Real-Time Workshop Research Articles

Learning complex nonlinear dynamics of a 3D translational parallel manipulator using neural network

This study investigates modeling the dynamics of a 3D translational parallel manipulator with closed chains using feedforward neural networks (FFNNs). The dataset exceeds 50,000 samples, incorporating experimental data collected from a robot prototype using MATLAB® real-time workshop and the National InstrumentsTM DAQ toolbox, as well as CAD simulation data from MSC ADAMS software. While achieving satisfactory mean squared error (MSE), some predictions did not fully capture the manipulator's dynamics, with small overfitting observed. A Deep Neural Network (DNN) was tested but faced overfitting and high computational costs, despite being trained on a subset of the dataset. This highlighted the limitations of DNNs for modeling such complicated parallel robots with closed chains and parallelograms. FFNNs were preferred for their simplicity and lower overfitting risk. L2 regularization and k-fold validation were applied to improve performance. Transfer learning (TL) was also employed, fine-tuning a new network with weights from pre-trained FFNNs using a smaller, unseen dataset. This approach significantly reduced MSE and completely eliminated overfitting, demonstrating the effectiveness of TL in refining model performance for forward and inverse dynamics. These findings suggest that FFNNs, combined with TL, L2 regularization, and k-fold validation, offer a robust method for accurately modeling complex robotic dynamics, enhancing control and optimization strategies for complicated robotic systems. Training for all networks was conducted within the MATLAB® environment.

Overcoming challenges in life cycle assessment of smart energy systems – A map of solution approaches

Current research underlines the benefits of digitalization to integrate renewable energy sources (RES) efficiently and to coordinate generation and supply. This development towards smart energy systems (SES) includes emerging use cases at the distribution grid level, e.g., smart charging strategies for electric vehicles or energy management systems in buildings. An environmental assessment of such, however, is challenging. The standardized Life Cycle Assessment (LCA) approaches seem insufficient since SES are emerging systems at the interface of digitalization and energy with multiple intended and unintended environmental effects. This article aims to derive solution approaches for LCA professionals that investigate use cases enabled by information and communication technology (ICT), specifically in SES. To identify challenges during the first two phases of an LCA and solution approaches, we examine seven recent research projects and conduct a real-time Delphi workshop with LCA experts in the field of SES. As a result, the article provides approaches on setting up an LCA, filling data gaps, and methods to draw upon the long-term impacts of use cases in SES. Key findings include a modified taxonomy of potential environmental effects. Results show that systemic effects in SES have potentially the highest impact on the LCA, followed by effects caused by user behavior. Assessing these effects of ‘higher-order’ poses an increased complexity. Determined solution approaches include combining the standardized LCA with energy system modeling or surveys on user behavior. Overall, this article reveals orientation strategies and recommendations to guide LCA professionals toward a holistic environmental assessment of use cases in SES.

Real-time scheduling for dynamic workshops with random new job insertions by using deep reinforcement learning

Dynamic real-time workshop scheduling on job arrival is critical for effective production. This study proposed a dynamic shop scheduling method integrating deep reinforcement learning and convolutional neural network (CNN). In this method, the spatial pyramid pooling layer was added to the CNN to achieve effective dynamic scheduling. A five-channel, two-dimensional matrix that expressed the state characteristics of the production system was used to capture the state of the real-time production of the workshop. Adaptive scheduling was achieved by using a reward function that corresponds to the minimum total tardiness, and the common production dispatching rules were used as the action space. The experimental results revealed that the proposed algorithm achieved superior optimization capabilities with lower time cost than that of the genetic algorithm and could adaptively select appropriate dispatching rules based on the state features of the production system.

ChatGPT for Fast Learning of Positive Energy District (PED): A Trial Testing and Comparison with Expert Discussion Results

Positive energy districts (PEDs) are urban areas which seek to take an integral approach to climate neutrality by including technological, spatial, regulatory, financial, legal, social, and economic perspectives. It is still a new concept and approach for many stakeholders. ChatGPT, a generative pre-trained transformer, is an advanced artificial intelligence (AI) chatbot based on a complex network structure and trained by the company OpenAI. It has the potential for the fast learning of PED. This paper reports a trial test in which ChatGPT is used to provide written formulations of PEDs within three frameworks: challenge, impact, and communication and dissemination. The results are compared with the formulations derived from over 80 PED experts who took part in a two-day workshop discussing many aspects of PED research and development. The proposed methodology involves querying ChatGPT with specific questions and recording its responses. Subsequently, expert opinions on the same questions are provided to ChatGPT, aiming to elicit a comparison between the two sources of information. This approach enables an evaluation of ChatGPT’s answers in relation to the insights shared by domain experts. By juxtaposing the outputs, a comprehensive assessment can be made regarding the reliability, accuracy, and alignment of ChatGPT’s responses with expert viewpoints. It is found that ChatGPT can be a useful tool for the rapid formulation of basic information about PEDs that could be used for its wider dissemination amongst the general public. The model is also noted as having a number of limitations, such as providing pre-set single answers, a sensitivity to the phrasing of questions, a tendency to repeat non-important (or general) information, and an inability to assess inputs negatively or provide diverse answers to context-based questions. Its answers were not always based on up-to-date information. Other limitations and some of the ethical–social issues related to the use of ChatGPT are also discussed. This study not only validated the possibility of using ChatGPT to rapid study PEDs but also trained ChatGPT by feeding back the experts’ discussion into the tool. It is recommended that ChatGPT can be involved in real-time PED meetings or workshops so that it can be trained both iteratively and dynamically.

Designing Practical Motivational Interviewing Training for Mental Health Practitioners Implementing Behavioral Lifestyle Interventions: Protocol for 3 Pilot Intervention Studies

Motivational interviewing (MI) is an evidence-based, patient-centered communication method shown to be effective in helping persons with serious mental illness (SMI) to improve health behaviors. In clinical trials where study staff conducted lifestyle interventions incorporating an MI approach, cardiovascular disease (CVD) risk profiles of participants with SMI showed improvement. Given the disproportionate burden of CVD in this population, practitioners who provide somatic and mental health care to persons with SMI are ideally positioned to deliver patient-centered CVD risk reduction interventions. However, the time for MI training (traditionally 16-24 hours), follow-up feedback, and the coaching required to develop and maintain patient-centered skills are significant barriers to incorporating MI when scaling up these evidence-based practices. We describe the design and development of the following 2 scalable MI training approaches for community mental health practitioners: real-time brief workshops and follow-up asynchronous avatar training. These approaches are being used in 3 different pilot implementation research projects that address weight loss, smoking cessation, and CVD risk reduction in people with SMI who are a part of ALACRITY Center, a research-to-practice translation center funded by the National Institute of Mental Health. Clinicians and staff in community mental health clinics across Maryland were trained to deliver 3 distinct evidence-based physical health lifestyle interventions using an MI approach to persons with SMI. The real-time brief MI workshop training for ACHIEVE-D weight loss coaches was 4 hours; IMPACT smoking cessation counselors received 2-hour workshops and prescribers received 1-hour workshops; and RHYTHM CVD risk reduction program staff received 4 hours of MI. All workshop trainings occurred over videoconference. The asynchronous avatar training includes 1 common didactic instructional module for the 3 projects and 1 conversation simulation unique to each study's target behavior. Avatar training is accessible on a commercial website. We plan to assess practitioners' attitudes and beliefs about MI and evaluate the impact of the 2 MI training approaches on their MI skills 3, 6, and 12 months after training using the MI Treatment Integrity 4.2.1 coding tool and the data generated by the avatar-automated scoring system. The ALACRITY Center was funded in August 2018. We have implemented the MI training for 126 practitioners who are currently delivering the 3 implementation projects. We expect the studies to be complete in May 2023. This study will contribute to knowledge about the effect of brief real-time training augmented with avatar skills practice on clinician MI skills. If MI Treatment Integrity scoring shows it to be effective, brief videoconference trainings supplemented with avatar skills practice could be used to train busy community mental health practitioners to use an MI approach when implementing physical health interventions. DERR1-10.2196/44830.

CAN message unpack and pack based on simulink automatic code generation technology

Aiming at the problem of a large amount of CAN communication message data of automobile controllers and low efficiency of traditional software development, this paper proposes a method of CAN message unpack and pack based on Simulink automatic code generation technology. S-Function is used to design CAN message sending and receiving model that can import DBC files, and use RTW (real-time workshop) to realize Simulink model to automatically generate C code. This method effectively solves the unpack and pack of CAN messages, simplifies the code development process, and improves the efficiency of software development, especially when there are DBC files, which simplifies the work of sending and receiving and testing.

A Novel Combined Control Strategy for a Two-Stage Parallel Full-Wave ZCS Quasi Resonant Boost Converter for PV-Based Battery Charging Systems with Maximum Power Point Tracking

This work deals with the design and validation of a combined control strategy to satisfy the requirements for both soft switching and Maximum Power Point Tracking (MPPT) for a Photo Voltaic based (PV-based) battery charging system. The proposed controller is employed for a two-stage parallel full-wave Zero Current Switching (ZCS) quasi resonant boost converter to obtain maximum voltage using Perturb and Observation (P&O) method. The controller utilizes frequency modulation to regulate the output voltage, considering any changes experienced due to the intermittent nature of the PV system. Operating principles of the tow-stage parallel boost converter are thoroughly analyzed, and Matlab Simscape toolbox and its real-time workshop capability is utilized to evaluate the performance of the proposed controller for a battery charging system.

RT-lab based real-time simulation of flywheel energy storage system associated to a variable-speed wind generator

This paper presents a new simulator used to distribute and execute real-time simulations: the RT-LAB, developed by opal-RT technologies (Montreal, Canada). One of its essential characteristics is the perfect integration with MATLAB/Simulink. The RT-LAB allows the conversion of Simulink models in real time via real-time workshop (RTW) and their execution on one or more processors. In this context, the paper focuses on the RT-LAB real-time simulation as a complement to the MATLAB/Simulink environment, which has been used to perform the simulation of the Flywheel energy storage system (FESS -variable speed wind generation (VSWG) assembly. The purpose of employing a fairly new real-time platform (RT-LAB OP -5600) is to reduce the test and prototype time. This application will be executed on each element of our model that was previously developed under MATLAB/Simulink. The real-time simulation results are observed in the workstation.

Real-time workshop digital twin scheduling platform for discrete manufacturing

Compared with other production methods, multi-variety, small-batch production driven by order become a lot more sensitive to the disturbances of workshop environment, orders, and processing equipment. This makes a great impact on workshop scheduling. Aiming at this problem, this paper designs a real-time workshop digital twin scheduling platform for discrete manufacturing. It improves the flexibility of the intelligent workshop and the response processing speed after dynamic disturbance. The platform can real-time monitor of the physical workshop and track orders, products, equipment and other information. Further, the platform and visualization technology were explored to work together. Then, the true display of changes after production line decision was displayed. It enables managers to carry out production scheduling verification in the virtual workshop, which reduces the repeated changes of physical workshop production scheduling. Finally, the platform was verified in a discrete manufacturing workshop. The scheduling platform based on digital twins helps manager to immersivity develop factory production strategies. The production efficiency was then enhanced. The platform can ensure the effective operation of the manufacturing system.

The Development of Therapeutic Radiographers in Imaging and Adaptive Radiotherapy Through Clinical Trial Quality Assurance

AimsAdaptive radiotherapy (ART) is an emerging advanced treatment option for bladder cancer patients. Therapeutic radiographers (RTTs) are central to the successful delivery of this treatment. The purpose of this work was to evaluate the image-guided radiotherapy (IGRT) and ART experience of RTTs before participating in the RAIDER trial. A plan of the day (PoD) quality assurance programme was then implemented. Finally, the post-trial experience of RTTs was evaluated, together with the impact of trial quality assurance participation on their routine practice. Materials and methodsA pre-trial questionnaire to assess the experience of the RTT staff group in IGRT and ART in bladder cancer was sent to each centre. Responses were grouped according to experience. The PoD quality assurance programme was implemented, and the RAIDER trial commenced. During stage 1 of the trial, RTTs reported difficulties in delivering PoD and the quality assurance programme was updated accordingly. A follow-up questionnaire was sent assessing experience in IGRT and ART post-trial. Any changes in routine practice were also recorded. ResultsThe experience of RTTs in IGRT and ART pre-trial varied. For centres deemed to have RTTs with more experience, the initial PoD quality assurance programme was streamlined. For RTTs without ART experience, the full quality assurance programme was implemented, of which 508 RTTs completed. The quality assurance programme was updated (as the trial recruited) and it was mandated that at least one representative RTT (regardless of pre-trial experience) participated in the update in real-time. The purpose of the updated quality assurance programme was to provide further support to RTTs in delivering a complex treatment. Engagement with the updated quality assurance programme was high, with RTTs in 24/33 centres participating in the real-time online workshop. All 33 UK centres reported all RTTs reviewed the updated training offline. Post-trial, the RTTs' experience in IGRT and ART was increased. ConclusionOverall, 508 RTTs undertook the PoD quality assurance programme. There was a high engagement of RTTs in the PoD quality assurance programme and trial. RTTs increased their experience in IGRT and ART and subsequently updated their practice for bladder cancer and other treatment sites.

A Study of Interpolation Compensation Based Large Step Simulation of PWM Converters

Real-time online simulation based on a real-time workshop (RTW) plays a vital role in the study and application of power electronics. However, restricted by the performance of equipment and hardware, the simulators so far available in the market mainly support simulation steps over 50 μs, while large step simulation may result in the action delay of pulse-width modulating (PWM), numerical oscillation and high-level non-characteristic harmonic distortion. In view of these problems, this paper puts forward a modeling method based on integral prediction and interpolation compensation. First of all, prediction is performed one step in advance by the implicit trapezoidal method to find out the accurate time when the triangle carrier wave intersects with the modulation wave. At the same time, a mathematic model is built for the insulated gate bipolar transistor (IGBT) to output equivalent voltage waveform according to the principle of area equivalent. Next, in MATLAB/Simulink, offline simulation is performed with the three-phase AC-DC-AC converter as the subject. By comparing the control accuracy, the content of harmonic wave and the simulation time, the simulation effects of the 50 μs fixed-step interpolation prediction model are the same as that for a 5 μs fixed-step standard model. Finally, the effectiveness and high efficiency of this algorithm are verified on a real-time simulator, marking the application of offline models on real-time simulators.

Research on Implementation Method of Fuzzy Logic Control Based on MCU

Fuzzy control belongs to the category of intelligent control, which has outstanding control advantages for more complex systems. Firstly, based on Matlab sltank fuzzy control system, a data extraction model has been established in this paper. By running the model, a number table can be obtained. Secondly, the number table is embedded into the two-dimensional lookup table module, and the C code is generated by real time workshop (RTW) function. Finally, the interpolation principle analysis is carried out, and the interpolation algorithm of two-dimensional lookup table is embedded into the MCU for testing. The real-time test results show that the interpolation result of the MCU is consistent with the off-line simulation result, and the real-time control of the MCU can be guaranteed.

Fuzzy PID speed control of BLDC motor based on model design

Brushless direct current (BLDC) motor has been widely used in industrial production. Based on the method of model design, BLDC motor speed control is studied. In Matlab/Simulink, a fuzzy PID speed control model of BLDC motor is established, and C Code is generated by Real-Time Workshop (RTW) technology. After that, Code Warrior is compiled into machine Code and written into ECU. The results show that the fuzzy Proportion Integration Differentiation (PID) controller can improve the speed performance of the BLDC.

Performance Evaluation of SEPIC Based Single-Phase Seven-Level Inverter for Renewable Applications

Contemporary research in multilevel inverters (MLIs) is becoming famous for low power renewable applications. In this paper, therefore, a new configuration of SEPIC based single-phase seven-level inverter is presented with the advantages of lower parts count, size, and reduced cost. The front-end sepic inverter is used to boost the input voltage to the desired voltage and cascaded with a 1:2 multi-winding high-frequency transformer to generate V dc and 2V dc which is fed to the asymmetrical six switch multilevel inverter. The simulation work is carried out in Matlab/Simulink environment, and a laboratory prototype model is developed to validate the concept. The control pulses for the SEPIC inverter is built using TMS3202812 DSP in real time workshop(RTW), and the switching pulses for MLI are generated using a Spartan-6 FPGA Processor. The performance of the proposed topology evolved for the step change in input voltages, and the different loading conditions. A detailed comparison of various seven-level inverter topologies is also conducted.

Design and Implementation of Device Integration Framework Based on Agent Technology in MES

The manufacturing process plays an important role in the Product-Service Systems(PSS). As a significant part of manufacturing process, Manufacturing Execution System (MES) controls the whole manufacturing process. MES supporting access to service-oriented devices provides data basis for the information of manufacturing enterprises. Agent-based MES proposed in this paper supports the bidirectional transmission of device data, which solves the problem of complex integration of traditional devices and difficulty in manufacturing data interaction between various systems. The service of devices integration based agent technology provides functions such as device registration, device search, device control, and real-time data acquisition for MES, and uses message queues and industrial gateways to decouple device control and MES. As a bridge for data interaction between MES and devices, the service of devices integration is a possible basis for ensuring data interaction between devices and upper management systems. The framework was demonstrated through a real-time metrology workshop case in the coatings industry.

Modeling and Real-Time Simulation of Induction Motor Using RT-LAB

<span lang="EN-US">This paper presents the modeling and real-time simulation of an induction motor. The RT- LAB simulation software enables the parallel simulation of power drives and electric circuits on clusters of a PC running QNX or RT- Linux operating systems at sample time below 10 µs. Using standard Simulink models including SimPowerSystems models, RT-LAB build computation and communication tasks are necessary to make parallel simulation of electrical systems. The code generated by the Real-Time Workshop of RT- LAB is linked to the OP5600 digital real-time simulator. A case study example of real-time simulation of an induction motor system is presented.This paper discusses methods to overcome the challenges of real-time simulation of an induction motor system synchronizing with a real-time clock.</span>

Study of dual closed-loop control strategy of exhaust gas recirculation for diesel engines

ABSTRACTWith the rapid development of the global economy, more vehicle ownership leads to the increasing of environmental pollution in recent years. In response to this matter, exhaust gas recirculation (EGR) has been used in most modern diesel engines, to control NOx emissions effectively. In this work, a dual closed-loop EGR control system was modeled by coupling the one-dimensional cycle simulation and the logic under Matlab/Simulink environment. The intake airflow and EGR valve position are regarded as the control targets in the key control logic concept. The results show that the deviation between simulation and experimental results is smaller than 5%, which can meet the needs of practical application. Moreover, the accuracy and feasibility of the code generated by the Real-Time Workshop module are verified simultaneously.

A Robotic Drilling End-Effector and Its Sliding Mode Control for the Normal Adjustment

A robotic drilling end-effector is designed and modeled, and a sliding mode variable structure control architecture based on the reaching law is proposed for its normal adjustment dynamic control. By using a third-order nonlinear integration chain differentiator for obtaining the unmeasurable speed and acceleration signals from the position signals, this sliding mode control scheme is developed with good dynamic quality. The new control law ensures global stability of the entire system and achieves both stabilization and tracking within a desired accuracy. A real-time control experiment platform is established in xPC target environment based on MATLAB Real-Time Workshop (RTW) to verify the proposed control scheme and simulation results. Simulations and experiments performed on the designed robotic end-effector illustrate and clarify that the proposed control scheme is effective.

Proposal of Real-time Shareable Citizen Collaborative Workshop for Urban Development Using My City Forecast

Proposal of Real-time Shareable Citizen Collaborative Workshop for Urban Development Using My City Forecast

HTML5-Based 3-D Online Control Laboratory With Virtual Interactive Wiring Practice

This paper introduces the schemes of remote wiring interactions in an online control laboratory using an HTML5-based virtual 3-D interface. Although virtual laboratories have drawn increasing research attention in the last decade, wiring practice, which is a crucial part of experimentation, is normally neglected. In this paper, a practice including 3-D modeling, HTML5-based rendering, and control algorithm design is implemented for the interactive virtual wiring based on the Networked Control System Laboratory (NCSLab) framework. The wiring practice is combined with control algorithm design, which is already realized in NCSLab, where users are allowed to customize algorithms using MATLAB/Simulink real-time workshop. Apart from remotely implementing the control algorithm, the 3-D virtual wiring process must be completed correctly before the online experiments can proceed properly. The proposed wiring laboratory is evaluated in practical teaching, with both students’ performance and perception considered. The conclusions derived from the report show that the 3-D virtual wiring interactions make virtual experimentation complete for simulating a real case, as well as providing an opportunity for a clearer comprehension of control systems.