Automated Program Repair (APR) is a task to automatically generate patches for the buggy code. However, most research focuses on generating correct patches while ignoring the consistency between the fixed code and the original buggy code. How to conduct adaptive bug fixing and generate patches with minimal modifications have seldom been investigated. To bridge this gap, we first introduce a novel task, namely AdaPR (Adaptive Program Repair). We then propose a two-stage approach AdaPatcher (Adaptive Patch Generator) to enhance program repair while maintaining the consistency. In the first stage, we utilize a Bug Locator with self-debug learning to accurately pinpoint bug locations. In the second stage, we train a Program Modifier to ensure consistency between the post-modified fixed code and the pre-modified buggy code. The Program Modifier is enhanced with a location-aware repair learning strategy to generate patches based on identified buggy lines, a hybrid training strategy for selective reference and an adaptive preference learning to prioritize fewer changes. The experimental results show that our approach outperforms a set of baselines by a large margin, validating the effectiveness of our two-stage framework for the newly proposed AdaPR task.

Microseismic monitoring technology serves as an effective means of providing early warning signs of rockburst, a type of disaster that poses a serious threat to life safety in tunnels. Given the substantial number of signals received during monitoring, manual rock fracture signal identification is a time-consuming and effort-intensive task. Therefore, automatic and robust digitalization of manual signal identification is urgently needed. This paper introduces a novel method for identifying rock fracture signals based on waveform characteristics. This method simulates and digitalizes the manual observation of microseismic signals. We simplify the waveform identification process to three automatic steps. The proposed method is tested on data from the Jinping Tunnel and Bayu Tunnel, which were excavated by a TBM and by drilling and blasting methods, respectively. The rock fracture signal recognition accuracies are 95.64% and 93.92%, with false-negative rates of 3.99% and 4.31%, respectively. Two field cases demonstrate that the digital identification method is fully automated and practical for MS monitoring in tunnels.

Phase picking is a critical step in the analysis of microseismic data. However, there is a lack of relevant methods for S-phase picking. In this letter, we pick the P-phase and extract the data around the S-phase arrival firstly based on previous studies. Then, we propose a method called time series segmentation clustering (TSSC) which is based on the K-means algorithm to pick the S-phase. In the TSSC method, we construct a feature vector of the microseismic signal and standardize the feature vector first. Then, we modify the K-means objective function into a function of time. We subsequently obtain the S-phase arrival corresponding to the minimum value of the objective function. We tested the objective function of the TSSC method on synthetic signals and microseismic signals, and the results show that the method is reliable. This automatic picking algorithm has been used to pick 1763 S-phase arrivals from microseismic signals. In comparison with manual picking results, a statistical analysis shows that this method is feasible.