No abstract

Measurements of laminar dispersion in a capillary have been used to determine the molecular diffusivities of O2 and N2 dissolved in water. Measurements made on the CO2-H2O system at 25°C ., a system for which the diffusion coefficient was well known, indicated good agreement with the values reported by other investigators. No solubility data were required to determine the diffusion coefficient in this work and, in this aspect, the experimental method used offered a significant advantage over other techniques. Several correlations of diffusivity with temperature were tested and a new correlation is proposed.

Considerable literature describing the use of artificial neural networks (ANNs) has evolved for a diverse range of applications such as fitting experimental data, machine diagnostics, pattern recognition, quality control, signal processing, process modeling, and process control, all topics of interest to chemists and chemical engineers. Because ANNs are nets of simple functions, they can provide satisfactory empirical models of complex nonlinear processes useful for a wide variety of purposes. This article describes the characteristics of ANNs including their advantages and disadvantages, focuses on two types of neural networks that have proved in our experience to be effective in practical applications, and presents short examples of four specific applications. In the competitive field of modeling, ANNs have secured a niche that now, after two decades, seems secure.

No abstract

No abstract

Figure 1 is a flow diagram of the chemical process. The test problem was a hydrocarbon refrigeration process in which the feed stream (stream number 1 of Figure 1) is a vapor mixture of ethane, propane, and n-butane (subscripts e, p and b, respectively) at 200°F and 500 psia. The product stream (stream number 8 of Figure 1) is liquid at -20°F at some reduced pressure. The nonlinear objective function was the minimization of the cost of the work done by the recycle stream compressors. There were 34 bounded variables (both upper bound and lower bound) associated with the process, 12 linear equality constraints, 18 nonlinear equality constraints, and 3 linear inequality constraints (see PROBLEM). The generalized reduced gradient code of Abadie and Guigou reached the solution shown in Table 1 from the nonfeasible starting point shown in Table 2.

No abstract

Artificial neural networks have capacity to learn and store information about process faults via associative memory, and thus have an associative diagnostic ability with respect to faults that occur in a process. Knowledge of the faults to be learned by the network evolves from sets of data, namely values of steady-state process variables collected under normal operating condition and those collected under faulty conditions, together with information about the degree of the faults and their causes.Here, we describe how to apply artificial neural networks to fault diagnosis. A suitable two-stage multilayer neural network is proposed as the network to be used for diagnosis. The first stage of the network discriminates between the causes of faults when fed the noisy process measurements. Once the fault is identified, the second stage of the network estimates the degree of the fault. Thus, the diagnosis of incipient faults becomes possible.