An improved discharge model based on a bidirectional neural network was developed. The bidirectional LSTM model was used, and it was trained by the experimental data from the Experimental Advanced Superconducting Tokamak (EAST) campaign 2010-2020 discharges. Compared to our previous works (Chenguang Wan et al 2021 Nucl. Fusion 61 066015), the present work reproduces the discharge evolution process through more key diagnostic signals, including the electron density ne, store energy W mhd , loop voltage V loop , actual plasma current Ip, normalized beta βn, toroidal beta βt, beta poloidal βp, elongation at plasma boundary κ, internal inductance l i , q at magnetic axis q 0 , and q at 95% flux surface q 95 . The similarity of electron density ne and loop voltage V loop is improved by 1%, and 5%. The average similarity of all the selected key diagnostic signals between modeling results and the experimental data are greater than 90%, except for the V loop and q 0 . The model has two main application scenarios: After tokamak discharge experiment, the model gives estimated values of the diagnostic signals based on the actual actuator signals. When the actual values of the diagnostic signals are close to the estimated values it means that the discharge is normal, and vice versa it means that the discharge is abnormal or a new discharge mode occurs. Before the tokamak discharge experiment, the proposal designer sets the values of the actuator signals, and the model has the promising for giving the estimated values of the diagnostic signals to assist in checking the reasonableness of the tokamak experimental proposal.