Dynamic Production System Identification for Smart Manufacturing Systems.

This paper presents a methodology, called production system identification, to produce a model of a manufacturing system from logs of the system's operation. The model produced is intended to aid in making production scheduling decisions. Production system identification is similar to machine-learning methods of process mining in that they both use logs of operations. However, process mining falls short of addressing important requirements; process mining does not (1) account for infrequent exceptional events that may provide insight into system capabilities and reliability, (2) offer means to validate the model relative to an understanding of causes, and (3) updated the model as the situation on the production floor changes. The paper describes a genetic programming (GP) methodology that uses Petri nets, probabilistic neural nets, and a causal model of production system dynamics to address these shortcomings. A coloured Petri net formalism appropriate to GP is developed and used to interpret the log. Interpreted logs provide a relation between Petri net states and exceptional system states that can be learned by means of novel formulation of probabilistic neural nets (PNNs). A generalized stochastic Petri net and the PNNs are used to validate the GP-generated solutions. The methodology is evaluated with an example based on an automotive assembly system.

Characterization of underwater sounds produced by hydraulic and mechanical dredging operations.

Sound recordings were made of two dredging operations at hydrophone depths of 3 and 9.1 m at distances up to 1.2 km from the source in shallow waters (<15 m) of New York Harbor. Sound sources included rock fracturing by a hydraulic cutterhead dredge and six distinct sources associated with a mechanical backhoe dredging operation during rock excavation. To place sound emitted from these dredges in perspective with other anthropogenic sounds, recordings were also made of several deep-draft commercial vessels. Results are presented as sound pressure levels (SPLs) in one-third octave versus range across the 20 Hz to 20 kHz frequency band. To address concerns for protection of fishery resource occupying the harbor, SPL were examined at frequency bands of 50-1000 Hz and 100-400 Hz, the ranges where the majority of fishes without hearing specializations detect sound and the range of greatest sensitivity, respectively. Source levels (dB re 1 µPa-1 m rms) were back calculated using fitted regression (15LogR). The strongest sound sources (180-188.9 dB) were emitted by commercial shipping. Rock fracturing produced a source level of 175 dB, whereas six distinct sources associated with rock excavation had source levels ranging from 164.2 to 179.4 dB re 1 µPa-1 m (rms).

Fishery resource utilization of a restored estuarine borrow pit: a beneficial use of dredged material case study.

Numerous pits in coastal waters are subject to degraded water quality and benthic habitat conditions, resulting in degraded fish habitat. A pit in Barnegat Bay, New Jersey (USA) was partially filled with dredged sediment to increase flushing, alleviate hypoxia, and enhance benthic assemblages. Restoration objectives were assessed in terms of benthic community parameters and fishery resource occupation. Restoration resulted in increased benthic diversity (bottom samples) and the absence of water column stratification. Fisheries resources occupied the entire water column, unlike pre-restoration conditions where finfish tended to avoid the lower water column. The partial restoration option effectively reproduced an existing borrow pit configuration (Hole #5, control), by decreasing total depth from -11 m to -5.5 m, thereby creating a habitat less susceptible to hypoxic/anoxic conditions, while retaining sufficient vertical relief to maintain associations with juvenile weakfish and other forage fishes. Partially filling pits using dredged material represents a viable restoration alternative.