Taking the small layer correlation as the starting point and based on the intelligent processing and interpretation of logging data, a instrumental software module is formed to solve the two major problems of massive data in multiple wells of the old area and too much individual analysis proportion in the previous conclusions. It improves the work efficiency of technicians effectively and reduces the multiplicity of solutions.
Penetrating the intelligent technology into oil and gas exploration and development, and it has become an indispensable means to solve the basic links of mature exploration areas, deepen reservoir knowledge, serve rolling exploration and efficient development.
There are 69 well data in the target block of an oilfield. The target interval contains 81-142 horizons with a layer thickness of 2m ~ 6m. Among them, there are 16 wells with incomplete sub layer division, and the horizon boundary of some wells is inaccurate. It is necessary to carry out secondary stratum division for 43 wells, recheck the horizon and fine division of the sub layers.
Working Time: ＜1hour
Consistency between artificial division and platform division: 72%~96%
Through the machine intelligent simulation of the artificial stratum correlation process and the real-time training model for the geological characteristics in different blocks, the characteristic curve and marker stratum suitable for the stratum correlation of the block are selected intelligently, and the correlation division scheme is intelligently designed for the target well. Then, through the morphological comparison of the characteristic curve, the target interval delimitation, marker stratum division and continuous stratum fine correlation and division are automatically carried out for the target well.
It can independently analyze the horizon logging characteristics in different blocks and excavate the characteristic curves and marker stratum that suitable for the block; the platform is with a wide range of application.
Strictly follow the business logic and process of artificial stratum correlation division, and build the model step by step, and then complete stratum correlation division gradually;
Processing a batch of wells concurrently and reduce 99% of working time.
In the key processes such as model training, scheme designing, marker bed dividing and continuous stratum correlating, users could control the process and result verification;
The consistency rate of intelligent division and artificial division is more than 85%.
Data Integration and Management
Visual Scheme Optimization
Automatic Identify and Divide the Stratum
Logging Characteristics Extraction and Integration
Research Result Sharing and Management
Depth correction and comprehensive visualization technology for logging curve;
Similarity measurement method for the stratum about the logging curve shape;
Curve filtering synthesis method for maximizing signal-to-noise ratio energy
Selection methods of logging curves and marker beds for variable data sets;
Reference well selection method of spatial well trajectory analysis;
The target interval delimitation method for the characteristics analysis of the marker layer in the whole well section;
Marker bed division method of stratum structure characteristics;
Continuous stratum correlation division method under the idea of sliding window and global optimization;
Multi task parallel processing can quickly complete the comparison and division of batch wells.