Theoretically, rate of penetration (ROP) model is the basic to drilling parameters design, ROP improvement tools selection and drill time & cost estimation. Currently, ROP modelling is mainly conducted by two approaches: equation-based approach and machine learning approach, and machine learning performs better because of the capacity in high-dimensional and non-linear process modelling. However, in deep or deviated wells, the ROP prediction accuracy of machine learning is always unsatisfied mainly because the energy loss along the wellbore and drill string is non-negligible and it's difficult to consider the effect of wellbore geometry in machine learning models by pure data-driven methods. Therefore, it's necessary to develop robust ROP modelling method for different scenarios. In the paper, the performance of several equation-based methods and machine learning methods are evaluated by data from 82 wells, the technical features and applicable scopes of different methods are analysed. A new machine learning based ROP modelling method suitable for different well path types was proposed. Integrated data processing pipeline was designed to dealing with data noises, data missing, and discrete variables. ROP effecting factors were analysed, including mechanical parameters, hydraulic parameters, bit characteristics, rock properties, wellbore geometry, etc. Several new features were created by classic drilling theories, such as downhole weight on bit (DWOB), hydraulic impact force, formation heterogeneity index, etc. to improve the efficiency of learning from data. A random forest model was trained by cross validation and hyperparameters optimization methods. Field test results shows that the model could predict the ROP in different hole sections (vertical, deviated and horizontal) and different drilling modes (sliding and rotating drilling) and the average accuracy meets the requirement of well planning. A novel data processing and feature engineering workflow was designed according the characteristics of ROP modelling in different well path types. An integrated data-driven ROP modelling and optimization software was developed, including functions of mechanical specific energy analysis, bit wear analysis and predict, 2D & 3D ROP sensitivity analysis, offset wells benchmark, ROP prediction, drilling parameters constraints analysis, cost per meter prediction, etc. and providing quantitative evidences for drilling parameters optimization, drilling tools selection and well time estimation.

There is an absence of industry-wide, globally accepted standards that provide comprehensive inspection procedures and acceptance criteria for inspection and maintenance of drilling bits, including: wear, cracking, and mechanical damage criteria for bit bodies and cutting elements. Nevertheless, bits are routinely inspected and evaluated to determine their usability for both land and offshore drilling operations. This creates significant risk for all drilling operators because the lack of clear inspection criteria can lead to the use of bits with flaws causing downhole failures. In addition, the lack of an industrywide bit inspection specification has challenged bit suppliers since the decision to use a bit with indications and damage can be subjective and the potential risk severity can be high. Industry standards like API, ISO and DS-1 for inspection of other drill stem components do exist. However, the application of these standards to bits, particularly those with matrix bodies, is inappropriate. Using acceptance criteria adopted from existing standards for other drill stem components creates significant risk by accepting minor damage and rejecting major damage without an industry accepted standard. To overcome these limitations, a technical committee consisting of operators, drilling contractors, service providers, manufacturers, and inspection companies, worked together to develop specific procedures and acceptance criteria for the inspection of bit bodies as well as cutting elements. This paper presents the procedures and acceptance criteria developed by the technical committee that address the inspection of cracks and porosity in matrix and steel bit bodies, wear and erosion of bit bodies, cracks in PDC cutters, and other damage to cutters. The information included in this paper was considered for development of the DS-1 Bit Inspection Technical Standard (BITS) to address the necessity of a globally accepted standard for the inspection of bits.

Digitalization and intelligence are attracting increasing attention in petroleum engineering. Amounts of published research indicates modern data science has been applied in almost every corner of petroleum engineering where data generates, however, mature products are few or the performance are not up to peoples’ expectations. Despite the great success in other industries (internet, transportation, and finance, etc.), the "amazing" data science algorithms seem to be challenged when "landing" in petroleum engineering. It is time to calmly analyze current situations and discuss the methodology to apply modern data science in petroleum engineering, for safety ensuring, efficiency improvement and cost saving. Based on the experiences of several data products in petroleum engineering and wide investigation of literatures, the methodology is summarized by answering some important questions: what is the difference between petroleum engineering and other industries and what are the greatest challenges for algorithms "landing"? how could we build a data product development team? why the machine learning models didn't work well in real world, which are derived by typical procedures in textbooks? are current artificial intelligent algorithms perfect and is there any limit? how could we deal with the relationship between prior knowledge and data-driven methods? what is the key point to keep data product competitive? Several specific scenarios are introduced as examples, such as ROP modelling, drilling parameters optimization, text mining of drilling reports and well production prediction, etc. where deep learning, traditional machine learning, incremental learning and natural language processing methods, etc. are used. Besides detailed discussions in the paper, conclusions are summarized as: 1) the strengths and weakness of current artificial intelligence should be viewed objectively, practical suggestions to make up the weakness are provided; 2) the combination of prior knowledge (from lab tests or expert experiences) and data-driven methods are always necessary and methods for the combination are summarized; 3) data volume and solution portability are the key points to improve data product competitiveness; 4) suggestions on how to build a multi-disciplinary R&D team and how to plan a product are provided. This paper conducts an objective analysis on challenges for modern data science applying in petroleum engineering and provides a clear methodology and specific suggestions on how to improve the success rate of R&D projects which apply data science to solve problems in petroleum engineering.

The measurement of the drilling parameters such as temperature and pressure helps mitigate drilling-related issues and optimize drilling operations on a cost-effective basis. Multiple technologies can measure these parameters; however, the current tools suffer from low bandwidth, associated high cost, and limited measurement locations near the drill bit. This reduced accuracy and transmission rate while drilling can be improved using intelligent microchip tracers and micro-memory balls. These tools can measure the temperature and pressure across an entire wellbore. The proposed tracers include a microprocessor-based circuit board equipped with sensors, a communication antenna, and a rechargeable battery, all protected from the harsh downhole environment through a robust composite material. The advanced microchip tracers and micro-memory ball technologies were tested in the field and provided innovative measurement platforms. The field tests were conducted in various environments, including oil and gas wells, deviated wells, multiple hole sizes, varied fluid densities, and different BHA (Bottom Hole Assembly) geometries. During the operation procedures, the tracers travel in the drilling strings through the drill bit and return to the surface across the annulus. The data is then exported from the tracers for a quasi-real-time analysis. The results showed high success rates, four out of six microchips were successfully retrieved, and the data was made available for immediate analysis. This paper explains the challenges faced during the logging and interpretation of the data needed to define the wellbore characteristics for efficient drilling processes. The developed time-stepping algorithm correlates the measurement timestamp with the calculated depth. Lastly, the report summarizes the highlights of the tracers in terms of density, release mechanism, and collection method.

Schlumberger, one of the world’s leading suppliers of oilfield technology, is a measurement and data-driven company that collects massive amounts of data in the course of its daily operations. These data, diverse in nature, are collected for use in various business and technical workflows. The data can be downhole, surface, post-analysis, and support functions from manufacturing, maintenance, asset management, and finance. Analysis of this Big Data has the potential to drive a step change in operational performance across multiple dimensions. However, accomplishing this step change is not easy to accomplish because often, the data are not well structured and are scattered across individual business systems that do not communicate well with each other. Most of the analysis of these scattered data occurs on a point basis, requiring the significant involvement of various experts and complex time-consuming manipulations. The results are short lived in that they cannot be tracked in real time and the effort expended is not applicable to other data sets or problems. Increasing data volumes, data diversity, and demand from engineers to record multiple new data attributes during the product or technology life cycle further limits the benefits of such a spot analytics process, with potentially severe impacts on the business due to inadequate decision support or missed opportunities. This paper presents a developmental model and change processes, challenges faced and resolution approaches leading to digital transformation, and finally, the resulting value creation through building data visualizations and comprehensible decision-making tools. Once the initial high-value data sets and visualizations are identified, automation opportunities can be exploited. These data sets become the foundation for predictive analysis and machine learning through artificial intelligence (AI) and Internet of things (IoT) to further influence product performance and development in support of customer needs.