air cooling method on account of economic feasibility. However, it is necessary that data centers have an efficient control method in order to achieve extra energy savings. In this paper, we propose an artificial intelligence based real-time optimal control method that minimizes electricity consumption and assures safe operation simultaneously. The main idea of our proposed method is to evolutionary search the optimal range of controlled variable during a normally operative condition. Furthermore, an optimal operating condition can be achieved without requiring large-scale data to learn a model. Experimental results demonstrate that indoor temperature of a data center can be constantly controlled safely and cost effectively based on our proposed methodology.

Applying fuzzy logic control to analyze real-time control for charging and discharging power of electric vehicles

The disorderly charging of large-scale electric vehicles will aggravate the peak-valley difference of the power grid, and affect the power quality and life of the transformer. The fuzzy logic control strategy for charging and discharging optimization of charging vehicles under the framework of fuzzy logic control from the perspective of the group is considered in this article. A real-time control method based on the clustering characteristics of the charging end time is proposed according to the different charging requirements of the connected electric vehicles and fuzzy logic control is adopted to solve the problem of optimal charging and discharging power of the entire cluster and a single electric vehicle. A fuzzy logic control model considering the charging and discharging of electric vehicles is established orienting at minimize daily load fluctuations and control penalties in the upper layer. The charging and discharging cost of electric vehicle owners is considered to solve the optimal control problem of the charging and discharging power of a single electric vehicle. Taking the data of the typical regional distribution network load as an example, it is verified that the real-time charging optimization strategy under fuzzy logic control through simulation can ensure the reliable operation of the power grid while considering the interests of all parties.