9 results about "Sequential probability ratio test" patented technology

The invention discloses an interpretable anomaly detection method and device for a top drive drilling device, equipment and a medium, which are applied to the field of drilling engineering, and are used for acquiring operation data of a to-be-detected mechanical part in the top drive drilling device, and dividing the operation data into various working condition data sets based on working condition parameters, extracting feature data of each feature parameter from each working condition data set; determining a working condition sensitivity index and a conflict index based on a grey correlation degree coefficient and a correlation coefficient between the characteristic parameters, and optimizing memory matrix input parameters by utilizing sensitivity analysis and correlation analysis; a clustering algorithm is used for screening sample data to construct a spatial memory matrix, and a multivariate state estimation method and a sequential probability ratio test method are combined to carry out anomaly detection on the mechanical part to be detected; furthermore, interpretability analysis of the abnormal parameters is carried out, and the abnormal key parameters are visually revealed. The self-adaptive judgment of the running state of the equipment and the abnormal traceability of each mechanical part in the top drive well drilling device are realized.

The invention relates to the technical field of intelligent security and protection, in particular to a key personnel identification passing and early warning system based on multi-modal biological characteristics, and the system is used for executing the flow: collecting and binding to generate a world line object; face features, speaker features and gait features are extracted through alignment modeling, an alignment time event sequence is obtained through optimal transmission, and combined evidence is formed through Copula combined modeling and topological data analysis; according to the consistent anti-verification, geometric and sound source beam consistency, audio-visual mutual prediction anti-verification, visual living body anti-verification and audio playback anti-verification are generated in alignment time, and evidences are accumulated into a logarithmic posteriori trajectory of world line identity; decision control implements confidence control through sequence probability ratio test and conformal prediction, outputs passing, attention or interception instructions, and gives consideration to real-time performance, accuracy and evidence obtaining traceability.

This invention discloses a deep learning-based method for predicting storage device failures, comprising: collecting operational monitoring data of the storage device; preprocessing to construct a time-series health representation sequence; performing adaptive window construction to extract the modeling sequence; establishing a topology graph and aggregating the node-level health representation sequences; constructing an improved SCINet model to obtain a prediction sequence; calculating the prediction residual sequence and generating a standardized residual sequence; outputting a failure risk judgment result based on the sequential probability ratio test; generating alarm information and triggering coordinated operation and maintenance actions. This invention, by combining the improved SCINet model and the sequential probability ratio test, achieves online prediction and early warning-based coordinated handling of storage device failure risks.

The present invention provides a hybrid fault-tolerant control method and system for scenarios where multiple sensors fail simultaneously. The method comprises: inputting historical time-series feature data of sensors into a long-short-term memory network and a stacking model, respectively, to obtain predicted values ​​of the sensor's output data at the current moment output by the long-short-term memory network and the stacking model; determining whether a sensor failure has occurred using a sequential probability ratio test based on the difference between the predicted value of the sensor's output data at the current moment output by the long-short-term memory network and the actual value of the output data; and, if a sensor failure has occurred, determining a reconstructed value of the sensor's output data at the current moment based on the predicted value of the sensor's output data at the current moment output by the long-short-term memory network and the stacking model. The present invention can perform real-time sensor fault detection and output data reconstruction, improving the stability and reliability of the system in the event of multi-point observation failure.

The invention provides a marine scientific research project fund execution progress monitoring model construction method, which belongs to the technical field of large model construction, and comprises the following steps: extracting a potential expenditure mode, identifying a project execution mode category by adopting a dynamic time warping algorithm, constructing a multi-task learning neural network, and predicting fund and progress at the same time. Starting a CUDA (Compute Unified Device Architecture) parallel computing framework to run a cumulative sum control chart, a Hotelling T square statistic and a wavelet multi-scale decomposition task in a three-layer thread block to realize anomaly detection, calculating an anomaly confidence coefficient through sequential probability ratio test to trigger an early warning mechanism, and adopting a multi-interpolation method for missing data, so as to complete the detection of the missing data. Robust M estimation is adopted for the abnormal observation value to reduce the influence weight, the optimal estimation result is output through the Kalman filtering fusion model prediction value and the noise observation value, and the technical problem that the marine scientific research project fund execution progress monitoring lacks the abnormal detection and prediction capability is solved.

The invention discloses a phase sequence automatic identification and correction distribution box system. The system comprises a three-phase voltage synchronous sampling module; a Clarke transformation calculation unit; a sequential probability ratio test judgment unit; the cross validation unit is used for reconstructing a space vector rotation angle from the two-phase static coordinate system component, converting the space vector rotation angle into an equivalent inter-phase included angle, substituting the equivalent inter-phase included angle into a cost function for independent scoring, and performing consistency comparison with a result of the sequential probability ratio test judgment unit; a safety interlocking unit; a correction execution unit; a three-phase imbalance factor output by the Clarke transformation calculation unit is fed back to the sequential probability ratio test judgment unit in real time, noise model parameters of the sequential probability ratio test judgment unit are dynamically adjusted, and a signal quality self-adaptive closed-loop judgment mechanism is formed. In conclusion, the invention provides the intelligent phase sequence automatic identification and correction distribution box system which can break through the contradiction between the detection speed and the judgment reliability, has signal quality self-adaptive capability and provides quantifiable misjudgment rate guarantee.

The invention relates to the technical field of industrial production management, and provides a multi-stage product production process decision-making method and system based on dynamic planning, and the method comprises the steps: carrying out the sampling of spare and accessory parts, semi-finished products and finished products through employing a sequential probability ratio inspection method, determining the defective rate of each stage of products, calculating the mathematical expectation of the defective rate of a confidence interval, and carrying out the calculation of the defective rate. The actual defective rate is obtained; based on the actual defective rate, determining an optimal production decision scheme through a dynamic planning model; wherein the construction step of the dynamic planning model comprises the following steps of: for a multi-process production process, simplifying processes into a plurality of regions through a region division method, constructing an objective function by taking part detection before assembly, semi-finished product detection after assembly, finished product detection after assembly and disqualified semi-finished product and finished product disassembly as decision variables and taking the regions as units, and constructing the dynamic planning model according to the objective function; and deducing a defective rate state transition equation of semi-finished products and finished products. The decision-making problem in multi-process production can be effectively solved, and global optimization is achieved.

The invention discloses an optimization method for destructive sampling detection in a product production process. The method comprises the following steps: 1, performing initialization setting in a simulated annealing algorithm stage; 2, performing simulated annealing algorithm iteration based on the parameters initialized in the step 1, and optimizing the parameters through an iteration process; 3, setting hypothesis and decision boundaries in the Bayesian sequential probability ratio test; step 4, calculating a likelihood ratio by using the parameters optimized in the step 2 and based on prior distribution optimized by a simulated annealing algorithm; and 5, comparing the likelihood ratio calculated in the step 4 with a decision boundary value to make a decision. On the premise of ensuring the inspection accuracy, the sampling efficiency is improved, and the sampling cost is reduced.

The invention discloses a digital filling control method and system based on machine learning, and the system comprises a collection and preprocessing module which is used for collecting multi-source data, completing the preprocessing, and generating fusion input data; the VMama prediction module is used for outputting prediction distribution parameters and visual risk indexes; the sequential inspection module is used for executing sliding window logarithm likelihood accumulation and observation dimension switching and outputting an inspection judgment result; the strategy compensation module is used for generating a filling control strategy, calculating a compensation control quantity and outputting a control parameter set; the constraint execution module is used for carrying out process verification and issuing a control instruction to realize real-time correction; and the traceability degradation module is used for recording traceability data and triggering security degradation and archiving. By improving the VMama model and the sequential probability ratio test, real-time prediction and self-adaptive compensation control of the filling amount are realized.