Intelligent instrument control method and system based on deep learning

By collecting multimodal data in real time and using deep learning models and DQN algorithms to generate optimized control strategies, the problem of dynamic adjustment of intelligent instrument control methods in complex scenarios is solved, thereby improving the accuracy and efficiency of control.

CN121834728AActive Publication Date: 2026-04-10YUNNAN INST OF MEASUREMENT TEST TECH RES
6 Cites 0 Cited by

Patent Information

Application Number
CN202610312374.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-16
Publication Date
2026-04-10
Estimated Expiration
2046-03-16

AI Technical Summary

Technical Problem

Existing intelligent instrument control methods are difficult to adapt to complex and ever-changing application scenarios. The control logic cannot be dynamically adjusted, the multi-source data processing capability is insufficient, and large overshoot and excessive steady-state error often occur. Furthermore, there is a lack of multi-modal data fusion mechanism.

Method used

Multimodal data is collected in real time through cameras, sensor networks, and IoT devices. The data is then normalized and outlier removed. Deep learning feature extraction models and DQN algorithms are used to generate optimized control strategies. Combined with visual, temporal, and environmental perception features, safety constraints are constructed, and control parameters are dynamically adjusted.

Benefits of technology

It enables comprehensive perception of complex working conditions, improves the accuracy of feature extraction, reduces the equipment failure rate, enhances the timeliness and efficiency of intelligent instrument control, and reduces manual intervention.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of intelligent control, and discloses an intelligent instrument control method and system based on deep learning, and the method comprises the steps: collecting instrument images, environment parameters and operation state data in real time through a camera, a sensor network and Internet of Things equipment, and constructing a multi-modal data set; performing normalization processing, abnormal value elimination and time sequence alignment on the data in the multi-modal data set to obtain a standardized data set; inputting the standardized data set into a feature extraction model, performing feature extraction through a visual feature extraction network, a time series data processing network and an environment perception fusion network, and distributing feature weights based on a self-attention mechanism to obtain a fusion feature vector; the fusion feature vector is used as state input, a security constraint condition is constructed, an optimized control strategy is generated by adopting a DQN algorithm, and the optimized control strategy is sent to an execution mechanism; the control timeliness and efficiency of the intelligent instrument are improved.
Need to check novelty before this filing date? Find Prior Art