Minimal-invasive methods for monitoring and supervision of industrial processes

STRŽINAR, ŽIGA (avtor), Škrjanc, Igor (mentor), Pregelj, Boštjan (komentor)

This thesis deals with the development of minimally invasive methods for the supervision and monitoring of industrial processes, focussing on time series analysis techniques. In the context of Industry 4.0, where industrial machines are increasingly equipped with networking and data acquisition capabilities, efficient machine supervision is an important aspect of efforts to improve the efficiency and reliability of production lines. This dissertation addresses the need to equip existing machines with low-cost, non-invasive monitoring hardware that -- supported by the state-of-the-art algorithms presented here -- enables effective monitoring of such machines. The dissertation proposes a processing pipeline consisting of data acquisition, segmentation, clustering, classification and sequence analysis. The proposed methods take into account the ever-changing nature of industrial processes and the limited availability of labelled time series from the past. To overcome these challenges, evolving mechanisms are incorporated into several of the algorithms. The thesis consists of five publications, all focussing on time series analysis. Several algorithms are presented in these publications -- two for time series classification and three for clustering. Four of the publications deal with pneumatic signals, which are common in industrial environments. A dataset of such signals has been published and made available for wider use by the research community. One publication diverges into the field of biomedical engineering and applies time series classification methods to measurements of electrodermal activity in order to recognise stress in humans. Several data sets are used to evaluate the proposed methods. Given the application focus, particular importance is placed on an industrial data set for validation. Nonetheless, the methods are also evaluated against a broad collection of publicly available time series datasets, including the University of California, Riverside (UCR) Time Series Archive and the Wearable Stress and Affect Detection (WESAD) dataset. The evaluation includes accuracy metrics, time complexity analyses, visual comparisons of results, and comparisons of computation times across multiple scenarios. The methods developed and presented in this thesis clearly show that non-invasive measurements can be used effectively for the supervision of industrial equipment. Furthermore, methods that support unsupervised learning are particularly well suited for industrial applications where large amounts of unlabelled data are common. The work presented is an important step towards realising the vision of data-driven manufacturing.

• Jezik: Angleški jezik
• Ključne besede: Time series analysis, Clustering, Classification, Evolving methods, Industrial processes, Monitoring
• Vrsta gradiva: Doktorsko delo/naloga
• Organizacija: FE - Fakulteta za elektrotehniko
• Leto izida: 2025
• PID: 20.500.12556/RUL-176603
• Datum objave v RUL: 05.12.2025

Sekundarni jezik

• Jezik: Slovenski jezik
• Naslov: Minimalno invazivne metode spremljanja in nadzora industrijskih procesov

Izvleček

Disertacija obravnava razvoj metod za minimalno invazivno spremljanje in nadzor industrijskih procesov s poudarkom na analizi časovnih vrst. V okviru industrije 4.0 proizvodna oprema pridobiva omrežno povezljivost ter zmožnost zajema podatkov, s tem se omogoča učinkovit nadzor strojev, kar je ključni korak za izboljšanje učinkovitosti in zanesljivosti proizvodnih linij. V disertaciji se posvečamo spremljanju že obstoječih strojev s pomočjo cenovno dostopne in neinvazivne merilne opreme ter razvoju algoritmov, ki omogočajo učinkovitejši nadzor nad proizvodnimi sistemi. Raziskava zajema širok spekter metod obdelave časovnih vrst – od zajema in segmentacije do gručenja, razvrščanja in analize zaznanih dogodkov. Predstavljene metode upoštevajo posebnosti industrijskih procesov ter se, kjer je mogoče, naslanjajo na principe samorazvijajočih se pristopov. Disertacija temelji na petih objavljenih znanstvenih člankih. Dva se osredotočata na področje razvrščanja časovnih vrst, preostali trije pa na gručenje. V štirih publikacijah so algoritmi preverjeni na podatkih meritev pnevmatskega tlaka iz industrijskega okolja. Podatkovno zbirko, ki jo uporabljamo, smo tudi objavili ter s tem omogočili nadaljnje raziskave. Ena od objav obravnava problem zaznave stresa, ki je v delu formuliran kot problem razvrščanja časovnih vrst. Poleg lastnega industrijskega podatkovnega nabora so za evalvacijo uporabljeni tudi javno dostopni viri, kot so Arhiv časovnih vrst Univerze Riverside v Kaliforniji (UCR Archive) ter specializiran podatkovni nabor za zaznavo stresa z nosljivimi napravami (WESAD). Rezultati disertacije jasno kažejo, da je neinvazivno zajete meritve mogoče uspešno uporabiti za nadzor industrijske opreme. Posebej obetavne so metode nenadzorovanega učenja, ki se izkažejo kot zelo uporabne v industrijskih okoljih, kjer prevladujejo velike količine neoznačenih podatkov. Delo tako predstavlja pomemben korak v smeri podatkovno vodenih industrijskih procesov.

• Ključne besede: Analiza časovnih vrst, Gručenje, Razvrščanje, Samorazvijajoče se metode, Industrijski procesi, Nadzorni sistemi