In order to study the application of nonlinear fractional differential equations in computer artificial intelligence algorithms. First, the concept, properties and commonly used neural network models of artificial neural network are introduced, the domestic and foreign status quo of the application of fractional calculus theory to neural network technology is described. Then, the definition, properties and numerical calculation methods of fractional calculus theory are introduced in detail. Then, based on the analysis of artificial intelligence neural network algorithm, the theory of fractional differentiation is introduced, construct BP neural network based on fractional order theory. The Sigmoid function is used as the node function of the neural network, and the actual data is used as the sample set, train a fractional-order network. Finally, by training the network, summarize the change of the two parameters a and p in the function, the impact on the training of the entire network, and make a simple comparison with the fractional order neural network based on the sigmoid function. Experiments show that a variable-order iterative learning algorithm is proposed and applied to the training of neural networks, the results show the feasibility of this algorithm and its advantages in convergence speed and convergence accuracy.

We use the Legendre wavelet method to study nonlinear fractional differential equations. Based on the in-depth study of the characteristics of various fractional-order dynamic system models, this paper designs a system for solving fractional-order differential equations, and we apply them to the anomaly analysis of big computer data. This method can improve the efficiency of big data classification. The results of computer numerical simulation show that the designed algorithm for solving fractional differential equations has high accuracy. At the same time, the algorithm can avoid misclassification and omission in big data analysis.

Because the current computer sensor data positioning analysis has positioning difficulties and false positioning problems, we use the Lagrangian multiplier method of the interactive direction to disassemble the computer sensor sound source. Through this algorithm, the information fusion of computer sensor nodes is realized. After using Lagrangian mathematical equations, these error correction measurements have achieved better target positioning results. Theoretical analysis and experimental results show that the algorithm improves the speed of computer sensor data association. To a certain extent, the correlation accuracy is improved.

In order to solve the system of compatible nonlinear equations, the author proposes a hybrid computational intelligence method of Newton's method and genetic algorithm. First, the Quasi-Newton Methods (QN) method is given. Aiming at the local convergence of the algorithm, it is easy to cause the solution to fail. By embedding the QN operator in the Genetic Algorithm (GA) and defining the appropriate fitness, thus, a hybrid computational intelligence algorithm of CNLE is obtained that combines the advantages of GA and QN method, which has both faster convergence and higher probability of solving. Experimental results show that: The value of the selection probability pn of the QN operator also directly affects the solution efficiency. Generally speaking, for strong nonlinear CNLE composed of multimodal functions, pn can be larger; For weakly nonlinear CNLE composed of functions with fewer extreme points and stronger monotonicity, pn can be smaller. It is demonstrated that the computational results show that this method significantly outperforms the GA and QN methods.

Deployable antennas, as the core content of national defense technology research at this stage, have the advantages of large flexibility and light weight in practical applications, so this type of antenna can also be called a rigid-flexible hybrid structure. According to the theoretical analysis of the dynamics of flexible multi-body systems, it can be seen that effective control of unfolding antennas is a basic requirement for practical applications. Due to the instability of the specific numerical solution of the static Lagrangian function, it is difficult to completely meet the constraint equation, which is also the main factor affecting the steady development of flexible multibody dynamics. Therefore, in-depth discussion of the numerical calculation method of the static Lagrangian function, obtaining efficient and stable numerical methods from it, and providing effective information for the process control of the deployment of the antenna, is the focus of scientific research scholars at this stage. Based on the understanding of the flexible multi-body dynamics modeling method, this paper systematically analyzes the calculation method of the differential equations, and combines the direct modification method of the constraint violation of the augmentation method to propose the simulation calculation of the model. The final results prove that the dynamics of flexible multi-body systems have a positive effect on the application analysis of deployable antennas.