14 results about "Bayesian risk" patented technology

The invention discloses a reservoir dam safety monitoring method and system based on edge calculation, and relates to the technical field of hydraulic engineering safety monitoring, and the method comprises the steps: obtaining monitoring data by each edge calculation node, carrying out the preprocessing, and generating a standardized data matrix; establishing a reference database, executing anomaly detection, and generating a labeling time sequence data matrix; performing multi-scale decomposition on the labeled time sequence data matrix, and constructing a node response feature matrix; the central processing unit receives data of each edge computing node, analyzes a multi-parameter spatial propagation mode by constructing a parameter-spatial correlation matrix, and obtains a spatial correlation feature matrix; establishing a Bayesian risk assessment model, predicting a dam risk level and outputting a risk evolution trend; and issuing a differentiated early warning instruction according to the risk assessment result. Through a distributed architecture combining edge calculation and central processing, real-time monitoring, intelligent analysis and accurate early warning of the dam safety state are realized, and the monitoring efficiency and the risk identification accuracy are improved.

The invention discloses a real-time multi-dimensional sensitivity evaluation and self-adaptive safety prevention and control method and system for natural resource geographic information. The method comprises the following steps: acquiring real-time natural resource geographic information data; obtaining a preset behavior graph model; updating a preset behavior graph model according to the real-time natural resource geographic information data so as to obtain an updated behavior graph model; acquiring an updated node risk vector according to the updated behavior graph model; obtaining a trained Bayesian risk prediction model; inputting the updated node risk vector into a trained Bayesian risk prediction model so as to obtain a real-time abnormal behavior identification result; and generating a personalized prevention and control strategy scheme according to the real-time abnormal behavior recognition result. According to the method, intelligent identification, dynamic evaluation and active protection of natural resource geographic information in a full life cycle are realized by constructing a multi-dimensional sensitivity quantitative model, a dynamic risk perception mechanism based on a graph structure and a safety prevention and control strategy capable of being updated in real time.

The invention relates to the technical field of intelligent fuel supply, in particular to an intelligent optimization method and system for fuel supply of a thermal power plant based on multi-source information fusion. The method comprises the following steps: collecting multi-source heterogeneous data and carrying out space-time alignment and normalization processing; constructing a coal as fired calorific value soft measurement model by adopting a physical constraint corrected LSTM network; generating a transportation delay predicted value and probability distribution thereof through an XGBoost regression model; calculating a comprehensive risk score in combination with a Bayesian risk network; solving a Pareto optimal solution set under the constraint of an inventory safety threshold by adopting a depth deterministic strategy gradient network, and generating a fuel scheduling instruction; and updating the as-fired coal calorific value soft measurement model on line. Through combination of the physical constraint corrected LSTM network and multi-source time sequence data fusion and regularization training, the fire coal calorific value prediction precision is remarkably improved, and the problems that a traditional method depends on off-line assay, response is lagged, and the real-time dynamic state of the combustion process is difficult to reflect are solved.

The invention provides a bidirectional LSTM photovoltaic power generation prediction method based on wavelet decomposition and double attention, and belongs to the technical field of power generation prediction. Selecting an optimal wavelet basis function by using a particle swarm optimization algorithm to carry out adaptive noise complete set empirical mode decomposition on the power sequence to obtain a multi-layer intrinsic mode function component, and carrying out adaptive denoising and power signal reconstruction according to a multi-scale permutation entropy and a Bayesian risk minimization criterion in combination with meteorological conditions; key feature variables are extracted through a maximum information coefficient, a bidirectional long-short-term memory network prediction framework is established, a feature attention mechanism and a double-path time attention structure are introduced, and when power mutation or irradiance mutation is detected, a sparse attention weight rapid reconstruction mechanism is triggered to complete prediction. The technical problem that the prediction precision is reduced when the photovoltaic power generation power changes suddenly under the cloudy weather condition is solved.

The invention discloses a cooperative spectrum prediction method based on minimum Bayesian risk, and relates to the technical field of cognitive radio and wireless communication. According to the method, each secondary user independently completes local spectrum sensing and power prediction; the fusion center performs system perception judgment by using a historical optimal fusion rule, calculates a channel state prior probability, and fits a predicted power condition probability density function of each user in two system states; then, according to a minimum Bayesian risk criterion, through alternative iteration optimization of each user judgment threshold and a system fusion rule, an optimal threshold and a fusion rule are obtained; and finally, obtaining a system-level cooperative spectrum prediction result through threshold comparison and fusion. The method does not depend on prior channel information, has good flexibility and expansibility when the number of users changes dynamically, improves prediction precision and robustness in a complex environment, and can balance main user protection and spectrum access efficiency through a cost factor.

The present invention proposes a method for analyzing unknown hazards of the expected functional safety of in-vehicle digital twins based on a Bayesian model, which includes four steps. Step 1: First, a digital twin of the autonomous driving vehicle to be evaluated is constructed using CARLA, and an autonomous driving scenario is constructed using CARLA, including a map, other traffic participants, etc. The twin scenario is repeatedly run, and the driving data of the vehicle to be evaluated and the probability of being exposed to risks are recorded; Step 2: A risk map is constructed based on the driving data of the vehicle to be evaluated, and the risk map is converted into a Bayesian risk map; Step 3: Based on the Bayesian risk map and combined with the Noisy-OR and Noisy-AND structures, a conditional probability table of triggering events of each node is calculated; Step 4: According to the conditional probability table obtained in step 3 and combined with the CVSS universal vulnerability scoring system, the expected functional safety with unknown triggering events is comprehensively evaluated, and a safety evaluation score is given.

The invention discloses an unknown risk analysis and evaluation method for a power distribution edge computing network. The analysis and evaluation method comprises the following steps: constructing a hierarchical Bayesian risk network HBRN; the hierarchical Bayesian risk network comprises a power grid topological structure, typical working conditions, working parameters, noise nodes and potential risk scenes; the triggering probability of an unknown triggering event is calculated and evaluated by combining the prior probability of the working parameters corresponding to the typical working conditions with the noise nodes; and evaluating a potential risk occurrence probability of the power distribution edge computing network and a corresponding noise node triggering probability by integrating a power grid topological structure and a noise node probability computing method, and taking the potential risk occurrence probability and the corresponding noise node triggering probability as a final risk evaluation score. The invention also discloses an analysis and evaluation system for realizing the analysis and evaluation method, and application of the method or the system in unknown risk analysis and evaluation of the power distribution edge computing network.

The application discloses a real-time multi-dimensional sensitivity evaluation and adaptive security prevention and control method and system for natural resource geographic information. The method comprises the following steps: acquiring real-time natural resource geographic information data; acquiring a preset behavior graph model; updating the preset behavior graph model according to the real-time natural resource geographic information data, thereby obtaining an updated behavior graph model; acquiring an updated node risk vector according to the updated behavior graph model; acquiring a trained Bayesian risk prediction model; inputting the updated node risk vector into the trained Bayesian risk prediction model, thereby obtaining a real-time abnormal behavior recognition result; and generating a personalized prevention and control strategy scheme according to the real-time abnormal behavior recognition result. The application realizes intelligent identification, dynamic evaluation and active protection of natural resource geographic information in the whole life cycle by constructing a multi-dimensional sensitivity quantification model, a dynamic risk perception mechanism based on a graph structure and a real-time updateable security prevention and control strategy.

The invention discloses a block cipher operation mode classification method and system based on a COMC-DBST model, and belongs to the technical field of information security. Comprising the following steps: converting an original ciphertext into a dual-scale grayscale image, and performing CLAHE enhancement on a high-resolution image to amplify texture features; a double-branch Swin Transform architecture is adopted to process double-scale images respectively, a learnable absolute position code and a layered window attention mechanism are integrated, and multi-scale feature fusion is achieved; a hard voting decision mechanism is designed based on Bayesian risk minimization, an ECB mode is recognized preferentially, and the misjudgment risk is reduced. According to the method, the defects of shallow feature modeling, insufficient structural feature utilization and limited generalization ability in password operation mode classification are overcome, block password operation mode classification can be quickly and accurately carried out, and the method is suitable for practical engineering scenes such as ciphertext analysis, network security audit and encryption configuration compliance check.

The application discloses a kind of government affair work order intelligent distribution and efficiency closed loop management method and system, belong to government affair service intelligent processing technical field, the implementation of this method includes: through multimodal fusion classification model processing work order input data, through deep learning model realizes high-precision semantic understanding and entity extraction, generates structured work order entity information;Based on reinforcement learning dynamic decision engine, according to real-time department load state and geographic weight calculation optimal distribution path;Utilize the risk early warning model of bayesian network to monitor the progress of disposal, when the probability threshold triggers when overdue, automatically supervise and deal with.This application realizes the upgrading of the precision, real-time and closed loop of the whole link of work order processing through multimodal fusion classification, reinforcement learning distribution decision and bayesian risk intervention triple technical innovation, solves the problem of insufficient semantic understanding accuracy, lack of dynamic scheduling capability and poor real-time supervision in existing government affair work order system.

The invention discloses an intelligent power-off control method and system for high-voltage transmission induced electricity monitoring data fusion, and belongs to the technical field of power system safety protection. The method comprises the following steps: constructing a heterogeneous data set through a multi-dimensional induced electricity monitoring array; extracting an induced electric intensity vector and an environment parameter vector based on the heterogeneous data set, and determining a first risk level based on the induced electric intensity vector and the environment parameter vector; constructing a dynamic Bayesian risk network according to the induced electric strength vector and the environmental parameter vector, and performing real-time risk assessment to obtain a second risk level; and performing weighted integration on the first risk level and the second risk level to obtain an integrated risk level, and determining a protection action of the circuit breaker based on the integrated risk level. According to the method, fusion of the multi-source data in the feature layer and the decision layer is realized, the depth and the real-time performance of data fusion are improved, and the problem of low fusion degree of the multi-source data in the prior art is solved.

The application provides an adaptive phase unwrapping method based on local gradient statistics, and relates to the technical field of ship navigation, and comprises the following steps: S1, pre-processing a received signal to separate two baseband continuous wave signals; S2, extracting instantaneous wrapped phases of the two baseband continuous wave signals and subtracting to obtain a wrapped phase difference sequence; S3, calculating a local gradient mean and a local standard deviation of the wrapped phase difference sequence by using a sliding window; S4, dynamically generating a phase jump detection threshold of each sampling point according to a Bayesian risk minimization criterion; S5, performing jump detection and compensation on the wrapped phase difference sequence according to the dynamic threshold to obtain a continuous phase difference sequence; and S6, performing least square smoothing on the continuous phase difference sequence to output a smoothed phase difference sequence. The application significantly improves the phase unwrapping success rate in a low signal-to-noise ratio environment.

The invention provides a fast phase and Doppler frequency shift estimation method based on prior information, and belongs to the technical field of aerospace navigation, and the method comprises the steps: building two types of prior estimation models according to whether a spacecraft state error is considered or not; a general Bayesian risk function is established according to a Bayesian model and a loss function, and different objective functions including maximum likelihood estimation and parameter prior information are obtained by selecting the loss function. For a non-convex problem of an objective function, a fast non-convex optimization method with interval constraint is provided, a parameter interval range is determined based on prior information, so that the objective function can be regarded as a convex function in a constraint interval, an F-BFGS-B algorithm is provided based on a BFGS algorithm framework, and the parameter range is limited. According to the method, the proper search step size can be quickly found, and the estimation precision and the real-time performance can be considered at the same time.