A New Approach to Predict Bit Life Based on Tooth or Bearing Failures

This paper presents a new methodology to predict the wear for three-cone bits under varying operating conditions. In this approach, six variables (weight on bit, rotary speed, pump rate, formation hardness, bit type, and torque) were studied over a range of values. A simulator was used to generate drlling data to eliminate arrors coherent to field measurements. The data generated was used to establish the relationship between complex patterns. A three-layer artificial neural network was designed and trained with measured data. This method incorporates computational intelligence to define the relationship between the variables. Further, it can be used to estimate the rate of penetration and formation characteristics. The new model was successful in predicting the condition of the bit. In this study, the value of 0.997 was obtained by the model as the correlation coefficient between the predicted and measured bearing wear and tooth wear values. The validity of the model was demonstrated with data from an existing field. Introduction There are numerous technological advances made in the design and manufacture of drilling bits. The demand to drill faster and physically for a longer period is the driving force behind these developments. Consequently, the trip times and the time spent to drill a well are reduced. This in turn yields a cost effective drilling operation. The need to understand the bit behavior has been long recognizedl-3. Several investigators conducted research to estimate the bit condition based on operational parameters and measured data from offset wells4-9.The models developed are based on assumptions that limit their applicability. Neural Networks. Recently, neural networks successfully applied in different areas of petroleum engineeringlO. The capability to ident.@ complex relationships is well suited to solve problems inherent to oil and natural gas operations. When sufllcient data exists, the use of neural networks are demonstrated in several areas such as multi-phase pipe flow’“12, reservoir characterization13”4, production15’16, and drilling17’18. Especially the drilling operation provides a unique challenge due to..the number of_vmjables involved. These parameters range from unknown formation characteristics and down hole conditions to surface operating conditions. A neural network to predict the rate of penetration values at a well based on recorded data was presented earlier18. In this study, a new neural network was designed and used to predict successfully the bit wear and life. Approach Anew methodolo~ is introduced to predict the bit tooth and bit bearing wear while drilling. In this study, a neural network model was selected to investigate a complex drilling problem. The study consists of simulated and field measured data sets. Approximately 8000 set of measurements were recorded using the rig floor simulator available in the departmental facilities. The use of simulated data provided additional information such as bit tooth and bearing wear that were not recorded in the field during the drilling operation. The bit condition in the field is determined only after it is pulled. The data recorded using the rig floor simulator consisted of bit tooth and bearing wear values as a function of time. The range of data used in this study are given in Table 1 where the formation drillability varied between 30 and 75 with smaller values representing harder formations. Similarly, the formation abrasiveness values represent an increasing abrasiveness from one to eight. The wellbore con.tlgurat.ionsand other operational parameters were kept constant during rig floor simulator runs. Several neural networks were developed to predict the bit tooth and bearing wear values. All networks used a typical three-layer feed-forward back propagation similar to Figure 1. The neural network models used in this study were consisted of 80 hidden neurons, nine or ten input parameters, and one or two output parameters. First and second neural networks were designed to predict bit tooth wear and bit bearing wear, respec-