5 results about "Immune genetic algorithm" patented technology

The application discloses a soft soil foundation settlement prediction method based on a physical information neural network, and relates to the technical field of geotechnical engineering monitoring. Multi-source data containing settlement, displacement and pore water pressure are collected, wavelet denoising and feature screening are performed, and a high-quality data set is constructed; a forward mapping model based on finite element FEM is constructed, an improved immune genetic algorithm IGA is used to minimize errors, and accurate inversion of key mechanical parameters is realized; the mechanical parameters are embedded into a long short-term memory network LSTM, a hybrid loss function containing data fitting loss and physical limit constraint loss is constructed, and a physical information neural network PINN-LSTM is formed; the future deformation trend is predicted through the network, the safety factor is calculated in combination with the limit equilibrium theory, and hierarchical early warning and disposal suggestion pushing are realized according to a dynamic early warning threshold. The method significantly improves the physical interpretability and precision of soft soil foundation settlement prediction, and has wide application value.

The invention relates to the technical field of feature screening, in particular to a multi-label data feature screening method and system based on an immune genetic algorithm. Each label population is constructed by single-label prior features, and recognition of complex information between features-features, features-labels and labels is realized through multi-population parallel operation, immunization, elite retention, concentration inhibition and global feature migration strategies. Therefore, the optimal feature subset screened out by each label has a good prediction effect on the corresponding label result, and the accuracy of multi-label medical disease prediction is improved. By constructing classification and survival multi-label models and calculating chromosome fitness values, the method can be simultaneously suitable for feature screening of medical multi-label classification and survival data.

The invention discloses a WESP feedforward control method and system considering frequency conversion and starting number of slurry pumps of a desulfurizing tower, and belongs to the technical field of automatic control of environmental protection islands of thermal generator sets. According to the method, modeling is carried out on slurry pump frequency and number step test data, a characteristic model between the slurry pump frequency and the concentration of smoke at an outlet of a desulfurizing tower is established, and gain, inertia time and lag time parameters are identified by adopting an immune genetic algorithm. And constructing a frequency feed-forward channel and a number feed-forward channel based on Pade approximation and a low-pass filter, and superposing the feed-forward compensation quantity and the PID feedback control quantity of the wet electric dust remover to generate the operation control quantity of the wet electric dust remover power supply. The control system comprises a slurry pump working condition acquisition module, a smoke dust concentration acquisition module, a model storage and calling module, a feed-forward and feedback operation module and a control quantity synthesis execution module, rapid response to the operation working condition of the slurry pump of the desulfurization tower is achieved, the auxiliary dust removal capacity of the desulfurization tower is fully utilized, and automatic, efficient and energy-saving control over the wet-type electric dust remover is achieved.

This invention discloses a hydraulic pump fault detection method based on signal processing, comprising: acquiring vibration signals during the operation of the hydraulic pump in real time using a vibration sensor, and extracting features from the vibration signals to obtain a feature vector of the vibration signals; wherein, is a first feature factor, is a second feature factor, is a third feature factor, is a fourth feature factor, is a fifth feature factor, is a sixth feature factor, and is a seventh feature factor; optimizing the connection weights of the SOM network model using an immune genetic algorithm to obtain an optimized SOM network model; using the feature vector of the vibration signals as input to the optimized SOM network model, finding the neuron in the competitive layer of the SOM network model that best matches the feature vector of the vibration signals, and using the output of the neuron that best matches the feature vector of the vibration signals as the detection result of the hydraulic pump fault.

This invention discloses a wave power generation control system based on an immune genetic algorithm. The outer loop control loop includes: an immune memory bank, a nonlinear error feedback control law, a primary dual-buoy object, a secondary dual-buoy object, and a mirror image of the secondary buoy object. The inner loop control loop includes: a vertical velocity control module and a process model. The output of the mirror image of the secondary buoy object is connected to the input of the nonlinear feedback control law. The output of the nonlinear error feedback control law is connected to the input of the vertical velocity control module. The output of the vertical velocity control module is connected to the input of the process model, the input of the secondary dual-buoy object, and the input of the mirror image of the secondary dual-buoy object. The output of the secondary dual-buoy object is connected to the input of the primary dual-buoy object. The output of the process model is connected to the input of the vertical velocity control module. This invention solves the problem of interference from unmeasurable state variables, optimizes the wavelength and wave height of the waves, and improves the stability of the system.