6results about How to "Realize complementary advantages" patented technology

The application relates to an independent hybrid frequency modulation energy storage power station capacity configuration method and device, computer equipment, a computer readable storage medium and a computer program product, relates to the field of electric power energy storage, and can improve the resource utilization rate of a hybrid energy storage system. The method comprises the following steps: acquiring total power control instructions of a hybrid energy storage system in a target frequency modulation scene and operation characteristic parameters of each energy storage unit; based on the operation characteristic parameters and the total power control instructions, determining first charge and discharge instructions and second charge and discharge instructions of different energy storage units according to a real-time power distribution strategy; based on the first charge and discharge instructions and a life attenuation model, determining a device replacement cycle of an energy type energy storage unit; based on system frequency modulation response and periodic resource consumption, determining a comprehensive performance model in a full life cycle; under the premise of meeting preset operation constraint conditions, taking the comprehensive performance value of the comprehensive performance model as a target, and determining capacity configuration parameters through a Bayesian optimization algorithm.

The application discloses a coalbed methane well gas production NP-LSTM combined prediction method and belongs to the technical field of oil and gas field development prediction. A two-level model fusion prediction framework is constructed by adopting a meta-learning idea. Firstly, in the base model layer, a NeuralProphet model is used to capture the seasonality and event regularity of gas production and other drainage parameters, and an LSTM model is used to learn deep nonlinear time series dependence between multiple parameters. Then, in the meta-model layer, the prediction results of the two base models are spliced with static geological parameters such as coal seam depth, thickness and gas saturation, and input into a random forest regression model for nonlinear fusion, and finally, high-precision gas production prediction values are output. The advantages of the two types of base models are integrated in a soft fusion manner, and the geological static information is effectively combined, so that the accuracy and robustness of the coalbed methane well gas production prediction are significantly improved, and reliable data support is provided for accurate development and production control of the coalbed methane field.

The application provides a fuel cell hybrid electric vehicle energy management method based on a sand cat group optimization algorithm fusion optimization, and comprises the following steps: in an offline optimization stage, an improved sand cat group optimization algorithm SCSO is used to globally optimize membership function parameters and rule weights of a fuzzy controller, so that a high-performance basic fuzzy controller is obtained; in an online adjustment stage, the basic fuzzy controller obtained in the offline optimization stage is taken as a starting point of a deep deterministic policy gradient algorithm DDPG, an equivalent factor adjustment amount is output by a DDPG agent according to real-time vehicle states, and the output of the basic fuzzy controller is dynamically corrected, so that adaptive optimization of the strategy is realized. The application realizes the consideration of global optimality and real-time adaptability, thereby effectively reducing hydrogen consumption of the whole vehicle, improving fuel cell durability, and improving system dynamic response performance.

This invention discloses a method for predicting geological risks in TBM construction based on multimodal historical data fusion, belonging to the field of tunnel and underground engineering technology. This method includes: aligning and unifying the format of the first multimodal geological data; constructing an initial TBM construction geological risk prediction model, including a text semantic feature extraction module, a graphic structure feature extraction module, a multimodal feature fusion module, and a risk classification prediction module; training the parameters of the initial TBM construction geological risk prediction model using a sample set to obtain a final TBM construction geological risk prediction model; inputting the acquired second multimodal geological data into the final TBM construction geological risk prediction model to output the geological risk type and probability of the section to be predicted. This invention achieves advanced prediction of geological risks ahead by deeply exploring the potential value of historical geological exploration reports and design drawings.

The application discloses a diesel engine under-charge real-time monitoring and fault diagnosis method, which measures the parameters such as cylinder pressure and crank angle signals of the diesel engine by comprehensively applying various sensors, firstly reads or calculates the cylinder pressure at the top dead center, the maximum explosion pressure, the effective power feature and the average effective pressure, respectively, calculates the difference value of the above parameters and the threshold value of the corresponding normal working condition, respectively, and preliminarily diagnoses whether the diesel engine is under-charge; secondly, the fault degree of each parameter is judged by calculating the deviation rate of each parameter; finally, the overall fault degree is comprehensively analyzed according to the above fault degree; according to the fusion of the fault characteristic information, the typical fault characteristics are compared, so that the composite fault diagnosis of the diesel engine is realized, various characteristic information is fully utilized, the diagnosis speed and accuracy are improved, qualitative and quantitative analysis is realized, and the application of the diesel engine fault diagnosis level will be improved.

The present application relates to the technical field of radio navigation signal ground ranging, specifically to a wheat plant height inversion method based on GNSS reflected signal, comprising: acquiring pseudo-range observation data, carrier phase observation data and signal strength observation of GNSS; analyzing the pseudo-range observation data and carrier phase observation data to extract multipath reflection components, and processing the signal strength observation to extract reflected interference signals; performing spectrum analysis and inversely reflecting the first reflection distance and the second reflection distance in parallel; performing cycle slip detection on the carrier phase observation data to generate phase anomaly markers; determining reliability weights according to the phase anomaly markers, weighting and fusing the first and second reflection distances to obtain preliminary reflection distances; correcting the preliminary reflection distances according to growth stages to obtain corrected reflection distances; and fusing the corrected reflection distances of multiple satellites to calculate the wheat plant height in combination with the initial height of the antenna. The present application improves the accuracy of plant height measurement through double-path fusion and multi-layer correction.