7 results about "Relative variation" patented technology

The invention discloses a method for determining an alarm threshold value of drill jamming early warning based on deep learning, and belongs to the technical field of petroleum drilling safety monitoring. Aiming at the problems of missing report and false report of double heights caused by large regional difference, scarcity of positive samples and incapability of a fixed threshold value to adapt to nonlinear high-dimensional data in the prior art, the method is based on logging data of six work areas including Ning, Lu, Yang, Huang, August and Foot and a jamming early warning model; three types of fluctuation ratio formulas of relative change rate, movement standard deviation and movement variation coefficient are innovatively provided and are matched with three threshold determination strategies of a double-side quantile warning method, a double-state quantile threshold method and an extreme value percentile warning method one by one, six sets of regionalization templates are formed, and accurate warning of one work area and one table is achieved. On-site verification shows that the early warning accuracy of drill jamming in each work area is improved by 15-35%, the highest early warning accuracy is 85%, and the false alarm amount is reduced by more than 30%.

The invention relates to the technical field of power systems, in particular to a wide area measurement system data time mark anomaly identification method and system, and the method comprises the following steps: S1, data collection and preprocessing; s2, constructing a time sequence relative variation matrix; s3, establishing an error data time sequence feature strategy table; s4, comparing and judging that the time marks are abnormal; and S5, carrying out abnormity positioning and alarming. According to the method, the time sequence relative variation matrix fused with the fractal features is constructed, and a composite similarity calculation method based on combination of DTW and cosine similarity is adopted to be compared with a predefined strategy table, so that whether the data time scale is abnormal or not and the type of the abnormality can be quickly and accurately judged; compared with a traditional method, the method has the advantages that the judgment speed and accuracy are greatly improved, and the false alarm rate of a WAMS-based power grid fault intelligent diagnosis and accident handling auxiliary decision-making system is reduced.

A method (100) for monitoring particle deposition in the magnetosphere comprises the steps of: detecting (101) charged magnetospheric particles by means of at least one particle detector (10) installed on at least one satellite vehicle (1) in orbit (3), associating the detected particles with respective detection data; processing (102) the detection data to associate respective kinetic energy estimates or kinetic energy measurements with the detected magnetospheric particles; obtaining a first count value N H (104) relating to the number of charged particles detected over a time period, the first count value being associated with relatively higher kinetic energy estimates or kinetic energy measurements comprised in a first energy range; obtaining a second count value N L (105) relating to the number of charged particles detected over said time period, the second count value N L being associated with relatively lower kinetic energy estimates or kinetic energy measurements comprised in a second energy range; detecting (106) a relative variation value of the second count value N L with respect to the first count value N H ; determining (107) that a pulse event of particle deposition in the magnetosphere - MPP event - has occurred over the aforementioned time period, comparing the aforementioned variation value with a threshold value; assigning (109) to said MPP event the geomagnetic longitude and time at which said MPP event occurred; defining (110) one or more groups of MPP events, each group comprising MPP events occurring over a time range, at the same geomagnetic longitude or at relatively close geomagnetic longitudes; identifying (111) a group of MPP events as indicative of a surface-originated activity, such as a pre-seismic activity or a seismic activity, based on the number of MPP events comprised in the group and / or based on the associated variation value found in the detection step (106).

This invention relates to a method for interpolating missing values ​​in arch dam temperature field monitoring data based on causal and proximity effects. The method includes: distinguishing between complete temperature time series and temperature time series to be interpolated; determining whether each missing value segment of each temperature time series to be interpolated meets the linear interpolation criteria based on the location and relative change amplitude of the missing value segments; if it meets the criteria, performing linear interpolation; if it does not meet the criteria, establishing a prediction model that considers both causal mechanisms and proximity effects, and performing machine learning interpolation based on a multi-measuring-point stratification standard and a same-layer priority criterion. This invention can achieve efficient and accurate interpolation of missing values ​​in arch dam temperature field monitoring data.

The application provides a slowness accumulation velocity field reliability evaluation method and system, the evaluation method comprises the following steps: using the relative change keeping thought of a velocity field, combining wave field continuation migration and rational approximation dispersion equation, and establishing the relationship between the wave field continuation operator and the migration velocity field; using the slowness accumulation item in the continuation operator to calculate the slowness matrix, and extracting the slowness accumulation curve of the migration velocity field to quantitatively depict the internal structure of the migration velocity field; using the cross-correlation function to calculate the similarity coefficient between the slowness accumulation curves of different original velocity fields and different migration velocity fields; using the slowness accumulation relative error and the migration result residual as constraints, and using the similarity coefficient of the slowness accumulation curve to represent the accuracy of the velocity field. The accuracy of the migration velocity field is efficiently and accurately determined.

The invention provides an industrial-grade communication performance evaluation and optimization method and system and a medium. The method comprises the steps of obtaining a preset number of real-time index feature data, processing the real-time index feature data to obtain effective index feature data, and processing the effective index feature data and corresponding historical index feature mean data to obtain relative change rate data, determining an importance weight value of each piece of relative change rate data, then processing by combining the relative change data to obtain communication performance change data, performing threshold comparison on the communication performance change data to obtain a communication performance change state, and obtaining a communication optimization scheme according to the communication performance change state and a preset communication performance requirement level of a preset position; therefore, by processing the historical index feature mean value data and the real-time index feature data and calculating the importance weight value and the communication performance change data, the industrial-grade communication performance evaluation and the optimization scheme obtaining are realized by combining threshold comparison.