In order to improve the measurement precision of pressure sensors in wildcat working

a method of error compensation on sensors using the BP neural networks trained by particle swarm optimization（PSO）is proposed.Using the characteristic of global optimum and fast convergence of the PSO arithmetic to train weights of net can effectively improve the convergence speed and learning capacity of BP neural networks traditional arithmetic.The result shows that this method greatly improves the measurement precision and stability of pressure sensor

also increases the efficiency of oil field operations.