Changes
On August 4, 2023 at 9:31:20 AM UTC, admin:
-
No fields were updated. See the metadata diff for more details.
f | 1 | { | f | 1 | { |
2 | "author": "Schlagenhauf, Tobias", | 2 | "author": "Schlagenhauf, Tobias", | ||
3 | "author_email": "", | 3 | "author_email": "", | ||
4 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | 4 | "creator_user_id": "17755db4-395a-4b3b-ac09-e8e3484ca700", | ||
5 | "doi": "10.35097/1398", | 5 | "doi": "10.35097/1398", | ||
6 | "doi_date_published": "2023", | 6 | "doi_date_published": "2023", | ||
7 | "doi_publisher": "", | 7 | "doi_publisher": "", | ||
8 | "doi_status": "True", | 8 | "doi_status": "True", | ||
9 | "extra_authors": [ | 9 | "extra_authors": [ | ||
10 | { | 10 | { | ||
11 | "extra_author": "Wolf, Jan", | 11 | "extra_author": "Wolf, Jan", | ||
12 | "orcid": "" | 12 | "orcid": "" | ||
13 | }, | 13 | }, | ||
14 | { | 14 | { | ||
15 | "extra_author": "Puchta, Alexander", | 15 | "extra_author": "Puchta, Alexander", | ||
16 | "orcid": "" | 16 | "orcid": "" | ||
17 | } | 17 | } | ||
18 | ], | 18 | ], | ||
19 | "groups": [], | 19 | "groups": [], | ||
20 | "id": "908ac5fc-1c48-44a9-9a84-0aeb817c6de2", | 20 | "id": "908ac5fc-1c48-44a9-9a84-0aeb817c6de2", | ||
21 | "isopen": false, | 21 | "isopen": false, | ||
22 | "license_id": "CC BY 4.0 Attribution", | 22 | "license_id": "CC BY 4.0 Attribution", | ||
23 | "license_title": "CC BY 4.0 Attribution", | 23 | "license_title": "CC BY 4.0 Attribution", | ||
24 | "metadata_created": "2023-08-04T08:50:42.398629", | 24 | "metadata_created": "2023-08-04T08:50:42.398629", | ||
t | 25 | "metadata_modified": "2023-08-04T09:04:16.028293", | t | 25 | "metadata_modified": "2023-08-04T09:31:20.925171", |
26 | "name": "rdr-doi-10-35097-1398", | 26 | "name": "rdr-doi-10-35097-1398", | ||
27 | "notes": "Abstract: The dataset was recorded during milling of | 27 | "notes": "Abstract: The dataset was recorded during milling of | ||
28 | 16MnCr5. Due to artificially introduced, though realistic anoma-lies | 28 | 16MnCr5. Due to artificially introduced, though realistic anoma-lies | ||
29 | in the workpiece the dataset can be applied for anomaly detection. | 29 | in the workpiece the dataset can be applied for anomaly detection. | ||
30 | Furthermore, milling tools with two different diameters where used | 30 | Furthermore, milling tools with two different diameters where used | ||
31 | which led to a dataset eligible for transfer | 31 | which led to a dataset eligible for transfer | ||
32 | learning.\r\nTechnicalRemarks: The dataset consists of seven folders. | 32 | learning.\r\nTechnicalRemarks: The dataset consists of seven folders. | ||
33 | Each folder represents one milling run. In each milling run the depth | 33 | Each folder represents one milling run. In each milling run the depth | ||
34 | of cut was set to 3 mm. A folder contains a maximum of three json | 34 | of cut was set to 3 mm. A folder contains a maximum of three json | ||
35 | files. The number of files depends on the time needed for each run | 35 | files. The number of files depends on the time needed for each run | ||
36 | which is a function of milling tool diameter and feed rate. Files in | 36 | which is a function of milling tool diameter and feed rate. Files in | ||
37 | each folder were numerated in sequence. For example, folder | 37 | each folder were numerated in sequence. For example, folder | ||
38 | \u201crun1\u201d contains the files \u201crun1_1\u201d and | 38 | \u201crun1\u201d contains the files \u201crun1_1\u201d and | ||
39 | \u201crun1_2\u201d with the last number indicating the order in which | 39 | \u201crun1_2\u201d with the last number indicating the order in which | ||
40 | the files were generated. The frequency of recording datapoints was | 40 | the files were generated. The frequency of recording datapoints was | ||
41 | set to 500 Hz. \r\nDuring each milling run the milling tool moved | 41 | set to 500 Hz. \r\nDuring each milling run the milling tool moved | ||
42 | along the longitudinal side and then was moved back alongside the | 42 | along the longitudinal side and then was moved back alongside the | ||
43 | workpiece. This way machining started always on the same side of the | 43 | workpiece. This way machining started always on the same side of the | ||
44 | workpiece. \r\nTable 1 provides an overview of the milling runs. Run 1 | 44 | workpiece. \r\nTable 1 provides an overview of the milling runs. Run 1 | ||
45 | to 4 were performed with a HSS tool with a diameter of 10 mm. The tool | 45 | to 4 were performed with a HSS tool with a diameter of 10 mm. The tool | ||
46 | in use was an end mill (HSS-E-SPM HPC 10 mm) developed by Hoffmann | 46 | in use was an end mill (HSS-E-SPM HPC 10 mm) developed by Hoffmann | ||
47 | Group. During the first three runs with this end mill no tool breakage | 47 | Group. During the first three runs with this end mill no tool breakage | ||
48 | occurred. However, in run 4 the tool broke. Runs 5 and 6 were | 48 | occurred. However, in run 4 the tool broke. Runs 5 and 6 were | ||
49 | performed by milling with an end mill of the same tool series | 49 | performed by milling with an end mill of the same tool series | ||
50 | (HSS-E-SPM HPC 8 mm) that just differs in tool diameter. In contrast | 50 | (HSS-E-SPM HPC 8 mm) that just differs in tool diameter. In contrast | ||
51 | to this run 7 was performed by using a solid carbid tool (Solid | 51 | to this run 7 was performed by using a solid carbid tool (Solid | ||
52 | carbide roughing end mill HPC 8 mm). Cutting with SC tools provides | 52 | carbide roughing end mill HPC 8 mm). Cutting with SC tools provides | ||
53 | much higher productivity with the downside being higher tool price. In | 53 | much higher productivity with the downside being higher tool price. In | ||
54 | our case the SC end mill performed cuts with a feed rate of 1150 | 54 | our case the SC end mill performed cuts with a feed rate of 1150 | ||
55 | mm/min compared to 191 mm/min achieved by a HSS end mill of the same | 55 | mm/min compared to 191 mm/min achieved by a HSS end mill of the same | ||
56 | diameter. Tool breakages were recorded on all runs with end mills of | 56 | diameter. Tool breakages were recorded on all runs with end mills of | ||
57 | diameter 8 mm. \r\nTable 1. overview of the data folders | 57 | diameter 8 mm. \r\nTable 1. overview of the data folders | ||
58 | \r\n\r\nfolder name | number of json files | tool diameter | tool | 58 | \r\n\r\nfolder name | number of json files | tool diameter | tool | ||
59 | breakage | tool type\r\nrun 1 2 10 mm No HSS\r\nrun 2 2 10 mm No | 59 | breakage | tool type\r\nrun 1 2 10 mm No HSS\r\nrun 2 2 10 mm No | ||
60 | HSS\r\nrun 3 2 10 mm No HSS\r\nrun 4 2 10 mm Yes HSS\r\nrun 5 2 8 mm | 60 | HSS\r\nrun 3 2 10 mm No HSS\r\nrun 4 2 10 mm Yes HSS\r\nrun 5 2 8 mm | ||
61 | Yes HSS\r\nrun 6 3 8 mm Yes HSS\r\nrun 7 1 8 mm Yes SC\r\n\r\nEach | 61 | Yes HSS\r\nrun 6 3 8 mm Yes HSS\r\nrun 7 1 8 mm Yes SC\r\n\r\nEach | ||
62 | json file consists of a header and a payload. The header lists all | 62 | json file consists of a header and a payload. The header lists all | ||
63 | parameters that were recorded such as position, motor torque and motor | 63 | parameters that were recorded such as position, motor torque and motor | ||
64 | current of each of a maximum of five axes of a milling machine. | 64 | current of each of a maximum of five axes of a milling machine. | ||
65 | However, the machine used in our experiments is a 3-axis machining | 65 | However, the machine used in our experiments is a 3-axis machining | ||
66 | center which leaves the payload of 2 possible additional axes to be | 66 | center which leaves the payload of 2 possible additional axes to be | ||
67 | empty. In the payload the sequential data for each parameter can be | 67 | empty. In the payload the sequential data for each parameter can be | ||
68 | found. A list of recorded signals can be found in Table | 68 | found. A list of recorded signals can be found in Table | ||
69 | 2.\r\n\r\nTable 2. recorded signals during milling\r\n\r\nSignal index | 69 | 2.\r\n\r\nTable 2. recorded signals during milling\r\n\r\nSignal index | ||
70 | in payload | Signal name | Signal Address |Type\r\n13-18 | 70 | in payload | Signal name | Signal Address |Type\r\n13-18 | ||
71 | VelocityFeedForward VEL_FFW|1* double\r\n19-24 Power POWER|1* | 71 | VelocityFeedForward VEL_FFW|1* double\r\n19-24 Power POWER|1* | ||
72 | string\r\n25-30 CountourDeviation CONT_DEV|1* double\r\n38-43 | 72 | string\r\n25-30 CountourDeviation CONT_DEV|1* double\r\n38-43 | ||
73 | TorqueFeedForward TORQUE_FFW|1* double\r\n44-49 Encoder1Position | 73 | TorqueFeedForward TORQUE_FFW|1* double\r\n44-49 Encoder1Position | ||
74 | ENC1_POS|1* double\r\n56-61 Load LOAD|1* double\r\n68-73 Torque | 74 | ENC1_POS|1* double\r\n56-61 Load LOAD|1* double\r\n68-73 Torque | ||
75 | TORQUE|1* double\r\n68-91 Current CURRENT|1* double\r\n \r\n* 1 | 75 | TORQUE|1* double\r\n68-91 Current CURRENT|1* double\r\n \r\n* 1 | ||
76 | represents x-axis, 2 represents y-axis, 3 represents z-axis and 6 | 76 | represents x-axis, 2 represents y-axis, 3 represents z-axis and 6 | ||
77 | represents spindle-axis.\r\nNote that our milling center has 3 axis | 77 | represents spindle-axis.\r\nNote that our milling center has 3 axis | ||
78 | and therefore values for axes 4 and 5 are null.", | 78 | and therefore values for axes 4 and 5 are null.", | ||
79 | "num_resources": 0, | 79 | "num_resources": 0, | ||
80 | "num_tags": 4, | 80 | "num_tags": 4, | ||
81 | "orcid": "", | 81 | "orcid": "", | ||
82 | "organization": { | 82 | "organization": { | ||
83 | "approval_status": "approved", | 83 | "approval_status": "approved", | ||
84 | "created": "2023-01-12T13:30:23.238233", | 84 | "created": "2023-01-12T13:30:23.238233", | ||
85 | "description": "RADAR (Research Data Repository) is a | 85 | "description": "RADAR (Research Data Repository) is a | ||
86 | cross-disciplinary repository for archiving and publishing research | 86 | cross-disciplinary repository for archiving and publishing research | ||
87 | data from completed scientific studies and projects. The focus is on | 87 | data from completed scientific studies and projects. The focus is on | ||
88 | research data from subjects that do not yet have their own | 88 | research data from subjects that do not yet have their own | ||
89 | discipline-specific infrastructures for research data management. ", | 89 | discipline-specific infrastructures for research data management. ", | ||
90 | "id": "013c89a9-383c-4200-8baa-0f78bf1d91f9", | 90 | "id": "013c89a9-383c-4200-8baa-0f78bf1d91f9", | ||
91 | "image_url": "radar-logo.svg", | 91 | "image_url": "radar-logo.svg", | ||
92 | "is_organization": true, | 92 | "is_organization": true, | ||
93 | "name": "radar", | 93 | "name": "radar", | ||
94 | "state": "active", | 94 | "state": "active", | ||
95 | "title": "RADAR", | 95 | "title": "RADAR", | ||
96 | "type": "organization" | 96 | "type": "organization" | ||
97 | }, | 97 | }, | ||
98 | "owner_org": "013c89a9-383c-4200-8baa-0f78bf1d91f9", | 98 | "owner_org": "013c89a9-383c-4200-8baa-0f78bf1d91f9", | ||
99 | "private": false, | 99 | "private": false, | ||
100 | "production_year": "2022", | 100 | "production_year": "2022", | ||
101 | "publication_year": "2023", | 101 | "publication_year": "2023", | ||
102 | "publishers": [ | 102 | "publishers": [ | ||
103 | { | 103 | { | ||
104 | "publisher": "Karlsruhe Institute of Technology" | 104 | "publisher": "Karlsruhe Institute of Technology" | ||
105 | } | 105 | } | ||
106 | ], | 106 | ], | ||
107 | "relationships_as_object": [], | 107 | "relationships_as_object": [], | ||
108 | "relationships_as_subject": [], | 108 | "relationships_as_subject": [], | ||
109 | "repository_name": "RADAR (Research Data Repository)", | 109 | "repository_name": "RADAR (Research Data Repository)", | ||
110 | "resources": [], | 110 | "resources": [], | ||
111 | "services_used_list": "", | 111 | "services_used_list": "", | ||
112 | "source_metadata_created": "2023", | 112 | "source_metadata_created": "2023", | ||
113 | "source_metadata_modified": "", | 113 | "source_metadata_modified": "", | ||
114 | "state": "active", | 114 | "state": "active", | ||
115 | "subject_areas": [ | 115 | "subject_areas": [ | ||
116 | { | 116 | { | ||
117 | "subject_area_additional": "", | 117 | "subject_area_additional": "", | ||
118 | "subject_area_name": "Engineering" | 118 | "subject_area_name": "Engineering" | ||
119 | } | 119 | } | ||
120 | ], | 120 | ], | ||
121 | "tags": [ | 121 | "tags": [ | ||
122 | { | 122 | { | ||
123 | "display_name": "Anomaly Detection", | 123 | "display_name": "Anomaly Detection", | ||
124 | "id": "772b074e-4795-4f11-80b4-362b2f8a0dca", | 124 | "id": "772b074e-4795-4f11-80b4-362b2f8a0dca", | ||
125 | "name": "Anomaly Detection", | 125 | "name": "Anomaly Detection", | ||
126 | "state": "active", | 126 | "state": "active", | ||
127 | "vocabulary_id": null | 127 | "vocabulary_id": null | ||
128 | }, | 128 | }, | ||
129 | { | 129 | { | ||
130 | "display_name": "Machine Learning", | 130 | "display_name": "Machine Learning", | ||
131 | "id": "c4f3defc-ca48-45a9-9217-ce35bd3ed73c", | 131 | "id": "c4f3defc-ca48-45a9-9217-ce35bd3ed73c", | ||
132 | "name": "Machine Learning", | 132 | "name": "Machine Learning", | ||
133 | "state": "active", | 133 | "state": "active", | ||
134 | "vocabulary_id": null | 134 | "vocabulary_id": null | ||
135 | }, | 135 | }, | ||
136 | { | 136 | { | ||
137 | "display_name": "Production Science", | 137 | "display_name": "Production Science", | ||
138 | "id": "063124a6-3750-4d15-816f-3ca083bfb257", | 138 | "id": "063124a6-3750-4d15-816f-3ca083bfb257", | ||
139 | "name": "Production Science", | 139 | "name": "Production Science", | ||
140 | "state": "active", | 140 | "state": "active", | ||
141 | "vocabulary_id": null | 141 | "vocabulary_id": null | ||
142 | }, | 142 | }, | ||
143 | { | 143 | { | ||
144 | "display_name": "Transfer Learning", | 144 | "display_name": "Transfer Learning", | ||
145 | "id": "b9a857f2-561d-4153-a58c-b2ba7d7ae58f", | 145 | "id": "b9a857f2-561d-4153-a58c-b2ba7d7ae58f", | ||
146 | "name": "Transfer Learning", | 146 | "name": "Transfer Learning", | ||
147 | "state": "active", | 147 | "state": "active", | ||
148 | "vocabulary_id": null | 148 | "vocabulary_id": null | ||
149 | } | 149 | } | ||
150 | ], | 150 | ], | ||
151 | "title": "Multivariate time series dataset of milling 16mncr5 for | 151 | "title": "Multivariate time series dataset of milling 16mncr5 for | ||
152 | anomaly detection", | 152 | anomaly detection", | ||
153 | "type": "vdataset", | 153 | "type": "vdataset", | ||
154 | "url": "https://doi.org/10.35097/1398" | 154 | "url": "https://doi.org/10.35097/1398" | ||
155 | } | 155 | } |