---

An excavation damage zone (EDZ) can be defined as a rock zone where the rock properties and conditions have been changed due to the processes related to an excavation. This zone affects the behavior of rock mass surrounding the construction that reduces the stability and safety factor and increase probability of failure of the structure. This paper presents an approach to build a model for the identification and classification of the EDZ. The Support vector machine (SVM) is a new machine learning method based on statistical learning theory, which can solve the classification problem with small sampling, non-linearity and high dimension. However, the practicability of the SVM is influenced by the difficulty of selecting appropriate SVM parameters. In this study, the proposed hybrid Harmony search (HS) with the SVM was applied for identification and classification of damaged zone, in which HS was used to determine the optimized free parameters of the SVM. For identification and classification of the EDZ, based upon the modulus of the deformation modulus and using the hybrid of HS with the SVM a model for the identification and classification of the EDZ was built. To illustrate the capability of the HS-SVM model defined, field data from a test gallery of the Gotvand dam, Iran were used. The results obtained indicate that the HS-SVM model can be used successfully for identification and classification of damaged zone around underground spaces.

---

The development of an excavation damaged zone (EDZ) around an underground excavation can change the physical, mechanical and hydraulic behaviors of the rock mass near an underground space. This might result in endangering safety, achievement of costs and excavation planed. This paper presents an approach to build a prediction model for the assessment of EDZ, based upon rock mass characteristics changed. Rock engineering systems (RES) was used as an appropriate method for choosing the best parameter that expresses the occurrence of EDZ. Modulus of deformation with the highest weight in the system was selected as the most effective changed parameter. The adaptive network-based fuzzy inference system (ANFIS) with modulus of deformation as input was used to build a prediction model for the assessment of EDZ. Three ANFIS models were implemented, grid partitioning (GP), subtractive clustering method (SCM) and fuzzy c-means clustering method (FCM). A comparison was made between these three models and the results show the superiority of the ANFIS-SCM model. Furthermore, a case study in a test gallery of the Gotvand dam, Iran was carried out to illustrate the capability of the ANFIS model defined.