18 results about "Alarm filtering" patented technology

A system capable of optimizing early alarm operation by introducing an alarm filtering technology so as not to cause false alarm to an abnormal signal due to signal noise is disclosed. The system comprises: a data acquisition unit for selectively acquiring historical data according to the operation of a electric power facility by selecting a preset multivariate input tag; a recommendation unit for generating learning data, which is a multivariate signal for machine learning, based on a preset similarity from the historical data; a compression unit for generating re-sampling data by compressing the learning data; a learning unit for performing real-time monitoring by using the re-sampling data as input data of a pre-designed early warning learning model; and a calculation unit for generating a final warning when a predetermined condition predefined through the real-time monitoring is satisfied.

The invention discloses a tunnel AI event detection system and method based on spatio-temporal feature fusion, and the system achieves the cross-point event merging and repeated filtering through constructing the differentiated feature vectors of congestion, parking and spilled objects and carrying out the weighted calculation of the comprehensive similarity through the three elements of time, space and features, and supports the dynamic adjustment of the spatial similarity parameters. And a filtering rule of crossing three points and low feature similarity is designed for a light object. The method is suitable for real-time detection and repeated alarm filtering of events such as congestion, parking and object throwing in the expressway tunnel, realizes real-time supervision of the events in the tunnel, then effectively analyzes and timely issues the event information, realizes real-time and accurate detection of various events affecting traffic safety in the expressway tunnel, and improves the traffic safety of the expressway tunnel. Therefore, effective services are provided for drivers and conductors and expressway managers. The tunnel traffic safety is ensured; and the traffic service capability is improved.

The application relates to the field of liquid treatment, in particular to a negative pressure self-alarming filter device which comprises a rigid vertical cylinder, a quick-release inner filter is arranged in the inside of the rigid vertical cylinder, a feeding pipe is arranged on the outer sidewall of the rigid vertical cylinder at the upper portion of the quick-release inner filter; a plugging bottom cover is tightly screwed on the bottom of the rigid vertical cylinder, a discharging pipe is arranged on the outer sidewall of the lower portion of the rigid vertical cylinder, a plugging top cover is arranged on the upper connecting flange of the top of the rigid vertical cylinder, one side of the plugging top cover is connected with the upper connecting flange through a lifting lug bolt, a pressure reference control component is arranged at the center hole of the plugging top cover, and an output end pressure component matched with the pressure reference control component is arranged on the rear sidewall of the lower portion of the rigid vertical cylinder.

The present application belongs to the field of transmission line online monitoring, and more particularly to a kind of image-based transmission overhead line passage hidden danger alarm filtering method.The method includes obtaining visualized photographed picture and manually drawing polygon protection zone, the polygon protection zone is divided into effective protection zone and invalid protection zone;According to the coordinate set C i Of the n endpoints of the polygon protection zone obtained in sequence, and the left lower vertex and the right upper vertex of the identified rectangular alarm box;According to the coordinate set C i And the left lower vertex and the right upper vertex of the rectangular alarm box, the positional relationship between the polygon protection zone and the rectangular alarm box is judged;Filter the alarm according to whether the polygon protection zone is effective protection zone or invalid protection zone.The present application solves the problem that the number of hidden danger alarms identified in the prior art is also increasing, the work pressure of manual secondary confirmation is also increasing, causing the difficulty of monitoring and operation.

The invention relates to the field of embedded software research and development, and discloses an embedded software defect detecting and filtering method and system and a medium. According to the method, a software static analysis defect detection report is output by performing static analysis on an embedded software source code by adopting a method of combining software static defect detection and large-model intelligent defect alarm filtering; generating a cue word script according to the defect detection requirement of the embedded software; and filtering the software static analysis defect detection report by using a pre-trained large model according to the cue word script, and outputting a software model analysis defect detection report. By further analyzing and processing a static detection result, filtering and determining real and effective software defects, the effect of detecting and positioning real defect vulnerabilities of the embedded system software is improved, the quality and stability of the embedded system software are enhanced, and rapid iterative upgrading of the embedded system software is supported.

The application belongs to the technical field of aircraft control system design, and particularly relates to an aircraft cabin alarm filtering method for improving man-machine efficiency, comprising: establishing a database including a correlation network of all alarm information of an aircraft; obtaining alarm information triggered by each component after the aircraft is powered on, and dividing the triggered alarm information into a correlation alarm group and a single alarm group other than the correlation alarm group through the correlation network, wherein a plurality of alarm information of the correlation alarm group is further divided into a core alarm and a plurality of induced alarms associated with the core alarm; and warning the core alarm, the single alarm and the induced alarm in different levels, which greatly improves the alarm recognition efficiency and disposal efficiency of pilots, reduces the cognitive load of pilots caused by redundant redundant alarms, and improves the flight safety of pilots.

The invention belongs to the technical field of intelligent power grid alarm processing, and particularly relates to a real-time alarm filtering method and system based on event filtering. The method comprises the following steps: setting a filter flag bit for each piece of alarm information according to a filter list, and then sending out the filter flag bit so as to filter the alarm information according to the filter flag bit of the alarm information; the filter list is updated in real time according to the following mode: when an event filter is enabled and a device of the event filter satisfies a corresponding filter rule, the filter list is updated so that information of the device and information of the event filter are written into the filter list; when an event filter is enabled and a device of the event filter does not satisfy a corresponding filter rule, the filter list is updated to cause information of the device and information of the event filter to be deleted from the filter list. According to the invention, the technical problem that the real-time performance of filtering the alarm during the occurrence period of the specific event is not high in the prior art is solved.

The application discloses a method and system for alarm screening display based on power plant working conditions and operation tasks, and the method comprises the following steps: establishing a power plant working condition alarm list corresponding to each power plant working condition according to different power plant working conditions, and screening alarm contents of the power plant working condition alarm list according to different state characteristics of different working conditions; establishing a self-defined alarm list according to operation tasks, and inputting alarm contents of the self-defined alarm list according to the operation tasks, which are different from the alarm contents of the power plant working condition alarm list; when an alarm is triggered, identifying whether the alarm is the alarm content of the power plant working condition alarm list or the self-defined alarm list, if yes, locating the position of the alarm in the two lists, and displaying the alarm on an interface. Through implementation of the application, the task load of alarm response of operators can be reduced in the work of the nuclear power plant, the performance of the operators is improved, and the risk of human error is reduced.

The invention provides a photovoltaic power station alarm filtering system and method based on Internet of Things modeling, and belongs to the technical field of photovoltaic power station fault detection. The Internet of Things platform carries out modeling on a meteorological station in the meteorological acquisition module, an inverter in the fault detection module, a power generation amount acquisition module and a grid-connected metering ammeter in the electric energy acquisition module. The Internet of Things platform judges day and night through solar radiation data collected by the weather station, and judges whether the photovoltaic power station breaks down or not through fault signals collected by the inverter when judging that the current time is daytime. And the Internet of Things platform collects the generating capacity data of the photovoltaic power station through the inverter, and calculates the daily generating efficiency of the photovoltaic power station in combination with the radiation daily accumulated value collected by the weather station. And the Internet of Things platform collects the electric energy output data of the photovoltaic power station through the grid-connected metering ammeter and calculates the power factor of the photovoltaic power station. The configuration efficiency of the alarm rule of the photovoltaic power generation system is improved.

The purpose of the embodiments of the present application is to provide a method, apparatus, medium, and electronic device for alarm filtering, the method comprising: obtaining an initial alarm event according to a detection rule; and confirming whether the initial alarm event is real alarm information by at least matching the initial alarm event with events in a noise filter set, wherein the events in the noise filter set are obtained by clustering the aggregated events. The embodiments of the present application do not require manual configuration of filtering rules (instead, the events in the noise filter set are obtained by clustering through an automatic clustering algorithm), which can eliminate the influence of human subjective judgment to a certain extent. The embodiments of the present application can effectively filter false alarms, reduce the false alarm rate, and thus reduce the burden on analysts.

The embodiment of the invention provides an automatic task alarm filtering method based on a multi-layer dynamic threshold value, and belongs to the technical field of data processing, and the method specifically comprises the following steps: retrieving all task data which is completed in a time window based on pre-configuration and has a final state of a preset completion state from a database; screening the task data by using a predefined normal state code set, and screening out the task data of which error codes exist in the normal state code set; sequentially executing at least three rounds of filtering based on a predefined static blacklist rule on the screened task data; distributing a real-time counter in a time window for each task type-error code combination, and taking the task data as target data when a count value of the real-time counter exceeds a threshold value of the corresponding combination; and assembling the target data into a structured alarm message, and pushing the structured alarm message based on the dynamically determined on-duty person information. By means of the scheme, the filtering precision and adaptability are improved.

The application discloses a log alarm filtering method and device, equipment and medium, and relates to the technical field of program control. The method comprises the following steps: configuring a first layer index according to the application name of a target application; determining target log data corresponding to the target application and a target filtering word related to an alarm based on the first layer index; traversing the target filtering word, extracting a keyword as a search key according to a preset rule for each target filtering word, and constructing a second layer index; and traversing the target log data by using the second layer index, performing fuzzy query and filtering on the target log data, and completing alarm filtering on the target log data. Through the above scheme, the problem of instability of the log system is avoided, the number of fuzzy queries and the content of fuzzy queries are reduced, and the efficiency of log alarm filtering is improved. Therefore, the number of fuzzy queries can be reduced and log alarm filtering can be optimized when log alarm filtering is performed.

The application discloses an alarm processing method, system, device, storage medium and program product, relates to the technical field of computers, and comprises the following steps: after receiving current attribute information set by a sensor alarm, a configuration file configured with an alarm filtering rule according to actual requirements is acquired; it is judged whether the current attribute information meets the alarm filtering rule; and in the case where the alarm filtering rule is met, the alarm of the sensor is removed. The application solves a series of problems caused by the failure to filter alarms, alarm filtering is performed through flexible and configurable alarm filtering rules, and the technical effects of reducing redundant log accumulation and improving log management efficiency are achieved.

In various embodiments, a process for alert filtering based on service to facilitate triage includes receiving an alert, identifying a configuration item of a computer information technology configuration management system associated with the alert, and identifying a property of the configuration item stored separately from one or more properties included in the alert. The process includes enabling filtering of the alert based on the property of the configuration item.

The invention belongs to the technical field of monitoring systems, and particularly relates to a data machine room environment dynamic monitoring system which comprises an intelligent sensing layer, an edge computing layer, a cloud analysis layer and a user interaction layer. The edge computing layer and the cloud analysis layer cooperatively execute three-level alarm filtering: in the first level, sensor data transient noise filtering is performed at an edge computing node; the second stage executes multi-sensor correlation analysis at an edge computing node to locate a root cause fault; and the third level verifies the alarm effectiveness in a cloud analysis layer through a dynamic threshold model trained by historical data, and the dynamic threshold model is associated with an equipment aging factor to correct an alarm triggering condition. The sensor data is preprocessed in real time through the edge calculation layer, the data transmission amount is reduced, the network delay is reduced, the real-time performance of the system is remarkably improved, and abnormal changes of the machine room environment can be quickly responded.

An object of the present invention is to provide a SCADA web HMI system that can reduce a load for processing an alarm signal in a large-scale system. An HMI server apparatus performs buffering processing and alarm filtering processing. In the buffering processing, in a case where a received block data includes a set of alarm signals, at least the set of alarm signals included in the block data is temporarily stored in an alarm buffer memory. In the alarm filtering processing, the set of alarm signals stored in the alarm buffer memory is taken out for every second period that is longer than a first period, and the alarm signal having a value varied from a previous value is extracted from the taken-out set of alarm signals.

The invention discloses a host security fine management and control system of an industrial control system, which comprises an application layer, a data transmission and analysis layer and an acquisition and terminal protection layer, and is characterized in that the application layer comprises a security instrument panel, a log analysis unit, a security alarm unit and a peripheral management unit; the data transmission and analysis layer comprises a log centralized convergence engine, a security baseline check engine, a user state management engine and an alarm optimization engine; and the acquisition and terminal protection layer comprises enhanced host Agent clients deployed at the industrial control nodes. According to the host security fine management and control system of the industrial control system disclosed by the invention, by constructing the enhanced host Agent client and a multi-engine collaborative architecture, log collection comprehensiveness, data processing high efficiency, baseline check refinement, account management and control precision and alarm filtering intellectualization are realized, and the host security protection capability of the Eimeson industrial control system is improved.

This invention discloses a method for analyzing the causes of alarm filtering failures in a network management system, including: S1. Retrieving relevant alarms and rules through an interface query, selecting one alarm and one rule as input parameters and passing them to the controller; S2. A verification environment generator searches for the filtering conditions of a rule based on its rule ID and dynamically compiles and generates a corresponding verification simulation environment; S3. Passing the alarm into the verification simulation environment to match each filtering sub-condition and obtain the filtering result; S4. Passing the filtering result into a filtering result analyzer to obtain an analysis report; S5. Displaying the analysis report on the interface. This invention transforms the problem analysis process from manual to code-based, improving analysis efficiency, reducing the probability of errors, and increasing the accuracy of problem analysis. Through interface interaction and the provision of precise and detailed analysis reports, it not only provides a user-friendly and intuitive way to locate the causes of filtering failures for specific alarms and rules but also reduces learning costs and labor costs.