As the inter symbol interference increases the bit error rate(BER) of the visible light communication system，a new artificial neural network (ANN) equalization receiving system is proposed. Based on angle diversity receiving technology and artificial neural networks, the system can not only reduce the influence of inter symbol inference, but also improve the signal to noise ratio(SNR) and decrease the bit error rate. The signal transmission test is simulated by Matlab. The simulation results show that the proposed system has lower bit error rate compared with the traditional system which uses single input and single output technology(SISO), what′s more, the former can weaken the influence of inter symbol interference under the same signal to noise ratios of the environment and signal source. This advanced system can optimize the channels performance of visible light communication system, and it obviously has a vast application prospect.