An energy-efficiency evaluation method for high-sulfur natural gas purification system using artificial neural networks and particle swarm optimization

Natural gas purification, especially with high sulfur content, is an energy-intensive chemical production process, for which there are considerable differences in the energy consumption patterns of different purification plants. Therefore, these purification plants are required to establish a universal evaluation standard for energy consumption performance. This article proposed a novel approach to evaluate the energy efficiency of the natural gas purification process from the systems engineering perspective. An evaluation system is established for the hierarchical indicators of energy consumption using this technique providing the detailed definition of evaluation indicators for process, unit, and device. At the same time, a technical route is proposed for intelligent algorithm optimization and artificial neural network modeling based on historical operation data of the plant to discover the energy consumption benchmarks under various raw gas flow rates. Using this proposed method, the energy consumption efficiency can be evaluated while analyzing the energy-savings potential of these natural gas purification plants with various process types or raw gas characteristics. Furthermore, the model based on historical operating data can objectively and truly reflect the plant's energy consumption features; therefore, the plant's energy consumption can be decreased to benchmark by adjusting the corresponding operation parameters. Ultimately, the computational process of the energy consumption benchmark is described thoroughly for a high-sulfur natural gas purification plant.