Development of an Expert System for Solids Control in Drilling Fluids

Expert system has the least focus on requirement engineering. In facts, requirement engineering is important to get all the requirements needed for an expert system. If the requirements do not meet the clients' needs, the expert system is considered fail although it works perfectly. Currently, there are a lot of studies proposing and describing the development of expert systems. However, they are focusing in a specific and narrow domain of problems. Also, the major concern of most researchers is the design issues of the expert system. Therefore, we emphasize on the very first step of success expert system development - requirement engineering. Hence, we are focusing in the requirement engineering techniques in order to present the most practical way to facilitate requirement engineering processes. In this paper, we analyze expert system attributes, requirement engineering processes in expert system developments and the possible techniques that can be applied to expert system developments. Next, we propose the most appropriate techniques for the expert system developments based on the analysis. From this paper, a set of techniques for expert system development will be provided.

Decision making to optimize the drilling operation is based on a variety of factors, among them real-time interpretation of drilled lithology. Since logging while drilling (LWD) tools are placed some meters above the bit, mechanical drilling parameters are the earliest indicators, although difficult to interpret accurately. This paper presents a novel deep learning methodology using mechanical drilling parameters for lithology classification. A cascade of multilayered perceptrons (MLPs) are trained on historical data from wells on a field operated by Equinor. Rather than an end-to-end approach, the drilling parameters are utilized to estimate LWD sensor readings in an intermediate step using the first MLPs. This allows continuous updates of the models during operation using delayed LWD data. The second MLP takes the virtual LWD estimates as input to predict currently drilled lithology, similar to manual expert interpretation of logs. This configuration takes into account case dependent (mud, BHA, wellbore geometry) and time varying (bit-wear, wellbore friction) relationships between drilling parameters and LWD readings, while assuming a constant rule when utilizing LWD data to classify lithology. Upon completion of training and validation, the system is tested on a separate, unseen wellbore, for which results are presented. Visualizations for true lithology alongside the estimates are given, along with confusion matrices and model accuracy. The system achieves high accuracy on the test set and presents low confusion between classes, meaning that it distinguishes well between the lithologies present in the wellbore. It can be seen that the borders between successive layers of lithology are detected rapidly, which is crucial seen from an optimization standpoint, so the driller may adjust accordingly immediately. It shows promise as an advisory system, capable of accurately classifying currently drilled lithology by continuously adapting to changing downhole conditions. Although we cannot expect perfect estimates of lithology purely based on drilling parameters, we can obtain a preliminary map of the subsurface this way. This novel configuration gives a real-time interpretation of the currently drilled lithology, allowing the driller to take proper actions to optimize the drilling operation in terms of rate of penetration (ROP) and best practices for different lithologies.

Expert-system technology has emerged from beneath the umbrella of Artificial Intelligence and into the mainstream of engineering problem solving. There already are several notable examples of the application of this state-of-the-art technology in the petroleum industry. Clearly, expert systems that run efficiently on standard personal computers are particularly of value. A new expert-system generator that overcomes the speed, memory and mass-storage limitations of XT/AT-class personal computers is presented in this paper. The shell is optimized for the specific characteristics of the target user, knowledge expert and computer. Expert systems developed using this shell currently are being used by our technical personnel for drilling fluid and related applications.

Background The authors study the development of decision support system (DSS) for designing the bottom-hole assembly (BHA) while drilling, as well as the development of software that implements the DSS. DSS includes expert system, knowledge base, analytics and modeling subsystem, database of drilling equipment. The analytics and modeling subsystems contain algorithms for drilling calculation of the optimal BHA parameters in accordance with the requirements for the well profile, rate of penetration and reduction of sticking danger. The authors discuss how to use the developed expert system as part of an automated control system for directional well drilling. The studied drilling equipment consists of: drill bits, calibrators, downhole screw motors, drilling jar, heavy-weight drill pipes and heavy-wall drill pipes. Analyzed the main parameters of drilling equipment affect sticking danger, rate of penetration and well trajectory. The developed database structure of drilling equipment allows you to calculate the above parameters. The result of the work of the decision-making software is a report defining the types and sequence of installation of the necessary downhole drilling equipment. Aims and Objectives For DSS development for the BHA designing while drilling is necessary to develop an expert system, a knowledge base, analysis and modeling subsystem, a database of drilling equipment to implement this DSS as a part of an automated control system for directional well drilling. Results The authors developed an ontological model for describing and choosing effective BHA design by the Protege software based on evaluation and analysis of the main attributes of BHA selection experience. The authors also developed the drilling equipment database structure for BHA equipment selection based on deductive inference mechanism for decision rules of the knowledge base.

The application of an expert system (expert system) which is very useful for the wider community is certainly very much needed by society today. Apart from that, this development also supports various human activities. Expert systems are also able to make recommendations for a series of user actions. The aim of this research is to determine the development of expert systems in management information systems. The research method used in this research is a descriptive research method with theoretical studies, namely a method that discusses several possibilities for solving actual problems by collecting data, compiling or classifying them, analyzing and interpreting them with existing theories and comparing them from literature sources. The research results show the development of expert systems in management information systems, namely knowledge bases, inference engines, and user interfaces. It can be concluded that expert systems help work and technological progress more quickly and the decision-making process is based on existing information and facts. Expert systems have also been used in various fields, from medical, legal, to financial. In developing an expert system, it is necessary to increase the level of knowledge related to the latest technology and information. So you can utilize modern technology to complete work more effectively and efficiently.

The requirements for corrosion expert systems have never been clearly stated, though many expert system developers must have had a “typical” user in mind, when designing their application. Reviewing some of the developed systems has shown that there exist quite some different approaches. In this paper, some general guidelines will be presented which pertain both to the development of expert systems in general, as well as to the development of expert systems for corrosion, in particular. Most of these guidelines stem from experience with the development of a large-scale expert system for materials selection and corrosion analysis, PRIME. The following topics will be discussed: concepts that affect design and construction, architectural issues, the selection of requisite expert system components in conjunction with user requirements, design issues affected by task type and organizational constraints.

This paper considers the possible enhancement of the capabilities of an expert system tool. Most of the commercial tools currently available are not particularly suitable for developing expert systems that involve routine design calculations. To overcome this drawback for engineering applications, numerical computations may be carried out by conventional computer programs which can be linked to an expert system tool through its external program interface. This type of expert systems is called a "hybrid" or "coupled" expert system. Practicing engineers will, sooner or later, face the need to use hybrid expert systems. This paper presents a case study which shows how the capabilities of a commercial expert system tool can be enhanced by integrating it with a conventional computer program. The hybrid expert system developed by the authors for illustration purpose can be used for the analysis of plane steel trusses and the evaluation of member design forces. It utilizes an in-house program called “Manager” to integrate two commercial software packages: an expert system tool called KES and a structural analysis package named PFRAME. The capabilities of the hybrid system appear to exceed those of the individual software packages. Key words: knowledge based expert systems, expert system building tools, hybrid expert systems, structural analysis, structural design.

Rate of penetration (ROP) has been a key indicator for drilling efficiency. Increasing ROP can lead to significant operational-time and cost savings in drilling. ROP can be estimated using the physics-based and data-driven models. The physics-based model, although it is derived from drilling physical principles, involves empirical coefficients and functional constrains for fitting that often lead to poor results. Recently, data-driven approach that utilize machine learning to analyze and learn patterns purely from the data could be use to overcome the drawback of the physics-based models. In this paper, we combine the insight from two physics-based models to determine the features that are used in the data-driven models. We rank the input features using adaptive boosting algorithm based on the input parameters in the Bingham's and Hareland and Rampersad's models. The results demonstrate that WOB, RPM, and rock strength have more influence on the ROP prediction compared to other drilling parameters in these two models. This outcome sets the base data-driven ROP model used in this study. Furthermore, ranking features using more drilling parameters are investigated, which inferring that flowrate, standpipe pressure, and torque also contribute on the ROP prediction. We include these new parameters, in addition to WOB, RPM, and rock strength, to develop an extended data-driven ROP model from the base model. We examine the base and extended models to estimate ROP using a dataset of a well drilled through a shale formation in North America. Statistical performance evaluation criteria including root-mean-square error and cross-correlation plots between the actual and estimated ROP are employed to evaluate the prediction accuracy and robustness, respectively. The results show good agreement between the actual and predicted ROP for both the base and extended models.

Expert system is made to transfer the expert knowledge into the system, so it hopefully can give solution to problem.“Expert system for diagnosis of infection TBC lung disease” is an alternative for the various expert system that can be used to overcome the problem. The aim of designing expert system is for diagnosis of infection TBC lung disease, should that users can diagnose towards this illnes based on symptoms put into this system. Development of expert system uses knowledge base stored in database using Paradox, rule based with forward chaining method.The result of consultation with the system indicate that this system can determine disease and suggestion based on symptoms inputed by user. Keyword : Expert System, Forward Chaining, Knowledge Base

The development of digital infrastructure in the oil and gas industry has led to the proliferation of advisory systems that provide recommendations in real time to mitigate a variety of risks. To deliver their full potential, these advisory systems need to coexist on a common platform across vendors and disciplines (e.g., hydraulic and pressure management, directional drilling, mechanical integrity of the drilling system, and vibration mitigation). Despite the rise of closed-loop automation, however, there is a lack for a scalable tool or platform that can orchestrate multiple digital advisors to coordinate sometimes-conflicting recommendations. Whilst industry players are well versed about determining recommendations, the conventional approach for this problem has been rule- and experience-based. That methodology is not scalable nor transferable. Through this paper we present a framework that structures the process of determining a unified recommendation in real time by integrating the advice from multiple independent digital advisors. The novelty of the approach resides in its ability to structure the process of determining safe and robust recommendations using a scalable and computationally inexpensive algorithm that can run on standard engineering computers at the rig site and virtual-remote-operations centers. INTRODUCTION Digital transformation has become an indispensable and significant part in drilling engineering. The digital transformation sweeping through the industry has led to the development of a variety of applications and algorithms to help drive drilling efficiencies, offset-well learning, and automated detection and interpretation of drilling events and dysfunctions. However, this global push has led to multiple challenges, discussed below. Different teams, divisions, entities, and companies have developed differing solutions that target similar or complementary problems, and the differing solutions may not be compatible or combinable. These solutions can rely on different methodologies (e.g., data-based, physics-based, or hybrid) and can have different technology readiness levels. Some solutions can have conflicting objectives that need to be harmonized to provide a consistent set of actions, such as advisory drilling parameters for automating operations. Typical examples are rate of penetration (ROP) that is typically to be maximized while not exceeding a technical threshold from a hole cleaning point of view, or drilling parameter targets and limits from directional, mechanical, or hydraulic objectives that can conflict as they seek to optimize different aspects of the drilling process. For instance, a vibration advisor (a case study is shown in (Greenwood (2016a,b))) can recommend increasing the rotations per minute (RPM) of the drill pipe and reducing the weight-on-bit (WOB) if a stick/slip vibration occurs. However, from a hole cleaning and pressure management standpoint it may not be advisable to increase the RPM because doing so might exceed the equivalent circulating density (ECD) limit. Similarly, to mitigate a bit bounce or whirl vibration, the advisor can recommend decreasing the RPM, whereas from a hole cleaning point of view the RPM can be recommended to be increased to achieve the target ROP under current average conditions. During such conflicting scenarios it can be difficult for a user or an automation platform to consistently determine the best recommendation from a drilling efficiency standpoint. There may not be a cohesive framework that encompasses the above challenges and the other factors that go into the well construction decision process. Also, there may not exist a common platform where independent advisory systems from different vendors and disciplines can coexist and an open composite advice produced in real time by integrating their recommendations.

Ameliorating the Pregnant Man problem: a verification tool for personal computer based expert systems

An optimized design of a matrix treatment involves fluid selection and acidizing simulations to predict the outcome of the treatment; Many matrix acidizing treatment designs and fluid selections have been successfully accomplished by utilizing expert system technology. However, none of these present a complete and optimized result (i.e., by utilizing the output of the expert system to predict the acidizing outcome using an acidizing numerical simulator). In the meantime, several acidizing computer simulation studies have been conducted separately. This paper presents a study which integrates the treatment design, particularly the fluid selection process, and acidizing simulation for sandstone formations. Required parameters for sandstone acidizing such as acid type, concentration, volume, and injection rate/pressure are first selected using an expert system. The output from the expert system is further used for the input to an acidizing numerical simulator (UTACID). A new sandstone acidizing reaction model, appropriate for a high-temperature environment, and anisotropic medium have been implemented into UTACID to enhance the performance of the simulator. The expert system and the simulator have been integrated to provide an optimization tool for sandstone acidizing treatment design and simulation.

This article discusses the selection of the domain for a knowledge-based expert system for a corporate application. The selection of the domain is a critical task in an expert system development. At the start of a project looking into the development of an expert system, the knowledge engineering project team must investigate one or several possible expert system domains. They must decide whether the selected application(s) are best suited to solution by present expert system technology, or if there might be a better way (or, possibly, no way) to attack the problems. If there are several possibilities, the team must also rank the potential applications and select the best available. To evaluate the potential of possible application domains, it has proved very useful to have a set of desired attributes for good expert domain. This article presents such a set of attributes. The attribute set was developed as part of a major expert system development project at GTE Laboratories. It was used recurrently (and modified and expanded continually) throughout an extensive application domain evaluation and selection process.

Depending on the specific expert system application, individuals and organizations involved in the expert system development and marketing chain may unwittingly surrender themselves to high-risk exposure to tort liability legal actions, in the event that an innocent third party should suffer physical harm. The degree of risk turns on whether the expert system is viewed by the court as a 'product' or as a 'service'. The author examines the implication of this determination in two areas of tort, product liability and negligence, and then outlines the issues surrounding the 'product-service continuum' as applied specifically to the expert system development and marketing environment. Finally, the author presents proactive measures that expert system developers and vendors should consider in order to minimize exposure to risk.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Knowledge-based expert system for optimal reactive power control in distribution system