Complex Facilities Research Articles

ANALYTICAL REVIEW OF MULTI-AGENT REINFORCEMENT LEARNING PROBLEMS

This paper is devoted to the problem of collective artificial intelligence in solving problems by intelligent agents in external environments. The environments may be: fully or partially observable, deterministic or stochastic, static or dynamic, discrete or continuous. The paper identifies problems of collective interaction of intelligent agents when they solve a class of tasks, which need to coordinate actions of agent group, e. g. task of exploring the territory of a complex infrastructure facility. It is revealed that the problem of reinforcement training in multi-agent systems is poorly presented in the press, especially in Russian-language publications. The article analyzes reinforcement learning, describes hierarchical reinforcement learning, presents basic methods to implement reinforcement learning. The concept of macro-action by agents integrated in groups is introduced. The main problems of intelligent agents collective interaction for problem solving (i. e. calculation of individual rewards for each agent; agent coordination issues; application of macro actions by agents integrated into groups; exchange of experience generated by various agents as part of solving a collective problem) are identified. The model of multi-agent reinforcement learning is described in details. The article describes problems of this approach building on existing solutions. Basic problems of multi-agent reinforcement learning are formulated in conclusion.

Interventions designed to control postpasteurization contamination in high-temperature, short-time-pasteurized fluid milk processing facilities: A case study on the effect of employee training, clean-in-place chemical modification, and preventive maintenance programs

Postpasteurization contamination (PPC) with gram-negative bacteria adversely affects the quality and shelf-life of milk through the development of flavor, odor, texture, and visual defects. Through evaluation of milk quality at 4 large fluid milk processing facilities in the northeast United States, we examined the efficacy of 3 strategies designed to reduce the occurrence of PPC in fluid milk: (1) employee training (focusing on good manufacturing practices) alone and (2) with concurrent implementation of modified clean-in-place chemistry and (3) preventive maintenance (PM) focused on replacement of wearable rubber components. Despite increases in employee knowledge and self-reported behavior change, microbiological evaluation of fluid milk before and after interventions indicated that neither training alone nor training combined with modified clean-in-place interventions significantly decreased PPC. Furthermore, characterization of gram-negative bacterial isolates from milk suggested that specific bacterial taxonomic groups (notably, Pseudomonas sequence types) continued to contribute to PPC even after interventions and that no major changes in the composition of the spoilage-associated microbial populations occurred as a consequence of the interventions. More specifically, in 3 of 4 facilities, gram-negative bacteria with identical 16S rDNA sequence types were isolated on multiple occasions. Evaluation of a PM intervention showed that used rubber goods harbored PPC-associated bacteria and that PPC may have been less frequent following a PM intervention in which wearable rubber goods were replaced (reduction from 3/3 samples with PPC before to 1/3 samples after). Overall, our findings suggest that commonly used "broad stroke interventions" may have a limited effect on reducing PPC. Our case study also demonstrates the inherent complexities of identifying and successfully addressing sanitation problems in large and complex fluid milk processing facilities. For example, broad changes to sanitation practices without improvements in PM and sanitary equipment design may not always lead to reduced PPC. Our data also indicate that although short-term evaluations, such as pre- and post-tests for employee training, may suggest improvements after corrective and preventive actions, extensive microbial testing, ideally in combination with isolate characterization, may be necessary to evaluate return on investment of different interventions.

SIMULATION MODEL OF THE ADAPTIVE MAINTENANCE PROCEDURE OF COMPLEX RADIOELECTRONIC FACILITIES

Context. The process of maintenance of modern radio-electronic facilities is aimed at supporting the serviceability or performance of the facilities during their technical operation. Specifications for achieving high reliability of operation are often contrary to other required characteristics, such as reducing the size of the product, obtaining high accuracy, reducing the cost of operation, etc. Therefore, the problem of the optimal choice of maintenance parameters to solve various tasks of operation using different criteria is relevant.Objective. The objective of this research is developing approaches to determine the optimal parameters of the process of adaptive maintenance.Method. Within the framework of the general simulation statistic model of the process of maintenance and repair of a complex facility (REF), we have developed a simulation model for parameter optimization of one of the maintenance strategies. The general simulation statistic model is intended to simulate the process of the TMR of the FEF in order to predict the reliability and value of the facility operation. Optimization of maintenance parameters improves both indicators of reliability of the facility and economic indicators of operation of the facility as a whole. The parameters are optimized on the basis of the criterion of a minimum specific cost of the REF operation or the criterion of the maximum ratio of technical use. In both cases, limitation means the required value of the mean time between failures of the facility, and as a method of optimization, we use the method of directed search within the scope of the maintenance parameters. An expert can participate in the process of finding an optimal solution, being involved in the analysis of intermediate data and making a decision on the completion of the search process.Results. The improved method of optimizing the maintenance parameters is a mathematical and algorithmic basis for the general software of the simulation statistic model of the maintenance and repair process. The method is programmed and tested in solving testing tasks. The results of the computational experiment are illustrated in the tabular form.Conclusions. In our work we have developed the simulation model of the process of adaptive maintenance of a complex radioelectronic facility. The model enables to substantially simplify and automate the process of research and optimization of the adaptive maintenance parameters of a complex radio-electronic facility. By adding the least reliable elements gradually to a plurality of items subject to servicing and modeling the random moments of the failure time, the simulation model calculates the optimal maintenance options with the adaptive time of condition monitoring. The simulation model is based on the algorithmic model and algorithmic optimization methods for adaptive maintenance, developed in our research, and works in the ISMPN software environment. As a method of optimization, we use the method of directed search within the scope of the maintenance parameters, with a DN distribution as a mathematical reliability model for electronic components and DM distribution for mechanical components.The practical value of the research lies in developing software which optimizes the maintenance parameters and predicts the reliability and value of operation for the given REF. The results obtained are to be used when determining the requirements for the parameters of operation of both new facilities and those of the available stock.

Fire and explosion safety management at fuel and energy facilities in special conditions

Introduction. The decision-makers (DM) are bear responsibility for fire safety (FS) at the fuel and energy complex (FEC) facilities. There is the fact of the impact of production intensification and data volume growth on the intensity of the load on the human resources. Which in turn increases the probability of errors of the DM. Automation and the use of information technologies allow us to optimize production processes. However, the level of responsibility of the DM is not reduced. In addition, it is noted that the reserve of time for decision making at the FEC facilities is being reduced. The objective of scientific research is to substantiate the relevance and necessity of using strategic planning methods in improving the planning of fire and explosion safety (FES) activities at the FEC facilities in special conditions. Theoretical bases. Such concepts as strategy, aggregate goal, planning horizon, target function, and non-formalized information are analyzed. The necessity of creating a tree of plans for the DM in order to conduct and control actions over the management object is justified. There is described the relationship between an aggregate goal and a strategy consisting of a sequence of actions by the DM to achieve certain values of aggregate quality indicator. Research results. This part of article justifies the necessity of applying strategic planning methods in order to preserve the performance indicators for DM at FEC facilities in the direction ofFES in changing special conditions. The characteristics of these conditions and the reasons for their occurrence are presented. In the absence of necessary planning and management methods in such conditions, the acceptable response time to a change in the environment will be exceeded. In order to overcome the tendency to reduce the efficiency of DM at FEC facilities in special conditions, it is proposed to use the software-hardware complex of the information and analytical system for strategic planning ofFES activities. Conclusion. Finally, it was noted the relationship between the number of errors of DM in the decision making process for subsystems of theFES and the increase in the volume of information from the means of accumulation and transmission data. It is really important to adapt theFES subsystems to the new special conditions with the use suggested information and analytical system for strategic planning.

Technology Focus: Intelligent Operations (May 2020)

Intelligent operations have been a focus for many parts of our industry for close to 2 decades. Our understanding of what this means, how it can be realized, and the boundaries of what is possible have advanced significantly in this period. Initial industry focus was around acquiring more real-time data (e.g., pressures and temperatures) along the flow path from reservoir to the point of sale and optimizing overall field performance. From the initial, simpler integrated-asset models, we have advanced to integrated work flows that enable optimal management of very large and complex fields and their equally complex surface facilities (papers SPE 196564 and SPE 197361). Another area of focus was using smart well completions to optimize production and injection reactively and proactively. Downhole technology and capabilities have matured significantly since the original installations in the late 1990s. The first paper highlighted here, SPE 195935, describes learnings from more than 100 intelligent well completions in presalt fields located in the ultradeepwater Santos Basin offshore Brazil. The industry continues to push the boundary on how this technology can be applied further (papers SPE 195850 and SPE 195361). The future of intelligent operations in our industry is being driven by advances from other sectors that have been embraced for petroleum applications. Foundational changes already taking place include advances in the type and volume of data being acquired (e.g., distributed-temperature- and distributed-acoustic-sensor data through fiber) and how the data are used. Paper SPE 194127 describes how smarter gauges with microelectromechanical-system inertial measurement sensors can enable more-accurate wellbore-trajectory estimation. We are leveraging the Internet of things, artificial intelligence, and machine-learning technologies capable of handling large volumes of data to analyze and optimize all aspects of upstream operations in real time, as seen in the next two papers highlighted in this section. In paper SPE 194084, electrical engineers, computer scientists, and drillers collaborate to use deep-learning techniques for real-time classification of cutting volumes at the shale shakers using a video feed from the rig. All of the technology advances also come together in paper OTC 29531, where live data streams from multiple sources, including wave states, motion sensors, and pressure and temperature gauges, are used with machine learning to develop a live fatigue counter for the risers on a floating production, storage, and offloading vessel and establish that facility life extension is possible. However, especially in these uncertain times, frequent hand washing with soap might indeed be the most intelligent operation of all. Stay safe!

Monitoring the technical and technological state of electric power complex facilities

The presented study is devoted to monitoring the technical and technological state of electric power complex facilities. As part of the study, the basic principles of monitoring and examining the state of equipment were analyzed, the process and procedure for monitoring the status of equipment and structures of the electric power complex were examined. The work analyzed the periods of preparation for the heating season of the Russian electric power industry, as a result of which it was revealed that the number of violations at electric power facilities was increasing, and the equipment of the federal districts was not fully prepared for the heating season by the readiness index. The work revealed that for almost all indicators of heat supply, water supply and sanitation, the number of violations and incidents during the heating period is increasing. At the end of the study, measures were presented that will ensure the stability and reliability of energy supply to consumers.

Real time detection of acoustic anomalies in industrial processes using sequential autoencoders

AbstractDevelopment of intelligent systems with the pursuit of detecting abnormal events in real world and in real time is challenging due to difficult environmental conditions, hardware limitations, and computational algorithmic restrictions. As a result, degradation of detection performance in dynamically changing environments is often encountered. However, in the next‐generation factories, an anomaly detection system based on acoustic signals is especially required to quickly detect and interfere with the abnormal events during the industrial processes due to the increased cost of complex equipment and facilities. In this study we propose a real time Acoustic Anomaly Detection (AAD) system with the use of sequence‐to‐sequence Autoencoder (AE) models in the industrial environments. The proposed processing pipeline makes use of the audio features extracted from the streaming audio signal captured by a single‐channel microphone. The reconstruction error generated by the AE model is calculated to measure the degree of abnormality of the sound event. The performance of Convolutional Long Short‐Term Memory AE (Conv‐LSTMAE) is evaluated and compared with sequential Convolutional AE (CAE) using sounds captured from various industrial manufacturing processes. In the experiments conducted with the real time AAD system, it is shown that the Conv‐LSTMAE‐based AAD demonstrates better detection performance than CAE model‐based AAD under different signal‐to‐noise ratio conditions of sound events such as explosion, fire and glass breaking.

Complex Meteorology over a Complex Mining Facility: Assessment of Topography, Land Use, and Grid Spacing Modifications in WRF

AbstractThe performance of the Weather Research and Forecasting (WRF) Model is evaluated in predicting the meteorological conditions over a complex open-pit mining facility in northern Canada in support of more accurate operational reporting of area-fugitive greenhouse gas emission fluxes from such facilities. WRF is studied in a series of sensitivity tests by varying topography, land use, and horizontal and vertical grid spacings to arrive at optimum configurations for reducing modeling biases in comparison with field meteorological observations. Overall, WRF shows a better performance when accounting for the mine topography and modified land use. As a result, the model biases reduce from 1.10 to 0.08 m s−1, from 1.04 to 0.50 m s−1, from 0.98 to 0.32 K, and from 45.7 to 17.3 W m−2, for near-surface wind speed, boundary layer wind speed, near-surface potential temperature, and turbulent sensible heat flux, respectively. Refining the model horizontal and vertical grid spacings results in bias reductions from 3.31 to 0.08 and from 0.80 to −0.11 m s−1 for near-surface and boundary layer wind speeds, respectively. The simulation results also agree with previous observations of meteorological effects on enclosed Earth depressions, characterized by formation of a cool pool of air, reduced wind speeds, and horizontal wind circulations at the bottom of the depression under thermally stable conditions. The results suggest that such configurations for WRF are necessary to arrive at more accurate meteorological predictions over complex open-pit mining terrains with similar features.

A study of problematic issues in information resources integration in Russia

The introduction of computer, information and telecommunication technologies has radically changed the capabilities of management processes in all spheres of life of modern states. Large-scale automation of a wide variety of processes, monitoring of the state of objects and processes, comprehensive support of activities for preparation and decision-making in close to real time mode, allowed for a significant expansion of the scope for increased efficiency in management. Further integration of information management and telecommunication systems has made it possible to manage even more complex objects distributed geographically, due to a substantially decentralized structure and heterogeneous by its nature both in the composition of hardware and software, and in the composition and structure of information resources. Over the decades, the goals of integrating computing and information resources have gradually transformed, showing a significant dependence, on both the capabilities of computer hardware and communication systems, and additionally on the capabilities of software, up to the level of development of information technologies. Often ahead of integration opportunities, practical needs determine the need to manage increasingly complex facilities. The evolution of command and control facilities began from private processes of ensuring daily activities (or combat command and control), passing through similar processes at the level of territorial entities, ministries and departments, and in our time has led to the emergence of objects combined into a single complex structure, distributed throughout the state and intended for solving state tasks of strategic importance.

Where are we going and where have we been? Examining the effects of maps on spatial learning in an indoor guided navigation task

BackgroundInternational Atomic Energy Agency (IAEA) safeguards inspectors are faced with the difficult task of learning the layout of complex nuclear facilities while being escorted through the facilities. This study addresses a gap in the literature regarding how to best support the development of inspectors’ spatial knowledge, given the constraint that they cannot bring digital devices into most nuclear facilities. We tested whether viewing a map before learning a guided route or carrying a map along the route enabled better spatial learning than having no exposure to a map. Moreover, we tested the impact of carrying maps with different levels of detail (simple 2D, simple 3D, or complex 2D maps) on spatial learning outcomes, as well as interactions between map type and individual differences in sense of direction.ResultsThe results showed nearly opposite patterns of performance for participants with good and poor sense of direction scores. Participants with a good sense of direction showed higher levels of spatial knowledge when studying or carrying simple maps, whether 2D or 3D, but they did not benefit from using a complex map. Participants with a poor sense of direction showed lower levels of spatial knowledge when using a simple map relative to using no map or a complex map, suggesting that they did not attempt to use the complex map. For both groups of participants, referring to a simple map while learning a route decreased their awareness of their environment, as measured by response times on a memory test that included incidentally learned items.

A Dynamic Bayesian Network Structure for Joint Diagnostics and Prognostics of Complex Engineering Systems

Dynamic Bayesian networks (DBNs) represent complex time-dependent causal relationships through the use of conditional probabilities and directed acyclic graph models. DBNs enable the forward and backward inference of system states, diagnosing current system health, and forecasting future system prognosis within the same modeling framework. As a result, there has been growing interest in using DBNs for reliability engineering problems and applications in risk assessment. However, there are open questions about how they can be used to support diagnostics and prognostic health monitoring of a complex engineering system (CES), e.g., power plants, processing facilities and maritime vessels. These systems’ tightly integrated human, hardware, and software components and dynamic operational environments have previously been difficult to model. As part of the growing literature advancing the understanding of how DBNs can be used to improve the risk assessments and health monitoring of CESs, this paper shows the prognostic and diagnostic inference capabilities that are possible to encapsulate within a single DBN model. Using simulated accident sequence data from a model sodium fast nuclear reactor as a case study, a DBN is designed, quantified, and verified based on evidence associated with a transient overpower. The results indicate that a joint prognostic and diagnostic model that is responsive to new system evidence can be generated from operating data to represent CES health. Such a model can therefore serve as another training tool for CES operators to better prepare for accident scenarios.

An experimental setup for creating and imaging 4He2 * excimer cluster tracers in superfluid helium-4 via neutron-3He absorption reaction.

For the purpose of future visualization of the flow field in superfluid helium-4, clusters of the triplet state excimer 4He2 * are generated along the micro-scale recoil tracks of the neutron-absorption reaction n + 3He → 3T + p. This reaction is induced by neutron irradiation of the 3He fraction contained in natural isotopic abundance liquid helium with neutron beams either from the Japan Proton Accelerator Research Complex, Materials and Life Science Experimental Facility (JPARC)/Materials and Life Science Experimental Facility or from the Kyoto University Institute for Integrated Radiation and Nuclear Science. These 4He2 * clusters are expected to be ideal tracers of the normal-fluid component in superfluid helium with several advantageous properties. Evidence of the excimer generation is inferred by detection of laser induced fluorescence emitted from the 4He2 * clusters excited by a purpose-built short pulse gain-switched titanium:sapphire (Ti:sa) laser operating at a wavelength of 905 nm. The setup and performance characteristics of the laser system including the Ti:sa and two continuous wave re-pumping lasers are described. Detection at the fluorescence wavelength of 640 nm is performed by using optical bandpass filtered photomultiplier tubes (PMT). Electrical noise in the PMT acquisition traces could successfully be suppressed by post-processing with a simple algorithm. Despite other laser-related backgrounds, the excimer was clearly identified by its fluorescence decay characteristics. Production of the excimer was found to be proportional to the neutron flux, adjusted via insertion of different collimators into the neutron beam. These observations suggest that the apparatus we constructed does function in the expected manner and, therefore, has the potential for groundbreaking turbulence research with superfluid helium.

The Role of a Region in the Implementation of Innovative Projects for Non-Defence High-Technology Production

The article discusses the problems of involving the innovative potential of enterprises of the military-industrial complex in the implementation of innovative projects for the non-defence high-technology production, as well as determining the role and place of the regional innovation infrastructure in their implementation. The aim of the study is to justify the role of a region in the implementation of innovative projects for the non-defence high-technology production, to determine features and formulate requirements for the development of the regional innovation infrastructure that provides support for these innovative projects based on the interaction of the regional innovation system enterprises with the military-industrial complex and infrastructure facilities at the national and international levels. As a result of the study, the authors highlighted the most important areas of interaction between the enterprises of the military-industrial complex and the region’s innovative infrastructure facilities (raising funds, promoting high-tech civilian products to national and international markets, etc.) and formulated the requirements for its formation. The results of the study can be used in managing the innovative development of the regions where high-tech enterprises of the militaryindustrial complex are located

The Method of Complex Facility’s Function Chart Comparison Produced by its Operator Expression and Application of Such a Method

The Method of Complex Facility’s Function Chart Comparison Produced by its Operator Expression and Application of Such a Method

제주 MICE 산업 활성화를 위한 6차 산업과의 연계 전략 방안 연구

The aim of this study is to provide implications in connection with 6th industry for Jeju MICE activation. The literature review of Jeju MICE industry features, 6th industry conditions and previous studies was conducted. And a case study method was applied to the Jeju. As a result, the Jeju MICE industry was initially built with infrastructure, but its competitiveness has been falling due to aging and increased similar facilities. The role of Jeju CVB, an operating organization, is becoming important. Jeju has a variety of regional resources, but conditions have not been prepared to upgrade, and its area and production are decreasing. As the link and activation factor of Jeju MICE industry and the 6th industry, hardware can be expanded into a complex facility to map out plans for regional and shared growth, and with the 6th industry and related fairs held, local residents could also participate in MICE industry. Jeju CVB won the Best Alliance Award. The study suggested that the terms of facilities and themes that reflect originality. Second, the core event linked to Jeju will be selected and intensively fostered. Third, local MICE organization should try to collaborate with various organizations and local residents.

Определение риска для объектов стартового комплекса с учетом их обваловки в случае аварии ракеты-носителя на начальном участке полета

Определение риска для объектов стартового комплекса с учетом их обваловки в случае аварии ракеты-носителя на начальном участке полета

Enhancing Patients' Wayfinding and Visitation Experience Improves Quality of Care

PurposeTo understand the impact of wayfinding challenges on patient hospital visitation experience, organizational costs, and emerging technology trends that may alleviate wayfinding challenges. DesignA review of literature on the relationship of wayfinding to patient's hospital visitation experience. MethodsA literature search identifying issues associated with wayfinding challenges in complex health care facilities was conducted. Case examples are provided to illustrate that the removal of barriers can improve the wayfinding experience. This review also informs technology trends that may effectively facilitate wayfinding in complex health care facilities. FindingsLarge hospital complexes exhibit many characteristics comparable to the physical features of a city environment. These complexities present challenges to patients to navigate to their destinations. An effective wayfinding system is a collection of tools that combines permanent signage, printed information, landmarks, architectural features and design elements, and human interactions. Navigational technology modeling holds the promise to aid patients and individuals with visual and cognitive challenges to find their way to their desired destinations effectively and efficiently, and improves their quality of life. ConclusionsImproved patient travel time correlates to reduce idled nursing time, with cost savings accrued to organization. Research shows that wayfinding mobile applications hold the promise of improving patients' hospital visitation experience.

Analysing oil and gas production facilities impact on atmospheric air of Potochnoye field

Environmental issues are always relevant. Nature is subject to constant human intervention. At the same time, associated institutions are being created to solve the tasks of reducing the level of harmful effects and the full restoration of environment. In this article, we assess the level of harmful emissions and wastes of oil and gas complex facilities during drilling, construction of facilities for field development and their operation, and present basic measures to reduce their impact on the air in Potochnoye field. We have examined the amount of emissions and waste from stationary and mobile sources. During wells drilling and facilities construction, the average annual evidence of pollutant emissions into the atmosphere caused by stationary sources will amount to 141.29 tons per year while the pollutant emissions caused by road and construction equipment and vehicles will be equal to 200.8 tons per year. Every year the amount of emissions into the atmosphere caused by the maintenance of the designed facilities will be 13730.9 tons per year, emissions from vehicles will be 47.1 tons per year. During field development, all work on the field should be carried out in compliance with the standards of the legislation of the Russian Federation. Having analyzed the amount of estimated emissions, a set of measures has been drawn up with the objective to reduce the impact of oil and gas complex on atmospheric air.

The new approach in evaluating the mechanism of the blast effect and organizing the blasting operations while tunneling

It is relevant for the organization of blasting operations with consideration to the mechanism of blast effect to justify new provisions due to the emergence of new explosives, means of initiating charges and instrumental measurement of parameters. In view of this, a new approach is needed for evaluating the mechanism of blast effect in the combined application of short-delay and delay-action blastings with a high level of organization and safety. Analyzing the results in the justification of the short-delayed blasting, obtained by many researchers in recent decades, its main advantages and some limitations in its evaluation have been identified. A clear justification for the combined application under seismic safety is provided. New results to explain the mechanism of the blast effect in the combined application of short-delay and delay-action blastings at tunneling facilities have been obtained. They help in the seismic action reduction under the conditions of close city development. Methodological approaches to organize blasting operations at complex facilities in Ukraine implemented during tunneling have been developed.

State of FAIRness in ESFRI Projects

Since 2009 initiatives that were selected for the roadmap of the European Strategy Forum on Research Infrastructures started working to build research infrastructures for a wide range of research disciplines. An important result of the strategic discussions was that distributed infrastructure scenarios were now seen as “complex research facilities” in addition to, for example traditional centralised infrastructures such as CERN. In this paper we look at five typical examples of such distributed infrastructures where many researchers working in different centres are contributing data, tools/services and knowledge and where the major task of the research infrastructure initiative is to create a virtually integrated suite of resources allowing researchers to carry out state-of-the-art research. Careful analysis shows that most of these research infrastructures worked on the Findability, Accessibility, Interoperability and Reusability dimensions before the term “FAIR” was actually coined. The definition of the FAIR principles and their wide acceptance can be seen as a confirmation of what these initiatives were doing and it gives new impulse to close still existing gaps. These initiatives also seem to be ready to take up the next steps which will emerge from the definition of FAIR maturity indicators. Experts from these infrastructures should bring in their 10-years' experience in this definition process.