Search results for "industrial engineering"
showing 10 items of 835 documents
How can we do our best, in manufacturing processes?
2018
Using Two-Level Context-Based Predictors for Assembly Assistance in Smart Factories
2020
The paper presents some preliminary results in engineering a context-aware assistive system for manual assembly tasks. It employs context-based predictors to suggest the next steps during the manufacturing process and is based on data collected from experiments with trainees in assembling a tablet. We were interested in finding correlations between the characteristics of the workers and the way they prefer to assemble the tablet. A certain predictor is then trained with correct assembly styles extracted from the collected data and assessed against the whole dataset. Thus, we found the predictor that best matches the assembly preferences.
Evaluation of Perception Latencies in a Human-Robot Collaborative Environment
2020
The latency in vision-based sensor systems used in human-robot collaborative environments is an important safety parameter which in most cases has been neglected by researchers. The main reason for this neglect is the lack of an accurate ground-truth sensor system with a minimal delay to benchmark the vision-sensors against. In this paper the latencies of 3D vision-based sensors are experimentally evaluated and analyzed using an accurate laser-tracker system which communicates on a dedicated EtherCAT channel with minimal delay. The experimental results in the paper demonstrate that the latency in the vision-based sensor system is many orders higher than the latency in the control and actuat…
Modified F-transform Based on B-splines
2018
The aim of this paper is to improve the F-transform technique based on B-splines. A modification of the F-transform of higher degree with respect to fuzzy partitions based on B-splines is done to extend the good approximation properties from the interval where the Ruspini condition is fulfilled to the whole interval under consideration. The effect of the proposed modification is characterized theoretically and illustrated numerically.
Application of Selected Methods of Black Box for Modelling the Settleability Process in Wastewater Treatment Plant
2017
Abstract The paper described how the results of measurements of inflow wastewater temperature in the chamber, a degree of external and internal recirculation in the biological-mechanical wastewater treatment plant (WWTP) in Cedzyna near Kielce, Poland, were used to make predictions of settleability of activated sludge. Three methods, namely: multivariate adaptive regression splines (MARS), random forests (RF) and modified random forests (RF + SOM) were employed to compute activated sludge settleability. The results of analysis indicate that modified random forests demonstrate the best predictive abilities.
Metric Rectifiability of ℍ-regular Surfaces with Hölder Continuous Horizontal Normal
2021
Abstract Two definitions for the rectifiability of hypersurfaces in Heisenberg groups $\mathbb{H}^n$ have been proposed: one based on ${\mathbb{H}}$-regular surfaces and the other on Lipschitz images of subsets of codimension-$1$ vertical subgroups. The equivalence between these notions remains an open problem. Recent partial results are due to Cole–Pauls, Bigolin–Vittone, and Antonelli–Le Donne. This paper makes progress in one direction: the metric Lipschitz rectifiability of ${\mathbb{H}}$-regular surfaces. We prove that ${\mathbb{H}}$-regular surfaces in $\mathbb{H}^{n}$ with $\alpha $-Hölder continuous horizontal normal, $\alpha> 0$, are metric bilipschitz rectifiable. This impr…
A Novel Intelligent Technique of Invariant Statistical Embedding and Averaging via Pivotal Quantities for Optimization or Improvement of Statistical …
2020
In the present paper, for intelligent constructing efficient (optimal, uniformly non-dominated, unbiased, improved) statistical decisions under parametric uncertainty, a new technique of invariant embedding of sample statistics in a decision criterion and averaging this criterion over pivots’ probability distributions is proposed. This technique represents a simple and computationally attractive statistical method based on the constructive use of the invariance principle in mathematical statistics. Unlike the Bayesian approach, the technique of invariant statistical embedding and averaging via pivotal quantities (ISE&APQ) is independent of the choice of priors and represents a novelty i…
Robust Network Agreement on Logical Information
2011
Abstract Logical consensus is an approach to distributed decision making which is based on the availability of a network of agents with incomplete system knowledge. The method requires the construction of a Boolean map which defines a dynamic system allowing the entire network to consent on a unique, global decision. Previous work by the authors proved the method to be viable for applications such as intrusion detection within a structured environment, when the agent's communication topology is known in advance. The current work aims at providing a fully distributed protocol, requiring no a priori knowledge of each agent's communication neighbors. The protocol allows the construction of a r…
Orchestrated learning: creating a company-specific production system (XPS)
2021
Purpose Companies create company-specific production systems (XPS) by tailoring generic concepts to fit their unique situation. However, little is known about how an XPS is created. This paper aims to provide insights into the creation of an XPS. Design/methodology/approach A retrospective case study was conducted in a Norwegian multinational company over the period 1991–2006, using archival data and interviews. Findings The development of the XPS did not start with a master plan. Instead, dispersed existing initiatives were built upon, along with an external search for novel ideas. Widespread experimentation took place, only later to be combined into a coherent approach. Once established,…
TOWARDS SMART MANUFACTURING WITH VIRTUAL FACTORY AND DATA ANALYTICS
2017
International audience; Virtual factory models can help improve manufacturing decision making when augmented with data analytics applications. Virtual factory models provide the capability of simulating real factories and generating realistic data streams at the desired level of resolution. Deeper insights can be gained and underlying relationships quantified by channeling the simulation output data to an external analytics tool. This paper describes integration of a virtual factory prototype with a neural network analytics application. The combined capability is used to create a neural network capable of predicting the expected cycle times for a small job shop. The capability can adapt by …