Search

CN-121997239-A - Multi-mode sensing abnormality detection and acousto-optic interaction method and system for process layer equipment

CN121997239ACN 121997239 ACN121997239 ACN 121997239ACN-121997239-A

Abstract

The application provides a multi-mode sensing abnormality detection and acousto-optic interaction method and system of process layer equipment, which relate to the technical field of industrial automation, and are characterized in that an original operation data set is formed by collecting energy consumption fluctuation data and wireless communication quality data of a process layer equipment cluster and combining equipment identification, an associated identification of equipment is marked for the original operation data set to form an associated data set, an initial filtering gain parameter of a self-adaptive filtering circuit is regulated and verified, a target filtering gain parameter is determined, signal filtering is carried out on the associated data set according to the initial filtering gain parameter, an equipment operation link is finally generated, abnormal equipment with parameters deviating from a normal range in the link is identified, an equipment abnormality judgment result is generated, an alarm level is determined, and corresponding alarm audio signals, optical signals and ultrasonic carriers are generated; the characteristic parameters are modulated to the ultrasonic carrier wave, and the directional acousto-optic prompt of the abnormal region is completed by combining the optical signals, so that the precise identification, abnormal detection and the intellectualization and the precision of the acousto-optic prompt of the hidden abnormality under the complex working condition are realized.

Inventors

  • MENG YUEFENG
  • ZHOU ZHENG

Assignees

  • 斯普屹科技(北京)有限公司

Dates

Publication Date
20260508
Application Date
20260407

Claims (10)

  1. 1. The multi-mode sensing abnormality detection and acousto-optic interaction method for the process layer equipment is characterized by comprising the following steps of: Collecting energy consumption fluctuation data and wireless communication quality data generated in the operation process of each device in the process layer device cluster, and combining device identifiers of each device to form an original operation data set of the process layer device cluster; counting the physical connection frequency and the data interaction quantity among the devices to label the device association identifier for the original operation data set and form an association data set comprising the device association identifier; according to the associated data set, the initial filter gain parameter of the adaptive filter circuit is adjusted and verified to obtain a target filter gain parameter, so that the associated data set is subjected to signal filtering operation, and a processed associated data set is generated; Generating a device operation link according to the processed associated data set, and identifying abnormal devices in which energy consumption fluctuation data and wireless communication quality data deviate from corresponding normal ranges in the device operation link through a graph neural network so as to generate a device abnormality judgment result; determining an alarm level according to the equipment abnormality judgment result to generate an alarm audio signal, an optical signal and an ultrasonic carrier corresponding to the alarm level; modulating the characteristic parameters of the alarm audio signal to the ultrasonic carrier wave to form a directional ultrasonic carrier wave signal, and combining the optical signal to finish directional acousto-optic prompt of a specific area where the abnormal equipment is located.
  2. 2. The method of claim 1, wherein modulating the characteristic parameters of the alert audio signal to the ultrasound carrier wave to form a directional ultrasound carrier wave signal, and combining the optical signal to complete a directional acousto-optic cue of a specific area where the abnormal device is located, comprises: Extracting characteristic parameters for modulating to an ultrasonic carrier wave from the alarm audio signal, wherein the characteristic parameters comprise signal frequency, playing duration and electric signal amplitude corresponding to tone height respectively; modulating the characteristic parameters to the ultrasonic carrier wave to form a modulated ultrasonic signal; According to the abnormal equipment and the position information of the corresponding abnormal equipment in the equipment abnormality judging result, the modulated ultrasonic signals are directionally transmitted through an ultrasonic transmitting device so as to form a focusing sound field in a specific physical area where the abnormal equipment is located, and the modulated ultrasonic signals are combined to form a directional ultrasonic carrier signal; Generating an optimized optical signal with the emission time synchronous with the directional ultrasonic carrier signal and the optical coverage matched with the range of the focusing sound field according to the optical signal parameters and the optical signal; And when the directional ultrasonic carrier signal is received in the focusing sound field, generating an audible prompt corresponding to the alarm audio signal and a visual prompt corresponding to the optimized optical signal and a specific physical area where each abnormal device is located so as to finish the directional audible and visual prompt of the specific area where the abnormal device is located.
  3. 3. The method according to claim 2, wherein according to the abnormal devices and the position information of the corresponding abnormal devices in the device abnormality determination result, the modulated ultrasonic signals are directionally transmitted by an ultrasonic transmitting device to form a focused sound field in a specific physical area where the abnormal devices are located, and the modulated ultrasonic signals are combined to form a directional ultrasonic carrier signal, including: determining the relative orientation of the abnormal equipment and the ultrasonic transmitting device according to the abnormal equipment position information in the equipment abnormality judging result, and converting the relative orientation into a directional transmitting angle; Determining the directional transmitting power required for maintaining the signal strength according to the space distance between the specific physical area where the abnormal equipment is located and the ultrasonic transmitting device; Transmitting the modulated ultrasonic signals by utilizing an ultrasonic transmitting device according to the directional transmitting angle and the directional transmitting power so as to form a focused sound field with coverage matched with the specific physical area; And forming a directional ultrasonic carrier signal according to the space constraint action and the directional propagation attribute of the focused sound field on the modulated ultrasonic signal.
  4. 4. The method of claim 1, wherein adjusting and verifying the initial filter gain parameters of the adaptive filter circuit to obtain target filter gain parameters based on the associated dataset to perform signal filtering operations on the associated dataset to generate a processed associated dataset, comprising: selecting signal data in a preset time period from the associated data set; Identifying a target signal component with signal amplitude exceeding a preset amplitude range in the signal data by a signal detection unit of the adaptive filter circuit, wherein the target signal component is a characteristic component corresponding to clutter signals generated by environmental electromagnetic interference; Calculating the sampling point duty ratio of the target signal component and the signal data, and adjusting and verifying the initial filter gain parameter of the self-adaptive filter circuit by combining parameter configuration data corresponding to the process layer equipment cluster to obtain a target filter gain parameter; And performing signal filtering operation on the associated data set by utilizing a signal processing unit of the self-adaptive filter circuit according to the target filter gain parameter to form a processed associated data set, wherein the corresponding relation between the energy consumption fluctuation data and the wireless communication quality data of each device and the device association identifier are reserved in the filtering operation.
  5. 5. The method of claim 4, wherein calculating the sampling point duty ratio of the target signal component to the signal data, in combination with parameter configuration data corresponding to a process layer device cluster, adjusts and validates an initial filter gain parameter of the adaptive filter circuit to obtain a target filter gain parameter, comprises: Counting the total signal sampling point number of the signal data and the signal sampling point number corresponding to the target signal component to calculate the sampling point duty ratio; according to the electromagnetic interference environment of the process layer equipment cluster, corresponding parameter configuration data are called, wherein the parameter configuration data comprise a preset first occupation ratio value, a preset second occupation ratio value and a gain adjustment rule of the adaptive filter circuit; According to the gain adjustment rule, the initial filtering gain parameter of the self-adaptive filter circuit is adjusted by combining the comparison result of the sampling point duty ratio with the first duty ratio and the second duty ratio to obtain an adjusted gain parameter; And verifying the adjusted gain parameters to obtain target filter gain parameters.
  6. 6. The method according to claim 1, wherein generating a device operation link from the processed association data set, identifying, by a graph neural network, an abnormal device in which energy consumption fluctuation data and wireless communication quality data deviate from a corresponding normal range in the device operation link, to generate a device abnormality determination result, comprises: Identifying the change trend of the energy consumption fluctuation data and the wireless communication quality data of each device under the same device association identifier from the processed association data set, and connecting the devices with synchronous association of the change trend according to the physical connection frequency to form a device operation link; setting a first normal range of energy consumption fluctuation data of each device and a second normal range of wireless communication quality data according to historical normal operation data of each device in the process layer device cluster; The equipment in the equipment operation link is used as a node, energy consumption fluctuation data and wireless communication quality data corresponding to each node are used as node attributes, and the node attributes of the nodes are respectively compared with the first normal range and the second normal range through a graph neural network, so that the node with the node attribute exceeding the corresponding normal range is marked as abnormal equipment; inquiring the corresponding relation between the prestored equipment identifier and the equipment position information according to the equipment identifier corresponding to the abnormal equipment, and determining the abnormal equipment position information corresponding to the abnormal equipment; and forming equipment abnormality judgment results by all abnormal equipment, corresponding equipment identifiers and abnormal equipment position information.
  7. 7. The method of claim 1, wherein determining an alert level based on the device anomaly determination result to generate an alert audio signal, an optical signal, and an ultrasonic carrier corresponding to the alert level comprises: calculating parameter deviation values of abnormal equipment in the equipment abnormality judgment result, and determining an alarm level by combining prestored alarm level rules; setting a first corresponding relation between the alarm level and the optical signal parameters based on the perception characteristic of human eyes on the optical signal so as to generate an optical signal corresponding to the alarm level; setting a second corresponding relation between the alarm level and the audio parameters according to the sound field environment characteristics of the process layer equipment cluster, and generating an alarm audio signal corresponding to the alarm level by combining the alarm level; Dividing the process layer equipment cluster into a plurality of physical areas based on the physical layout of the process layer equipment cluster, and distributing different preset frequency segments for each physical area; According to the abnormal equipment position information in the equipment abnormality judging result, determining a target frequency segment of a physical area to which each abnormal equipment belongs, selecting a center frequency in the target frequency segment, and generating an ultrasonic carrier wave with the center frequency as a frequency.
  8. 8. The process layer equipment multi-mode perception abnormality detection and acousto-optic interaction system is characterized by comprising: The acquisition module is used for acquiring energy consumption fluctuation data and wireless communication quality data generated in the operation process of each device in the process layer device cluster, and combining the device identifiers of each device to form an original operation data set of the process layer device cluster; The marking module is used for counting the physical connection frequency and the data interaction quantity among the devices so as to mark the device association identifier for the original operation data set and form an association data set comprising the device association identifier; The filtering module is used for adjusting and verifying the initial filtering gain parameter of the self-adaptive filtering circuit according to the associated data set to obtain a target filtering gain parameter so as to perform signal filtering operation on the associated data set and generate a processed associated data set; The identification module is used for generating a device operation link according to the processed associated data set, and identifying abnormal devices with energy consumption fluctuation data and wireless communication quality data deviating from a corresponding normal range in the device operation link through a graph neural network so as to generate a device abnormality judgment result; The determining module is used for determining an alarm level according to the equipment abnormality judging result so as to generate an alarm audio signal, an optical signal and an ultrasonic carrier wave corresponding to the alarm level; And the prompting module is used for modulating the characteristic parameters of the alarm audio signal to the ultrasonic carrier wave to form a directional ultrasonic carrier wave signal, and combining the optical signal to finish directional acousto-optic prompting of the specific area where the abnormal equipment is positioned.
  9. 9. An electronic device, comprising: A memory for storing a computer program; A processor for implementing the steps of the process layer device multimodal aware anomaly detection and acousto-optic interaction method of any one of claims 1 to 7 when executing the computer program.
  10. 10. A computer readable storage medium, wherein a computer program is stored in the computer readable storage medium, and when the computer program is executed by a processor, the computer program can implement the method for detecting and interacting with acousto-optic by using the process layer device multimode sensing according to any one of claims 1 to 7.

Description

Multi-mode sensing abnormality detection and acousto-optic interaction method and system for process layer equipment Technical Field The application relates to the technical field of industrial automation, in particular to a multimode-sensing abnormality detection and acousto-optic interaction method and system for process layer equipment. Background In complex systems such as industrial automation and smart grids, a process layer device cluster bears key tasks such as data acquisition, instruction execution and real-time control, and the running state of the process layer device cluster is directly related to the stability and safety of the whole system. With the continuous improvement of the integration level of the devices and the complexity of the system, the coupling relation among the devices is increasingly compact, and the abnormality of a single device can be rapidly propagated through physical connection or data interaction, so that the chain reaction is initiated, and the local and even global functions are disabled. The prior proposal tries to collect the operation parameters such as vibration, temperature, current and the like of equipment by deploying a distributed sensor network, and uses a machine learning algorithm to carry out pattern recognition on the collected data so as to judge whether the equipment has abnormal operation. However, the existing solutions are exposed to significant drawbacks in practical applications. For example, a fixed threshold value or a static filtering strategy is generally adopted in the data processing process, so that the dynamic change of signal interference in a complex electromagnetic environment is difficult to adapt, effective signals and noise are difficult to effectively separate, the accuracy of anomaly identification is influenced, modeling of cooperative operation relation among devices is lacking, potential faults caused by linkage anomalies of associated devices cannot be captured, early symptoms are easy to miss, and the like. Disclosure of Invention The application aims to provide a multi-mode sensing abnormality detection and acousto-optic interaction method and system for process layer equipment, which are used for solving the problems of difficult signal separation, early failure leakage and inaccurate abnormality identification caused by adopting fixed threshold or static filtering and lacking equipment collaborative modeling in the prior art. In order to solve the technical problems, in a first aspect, the present application provides a method for detecting abnormality and interacting with acousto-optic in process layer equipment by multi-mode sensing, comprising: Collecting energy consumption fluctuation data and wireless communication quality data generated in the operation process of each device in the process layer device cluster, and combining device identifiers of each device to form an original operation data set of the process layer device cluster; counting the physical connection frequency and the data interaction quantity among the devices to label the device association identifier for the original operation data set and form an association data set comprising the device association identifier; according to the associated data set, the initial filter gain parameter of the adaptive filter circuit is adjusted and verified to obtain a target filter gain parameter, so that the associated data set is subjected to signal filtering operation, and a processed associated data set is generated; Generating a device operation link according to the processed associated data set, and identifying abnormal devices in which energy consumption fluctuation data and wireless communication quality data deviate from corresponding normal ranges in the device operation link through a graph neural network so as to generate a device abnormality judgment result; determining an alarm level according to the equipment abnormality judgment result to generate an alarm audio signal, an optical signal and an ultrasonic carrier corresponding to the alarm level; modulating the characteristic parameters of the alarm audio signal to the ultrasonic carrier wave to form a directional ultrasonic carrier wave signal, and combining the optical signal to finish directional acousto-optic prompt of a specific area where the abnormal equipment is located. Optionally, modulating the characteristic parameter of the alarm audio signal to the ultrasonic carrier wave to form a directional ultrasonic carrier wave signal, combining the optical signal to complete directional acousto-optic prompt of a specific area where the abnormal equipment is located, including: Extracting characteristic parameters for modulating to an ultrasonic carrier wave from the alarm audio signal, wherein the characteristic parameters comprise signal frequency, playing duration and electric signal amplitude corresponding to tone height respectively; modulating the characteristic parameters to the ultrasonic