Efficient Online Log Parsing with Log Punctuations Signature

Logs, recording the system runtime information, are frequently used to ensure software system reliability. As the first and foremost step of typical log analysis, many data-driven methods have been proposed for automated log parsing. Most existing log parsers work offline, requiring a time-consuming training progress and retraining as the system upgrades. Meanwhile, the state of the art online log parsers are tree-based, which still have defects in robustness and efficiency. To overcome such limitations, we abandon the tree structure and propose a hash-like method. In this paper, we propose LogPunk, an efficient online log parsing method. The core of LogPunk is a novel log signature method based on log punctuations and length features. According to the signature, we can quickly find a small set of candidate templates. Further, the most suitable template is returned by traversing the candidate set with our log similarity function. We evaluated LogPunk on 16 public datasets from the LogHub comparing with five other log parsers. LogPunk achieves the best parsing accuracy of 91.9%. Evaluation results also demonstrate its superiority in terms of robustness and efficiency.

Using rock physics models to validate rock composition from multimineral log analysis

Multimineral log analysis is a quantitative formation evaluation tool for geological and petrophysical reservoir characterization. Rock composition can be estimated by solving equations that relate log measurements to the petrophysical endpoints of minerals and fluids. Due to errors in log data and uncertainties in petrophysical endpoints of constituents, we propose using effective medium models from rock physics as additional independent information to validate or constrain the results. In this paper, we examine the Voigt-Reuss (VR) bound model, self-consistent approximation (SCA), and differential effective medium (DEM). The VR bound model provides the first-order quality control of multimineral results. We first show a conventional carbonate reservoir study with intervals where the predicted effective medium models from multimineral results are inconsistent with the measured elastic properties. We use the VR bound model as an inequality constraint in multimineral analysis for plausible alternative solutions. SCA and DEM models provide good estimates in low porosity intervals and imply geological information for the porous intervals. Then, we show a field case of the Bakken and Three Forks formations. A linear interpolation of the VR bound model helps validate multimineral results and approximate the elastic moduli of clay. There are two major advantages to use our new method (a) rock physics effective medium models provide independent quality control of petrophysical multimineral results, and (b) multimineral information leads to realistic rock physics models.