Identification of partially observable discrete event manufacturing systems

Abstract

This paper deals with black-box identification of discrete event manufacturing systems that are automated using a programmable logic controller (PLC). The behavior of the system is observed during its operation and is represented by a single long sequence w of observed input/output (I/O) signals vectors. The identification method, conceived for addressing large and complex industrial systems, consists of two complementary stages; the first one obtains, from w, the observable part of an interpreted Petri net (PN) model composed of observable places and transitions describing the reactive behavior of the system. Afterwards, w is transformed into a sequence S of transition firings from which a PN model that reproduces S is inferred. This paper focuses on the second stage of the method in which a PN is built by adding non-labeled places and arcs that represent the non-observed behavior of the whole system by assuring the reproduction of w; this technique is based on discovering the causal and concurrent relationships between transitions in S.

Petri net discovery of discrete event processes by computing t-invariants

“…In the context of automated manufacturing systems, Si represents the observation of relevant input-output events sampled from the controller during a long execution period of time, for example a complete production process performing repetitive jobs [10].…”

“…An extension to this method that allows obtaining distributed system models is presented in [9]. In [10] Input-output identification of automated manufacturing process is addressed; an interpreted PN is obtained from a set of sequences of input-output vectors collected from the controller during the system cyclic operation. The method is extended for dealing with a long single observation of input-output vectors [11].…”

“…In the present paper a new method for building a safe Petri net (PN) from a single sequence of tasks S, composed by numerous processes execution traces, is proposed. It follows the approach presented in [10] and proposes new results allowing addressing more complex behaviours such as implicit dependencies between tasks that are not observed consecutively. The method is based on determining, from S, causal and concurrency relations between tasks and the computing of the t-invariants of the PN to discover.…”

Identification of discrete event systems unobservable behaviour by petri nets using language projections

“…A method to discover the unobservable behaviour from a firing sequence is proposed in [7], based on the study of consecutive pairs of events in the sequence, leading to the impossibility of finding long-term dependencies, i.e. memory effects of the system.…”

Modeling Framework for Automated Manufacturing Systems Based on Petri Nets and ISA Standards

“…The low level deals with the design of routines of pneumatic, hydraulic and electrical devices and its translation to the programming languages of local controllers like PLC's, for instance [4,5].On the other hand, the high level studies the case of equipment and modules coordination of AMS, where the concurrency, blocking, fault detections, time optimization of routines and the computer-based supervision appear in the DES model to facilitate the manufacturing of different and concurrent products [1,6].…”