The technical solution to reduce the cost of eliminating the seizure of the drill string in the well

The analysis of the nonproductive time when drilling wells is conducted in the paper. it is established that the most of it is associated with the accidents and complications, with the main share (60%)-seizures. The statistical analysis of the reasons for the occurrence of seizures and the effectiveness of methods for their elimination is presented. A drill string disconnector (RBC) developed at the Tyumen Industrial University is proposed for unscrewing drill pipes and freeing them from trapped pipes. Keywords: well; drill pipes; accidents; seizure; drilling tool; drill string break.

Parameter substantiation of supra bit jet pump for productive formation opening

The purpose of the study is to develop a supra bit jet pump taking into account the unsteadiness of low-speed drilling for crushing the cuttings injected from the annular space under productive formation opening. The article proposes a device for drill string bottom assembly intended for the initial opening of the productive formation. The device includes a supra bit jet pump and a colmatator. The jet pump creates an additional circulation loop of the drilling fluid above the well bottom, crushes the cuttings injected from the annular space in the mixing chamber and delivers it to the colmatator. An additional circulation loop above the well bottom creates a local drawdown of the formation while maintaining the hydrostatic pressure in the well. Crushing of cuttings in the mixing chamber of the jet pump occurs due to the creation of cross flows in the jet pump. The cross flows are provided due to the angular and eccentric displacement of the working nozzle of the jet pump relative to the mixing chamber. The colmatator creates an impermeable screen on the borehole wall for temporary isolation of the productive formation under initial opening. The conducted study allowed the authors to propose head characteristics of the jet pump taking into account the angular, eccentric displacement of the working nozzle. The head characteristic of the jet pump has been developed for the unsteady operation of the jet pump in the drill string bottom assembly. The head characteristics take into account the roughness of the flow path of the jet pump. Using the head characteristics, the permissible displacements of the working nozzle of the jet pump have been determined. Recommendations for the design of jet pumps for drill string bottom assemblies are proposed.

Seismic-while-drilling by drill-bit source and large-aperture ocean-bottom array

Seismic while drilling (SWD) by drill-bit source has been successfully used in the past decades and is proven using variable configurations in onshore applications. The method creates a reverse vertical seismic profile (RVSP) dataset from surface sensors deployed as arrays in the proximity of the monitored wells. The typical application makes use of rig-pilot reference (pilot) sensors at the top of the drill-string and also downhole. This approach provides while-drilling checkshots as well as multioffset RVSP for 2-D and 3-D imaging around the well and prediction ahead of the bit. For logistical (sensor deployment) and cost (rig time related to technical installation) reasons the conventional drill-bit SWD application is typically much easier onshore than offshore. We present a novel approach that uses a network of passive-monitoring sea bottom nodes pre-deployed for microseismic monitoring to simultaneously and effectively record offshore SWD data. We study the results of a pilot test where we passively monitored the drilling of an appraisal well at the Wisting discovery in the Barents Sea with an ocean-bottom cable deployed temporarily around the drilling rig. The continuous passive recording of vibration signals emitted during the drilling of the well provides the SWD data set, which is treated as a reverse vertical seismic profile. The study is performed without rig-pilot signal. The results are compared with legacy data and demonstrate the effectiveness of the approach and point to future applications for real-time monitoring of the drilling progress, both in terms of geosteering the drill bit and predicting formation properties ahead of the bit by reflection imaging.

Machine Learning Microservice for Identification of Accident Predecessors

Drilling accidents prediction is the important task in well construction. Drilling support software allows observing the drilling parameters for multiple wells at the same time and artificial intelligence helps detecting the drilling accident predecessor ahead the emergency situation. We present machine learning (ML) algorithm for prediction of such accidents as stuck, mud loss, fluid show, washout, break of drill string and shale collar. The model for forecasting the drilling accidents is based on the "Bag-of-features" approach, which implies the use of distributions of the directly recorded data as the main features. Bag-of-features implies the labeling of small parts of data by the particular symbol, named codeword. Building histograms of symbols for the data segment, one could use the histogram as an input for the machine learning algorithm. Fragments of real-time mud log data were used to create the model. We define more than 1000 drilling accident predecessors for more than 60 real accidents and about 2500 normal drilling cases as a training set for ML model. The developed model analyzes real-time mud log data and calculates the probability of accident. The result is presented as a probability curve for each type of accident; if the critical probability value is exceeded, the user is notified of the risk of an accident. The Bag-of-features model shows high performance by validation both on historical data and in real time. The prediction quality does not vary field to field and could be used in different fields without additional training of the ML model. The software utilizing the ML model has microservice architecture and is integrated with the WITSML data server. It is capable of real-time accidents forecasting without human intervention. As a result, the system notifies the user in all cases when the situation in the well becomes similar to the pre-accident one, and the engineer has enough time to take the necessary actions to prevent an accident.

Field Application of Reaming-While-Drilling Technology in the Super Deep Composite Anhydrite-Salt Layers of Kuche Mountain Front in Tarim Oilfield

The implementation of drilling technique for multiple lithology interbeds and high-pressure anhydrite-salt in the complex Mountain Front area has been completed. The plastic creep of the anhydrite-salt layers, the losses of the low-pressure sandstone, the overflow of the high-pressure salt-water, the narrow mud density window and frequent pipe-stuck occurrence are significant issues, which trigger significant engineering challenges downhole. This study presents the application of the reaming-while-drilling (RWD) technology which has led to minimize the downhole non-productive time (NPT) and achieve successful results. The RWD technique was applied in the composite anhydrite-salt formation of the Kumugeliemu group. Through optimized combination of the RWD tools, bits, reaming blades, and the mechanical analysis the drill string with shock-absorbing design and hydraulics optimization to guarantee the bit and the reamer blades have the proper pressure drop, hydraulic horsepower and flow-field distribution, the RWD was used with the vertical seeking tool drilling technology, resulting in minimum vibration and/or stick-slip, and achieving the expected rate of penetration (ROP) as well as target inclination. It improved the operation efficiency significantly while avoiding the downhole complexities at the same time. Since the geological structure of the offset well Keshen X (no RWD) is similar to Keshen XX (RWD technology was applied), a comparison between the two wells was performed. The reaming meterage in the composite anhydrite-salt layers in Keshen XX was 791 m, spending 15 days, average ROP is 3.73 m/hr. There was no overflew or loss during the drilling. It was smooth, no pipe sticking when checking the reaming effect during the wiper trip and the tripping out. On the other hand, Keshen X spent 29 days with average ROP of 1.35 m/hr to drill the 449 m composite anhydrite-salt rock. Moreover, it was difficult to trip in and trip out during the drilling, and the pipe sticking happened frequently, back-reaming frequently as well. There were losses during both the drilling and the casing running. Due to the unsmooth wellbore, this well increased additional 3 runs of reaming after drilling operation and 4 clean-out runs. 13 days later after the reaming operation, the anhydrite-salt rock creep was checked and found that the hole was still smooth, no pipe sticking existing. Hence, RWD technology has accomplished both goals of preventing the downhole complexities and speeding up drilling. The novel RWD technology can be well illustrated by presenting all the details of its application in salt-base formations.

A Real-Time Friction Prediction Model for in Service Drill String Based on Machine Learning Methods Coupling with Mechanical Mechanism Analysis

With highly deviated wells and horizontal wells are widely used in the oil industry. The large slope well sections and long horizontal well sections will lead to a sharp increase of the drill string torque and friction, which may reduce the drilling efficiency, and even lead to accidents. Therefore, real-time and accurate analysis of drill string’s torque and friction is an urgent problem facing by the modern drilling technology. The paper established a real-time friction prediction model that combines machine learning methods with drill string mechanical mechanism analysis model. Based on 84000 sets of field monitoring data obtained on-site, a regular data training set for weight on bit (WOB) and torque prediction was constructed with 23 types of time-series related parameters and 10 types of timing independent parameters. Relationships between time-series related parameters and timing independent parameters with the weight on bit and torque were trained to utilize long and short-term memory (LSTM) neural network and muti-layer back propagation (BP) network respectively. The new developed LSTM-BP neural network achieves high-precision prediction results of WOB and torque with a relative error of less than 14%. Based on derived WOB and torque prediction results, a theoretical mechanical analysis model of the entire drill string was adopted in this paper to develop the quantitative relation between WOB and torque with the friction coefficient of the drill string and oil casing. Suitable friction coefficients along the drill string can be finally obtained by solving the equilibrium function between predicted WOB, torque and measured hook load, rotary-table torque via an iteration algorithm. A case study was performed finally using the proposed intelligent analysis method to calculate the friction coefficients. This proposed methodology can be referenced to decrease the sticking risks and improve the drilling efficiency, which can finally increase the extension limit of horizontal wells in complex strata.

A Tool for Derivation of Real Time Lithological Information from Drill Bit Sound

Real time lithological information at the drill bit is required for some important drilling operations, such as geo-steering and casing shoe positioning. This paper presents a novel tool "Petro-phone" for recording and processing drill bit sounds, which are generated by the drill bit cutting the rock, in order to provide real time lithological information for the rock at the drill bit. A prototype and a preliminary professional version of Petro-phone have been developed and field trialed. Petro-phone is a surface tool with its acoustic sensors attached to the top drive of a drill rig at some strategical locations for maximally picking up drill bit sounds. The drill bit sounds generated at the drill bit transmit along drill string and drive shaft to reach to the acoustic sensors. Since all the parts along the drill bit sound transmission pathway are made of steel, the drill bit sounds transmit efficiently from the source (drill bit) to the sensors. Preliminary results from two field trials show that drill bit sound patterns correlate with lithologies. The results also indicate that a parameter "Apparent Power" of drill bit sounds negatively correlates with gamma log. Due to its true real time nature, Petro-phone potentially has some real time applications, such as geo-steering, casing shoes positioning. Recorded drill bit sound can also potentially be used to derive lithological information, such as lithology type.