A kind of intelligent detection method and system for abnormality of tailings filling pipeline
A technology for tailings filling and intelligent detection, applied in neural learning methods, digital data information retrieval, instruments, etc., can solve problems such as lack of detection technology, improve safety, avoid serious accidents, and reduce economic losses.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0053] Aiming at the problems of lack of index system and insufficient amount of negative sample data widely existing in the current abnormality detection of industrial equipment, this embodiment provides an intelligent detection method for abnormality of tailings filling pipeline, which can be realized by electronic equipment. A device can be a terminal or a server.
[0054] The method is based on the flow and pressure data measured at each monitoring node of the tailings filling site pipeline. After data preprocessing, the flow and pressure time series pipeline transportation characteristic sequences in the process of filling slurry are constructed respectively based on the sliding window time series segmentation model; Then, using the flow and pressure time series pipeline feature sequences as two nodes that are mutually dual, the feature sequences are spliced into a multi-dimensional flow and pressure feature matrix as input, and two dual generative adversarial networks w...
no. 2 example
[0110] This embodiment provides an intelligent detection system for tailings filling pipeline abnormalities, which includes the following modules:
[0111] The pipeline parameter time series feature sample building module is used to collect the pipeline parameters of each monitoring node in the normal operation state of the pipeline during the tailings filling process, and build the time series feature sample data based on the collected pipeline parameters; wherein, the pipeline Parameters include flow and pressure;
[0112] The pipeline parameter generation model building module is used to construct a generative adversarial network model, and the constructed generative adversarial network model is trained by using the time series feature sample data constructed by the pipeline parameter time series feature sample building module, so as to obtain a Generate a pipeline parameter generation model for pseudo pipeline parameters;
[0113] The filling pipeline abnormality detectio...
no. 3 example
[0116] This embodiment provides an electronic device, which includes a processor and a memory; wherein, at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor to implement the method of the first embodiment.
[0117] The electronic device may vary greatly due to different configurations or performances, and may include one or more processors (central processing units, CPU) and one or more memories, wherein the memory stores at least one instruction, so The instructions are loaded by the processor and execute the above method.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More