7results about How to "Increase vertical resolution" patented technology

The application discloses a sedimentary reservoir prediction method based on three-dimensional seismic data, which comprises the following steps: step one, feature extraction; step two, feature dynamic fusion; step three, model establishment and training; step four, optimization of storage prediction results; and step five, visualization interaction. The system comprises a data processing module, a feature fusion module, a model training module, a reservoir prediction module and a visualization interaction module. The dynamic weight distribution algorithm is used to fuse multi-dimensional features such as seismic waveforms, frequency spectra and geometric attributes, so that the vertical resolution of thin interbedded layers is significantly improved, the identification difficulty of hidden reservoirs is solved, and the loss risk is reduced. A double-channel neural network model is established to automatically extract seismic features and sedimentary facies knowledge, so that the deviation of artificial feature engineering is avoided, the rapid modeling demand of a complex sedimentary environment is met, and the prediction results are constrained and corrected, so that the continuity of a vertical sedimentary sequence is ensured.

This invention discloses an improved machine learning-based intelligent prediction method for stratigraphic models and related equipment. By fusing depth-aligned high-frequency active seismic source data and low-frequency passive seismic source data, a multi-dimensional complementary source feature vector is constructed, significantly improving the vertical resolution and deep penetration capability of stratigraphic prediction. A genetic algorithm is used to globally search and optimize the network parameters of the convolutional neural network. Combining binary encoding and genetic operations effectively avoids the pitfalls of traditional gradient descent methods, which are prone to getting trapped in local optima, thus improving the globality and stability of model parameter optimization. Through iterative fitness verification and threshold determination, the optimal network parameters are adaptively determined without manual intervention, significantly reducing the cost of hyperparameter tuning while effectively ensuring the generalization performance of the prediction model. The final prediction model can perform fast and accurate stratigraphic prediction based on real-time source data and can be widely applied in the field of data processing technology.

The invention discloses a pipeline interior detection instrument, and relates to the technical field of pipeline detection, the pipeline interior detection instrument comprises a plurality of preset probe groups which are arranged in sequence, each preset probe group comprises a plurality of preset probes, and all the preset probes in each preset probe group are arranged in an annular array; the distance between every two adjacent preset probe groups is not an integral multiple of a measurement interval, and the measurement interval is the displacement of the preset probes in one measurement period. According to the invention, the plurality of preset probe groups are sequentially arranged, and the distance between every two adjacent preset probe groups is not the integral multiple of the measurement interval, so that the longitudinal measurement points of the pipeline can be encrypted, the longitudinal resolution of the detection in the pipeline can be improved, and the method can adapt to a high-speed detection scene; the preset probes in other preset probe groups can still perform normal detection, and the longitudinal resolution of the detection in the pipeline is still higher than the longitudinal resolution of a traditional detection instrument in the pipeline.

The invention provides a reservoir fluid identification method, device and equipment and a storage medium, and the method comprises the steps: obtaining geological information data of a research area, building an initial geoelectric model, and determining the top and bottom depths of each target stratum; acquiring wide-area apparent resistivity data of all stratums to obtain an overall wide-area apparent resistivity profile, and deleting data of each target stratum in the overall wide-area apparent resistivity profile to obtain an original wide-area apparent resistivity profile; based on a frequency spectrum encryption technology and a wide area electromagnetic method, obtaining wide area apparent resistivity data of each target layer; according to the initial geoelectric model, the undisturbed wide area apparent resistivity profile and the wide area apparent resistivity data of each target stratum, taking the initial geoelectric model as a current geoelectric model, executing a multi-target stratum progressive inversion strategy, and obtaining a target inversion apparent resistivity profile containing all target stratum information; and fluid identification and division are carried out according to the target inversion apparent resistivity profile. According to the method, the speed and the precision of fluid identification can be improved through multi-objective layer progressive inversion.

The invention discloses a GNSS-based large-scale marching type ionosphere disturbance three-dimensional monitoring method and system. The method comprises the following steps: calculating the total electron content of an oblique ionosphere between a satellite and a receiver by adopting non-difference non-combination precise point positioning; based on Savitzky-Golay smoothing and Butterworth band-pass filtering, the total electron content of the detrending oblique ionized layer is obtained; based on spatial and temporal distribution formed by multiple stations, multiple satellites and multiple elevation puncture points, a three-dimensional ionosphere electron density disturbance model is constructed, and ionosphere disturbance three-dimensional propagation characteristics are solved. According to the method, the total electron content of the detrended oblique ionized layer is obtained based on Savitzky-Golay smoothing and Butterworth band-pass filtering, trend removal and disturbance reservation can be better balanced, and the signal-to-noise ratio and reliability of the extracted large-scale marching type ionized layer disturbance signal are improved; meanwhile, the constructed three-dimensional ionosphere electron density disturbance model not only can reveal vertical coupling characteristics of ionosphere disturbance, but also can stably extract key propagation elements and improve monitoring accuracy.

This invention provides a method for determining deconvolution parameters and a method for processing seismic data, belonging to the field of seismic exploration of oil and gas. The method for determining deconvolution parameters includes the following steps: selecting N experimental parameter values ​​for the target exploration area and performing a first inverse selection process, a second inverse selection process, and a third inverse selection process respectively; based on the inverse selection results of the first, second, and third inverse selection processes, inversely selecting out N-1 experimental parameter values ​​to determine the deconvolution parameters, where N is an integer and N≥2. By integrating multiple qualitative and quantitative evaluation results and using an inverse selection method, the method achieves the determination of deconvolution parameters suitable for the target exploration area, and the results are unique, objective, and accurate, avoiding interference from subjective human factors, and obtaining deconvolution parameters that balance the vertical resolution and signal-to-noise ratio of seismic data.

The invention provides an earthquake attenuation gradient calculation method and system based on Hamiltonian characteristic analysis, and relates to the technical field of geophysical exploration and signal processing, and the method comprises the steps: obtaining at least two geophysical attributes sensitive to medium absorption attenuation through attribute extraction based on seismic data; based on geophysical attributes, constructing an effective quantum potential field which comprehensively reflects the absorptivity and heterogeneity of the underground medium; constructing a discrete Hamiltonian matrix for describing a seismic signal quantization system based on the effective quantum potential field; performing characteristic decomposition on the discrete Hamiltonian matrix to obtain an orthogonal quantum adaptive characteristic function; and analyzing local time-frequency spectrum attenuation characteristics of the quantum adaptive characteristic function, and obtaining a quantum attenuation gradient value through calculation and synthesis. The method solves the problems that an existing seismic attenuation gradient estimation method is low in resolution, poor in noise immunity, insufficient in capacity of distinguishing elastic impedance difference and inherent attenuation, and lack of a unified physics and mathematics framework for organically fusing multi-attribute information.