Integrating Artificial Intelligence (AI) with the Industrial Internet of Things (IIoT) has transformed industrial processes, enhancing productivity, quality control, and operational efficiency. However, ensuring the precision and reliability of sensor-generated data remains a critical challenge due to the evolving nature of industrial processes and the limitations of conventional validation methods. Traditional rule-based and supervised learning approaches struggle to adapt to process shifts, drifts, and novel anomalies, making sensor data validation an ongoing issue. This article introduces UDAVA (Unsupervised Learning Approach using Process Mining for Sensor Data Validation in IIoT), a novel AI-driven pipeline designed to automate the identification of reference patterns in sensor data and validate subsequent production cycles by recognizing deviations from expected behaviors. UDAVA employs a multi-stage process that includes preprocessing sensor data, clustering recurring patterns, and assessing deviations. It supports semi-supervised learning by integrating manual labels where available, improving interpretability and accuracy. One of UDAVA’s key strengths lies in its ability to extract features from sensor data rather than relying on raw time series similarity, making it robust against noise and diverse process variations. Additionally, UDAVA integrates process mining techniques—process discovery and conformance checking—to enhance its ability to detect even subtle anomalies and deviations in industrial workflows. We conduct a comprehensive evaluation of UDAVA using three industrial datasets, demonstrating its effectiveness in identifying high-level process behaviors, detecting process shifts and drifts, and ensuring data validation across multiple production cycles. The results highlight UDAVA ’s adaptability across different industrial processes, making it a valuable tool for optimizing operations and ensuring sensor data reliability in IIoT environments.
This digital artefact documents the results of experiments in metals tribology. It is constructed strictly observing the FAIR data principles. The experiments test the reciprocation sliding of a 10-mm single-crystal sapphire sphere against a polycrystal (average size ~45 µm) copper base body. The range of normal loads is 0–4.5 N, the sliding velocity is always 0.5 mm/s, and the experiments are performed in ambient 50% RH atmosphere. How to work with this data: The files in this Zenodo record carry the metadata and descriptions associated with the experiments. They are serialized in RDF. All raw and processed data is collected into RO-Crates (10.3233/DS-210053), and are stored at institutional servers with the following addresses (these are also semantically linked using Zenodo's schema on the right): https://dx.doi.org/10.35097/1028 https://dx.doi.org/10.35097/1029 https://dx.doi.org/10.35097/1030 https://dx.doi.org/10.35097/1036 https://dx.doi.org/10.35097/1037 https://dx.doi.org/10.35097/1038 https://dx.doi.org/10.35097/1039 https://dx.doi.org/10.35097/1041 https://dx.doi.org/10.35097/1043 https://dx.doi.org/10.35097/1045 https://dx.doi.org/10.35097/1047 https://dx.doi.org/10.35097/1049 https://dx.doi.org/10.35097/1051 https://dx.doi.org/10.35097/1052 https://dx.doi.org/10.35097/1053 https://dx.doi.org/10.35097/1054 https://dx.doi.org/10.35097/1057 https://dx.doi.org/10.35097/1058 https://dx.doi.org/10.35097/1059 https://dx.doi.org/10.35097/1060 https://dx.doi.org/10.35097/1061 https://dx.doi.org/10.35097/1063 https://dx.doi.org/10.35097/1065 https://dx.doi.org/10.35097/1066 https://dx.doi.org/10.35097/1067 https://dx.doi.org/10.35097/1070 https://dx.doi.org/10.35097/1071 https://dx.doi.org/10.35097/1072 https://dx.doi.org/10.35097/1073 https://dx.doi.org/10.35097/1074 https://dx.doi.org/10.35097/1075 https://dx.doi.org/10.35097/1076 https://dx.doi.org/10.35097/1077 https://dx.doi.org/10.35097/1078 https://dx.doi.org/10.35097/1079 https://dx.doi.org/10.35097/1080 https://dx.doi.org/10.35097/1082 https://dx.doi.org/10.35097/1083 https://dx.doi.org/10.35097/1085 https://dx.doi.org/10.35097/1086 https://dx.doi.org/10.35097/1087 https://dx.doi.org/10.35097/1088 https://dx.doi.org/10.35097/1089 https://dx.doi.org/10.35097/1090 https://dx.doi.org/10.35097/1091 https://dx.doi.org/10.35097/1092 https://dx.doi.org/10.35097/1093 https://dx.doi.org/10.35097/1094 https://dx.doi.org/10.35097/1095 https://dx.doi.org/10.35097/1096 https://dx.doi.org/10.35097/1097 https://dx.doi.org/10.35097/1098 https://dx.doi.org/10.35097/1099 https://dx.doi.org/10.35097/1100 Records have been anonymized prior to publishing. Statistics about the data: 150,717 RDF triples 51 Experimental Series, 488 Individual Events 89 Lab Equipment Descriptions 108 Experimental Object Descriptions 238.6 GB in Total Size Types of procedures and equipment involved (and count): Data Processing: 300 Block Specimen: 89 Light Microscopy: 76 Tribological Experiment: 53 Optical Surface Profilometry: 33 Metal Sawing: 30 Polishing: 27 Electron Microscopy: 26 Grinding: 25 Electropolishing: 18 Heat Treatment: 8 Software: 6 Tribometer: 6 Ultrasonic Cleaner: 3 Cup Grinding Machine: 2 Electropolishing Machine: 2 Furnace: 2 Grinding Machine: 2 Optical Surface Profilometer: 2 Band Saw: 1 Publication: 1 Demagnetizing Plate: 1 Electrolyte: 1 Hardness Tester: 1 Light Microscope: 1 Scanning Electron Microscope: 1 Tactile Surface Profilometer: 1 Wire Saw: 1 Vocabulary Schema Used: Schema.org, Vocabulary of Tribological Experiments Versions: 0.1.0 First Publication Related Documents: Bachelor's and Master's theses (to be published) For any questions, suggestions, or anything else: nikolay.garabedian@kit.edu or linkedin.com/in/nick-garabedian/ More information will be continuously updated. Metadata Preview: @prefix k4m784: . @prefix ns1: . @prefix rdf: . @prefix rdfs: . @prefix schema: . @prefix xsd: . a schema:Dataset ; rdfs:isDefinedBy [ ns1:gen_inf_equ-de13e7d124b44501a2f75fe330ac1704-vp [ ns1:com_orx_ven-d0357c2850b345cbb8e0185605de3faa-vp "Centre Suisse d'Electronique et de Microtechnique" ; ns1:equ_idx_xxx-55f9296489064da2b4839d6c2d27b3e3-vp "10-157" ; ns1:equ_orx_pro-bb4767e222854d6dae67280595736f6a-vp "Pin-on-Disc Machine" ; ns1:loc_inf_xxx-b24999e0e7264fa29369c967a3843d82-vp [ ns1:bui_xxx_xxx-9f2db0860b7f459f87a29b49c906bc25-vp "MZE, 30.48" ; ns1:flo_xxx_xxx-43fbb63ac5a44d7dbc9670fb37ff8216-vp [ a schema:QuantitativeValue ; schema:value 0 ] ; ns1:ins_loc_xxx-541d1514f1c64a1ba20c8a039cda319a-vp "Karlsruhe Institute of Technology (KIT)" ; ns1:roo_num_xxx-6c175c129e0a4b8a85008af4925882ac-vp "005" ] ; ns1:ope_inx_cha-a975eb0936f449b781eda6b2090c1f91-vp [ ns1:fir_nam_xxx-bbecf3efe21c4237803d09ed15981e2a-vp "***" ; ns1:ins_nam_xxx-81d6c0ba2f1d4dee805ba5c9b2aab29f-vp "Karlsruhe Institute of Technology (KIT)" ; ns1:las_nam_xxx-1be0c624e4114f38872871e5885535f5-vp "***" ; ns1:use_rol_xxx-3d0c936c282b4568ab1c5afcca84a413-vp "Technician" ; ns1:use_tok_xxx-f927a3e2e3d54a7da9526ce37964fdda-vp "***" ] ] ; ns1:per_inf_xxx-104611d1741a4c0680280d10c6d074c3-vp [ ns1:con_pcx_xxx-e43d8b226042456c90b95cb5ed076397-vp [ ns1:arr_ofx_sof-3109a4d5e7d2403eb4d11e3c82bbb7e1-vp [ ns1:sof_nam_xxx-cf5c9ddddb4e4cf0b406e56219af75e6-vp "LabVIEW" ; ns1:sof_ver_xxx-f712859d56484eb9a977ce1ee44d5250-vp "6.1" ] ; ns1:equ_idx_xxx-55f9296489064da2b4839d6c2d27b3e3-vp "00-30-84-6c-0c-bd" ; ns1:lis_ofx_equ-e1d2a3c6048645acaf3864d8ad05ac70-vp ( [ rdf:object [ ns1:equ_rol_xxx-1a1ac062807c4c2497789eee0ab9c3a0-vp "Signal Recording" ] ] [ rdf:object [ ns1:equ_rol_xxx-1a1ac062807c4c2497789eee0ab9c3a0-vp "Motion Control" ] ] ) ; ns1:ope_sys_nam-9a654273d201480f89bffe5473c98e0f-vp "Windows 98" ] ] ; ns1:tec_spe_tri-94e2c75e46434abfaad7f3edeb7982b5-vp [ ns1:arr_ofx_inf-55504fb383534ab397da31ddd82ab9c5-vp ( [ rdf:object [ ns1:con_amp_inf-ed869401a24a4a2eac2bddb2c8b6bf00-vp [ ns1:daq_con_por-e3bb88450b4a46188ad7137b9f285f9a-vp "ai1" ; ns1:equ_orx_pro-bb4767e222854d6dae67280595736f6a-vp "MW 210-13-3" ] ; ns1:equ_rol_xxx-1a1ac062807c4c2497789eee0ab9c3a0-vp "Measure the Height of the Base Body's Surface of Tribological Interest - Respectively Its Waviness" ; ns1:mea_pri_xxx-2c1313b7c58a457b9b2515a0f3e485c7-vp "Capacitive Sensing" ] ] [ rdf:object [ ns1:con_amp_inf-ed869401a24a4a2eac2bddb2c8b6bf00-vp [ ns1:daq_con_por-e3bb88450b4a46188ad7137b9f285f9a-vp "ai2" ; ns1:equ_orx_pro-bb4767e222854d6dae67280595736f6a-vp "MW 210-13-3" ] ; ns1:equ_rol_xxx-1a1ac062807c4c2497789eee0ab9c3a0-vp "Measure the Height of the Counter Body's Bulk - Respectively Its Wear" ; ns1:mea_pri_xxx-2c1313b7c58a457b9b2515a0f3e485c7-vp "Capacitive Sensing" ] ] [ rdf:object [ ns1:con_con_inf-83f4146732e9405da9032e9389b4bd71-vp [ ns1:com_orx_ven-d0357c2850b345cbb8e0185605de3faa-vp "Centre Suisse d'Electronique et de Microtechnique" ; ns1:daq_con_por-e3bb88450b4a46188ad7137b9f285f9a-vp "ai0" ; ns1:equ_idx_xxx-55f9296489064da2b4839d6c2d27b3e3-vp "10-157" ; ns1:equ_orx_pro-bb4767e222854d6dae67280595736f6a-vp "Pin-on-Disc Machine" ] ; ns1:equ_rol_xxx-1a1ac062807c4c2497789eee0ab9c3a0-vp "Measure Load Cell Displacement - Respectively the Friction Force" ; ns1:mea_pri_xxx-2c1313b7c58a457b9b2515a0f3e485c7-vp "Linear Variable Differential Transformer (LVDT) Sensing" ] ] ) ; ns1:arr_ofx_inf-dd899488f1414b4fa1b4e44307b3fc92-vp ( [ rdf:object [ ns1:daq_att_xxx-4214a14bf863452ca6271f2bb08f6f17-vp [ ns1:com_orx_ven-d0357c2850b345cbb8e0185605de3faa-vp "National Instruments" ; ns1:equ_orx_pro-bb4767e222854d6dae67280595736f6a-vp "USB-6212" ] ; ns1:daq_int_nam-2ead3c13b6884332a5d212595b039cc7-vp "USB" ] ] ) ; ns1:mot_ind_sub-64d48ea342d4415b9c20a13297050f90-vp ( [ rdf:object [ ns1:axi_nam_xxx-7c10343c04934f05a583f21b2a927499-vp "Base Body Rotation" ; ns1:mot_ind_sub-93a6d6b8c5c748a585f94cd37a2d6256-vp [ ns1:com_orx_ven-d0357c2850b345cbb8e0185605de3faa-vp "CSEM" ; ns1:equ_orx_pro-bb4767e222854d6dae67280595736f6a-vp "Build-in Drive" ] ; ns1:pri_ofx_mot-3c829fbb032845d8b7a202d7cce9e2cd-vp "DC Motor" ] ] ) ; ns1:str_inf_xxx-e9298074c4be472798076fcf5efbbca3-vp [ ns1:bas_bod_cla-ad66c57967a048db811d6c64db25f2bc-vp "Bolt" ; ns1:cou_bod_cla-a45820b32a1d498195988b9c468f4110-vp "Bolt (Mandrel)" ; ns1:hou_met_xxx-765e29fc1f65482b90b9c0da6c76815a-vp "Climate Box" ; ns1:pri_ofx_loa-000c058b7b324521a13bc44f8cdbb210-vp "Dead Weight(s)" ; ns1:sam_sub_met-d0762a0ba7964091b0e9da84932345a2-vp "Rim around Disc" ; ns1:vib_mit_met-2cc6a1c2302b4ceda57a78c553f8867d-vp "Lab Bench" ] ] ] ; schema:additionalType k4m784:lab%20equipment ; schema:author ; schema:dateCreated "2021-02-17T15:23:52.448311+00:00"^^xsd:dateTime ; schema:dateModified "2023-04-29T14:17:13.990908+00:00"^^xsd:dateTime ; schema:identifier "7addb4cda29d4f80b3e63df5ac674e7c-vp-aaazd-kitmt" ; schema:keywords "001066-79dfbfc9fd3882a1c2d10053800c6306-vp", "09aa26cf985681760020f32222a06c25-vp", "7addb4cda29d4f80b3e63df5ac674e7c-vp", "csem", "d879a97efd724dedbc16e6b223b8e961-vp", "kitmtxx-41732562-vp", "tri_xxx_xxx-c98170df4aa14cd38e9ba0d1b94ebdf0-vp", "tribometer" ; schema:license ; schema:name "Tribometer CSEM" ; schema:text """*Info:* A unidirectional pin-on-disc tribometer that can be used to conduct tribological experiments. It allows monitoring and recording of friction force and linear wear (via capacitive distance sensors)""".
