This thesis mainly studies the structure and algorithm design of the quantum-inspired neural network model, and in the oil field logging interpretation involves the water flooded layer to predict the specific application, as well as the application of oil field logging interpretation that involves the water flooded layer prediction.In the structure of quantum-inspired neural network model respect, a quantum neural networks model, whose input of each dimension is a discrete sequence, is proposed. This model concludes three layers, in which the hidden layer consists of quantum neurons, and the output layer consists of common neurons. The quantum neuron consists of the quantum rotation gates and the multi-qubits controlled-not gates. By using the information feedback of target qubit from output to input in multi-qubits controlled-not gate, the overall memory of input sequences is realized. The output of quantum neuron is obtained from the entanglements of multi-qubits in controlled-not gates. In the training algorithm of the model respect,it is based on quantum compution theory integrates into existing L-M algorithm, and designed the learning algorithm of this model. The features of input sequences can be effectively obtained in two ways of breadth and depth. The simulation results show that, when the input nodes and the length of the sequence satisfy a certain relations, the proposed model is obviously superior to the common artificial neural networks. To enhance the convergence ability of the model, it combines quantum compution with evolutionary algorithm, and quantum-inspired evolutionary algorithm based on Bloch sphere is proposed, firstly, the individuals are expressed with qubits in this algorithm, the axis of revolution is established with Pauli matrix,and the evolution search is realized with the rotation of qubits in the Bloch sphere,then,in order to avoid premature convergence,the mutation of individuals is achieved with Hadamard gates.Such rotation can make the current qubit approximate the target qubit along with the biggest circle on the Bloch sphere,which can accelerate the optimization process.Applying the algorithm to quantum-inspired neural network training, the results show that this method is better than L-M algorithm and the particle swarm optimization algorithm. Finally, the proposed model algorithm applied to oil well logging water flooded layer identification, to verify the advantage of this method. |