A Heading Control Strategy Based On Neural Network PID Controller

This paper reports a new technique of control combining the concepts of sliding mode control and the multimodel approach. Baptized Integral Pseudo Sliding Mode Control, this control strategy, reduces the library of models whose number can block the establishment of the multi model control strategy in real time. It also allows, on the one hand, having a robust behavior compared to certain classes of uncertainties, and, on the other hand eliminating completely the chattering phenomenon.

With the continuous development of vehicle intelligence technology and active safety technology, the autonomous emergency braking pedestrian (AEB-P) system has emerged as a crucial element of contemporary automotive active safety systems. However, there are still some deficiencies in the control strategies utilized by the current AEB-P system. It is imperative to design an AEB-P system that can adapt the safety threshold and control strategy in real time based on the current driving conditions. The objective of this paper is to propose an AEB-P system with an adaptive control strategy and analyse its effectiveness from the perspective of pedestrian head injuries. Initially, an algorithm for adaptive collision time threshold model is proposed, and the AEB-P control strategy integrating this threshold is designed. Subsequently, a finite element model of the human head is developed to predict pedestrian head injuries in pedestrian-vehicle collision (PVC) scenarios with AEB-P intervention. Additionally, a simplified finite element model of PVC is established, and real PVC scenarios are reconstructed to assess the effectiveness of various AEB-P control strategies in mitigating pedestrian head injuries. The results demonstrate that the conventional control strategy is ineffective in reducing the risk of pedestrian head injuries at medium to high speeds. Conversely, the AEB-P system, which incorporates an adaptive control strategy, proves to be effective in decreasing the risk of pedestrian head injuries. Overall, the AEB-P system with adaptive control strategy enhances pedestrian safety, particularly in scenarios where PVCs are inevitable.

An intelligent control strategy for plasma arc cutting technology

The human hand along with its fingers possess one of the highest numbers of nerve endings in the human body. It thus has the capacity for the richest tactile feedback for positioning capabilities. This article shares a new technique of controlling slippage. The sensing system used for the detection of slippage is a modified force sensing resistor (FSR®). The control system is a fuzzy logic control algorithm with multiple rules that is designed to be processed on a mobile handheld computing platform and integrated/working alongside a traditional Electromyography (EMG) or Electroencephalography (EEG) based control system used for determining position of the fingers. A 5 Degrees of Freedom (DOF) hand, was used to test the slippage control strategy in real time. First a reference EMG signal was used for getting the 5 DOF hand to grasp an object, using position control. Then a slip was introduced to see the slippage control strategy at work. The results based on the plain tactile sensory feedback and the modified sensory feedback are discussed.

In this paper, a neural network PID controller with dynamic structure adjustment is proposed for DC-DC switching converters. To improve the efficiency of the controller and reduce its power consumption, the neural network for the proposed controller can change its structure adaptively in transient state according to the variation of voltage error, while it is disabled in steady state. Firstly, the whole voltage error range is divided into four parts to distinguish the location of voltage error. Then, the adaptive structure change mechanism is designed for neural network. Furthermore, a buck DC–DC switching converter using the proposed controller is designed and implemented on the field programmable gate array (FPGA) and printed circuit board (PCB). The experimental results demonstrated that it has similar transient performance in a DC-DC switching converter to that the conventional neural network PID controller, where neural network has the fixed structure. Meanwhile, the proposed controller has less power consumption and higher efficiency in transient state than a conventional neural network PID controller.

Intelligent transportation systems (ITS) typically rely on massive sources of data to monitor the transportation system, estimate its current state, forecast its future state, and react with a set of control and management strategies in real time. This requires the prompt processing of a variety of data sources that is consistently changing with time and typically challenging to combine (and make sense of) in real time. This paper presents thoroughly the studies related to big data applications in ITS and its associated challenges.

This paper proposes two real-time feedback control strategies based on hourly measurements of effluent NH4-N and NOX-N concentrations. Using modified sigmoid functions to decide the DO setpoint, a control structure similar to the cascade-type control loop was selected as the real-time feedback NH4-N control strategy. For the realtime feedback NOX-N control strategy, a proper external carbon dose flow rate could be calculated based on the estimated NOX-N concentration in anoxic reactor by using the empirical equation. A control system, which included two proposed control strategies, was developed and applied in the pilot-scale A2/O process. As a result, the effluent NH4-N and NOX-N concentrations were maintained stably lower than the target values of 3 and 5 mg/L, respectively. Moreover, because the manipulated variables for removing the NH4-N and NOX-N concentrations were divided in the control strategies, the two different control strategies could be successfully applied together in the A2/O process.

BackgroundPattern recognition (PR) based strategies for the control of myoelectric upper limb prostheses are generally evaluated through offline classification accuracy, which is an admittedly useful metric, but insufficient to discuss functional performance in real time. Existing functional tests are extensive to set up and most fail to provide a challenging, objective framework to assess the strategy performance in real time.MethodsNine able-bodied and two amputee subjects gave informed consent and participated in the local Institutional Review Board approved study. We designed a two-dimensional target acquisition task, based on the principles of Fitts’ law for human motor control. Subjects were prompted to steer a cursor from the screen center of into a series of subsequently appearing targets of different difficulties. Three cursor control systems were tested, corresponding to three electromyography-based prosthetic control strategies: 1) amplitude-based direct control (the clinical standard of care), 2) sequential PR control, and 3) simultaneous PR control, allowing for a concurrent activation of two degrees of freedom (DOF). We computed throughput (bits/second), path efficiency (%), reaction time (second), and overshoot (%)) and used general linear models to assess significant differences between the strategies for each metric.ResultsWe validated the proposed methodology by achieving very high coefficients of determination for Fitts’ law. Both PR strategies significantly outperformed direct control in two-DOF targets and were more intuitive to operate. In one-DOF targets, the simultaneous approach was the least precise. The direct control was efficient in one-DOF targets but cumbersome to operate in two-DOF targets through a switch-depended sequential cursor control.ConclusionsWe designed a test, capable of comprehensively describing prosthetic control strategies in real time. When implemented on control subjects, the test was able to capture statistically significant differences (p < 0.05) in control strategies when considering throughputs, path efficiencies and reaction times. Of particular note, we found statistically significant (p < 0.01) improvements in throughputs and path efficiencies with simultaneous PR when compared to direct control or sequential PR. Amputees could readily achieve the task; however a limited number of subjects was tested and a statistical analysis was not performed with that population.

Due to the growth characteristics of the flowers and fruits of camellia in the same period, the vibrating camellia fruit picking machine needs to ensure the constant rotational speed of the vibrating hydraulic motor when the picking mechanism is operating, to achieve a constant vibration frequency, to ensure that the camellia fruit can smoothly fall off the branches through vibration. In contrast, the camellia fruit does not fall off. In this regard, this paper deduced the state space equation of the camellia fruit picking machine’s valve-controlled vibrating hydraulic motor system and designed a fuzzy wavelet neural network PID controller (FWNN PID controller) based on the traditional incremental PID control principle. Then the designed vibration picking manipulator control system was simulated under no-load, 5 s load conditions, and load start conditions with MATLAB/Simulink, a general PID controller and a fuzzy RBF neural network PID controller (FRBFNN PID controller) were used to contrast with it. The results show that the general PID controller has a slow response speed and poor robustness, while fuzzy neural network PID controllers (including FWNN PID controller and FRBFNN PID controller) have a fast response speed and strong robustness, which can well meet the requirements of a specific vibration frequency. Finally, a field test was carried out. The results show that the FWNN PID control is better than the FRBFNN PID control. Furthermore, the FWNN PID controller obviously reduced the drop rate of camellia flowers within 6% while ensuring the picking efficiency above 90%, which can well meet the needs of the camellia fruit picking operation.

Introduction: Blood pressure (BP) control in the United States among persons with hypertension (HTN) is less than 50%. Performance and quality measures to improve care and outcomes for patients with high BP were published in 2019. The American Heart Association (AHA) recently completed its federally funded cooperative agreement, the National Hypertension Control Initiative (NHCI) to improve BP control in 350 community health centers (CHCs) with 1.5 million persons with HTN. Hypothesis: Use of a population health management platform can provide CHCs with more actionable, real-time Electronic Health Record (EHR) data to advance quality improvement (QI) efforts and evaluation capabilities. Methods: AHA identified a population health management platform to source EHR-derived data from 38 of 350 CHCs participating in NHCI. The objective was to demonstrate the value of readily accessing and using established measures for BP control in a project and system not already set up to do so. Eighteen clinical measures were used based on established performance and quality measures, aligning with Healthcare Effectiveness Data Information Set (HEDIS) where possible. Data for chosen measures was pulled from CHC EHRs on a monthly, quarterly, and ad hoc basis. This data expanded beyond what is required to be reported by CHCs to the Uniform Data System (UDS). Data sharing agreements were secured from 38 NHCI CHCs and 12 non-NHCI CHCs, as a comparison group, and all measures were made available to participating CHCs and other users. Results: Data was received for 12 quarters (January 2021 through December 2023) from the 50 CHCs on over 4.3 million encounters for 2.8 million patients. Data show a 48.7% relative improvement in the number of CHCs taking a BP reading at each patient encounter from Q1 2021-Q4 2023 (57.4% to 85.4%). Additionally, CHC BP control &lt;140/90 mm Hg and &lt;130/80 mm Hg reached 65.4% and 27.9%, respectively, in Q4 2023, as compared to the UDS reported 2023 BP control rate &lt;140/90 mm Hg of 60.9% for 350 NHCI CHCs. Conclusion: The expanded 18 measures allowed for more timely, frequent, detailed, and potentially actionable data to inform QI efforts. The timeliness and higher frequency of data should enable CHCs to understand the effects of their BP control strategies in real time. Using a population health management platform that emphasizes clinical performance measures based on “real-time” EHR data may strengthen and accelerate BP control QI and evaluation efforts.

Для адаптации систем водоотведения к условиям совокупного влияния урбанизации и изменения климата в мировой практике применяются традиционные статические способы, которые базируются на использовании «серо-зеленых» технологий, включая разделение общесплавных систем на раздельные, а также динамические решения с помощью контроля в режиме реального времени – Real Time Control (RTC). Опыт внедрения показывает, что ни одно из адаптационных мероприятий не может обеспечить 100%-ной эффективности. Следовательно, переливы в системах водоотведения не могут быть запрещены (это положение закреплено в законодательстве практически всех стран мира). При этом стратегия RTC является наиболее экономически выгодной мерой, но ограниченной по эффективности (20–30%). Поэтому в тех случаях, когда эффективности мероприятий RTC недостаточно, их целесообразно сочетать с регулирующими резервуарами. В связи с этим проведена оценка экономической эффективности применения автоматизированной системы управления водоотведением Санкт-Петербурга в режиме реального времени. Основным способом исследований являлось гидравлическое динамическое моделирование, с применением которого оценивались: эффективность управления в режиме реального времени регулирующими резервуарами; эффективность управления в режиме реального времени перебросками сточных вод между тремя бассейнами водоотведения Санкт-Петербурга с учетом параметра, характеризующего неравномерность распределения дождей по площади. In order to adapt wastewater disposal systems to the joint effect of urbanization and climate change, traditional static measures are applied in global practice based on the use of «gray-green» technologies inclusive of dividing combined systems into separate ones, as well as dynamic solutions using real-time control – Real Time Control (RTC). The experience of implementation shows that none of the adaptation measures can provide for 100% efficiency. Therefore, overflows in wastewater disposal systems cannot be prohibited (this provision is enshrined in the legislation of almost all countries of the world). At the same time, the RTC strategy is the most cost-effective measure, however, limited in efficiency (20–30%). Therefore, in case the efficiency of RTC measures is insufficient, combining them with intermediate storage tanks is advisable. In this regard, an estimation of the economic efficiency of using an automated system for wastewater disposal management in St. Petersburg in real time was carried out. The main method of research was hydraulic dynamic modeling, with estimating: the efficiency of the storage tank control in real time; the efficiency of transferring wastewater between three sewer zones of St. Petersburg in real time, taking into account the parameter characterizing the uneven rainfall distribution areally.

Progress in preparing real-time control schemes for Deuterium-Tritium operation in JET

Real time control of biofilters delivers stormwater suitable for harvesting and reuse

The temperature and efficiency of the three way catalytic converters of hybrid electric vehicle may be decreased and emission is deteriorated because of the engine's frequent start/stop during mode switching process.In order to minimize the fuel consumption and emission from the outlet of catalytic converter of full hybrid electric vehicles in the NEDC cycle,based on Pontryagin minimum principle the cost function relating the battery's state of charge and the temperature of three-way catalytic converter is established and solved to get the extreme value,then the global optimum real-time control strategy is obtained in order to minimize the fuel consumption and emission from the outlet of catalytic converter of full hybrid electric vehicles in the NEDC cycle.The control strategy during braking and stopping operations is simplified to analytically compare the effects of the control strategies with and without engine's start-stop optimum on the fuel consumption and emission.Dynamic model of the vehicle is established on the platform of Matlab / Simulink to validate the optimum control strategy and to compare the optimum control strategy with Rules control strategy.The results show that the optimum control strategy can optimize the engine's start-stop with the purpose of significantly speeding up the catalytic converter's light-off.The vehicle's fuel economy and emission from the outlet of three way catalyst are optimized from global perspective.Compared to the Rules control strategy,each index in Pareto solution set is improved effectively.

Convex optimization-based predictive and bi-level energy management for plug-in hybrid electric vehicles