Real-time Process Control Research Articles

Research on Full Link Intelligent Control Platform for Substation Maintenance through Edge-Aware

In view of the imperfect process control, safety control and data control in substation maintenance operation, this paper proposes a full link intelligent control platform for substation maintenance operation based on edge-aware. The platform is composed of on-site edge-aware system and big data decision service system. The on-site edge-aware system uses various intelligent tools to collect data, carries out real-time safety behavior early warning, maintenance quality control and maintenance process supervision through edge computing technology, and uploads the analyzed and processed information to the big data decision service system. The big data decision service system provides support for online decision-making of substation equipment maintenance according to the panoramic multi-source information of the maintenance site provided by the site edge perception system. The full link intelligent control platform for substation maintenance operation has built a control system for real-time control of on-site maintenance operation process, on-site maintenance information and on-site maintenance safety information, which improves the management efficiency of substation maintenance on-site operation and enhances the safety guarantee of maintenance operation.

THE APPLICATION OF COMPUTER VISION FOR THE ESTIMATION OF SHRINKAGE AND DEFORMATION OF THIN MANGO SLICES DURING AIR DRYING PROCESS

Computer vision has been currently a new trend in developing new tools for automatic real-time quality control process in food drying. During drying process, the size and shape of mango slides are critically changed. These changes usually determine the sensorial value of products, as well as which drying conditions would be needed to obtain the highest quality of dried products. In this study, we report on the development of a computer vision tool, requiring a normal digital camera installed, to evaluate the changes in size and shape of mango slides during the drying process. The technique is expected to replace the observation with human eyes to evaluate the changes of food products during the drying process, which might not be able to provide reliable and consistent judgements all the time. Image of drying mango slide is taken by a digital camera, then the feature extraction is implemented. The area of mango slice is determined by the area ratio via the pixel number counting and the comparison to an original sample with predefined reference size. The shrinkage deformation is evaluated by elliptical fitting to develop the automated utility. The utility is built on MATLAB platform. The variations in size and shape of the mango slices during a convective drying process with different processing conditions are examined and acquired by the built software which achieves real-time performance on the personal laptop.

Automated melt electrowritting platform with real-time process monitoring

Melt electrowriting (MEW) is an additive manufacturing (AM) technology with the ability to fabricate complex designs with high-resolution. The utility of MEW is studied in many fields including tissue engineering and soft robotics. However, current MEW hardware offers only basic functionality and is often designed and built in-house. This affects results replication across different MEW devices and slows down the technological advancement. To address these issues, we present an automated MEW platform with real-time process parameter monitoring and control. We validate the developed platform by demonstrating the ability to accurately print polymer structures and successfully measure and adjust parameters during the printing process. The platform enables the collection of large volumes of data that can be subsequently used for further analysis of the system. Ultimately, the concept will help MEW to become more accessible for both research laboratories and industry and allow advancing the technology by leveraging the process monitoring, control and data collection.

Artificial neural network modeling of full-scale UV disinfection for process control aimed at wastewater reuse

Accurate modeling of wastewater ultraviolet disinfection is fundamental as support for process optimization and control. Detailed modeling of hydrodynamics and fluence rate via computational fluid dynamics, coupled to laboratory studies of inactivation kinetics, are usually the preferred approach for UV disinfection modeling. Despite this approach often provides accurate predictive performance, it requires significantly high computational time, making it unfeasible for real-time process control. In this study, to enable an effective process control, black-box regression models were assessed as a modeling alternative for UV disinfection, synthesizing hydrodynamics, fluence rate and inactivation kinetics. UV disinfection of a full-scale wastewater treatment plant in Italy was monitored for 10 months, measuring influent and effluent E. coli concentration, turbidity, absorbance at 254 nm, temperature and flow rate at different UV doses. Considering the usually observed distribution of effluent E. coli concentration and the zero inflation of the collected dataset, Poisson, zero-inflated Poisson and Hurdle generalized linear models were tested, as well as two-part models coupling a classifier describing the E. coli zero-count events and a regressor estimating the magnitude of E. coli concentrations in positive-count events. The two-part artificial neural network model showed the best predictive performance, being able of both describing nonlinearities and handling the high proportion of null values in the dataset. The deployment of this model to control ultraviolet disinfection was simulated, estimating a plausible 63% energy saving.

Quality Variable Prediction for Nonlinear Dynamic Industrial Processes Based on Temporal Convolutional Networks

Soft sensors have been extensively developed to estimate the difficult-to-measure quality variables for real-time process monitoring and control. Process nonlinearities and dynamics are two main challenges for accurate soft sensor modeling. To cope with these problems, two temporal convolutional network (TCN)-based soft sensor models are developed in this paper. With a hierarchy of temporal convolution kernels and large receptive fields, TCN is able to describe the nonlinearities and long dynamic dependence of process variables. Thus, a TCN model is first designed for nonlinear dynamic soft sensing. However, the original TCN model neglects the auto-correlations of the quality variable, as well as the cross-correlations between the quality variable and process variables. Hence, an autoregressive TCN (AR-TCN) is further constructed by integrating the lagged quality data in the past neighboring samples for quality prediction of the current sample. Thus, AR-TCN is able to capture the auto-correlations and cross-correlations between the quality variables and process variables, which are more beneficial for quality prediction. The effectiveness of two proposed models is validated on an industrial debutanizer column and an industrial hydrocracking process.

Model predictive control strategy of head rice yield in paddy rice intermittent drying

This paper proposes a paddy rice model predictive control (MPC) drying strategy to achieve the real-time rolling optimization control of paddy rice intermittent drying process for the maximization of head rice yield (HRY). In the rolling optimization process, the adjusted evaluation index of predicted HRY ( AEHRY ) is used as the performance index to calculate the optimal control law in real-time. By comparing the simulation results of proposed drying strategies, the optimal drying strategy was chosen. Intermittent drying experiments of proposed MPC drying strategy were carried out to evaluate its performance. Experimental results showed that the proposed MPC drying strategy had the greatest AEHRY and HRY. In terms of Nanjing 9108 with initial moisture content of 22.88% wet basis, the average AEHRY s of 50 °C, 55 °C, 60 °C constant temperature drying, and MPC drying were 0.0773, 0.2130, 0.2283 and 0.3147, with average HRYs of 0.7121, 0.7129, 0.7163 and 0.7202, respectively. The feasibility of the proposed paddy rice MPC drying strategy was proved. The paddy rice intermittent drying processes under different application conditions have different drying requirements and restrictions. By modifying constraint part of the proposed MPC drying strategy, the ranges of drying parameters and the relationship during the drying parameters can be constrained to realize the real-time online optimization of these intermittent drying processes.

Online measurements of material flow compositions using acoustic emission: Case of gypsum and anhydrite

In this study, acoustic emission technology (AE), an established technology in various applications, has been investigated for its suitability for material flow characterization of bulk material. High-frequency waves generated during impact processes are recorded as acoustic emission signals to be used as a suitable measurement technology. By analysing the acoustic emission signals of known material flow compositions, suitable parameters and algorithms can be developed. Based on AE technology, the study focused on determining the gypsum and anhydrite content of an unknown material flow with the aim of building an online measuring system that could be integrated into the process of gypsum mining and processing. If successful, this approach could partly replace current offline analysis methods and enable real-time process control in the gypsum industry. The AE application was tested in laboratory experiments on a custom-built circulation test bench as well as in gypsum processing plants. Online measurements of the gypsum content were successfully achieved with an accuracy of 2.5% and an update rate of every five seconds.

Review of Soft Sensors in Anaerobic Digestion Process

Anaerobic digestion is associated with various crucial variables, such as biogas yield, chemical oxygen demand, and volatile fatty acid concentration. Real-time monitoring of these variables can not only reflect the process of anaerobic digestion directly but also accelerate the efficiency of resource conversion and improve the stability of the reaction process. However, the current real-time monitoring equipment on the market cannot be widely used in the industrial production process due to its defects such as expensive equipment, low accuracy, and lagging analysis. Therefore, it is essential to conduct soft sensor modeling for unmeasurable variables and use auxiliary variables to realize real-time monitoring, optimization, and control of the an-aerobic digestion process. In this paper, the basic principle and process flow of anaerobic digestion are first briefly introduced. Subsequently, the development history of the traditional soft sensor is systematically reviewed, the latest development of soft sensors was detailed, and the obstacles of the soft sensor in the industrial production process are discussed. Finally, the future development trend of deep learning in soft sensors is deeply discussed, and future research directions are provided.

Real-Time Protocols For Communication and Collaboration Environments in Telemedical Applications

World is now moving in the era of high information and communication technology. Under the term telemedicine and tele-cooperation research series are carried out presently, intended to enable and expand a distributed, group-related cooperative work within the area of medicine. For this purpose, applications are needed, which support real-time control processes, distributed applications, communication and cooperation technology, and the representation of shared information and data. Real-Time Protocols are the basis of telemedical applications. They are needed in almost all fields of telemedicine reaching from communication transmission to reliable data transfer. In a telemedical system, how these real-time protocols are used for communications, collaboration with telemedicine applications is worth to be explored and has been discussed in this research article along with the challenges of real-time applications and their solutions by using real-time protocols.

Self-correcting error-based prediction model for the COVID-19 pandemic and analysis of economic impacts

In order to improve the prediction accuracy of COVID-19 and strengthen the economic management and control, a self-correcting intelligent pandemic prediction model is proposed. The research shows that: (1) The pandemic, as a major social factor, has a great impact on the consumption expenditure level of various industries, and directly affects the public consumption expenditure level in different periods for example the spend_all in California decreased by 37.7%; (2) The economic losses caused by the increasingly serious pandemic period far less than the economic losses caused by the panic in the early stage of the pandemic, and the reason is the government's strong guarantee policies stimulate economic recovery. For example, the spend_all in California has increased from -37.7% to about -18%; (3) The proposed model improves the prediction accuracy of economic trend, and the government can make prediction according to the early warning economic prediction, which provides reference for the economic management control at the micro level of enterprises and the macro level of the nation; (4) The dual strategies of self correcting prediction and pandemic control realize the overall design of real-time control and performance optimization of economic process, and provide reference for the overall recovery of the economy.

Adopting MR-guided stereotactic laser ablations for epileptic lesions: initial clinical experience and lessons learned.

MR-guided laser interstitial thermal therapy (MRgLITT) is a minimally invasive technique for ablating brain lesions under real-time MRI feedback and control of the ablation process. The Medtronic Visualase system was recently approved for use in Europe and Israel. We report our initial technical experience using the system in the first 16 cases in which the system was used to ablate focal epileptogenic lesions. We included all consecutive patients with intractable epilepsy who underwent MRgLITT procedures between 2018 and 2020. We reviewed medical charts and imaging studies of patients. Post-ablation MRIs were used to calculate ablation volumes. Seventeen MRgLITT procedures were performed in 16 patients. One cooling catheter/laser fiber assemblies were placed per patient. Indications for surgery were intractable epilepsy due to TLE (n = 7),suspected low-grade glioma (n = 4), radiological cortical dysplasia (n = 1), hypothalamic hamartoma (n = 1), and MR-negative foci (n = 3). Ablations were made using 30 to 70% of the maximal energy of the Visualase system. We used serial ablations as needed along the tract of the catheter by pulling back the optic fiber; the length of the lesion ranged between 7.4 and 38.1mm. Ablation volume ranged between 0.27 and 6.78 mm3. Immediate post-ablation MRI demonstrated good ablation of the epileptic lesion in 16/17 cases. In one case with mesial temporal sclerosis, no ablation was performed due to suboptimal position of the catheter. That patient was successfully reoperated at a later date. Mean follow-up was 14.9months (± 11.6months). Eleven patients had follow-up longer than 12months. Good seizure control (Engel I, A) was achieved in 7/11 patients (63%) and 1/11 (9%) had significant improvement in seizure frequency (Angle IIIa). Three patients (27%) did not experience improvement in their seizure frequency (Engel IV, B), and one of these patients died during the follow-up period from sudden unexpected death of epilepsy (SUDEP). No immediate or delayed neurological complications were documented in any of the cases during the follow-up period. MRgLITT is a promising technique and can be used safely as an alternative to open resection in both lesional and non-lesional intractable epilepsy cases. In our local series, the success rate of epilepsy surgery was comparable to recent publications.

Cyber-Physical System Implementation for Manufacturing With Analytics in the Cloud Layer

Abstract Effective and efficient modern manufacturing operations require the acceptance and incorporation of the fourth industrial revolution, also known as Industry 4.0. Traditional shop floors are evolving their production into smart factories. To continue this trend, a specific architecture for the cyber-physical system is required, as well as a systematic approach to automate the application of algorithms and transform the acquired data into useful information. This work makes use of an approach that distinguishes three layers that are part of the existing Industry 4.0 paradigm: edge, fog, and cloud. Each of the layers performs computational operations, transforming the data produced in the smart factory into useful information. Trained or untrained methods for data analytics can be incorporated into the architecture. A case study is presented in which a real-time statistical control process algorithm based on control charts was implemented. The algorithm automatically detects changes in the material being processed in a computerized numerical control (CNC) machine. The algorithm implemented in the proposed architecture yielded short response times. The performance was effective since it automatically adapted to the machining of aluminum and then detected when the material was switched to steel. The data were backed up in a database that would allow traceability to the line of g-code that performed the machining.

Classification of transfer modes in gas metal arc welding using acoustic signal analysis

Gas metal arc welding (GMAW) is a welding process in which an electric arc is formed between a wire electrode and a metal workpiece alongside a shielding gas to protect the arc from contaminants. There are several ways in which the molten electrode droplet can be transferred to the weld pool known as metal transfer modes. Identifying the metal transfer mode automatically is essential to monitor and control the welding process, especially in automated processes employed in modern Industry 4.0 manufacturing lines. However, limited research on this topic has been found in literature. This paper explores the automatic classification of metal transfer modes in GMAW based on machine learning techniques with various signals from the welding process, including acoustics, current, voltage and gas flow rate signals. Time and frequency domain features are first extracted from these signals and are used in a support vector machine classifier to detect the metal transfer modes. A feature selection algorithm is proposed to improve the prediction rate from 80 to 99% when all four signals are utilised. When only the non-intrusive acoustic signal is used, the prediction rates with and without the proposed feature selection algorithm are approximately 96% and 81%, respectively. The high prediction rate demonstrates the feasibility and promising accuracy of the acoustic signal–based classification method for future smart welding technology with real-time adaptive feedback control of the welding process.

Sensor based real-time information for monitoring and control of a manufacturing process

This paper demonstrates a real-time process monitoring and control framework for the implementation of Industry 4.0 in manufacturing. For a case study, friction stir welding (FSW) has been selected owing to its extensive usage of welding in various manufacturing sectors. Force data has been collected online during the welding and sent to a cloud server enabling telewelding. It is processed through several signal processing and machine learning (ML) techniques for assessment of the weld quality. A control system thereafter controls the weld quality for avoiding the occurrence of weld-defect in real-time. Two ML models have been built, one for assessment of the weld quality, and the other for forecasting the controlled parameters for avoiding defect occurrence. For manufacturing sectors involved in mass production, this technique will be useful to keep a track of the process in real-time and avoid rejection of material in case of occurrence of an anomaly in the process. It is always beneficial for the manufacturing industry to track the quality of a product in real-time, and control the rejection rate, both of which have been successfully shown in this paper.

In-situ sensing, process monitoring and machine control in Laser Powder Bed Fusion: A review

Process monitoring and sensing is widely used across many industries for quality assurance, and for increasing machine uptime and reliability. Though still in the emergent stages, process monitoring is beginning to see strong adoption in the additive manufacturing community through the use of process sensors recording a wide range of optical, acoustic and thermal signals. The ability to acquire these signals in a holistic manner, coupled with intelligence-based machine control has the potential to make additive manufacturing a robust and competitive alternative to conventional fabrication techniques. This paper presents an overview of the state-of the art of in-situ process monitoring in laser powder bed fusion processes and highlights some current limitations and areas for advancement. Also presented is an overview of real-time process control requirements, which when combined with the emergent process monitoring tools, will eventually allow for in-depth process control of the powder bed fusion process, which is essential for wide-scale industrial credibility and adoption of this technology.

The causal relationship between melt pool geometry and energy absorption measured in real time during laser-based manufacturing

During laser powder bed fusion additive manufacturing, laser power absorption is governed by a protean pool of molten metal that can present as a highly reflective surface, a deeply absorbing cavity, or some amalgamation thereof. These melt pool dynamics have been linked to defect creation, porosity, and surface finish quality. Although these are therefore critical for determining final part quality, their instantaneous influence on laser absorption have only been explored through simulation. To date, direct real-time observations have been elusive due to the locally extreme environment. In this work, we focus a laser on Ti-6Al-4V powder and bare plate while quantifying the time-dependent, absolute energy absorption by monitoring omnidirectional backscattered laser intensity. We also simultaneously record the projective melt pool geometries with high-speed synchrotron x-ray imaging. We find that laser absorption strongly reflects the stability of the vapor depression over a wide range of applied laser powers, oxygen content in the processing atmosphere, and with the presence of powder. During laser scanning of a powder bed surface, we find a significant absorption reduction after 400 µs due to a dramatic change in the vapor depression aspect ratio – an event known to create porosity. As several industrial scan strategies necessitate thousands of these events during a build, their identification and control is of significant practical importance. Lastly, a normalized enthalpy model is demonstrated to be effective in quantifying the relationship between the laser absorption and cavity depth, even under transient conditions. In addition to providing vital quantitative data for simulation calibration, the correlation of melt pool geometry with laser absorption during realistic processing conditions suggests the use of a total backscattered light detection system for real-time process control.

Real-Time Simulation of a Cerebellar Scaffold Model on Graphics Processing Units.

Large-scale simulation of detailed computational models of neuronal microcircuits plays a prominent role in reproducing and predicting the dynamics of the microcircuits. To reconstruct a microcircuit, one must choose neuron and synapse models, placements, connectivity, and numerical simulation methods according to anatomical and physiological constraints. For reconstruction and refinement, it is useful to be able to replace one module easily while leaving the others as they are. One way to achieve this is via a scaffolding approach, in which a simulation code is built on independent modules for placements, connections, and network simulations. Owing to the modularity of functions, this approach enables researchers to improve the performance of the entire simulation by simply replacing a problematic module with an improved one. Casali et al. (2019) developed a spiking network model of the cerebellar microcircuit using this approach, and while it reproduces electrophysiological properties of cerebellar neurons, it takes too much computational time. Here, we followed this scaffolding approach and replaced the simulation module with an accelerated version on graphics processing units (GPUs). Our cerebellar scaffold model ran roughly 100 times faster than the original version. In fact, our model is able to run faster than real time, with good weak and strong scaling properties. To demonstrate an application of real-time simulation, we implemented synaptic plasticity mechanisms at parallel fiber–Purkinje cell synapses, and carried out simulation of behavioral experiments known as gain adaptation of optokinetic response. We confirmed that the computer simulation reproduced experimental findings while being completed in real time. Actually, a computer simulation for 2 s of the biological time completed within 750 ms. These results suggest that the scaffolding approach is a promising concept for gradual development and refactoring of simulation codes for large-scale elaborate microcircuits. Moreover, a real-time version of the cerebellar scaffold model, which is enabled by parallel computing technology owing to GPUs, may be useful for large-scale simulations and engineering applications that require real-time signal processing and motor control.

Real-time fault detection and process control based on multi-channel sensor data fusion

Sensor signals acquired in industrial equipment contain rich information which can be analyzed to facilitate effective monitoring of equipment, early detection of system anomalies, quick diagnosis of fault root causes, and intelligent system design and control. In many mechatronic systems, multiple signals are acquired by different sensor channels (i.e., multi-channel data) which can be represented by high-order arrays (tensorial data). The multi-channel data has a high-dimensional and complex cross-correlation structure. It is crucial to develop a method that considers the interrelationships between different sensor channels. This paper proposes a new equipment monitoring approach based on uncorrelated multilinear discriminant analysis that can effectively model the multi-channel data to achieve a superior monitoring and fault diagnosis performance compared to other competing methods. The proposed method is applied directly to the high-dimensional tensorial data. Features are extracted and combined with multivariate control charts to achieve real-time fault detection of equipment. The effectiveness of the proposed method in quick detection of equipment faults is demonstrated with both the simulation and a real-world case study.

Predictive models using “cheap and easy” field measurements: Can they fill a gap in planning, monitoring, and implementing fecal sludge management solutions?

The characteristics of fecal sludge delivered to treatment plants are highly variable. Adapting treatment process operations accordingly is challenging due to a lack of analytical capacity for characterization and monitoring at many treatment plants. Cost-efficient and simple field measurements such as photographs and probe readings could be proxies for process control parameters that normally require laboratory analysis. To investigate this, we evaluated questionnaire data, expert assessments, and simple analytical measurements for fecal sludge collected from 421 onsite containments. This data served as inputs to models of varying complexity. Random forest and linear regression models were able to predict physical-chemical characteristics including total solids (TS) and ammonium (NH4+-N) concentrations, and solid-liquid separation performance including settling efficiency and filtration time (R2 from 0.51-0.66) based on image analysis of photographs (sludge color, supernatant color, and texture) and probe readings (conductivity (EC) and pH). Supernatant color was the best predictor of settling efficiency and filtration time, EC was the best predictor of NH4+-N, and texture was the best predictor of TS. Predictive models have the potential to be applied for real-time monitoring and process control if a database of measurements is developed and models are validated in other cities. Simple decision tree models based on the single classifier of containment type can also be used to make predictions about citywide planning, where a lower degree of accuracy is required.

Versatile edge gateway for improving manufacturing supply chain management via collaborative networks

ABSTRACT As a natural consequence of Industry 4.0 demands related to industrial processes control digitization, the smart manufacturing (SM) concept was enriched by integrating advanced technologies of digital information processing. This paper presents an original solution for improving the most representative instance of SM, namely, supply chain management (SCM), by using the most recent approach in hierarchical networked control systems (HNCS), that is Edge Computing. The paper presents both the software and hardware architecture of an Edge Gateway device which offers, on one hand, dual communication both on vertical (between the network layers from the local, inferior, represented by IIoT, to the central, superior, represented by the Cloud) and on horizontal (between similar devices located on the same Edge level) and, on the other hand, can locally process data to take fast decisions which facilitate real-time process control. The validity of the proposed solution is supported by a case study performed on a flexible assembly/disassembly line (laboratory model).