Statistical Method for Error Prediction in Decision Support and Control Systems

I: General Issues.- Modeling Knowledge: Model-based Decision Support and Soft Computations.- Benefits of Decision Support Using Soft Computing.- Evolving Connectionist-based Decision Support Systems.- An Agent-based Soft Computing Society with Application Applications in Financial Investment Planning.- A Rough Sets/Neoral Networks Approach to Knowledge Discovery for the Development of Decision Support Systems.- II: Applications and Implementations.- Decision Support Systems in Healthcare: Emerging Trends and Success Factors.- A View of Public and Private Sectors for Taiwan's BOT Project Financing Using Fuzzy Multi-Criteria Methods.- Relational Structures for the Analysis of Decision Information in an Electronic Market.- A Fuzzy Evaluation Model: A Case for Intermodal Terminals in Europe.- Application of Kemeny's Median for Group Decision Support.- An Internet-based Group Decision and Consensus Reaching Support System.- Limpio: A DSS for the Urban Waste Collection Problem.- A Decision Support System for Air Quality Control Based on Soft Computing Methods.- Multicriteria Genetic Tuning for the Optimization and Control of HVAC Systems.- Intelligent Information Systems for Crime Analysis.- Application of Fuzzy Decision Trees to Reservoir Recognition.- Introducing SACRA: A Decision Support System for the Construction of Cattle Diets.- Prediction of Parthenium Weed Dispersal Using Fuzzy Logic on GIS Spatial Image.

Towards the later part of the 20thcentury, the oil industry has been looking for more safer and beneficial drilling methods, especially in deep waters. The high well/field costs pushed the need for attractive technologies which would optimize drilling. Also ever since the catastrophic events of April 2010 in the Gulf of Mexico, the oil industry has been constantly scrutinized for the health and safety standards or rather the lack of it. The consequences of the blowout highlighted the need for improved kick detection and well control. In deepwater wells, there exists a narrow window between the fracture pressure and the pore pressure. This narrow margin poses a safety hazard both for the well and the crew operating on it. Drilling in these sort of fields require distinctive methodologies to achieve both objectives of safe and optimized drilling. Thus one such method which would optimize drilling and improve well control is Managed Pressure Drilling (MPD). This has been defined as "an adaptive drilling process to accurately control the annular pressure profile throughout the well". This technique would create a pressure profile in the well to be within tolerance and close to the boundaries or limits controlled by the pore and fracture pressure. For the understanding of kick detection, well control and circulation when MPD is being employed, a hypothetical well data with a narrow pressure window is selected and a kick is simulated to be controlled using MPD. The pump rate & mud density is studied and kick detection, well control and circulation is analyzed and interpreted. Obviously with the usage of the MPD tools and equipments during drilling, there would be a difference from conventional kick detection, which could probably be enhanced well control. MPD would thus, be able to properly manage any influxes from the formations thereby protecting the system and structure above and have a telling effect on the Non Productive Time (NPT). This paper aim to differentiate the conventional and MPD method of kick circulation based on simulations of lost time and lost circulation. By obtaining the desired result, we can justify the usage of MPD in a narrow pressure window field/reservoir for improved kick detection, control and circulation and thus drilling optimization.

Digitalisation and automation can account for massive efficiencies in wells operations. Managed Pressure Drilling (MPD) and Automated Well Control are examples of "smart" technologies that can mitigate risks and costs associated with drilling wells. The Automated Well Control system was developed to monitor the well, identify an influx, take control of the rig equipment and shut in the well. MPD provides annular pressure control, real-time information of the well parameters and conditions downhole and very accurate and immediate influx detection. However, if a high intensity influx is taken that exceeds the pre-planned operational limits of the MPD package, then secondary well control is required. Therefore, a combination of Automated Well Control and MPD has been developed to deliver both pressure control and well control in a safe, efficient and less error-prone manner. On an MPD operation, the Automated Well Control system shuts-in the well as soon as it is required to do so. With Automated Well Control in MPD mode, the MPD system decides when to shut in and the Automated Well Control technology will immediately space out, stop the mud pumps and top-drive, and shut in the well using the pre-selected blowout preventer. This interface between the two systems mitigates drilling hazards using automation. The sensitivity of MPD, combined with Automated Well Control technology enables fast identification, decision making and reaction to well control events. Consequently, this fully integrated solution improves safety and operational efficiency. The MPD and Automated Well Control systems were integrated into a test rig and several tests were efficiently performed. The tool enabled immediate action in the event of influxes, providing a valuable solution for the industry. This paper briefly describes MPD and Automated Well Control and summarises the interface between the two technologies, detailing how the integrated system works on a rig. Moreover, rig trialling results and further developments are presented.

Comparative impact of guidelines, clinical data, and decision support on prescribing decisions: an interactive web experiment with simulated cases

This study examines the verification approaches used by government agencies in East Malaysia to ensure the reliability of Decision Support Systems (DSS) in their decision-making processes. Focus group interviews were conducted, revealing various verification methods employed. The study aims to contribute to understanding DSS verification techniques and the unique challenges government agencies face. Challenges identified include a need for more technical expertise. It recommends investing in staff training and adopting standardized verification frameworks to enhance DSS reliability. These findings are valuable for East Malaysian government agencies and other similar contexts, enabling informed decision-making through reliable DSS.

A Real Time Production Tracking and a Decision Support System (PTDSS): A Case Study from an Apparel Company

Cranes are among the most expensive pieces of equipment in many construction projects as well as freight terminal operations, shipyards, and warehouses. Despite their wide range of application, a vast majority of cranes still in use do not feature the advanced automation and sensor technologies. A typical crane operator mostly uses visual assessment of the jobsite conditions which may be enhanced through a signalperson on the ground. However, the lack of an integrated decision support system which takes into account the evolving work conditions and the time and space constraints may lead to delays due to inefficient prioritization of crane service requests. In a longer term, this may affect or even change the project critical path which will ultimately lead to increased project time and cost. This paper presents the latest results of an ongoing study which aims to design and implement an automated crane decision support system to help crane operators fulfill service requests in the most efficient order.

Real-time computerised decision support is providing timely support to business decision makers. Real-time decision support systems (DSS) can support operational and tactical decisions, and may enhance strategic decision making in some situations. Current systems can deliver needed data, results, and communications with essentially no processing delay. When evaluating implementation of these systems, managers need to consider and respond to three categories of continuing challenges: (1) technical, (2) organisational and (3) social/psychological. Potential benefits include faster response, improved efficiency, reduced risk, and reduced operating costs. Real-time technological can be disruptive and likely threatens the competitive position and success of many organisations.

This paper presents a framework and methodology for integrating real-time Traffic Estimation and Prediction Systems (TrEPS) into weather-responsive traffic signal operations in Utah, USA. This study is motivated by the need for adjusting signal timing plans in response to changing traffic conditions during inclement weather in order to mitigate the impact of weather and maintain the network service level. This study provides a real-world application demonstrating that such a need can be effectively assisted by a TrEPS-based decision support system. Three components are introduced to form the overall decision support system: real-time TrEPS, Scenario Manager, and Scenario Library. Real-time TrEPS offers the capability to estimate and predict network states under various control scenarios; Scenario Manager provides an environment to identify and evaluate alternative signal control strategies based on TrEPS-predicted network states; and Scenario Library serves as a knowledge base defining available weather-responsive signal timing plans for Scenario Manager to access in real-time. The detailed implementation procedure and expected benefits of the proposed system are illustrated and discussed using a case study based on a historical snow event.

The sizing calculation of a traditional Mud Gas Separator (MGS) becomes crucial when flowrates as high as drilling flowrates could be utilized to circulate out formation fluids using a fully automated Managed Pressure Drilling (MPD) control system. With the technological advancements to detect influxes, some of today’s MPD systems are equipped with algorithms to automatically apply surface backpressure (SBP) in order to restore the overbalance while retaining the ability to circulate the small volumes of formation fluids (influx) that entered the wellbore, prior to achieving the overbalance (Patil 2018). Since the algorithms of MPD systems are designed to assist in minimizing influx size while the system achieves the necessary overbalance, circulation rates as high as drilling rates are typically used to maintain relatively lower Surface Backpressures (SBP) while circulating influxes with MPD systems. From the MPD perspective, the liquid and gas handling capacity of the MGS influences the MPD Influx Management Envelope (IME) which is designed to determine the operational limits of the influx volumes and pressures (Patil 2018). The MGS liquid and gas handling capacities influence these circulation rates to manage the peak liquid and gas flowrates below the calculated threshold of the MGS capacities. Reducing the circulation rates increases SBP requirements which directly affects the MPD IME. This paper focuses on evaluating the methodology described in SPE 20430 (MacDougall 1990) for calculating the MGS liquid and gas handling capacity when relatively higher flowrates are used to circulate formation fluids through the MGS. It compares the method to estimate friction pressure loss for gas exiting the vent line that is described in SPE 20430 to an iterative and complex simulation model that includes pressure, temperature, gas density, compressibility etc. Furthermore the paper illustrates the setup and the results obtained when using a CFD (Computational Fluid Dynamics) simulator to qualitatively assess the velocities and separation inside the MGS in comparison to the average velocities limited to 8.4ft/min (MacDougal 1990) inside the MGS which would prevent separator blow-through condition.

The objective of this research is to design a decision support system to guide the executives of small enterprise in developing a strategic plan for using information systems in a computer business. The development of the system begins with a conceptual model for planning strategic information systems. This conceptual modelwas then transformed into an easy to use software running on web browser incorporating analysis tools and frameworks such as PEST, SWOT, Competitive Five Forces, TOWS matrix, Critical Success Factors, and Application portfolio. The completed decision support system software was tested to ensure that the design output meets the users’ requirements and Its objectives. A case study of one company in the personal computer industry was used to illustrate the application of this decision support system. The sales manager and marketing manager of the case company were asked to use it in a trial run. The defined business need in this case is to be the most customer-focused, competitive, efficient, and innovative computer business in Bangkok by the year 2008. The outcome of the trial run is the specification of possible IS applications to support the defined business need. These applications are then classified into 4 sets: strategic, high potential, key operational, and support in the application portfolio to be managed according to their business contribution now and in the future. The identified possible IS applications include Internet ordering, financial decision systems, marketing forecasting systems, Network ordering and purchasing systems, production planning and control systems, product quality control systems, and database management systems. From the case study, it may be concluded that the users are able to link business needs to IS application required to create competitive advantage for the company. The IS applications are derived correspondingly with a business mission and business strategy, thus ensuring that these applications are developed properly to respond to both opportunities and threats based on the company resources, reasonably. Most of the IS applications can also be traced back to the business goals and business strategies. However, the decision support system itself also has some noticeable drawbacks that cause some difficulties to the users and need to be corrected. Help systems and information support are somewhat inadequate in this version of the decision support system, especially for users with no experience in strategy formulation or SIS planning. Therefore, with further improvement, this decision support system should better serve the intended users in strategic planning of information systems.

Objectives/Scope This case history paper describes the well integrity challenges Spirit Energy was faced with for executing the drilling operations on the Scarecrow wildcat well in the Barents Sea. The expected reservoir depth on Scarecrow was the shallowest reservoir ever drilled in the Barents Sea being only 188 m below mudline with a water depth of 454 m MSL. Several mitigating actions were implemented to improve robustness of the well integrity such as: The focus in this paper is to describe the qualification of a new automated pressure control method (Autochoke system) used on the Scarecrow wildcat well in the Barents Sea for circulating out an influx. Simulations and return of experience indicated that manual conventional well control practices would not provide sufficient pressure control precision to maintain bottomhole pressure within the +/- 4 bar (58 psi) operational window required to circulate out an influx. A new automated pressure control method based on a commercial managed pressure drilling (MPD) control system was developed, tested, and DNV approved to achieve the required pressure control precision for both single- and multi-phase scenarios, and permit safe operations. Methods, Procedures, Process A pressure control method was developed to automate control of well control chokes to maintain a constant standpipe pressure, as required during circulating using Driller's Method. The methodology used is comparable to commercial MPD pressure control systems, in which pressure transducer (PT) measurements are input to a control loop which actuates chokes to attain the pressure demand while minimizing overshoot. Unlike a typical MPD installation, in which PTs are typically located upstream of a choke manifold, this installation utilized PTs installed on the rig standpipe, with chokes installed in the well control manifold. The choke control system was improved to automatically compute and account for pressure wave propagation lag due to the distance between the chokes and the control PTs. Results, Observations, Conclusions The system was tested at a test rig in Norway that permitted the injection of air into the standpipe to simulate a gas kick. In multiple test cases, various quantities of air were injected into the standpipe, circulated into the annulus, and finally circulated out of the wellbore with automated chokes operating to maintain a constant standpipe pressure as the air was circulated out of the wellbore and through the chokes. Testing was repeated with varying quantities of injected air and varying standpipe pressure setpoints to validate the process across a range of operating conditions. The control system demonstrated standpipe pressure control precision of +/- 1 bar (14.5 psi) during all test phases, achieving the required precision. Testing under additional operating conditions was conducted to approximate a real-world well control scenario, in which constant casing pressure is maintained while ramping the pumps, and constant standpipe pressure is maintained while circulating out the kick (i.e. first circulation of driller's method of well control). The maximum observed deviation from the control value was 2 bar (29 psi), again meeting the required control precision. Novel/Additive Information These tests were observed, validated, and approved by DNV. The technology was introduced to the field in July 2018.

The objective of our participation in the Advanced Intelligent Systems for Sustainable Development Conference is to present our approach to manage merchandise transport in urban area, because Merchandise transport is one of the key factors of economic and social development, which requires intelligent management based on new information and communication technologies. We conducted this research within the framework of a research subject which concerns “Agent-based merchandise management and real-time decision support systems”. This research subject is based on the convergence of two axes: - Exploiting the potential of distributed artificial intelligence with intelligent multi-agent systems. - The aggregation of supplier and customer databases from an urban area into a decision support system. In this context that this article fits, since it proposes an approach making it possible to model the phenomenon of transport of goods based on agents, which will allow the interrogation of supplier information systems and feed the distributed database of the decision support system. This system through the “Anytime” algorithm will generate the appropriate times to transport the goods, the shortest route to reach the customer and the recommended delivery time to avoid peak traffic hours.

A Web-based real-time decision support system, connecting nine plants to a central information server, was implemented at a large oil and gas facility information centre in the Middle East. The case study presented shows how a real-time decision support system improved profitability. The implementation included a full well accounting package, allowing operators, engineers, petroleum engineers, and accountants to direct production and well properties, access test separator results, and reconcile production with the individual well settings. Qatar Petroleum chose Matrikon's ProcessNet as their Web-based decision support system, as it allowed them to retain their existing and proven business processes while enabling these processes through open connectivity, accessibility, and easy usability. By sharing and distributing information between the business processes and providing this information in single views, efficiency was greatly improved. Introduction Decisions at any corporation are made at a level which is usually applicable, but sometimes not pertinent, to the problem at hand. This situation comes about when all the information is not available to the key decision makers. An example is that of an operator, who might adjust process parameters beyond normal operation limits to address an issue caused upstream by changed feed-stock properties. This might put the product off-spec, whereas the feed-stock was purposely changed elsewhere to improve product quality. This illustrates the need for access to applicable information at every level in the plant. The operator should be able to view the feed-stock properties in the control room, and production staff should be able to analyse process conditions based on feed-stock properties to prevent future upsets. Whether made at the correct level or not, both long-term and short-term decisions are based on available information "processed" through experience or by analysis. Decisions based on experience are in danger of being biased or conservative, while decisions made by analysis could be misguided due to bad quality of data. An objective, fast, and reliable decision-making process requires timely and quality data, distributed to the correct levels in the corporation. The core technology implemented for the needed decision support system should allow the corporation to keep existing information- gathering infrastructure (i.e., process data in various forms, real-time and historian-based) and the long-time proven business processes (i.e., accounting data), while providing access to this information to the entire corporation, if desired. The barrier need no longer exist between plant process data, sales, supply chain, accounting, and management data. The project included configuration of many different and consolidated views, often comprised of Key Performance Indicators (KPIs) specific to the user's needs and job functions. Enabled with secured Web access, engineers can review the plant's performance while away from the site. At the same time, this engineer can query the maintenance database to check the last time a compressor was serviced, and correlate that to the current run-time of the compressor and its current power consumption. Discussion The following is a brief discussion of the base technology, followed by the details of the specific deployment at Qatar Petroleum, and how the project improved the decision-making processes on site.

Risk analysis of well blowout scenarios during managed pressure drilling operation