Breaking News | Acomaxun Wins Another National Invention Patent!

Recently, our independently developed "A Real-Time Online Monitoring Method for a Pneumatic Control Valve" was granted an invention patent by the National Intellectual Property Office, patent number: ZL202411284617.0, and the patent certificate was obtained. This marks authoritative recognition of our technological innovation in the field of control valves!

This invention provides a real-time online monitoring method for a pneumatic control valve, including:

Collecting real-time signal data during the operation of the pneumatic control valve and transmitting it to the edge computing node for processing; the real-time signal data includes air chamber pressure data, valve stem displacement data, temperature data, and vibration data;

Preprocessing and lightweight processing the real-time signal data to generate control valve spectrum data;

Extracting key frequency components from the control valve spectrum data through feature calculation to generate control valve feature data, and transmitting it to the central computing node;

Performing principal component extraction and dimensionality reduction on the control valve feature data to obtain principal component features;

Performing multi-source data fusion on the principal component features to generate principal component fusion features;

Analyzing the fusion features and extracting key features to generate a control valve fault feature set;

Using a random forest model to classify and identify the control valve fault feature set to obtain fault identification results;

Using an adaptive model update mechanism to adjust and update the random forest model;

Collecting historical operation data of the pneumatic control valve and the fault identification results to perform extended training and optimization of the random forest model, obtaining a multi-fault identification model.

Compared with the prior art, the beneficial effects of this invention are:

1. This invention first preprocesses the pneumatic control valve operation data, converts the preprocessed time-domain signal into a frequency-domain signal through fast Fourier transform, generates control valve spectrum data, and extracts key frequency components from it. This method transforms complex time-domain signals into more easily analyzable frequency-domain signals, extracting key frequency information reflecting the operating status of the control valve, solving the problem of high computational complexity in time-domain signal analysis in the prior art, and providing data support to improve the real-time performance and accuracy of online monitoring of pneumatic control valves.

2. This invention transfers the data feature extraction task to the edge computing node, extracts key feature data for real-time analysis and monitoring, detects abnormal features, and marks outliers. After compression and dimensionality reduction of the key feature data, principal component fusion features are generated through multi-source data fusion. This method solves the computational bottleneck problem of centralized data processing in the prior art and improves data processing efficiency. Meanwhile, multi-source data fusion simplifies data structure, enhances the processing and fault detection capability of multi-source information, and improves the robustness and real-time performance of online monitoring of pneumatic control valves.

3. This invention extracts fault-related key features from the principal component fusion features to generate a fault feature set; then uses a random forest model to classify and identify the fault feature set to obtain fault identification results; subsequently, it adjusts model parameters in real time through an adaptive mechanism, and based on historical operation data and fault identification results, performs extended training on the optimized random forest model. Finally, it adjusts and optimizes the model through a cross-entropy loss function to obtain a multi-fault identification model. This method combines fault feature extraction with random forest classification to solve the problem of difficulty in identifying concurrent faults in the prior art. By comprehensively applying adaptive updates and deep learning training, it improves the accuracy of real-time monitoring of pneumatic control valves.

Up to now, the company has obtained 7 authorized invention patents and 53 utility model patents, of which 80% have been industrialized. Technological innovation leads the future of the industry. AcmeXun will continue to uphold a low-key and pragmatic attitude, continuously pursue technological innovation and quality improvement, increase R&D investment, introduce more outstanding talents, continuously enhance the technical content and added value of products, and provide customers with higher quality products and services.