| 1. |
- Danhäll, D, et al.
(författare)
-
Naturligt grupperat arbete vid Volvo Lastvagnar – Slutrapport
- 1990
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Consumer report for the company in question (the Volvo Truck Company) which is financed by the company and partly also by a research foundation. It is a matter of a work that in this particular case were carried out during nine years in a number of experimental workshops located outside the Chalmers University of Technology. These workshops were financed by the Volvo Automobile and Truck companies. This achievement, as the final contribution to the Swedish automotive industry after having already treated this research field/problem area for more than two decades before this particular period if time (involving several junior and senior research competencies, as well as industrial and governmental foundings). A comment: As was the praxis during this (early) period of time at Chalmers University of Technology, as well as probably at some other universities. This means that frequent and vast academic publication by means of e.g. conference papers and refereed contributions to scientific journals was almost unheard of. At least so for some of the applied science disciplines. However, today are the situation indeed very different (i.e. earlier was the publication in many respects focused on trying to satisfy the executive administrator the research foundation in question etc.). To be more precise, this early praxis was definitively the case for the research and development work carried out at the Department of Transportation (a broadly applied science discipline), which was characterized by more practical strives to e.g. engineer research results. Rather than relying on truer scientific efforts in a narrower sense. Functional satisfaction (i.e. something engineered work as planned instead verification/falsification of a hypothesis) was judged as being a primary aim of this research and development work. Therefore are (in the context of the publications registered in Chalmers Public Library CPL) the author making distinctions between consumer reports, on one hand. And, one the other hand, reports and preprints (manuscripts), while instead the academically orientated publications are various sort of scientific contributions presented at conferences or published in scientific journals (actually it is somewhat more complex, but further explanations are omitted here). The consumer reports were aimed at a various external organization with who the authors cooperated, and these are in many cases not available in PDF format to be easily read by logging in at CPL. This particular approach has judged as being fair/relevant fair in order to mirror of work conducted by the author or authors during the passing decades. Besides, the competencies at Chalmers Library, who actually have been very helpful, have not managed to provide appropriate answers to the various questions implied being at hand just above (this despite trying to get hold of such answers, hence this very comment).
|
|
| 2. |
- Engström, Tomas, 1950, et al.
(författare)
-
Monteringsanvisningar för naturligt grupperat arbete
- 1988
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Consumer report for the company in question (the Volvo Automobile Company) which is financed by the company and partly also by a research foundation. It is a matter of a work that in this particular case were carried out during nine years in a number of experimental workshops located outside the Chalmers University of Technology. These workshops were financed by the Volvo Automobile and Truck companies. This achievement, as the final contribution to the Swedish automotive industry after having already treated this research field/problem area for more than two decades before this particular period if time (involving several junior and senior research competencies, as well as industrial and governmental foundings). These assembly work instructions were developed in one of the experimental workshops together with e.g. operators from the temporary learning and training workshop predating the Volvo Uddevalla plant and thereafter used for full-scale product purpose in the completed assembly plant. They were formalised by an information system used for such purposes. Thus, it is fair to state that these particular assembly work instructions were validated at an industrial scale (they actually represent years and years of work from ours' and others personnel' side). Specifically, this publication explains how the authors dealt with s the product architecture and product variation of the automotive products disassembled, which proved to necessary to be carried out in one of the experimental workshops (several complete automobiles and one heavy truck chassis were disassembled combined with having product data accessible in form of paper print-outs as well as by appropriate computer connections to the two Volvo companies etc.). That is, by using a special sort of “design analysis by means of axonometric hand-drawn illustrations” (see a conference contribution from 1992 that also is registered and available as o PDF-document at Chalmers Public Library (CPL) (a self-developed method found out together with a junior research competency from the School of Architecture at Chalmers).
|
|
| 3. |
- Pirasteh, Parivash, 1984-, et al.
(författare)
-
Interactive feature extraction for diagnostic trouble codes in predictive maintenance : A case study from automotive domain
- 2019
-
Ingår i: Proceedings of the Workshop on Interactive Data Mining. - New York, NY : Association for Computing Machinery (ACM). - 9781450362962
-
Konferensbidrag (refereegranskat)abstract
- Predicting future maintenance needs of equipment can be addressed in a variety of ways. Methods based on machine learning approaches provide an interesting platform for mining large data sets to find patterns that might correlate with a given fault. In this paper, we approach predictive maintenance as a classification problem and use Random Forest to separate data readouts within a particular time window into those corresponding to faulty and non-faulty component categories. We utilize diagnostic trouble codes (DTCs) as an example of event-based data, and propose four categories of features that can be derived from DTCs as a predictive maintenance framework. We test the approach using large-scale data from a fleet of heavy duty trucks, and show that DTCs can be used within our framework as indicators of imminent failures in different components.
|
|
