{"created":"2023-05-15T16:29:53.011591+00:00","id":804,"links":{},"metadata":{"_buckets":{"deposit":"7de42557-9704-4c10-9c06-58d2d4a2cedf"},"_deposit":{"created_by":2,"id":"804","owners":[2],"pid":{"revision_id":0,"type":"depid","value":"804"},"status":"published"},"_oai":{"id":"oai:nagasaki-u.repo.nii.ac.jp:00000804","sets":["14:21"]},"author_link":["3714","3711","3712","3713"],"item_2_biblio_info_6":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2020-04-18","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"9","bibliographicVolumeNumber":"13","bibliographic_titles":[{"bibliographic_title":"Arabian Journal of Geosciences"}]}]},"item_2_description_4":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"Effective selection of tunnel support patterns is one of the key factors affecting the safety and operation cost of tunnel engineering. This study developed an artificial neural network (ANN) model for estimating tunnel support patterns ahead of tunnel face. In this respect, measure while drilling (MWD) data sets and tunnel support patterns during construction are introduced to the ANN models. The nonlinear relationship between the MWD data and the support patterns is estimated. The MWD data includes penetration rate (PR), hammer pressure (HP), rotation pressure (RP), feed pressure (FP), hammer frequency (HF), and specific energy (SE), which were collected from 97 drill holes of a high-speed railway tunnel project that is 3.88 km long in Japan. A multilayer perceptron analysis method is used based on different input sample sizes and different ANN structures. The results show that a strong correlation exists between MWD data and support patterns. It is traced that a neural network with six inputs (PR, HP, RP, FP, HF, and SE) and one hidden layer is sufficient for the estimation of the support patterns. The increase in input sample size and hidden layer node has a positive optimizing effect on the performance of the ANN. However, an input sample size more than 6000 samples and a hidden layer larger than 30 nodes do not have a significant effect on optimizing the performance of the ANN. The size of input samples of 6000 and a three-layer neural network with topology 6-30-6 were found to be optimum. The proposed ANN model is suitable for selecting support patterns in practical engineering.","subitem_description_type":"Abstract"}]},"item_2_description_63":{"attribute_name":"引用","attribute_value_mlt":[{"subitem_description":"Arabian Journal of Geosciences, 13(9), art.no.321; 2020","subitem_description_type":"Other"}]},"item_2_publisher_33":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"Springer Nature"}]},"item_2_relation_12":{"attribute_name":"DOI","attribute_value_mlt":[{"subitem_relation_type":"isVersionOf","subitem_relation_type_id":{"subitem_relation_type_id_text":"10.1007/s12517-020-05311-z","subitem_relation_type_select":"DOI"}}]},"item_2_rights_13":{"attribute_name":"権利","attribute_value_mlt":[{"subitem_rights":"c 2020, Saudi Society for Geosciences. This is a post-peer-review, pre-copyedit version of an article published in Arabian Journal of Geosciences. The final authenticated version is available online at: http://dx.doi.org/10.1007/s12517-020-05311-z"}]},"item_2_source_id_7":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"18667511","subitem_source_identifier_type":"ISSN"}]},"item_2_source_id_8":{"attribute_name":"EISSN","attribute_value_mlt":[{"subitem_source_identifier":"18667538","subitem_source_identifier_type":"ISSN"}]},"item_2_version_type_16":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_ab4af688f83e57aa","subitem_version_type":"AM"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Liu, Jiankang"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Jiang, Yujing"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Ishizu, Sodai"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Sakaguchi, Osamu"}],"nameIdentifiers":[{}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2021-04-18"}],"displaytype":"detail","filename":"AJG13_321.pdf","filesize":[{"value":"823.4 kB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"AJG13_321.pdf","url":"https://nagasaki-u.repo.nii.ac.jp/record/804/files/AJG13_321.pdf"},"version_id":"1110c1a1-48e5-4a91-96cf-8c7f11cf11ed"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"Artificial neural network","subitem_subject_scheme":"Other"},{"subitem_subject":"Measure while drilling data","subitem_subject_scheme":"Other"},{"subitem_subject":"Network structure","subitem_subject_scheme":"Other"},{"subitem_subject":"Tunnel support pattern","subitem_subject_scheme":"Other"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"journal article","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"Estimation of tunnel support pattern selection using artificial neural network","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Estimation of tunnel support pattern selection using artificial neural network"}]},"item_type_id":"2","owner":"2","path":["21"],"pubdate":{"attribute_name":"公開日","attribute_value":"2020-12-18"},"publish_date":"2020-12-18","publish_status":"0","recid":"804","relation_version_is_last":true,"title":["Estimation of tunnel support pattern selection using artificial neural network"],"weko_creator_id":"2","weko_shared_id":2},"updated":"2023-05-15T23:00:49.510239+00:00"}