Optimal hydrate inhibition policies with the aid of neural networks

Hydrates are known to occur in a variety of natural-gas handling facilities and processing equipment in oil fields, refineries, and chemical plants wh en natural gas and water coexist at elevated pressure and reduced temperatu re. Prevention of hydrate formation costs large amounts of capital and resu lts in large operating expenses. Hydrate inhibition using chemical inhibito rs is still the most widely used method. Accurate prediction of hydrate inh ibition is required for cost-effective design and operation. Available mode ls have limitations in ranges of application and types and compositions of the fluids and inhibitors used. This paper describes the development and ap plication of neural networks for the prediction and optimization of natural -gas hydrate inhibition. Neural network models have been used to accurately determine the temperature depression of gas hydrates for a variety of type s and concentrations of inhibitors. Experimental data covering wide ranges of hydrate formation conditions, gas compositions, and concentrations of va rious types of inhibitors have been used in model validation. The factors t hat may affect the inhibition process, such as gas gravity and pressure, we re investigated. An optimization study has been carried out on the selectio n of inhibitor type and concentration using the developed neural network mo dels. Optimization was based on economical and technical performance consid erations concerning inhibitor losses in vapor and liquid hydrocarbons. The results indicate that optimal design depends on water content, operating co nditions of pressure and temperature, and gas composition. Optimized hydrat e inhibition strategies have been recommended for various gas composition s ystems.