Power-based industrial mechanical arm abnormal motion online detection method

Abstract

The invention discloses a power-based industrial mechanical arm abnormal motion online detection method, the method is implemented based on an industrial mechanical arm abnormal motion online detection system, and the system comprises a position data acquisition module, a power data acquisition module and an abnormality detection module; the two data acquisition modules acquire the position of themechanical arm during normal operation, and power sampling data is used as a model initialization sample; the anomaly detection module utilizes sample data to fit a generalization kinetic model of the industrial mechanical arm to achieve dissimilation of a power consumption model, and anomaly detection and model updating are further achieved according to whether accumulated deviation or instantaneous deviation, obtained by the power consumption model, between predicted power and actual consumed power exceeds a specified threshold value or not. According to the method, online detection can becarried out on hidden attacks such as false data injection, replay and man-in-the-middle aimed at being achieved through data tampering under the condition of not intervening normal operation of the mechanical arm.

Description

technical field [0001] The invention relates to the field of industrial control system security, in particular to an online detection method for abnormal motion of an industrial mechanical arm based on power. Background technique [0002] With the deep integration of industrialization and informatization, more and more industrial robotic arms are connected to the industrial Internet of Things platform, and its control system is therefore facing more information security risks, which may cause casualties, equipment damage, and reduce production. Physical security issues such as efficiency. How to detect anomalies in the face of attackers' malicious attacks has become an important problem in the current anomaly detection research. [0003] At present, the anomaly detection method for industrial manipulators is mainly considered from the following two perspectives: 1) Based on the operating status information of industrial manipulators: by collecting the operating state inform...

AI Technical Summary

Problems solved by technology

[0004] There are many problems in the existing anomaly detection technology when it is attacked (such as replay attack, data injection attack), including: 1) The state information uploaded by the method based on the operation state information of the industrial manipulator may be tampered with when facing the attack ( replay, injection, etc.), resulting in unreliable data, 2) gyroscope-based methods need to spend a lot of money on the installation of related sensors, for example, gyroscope-based abnormal detection needs to shut down the industrial robot arm, and install the gyroscope To the end effector of the robotic arm, so the cost is high. 3) The camera-based method has the problem of excessive video frame data dimensions, resulting in a decrease in real-time detection. 4) The method based on the microphone (collecting audio) is vulnerable to factory noise The problem of interference leads to a decrease in the accuracy of anomaly detection

Images