Most Intrusion Detection System(IDS) used in Supervisory Control and Data Acquisition (SCADA) systems now are focused on the cyber field but ignored the process states in physical field of the plants. Attacks aiming at the protocol traffics can be detected but attacks aiming at the processes are difficult to be detected such as the Man In The Middle (MITM) attacks and the Replay attacks. We propose a scheme in both cyber way and physical way to detect the above attacks. Validation of process states is used to detect malicious behaviors to prevent the physical components from being damaged which can be caused by MITM, Replay, and Zero-day attacks. Nonparallel hyperplane based fuzzy classifier is presented to realize the classification of branching shaped data sets which are difficult to be classified by two parallel hyperplane of Support Vector Machine(SVM) to detect attacks caused by DoS (SYN flood) and other attacks in cyber field. Modbus/TCP traffic data are used to test the algorithm and simulation process states are used to test the validation part and the performance of this hybrid scheme is excellent.

Surface defects have a serious detrimental effect on the quality of steel. To address the problems of low efficiency and poor accuracy in the manual inspection process, intelligent detection technology based on machine learning has been gradually applied to the detection of steel surface defects. An improved YOLOv8 steel surface defect detection model called YOLOv8-MGVS is designed to address these challenges. The MLCA mechanism in the C2f module is applied to increase the feature extraction ability in the backbone network. The lightweight GSConv and VovGscsp cross-stage fusion modules are added to the neck network to reduce the loss of semantic information and achieve effective information fusion. The self-attention mechanism is exploited into the detection network to improve the detection ability of small targets. Defect detection experiments were carried out on the NEU-DET dataset. Compared with YOLOv8n from experimental results, the average accuracy, recall rate, and frames per second of the improved model were improved by 5.2%, 10.5%, and 6.4%, respectively, while the number of parameters and computational costs were reduced by 5.8% and 14.8%, respectively. Furthermore, the defect detection generalization experiments on the GC-10 dataset and SDD DET dataset confirmed that the YOLOv8-MGVS model has higher detection accuracy, better lightweight, and speed.

SCADA (Supervisory Control And Data Acquisition) is a widely implemented structure to achieve remote measurement and control in many iron and steel plants. In traditional consideration more attention on physical network separation methods are paid to isolate the SCADA system from management network to keep SCADA in a considered ’safe’ state. Additionally, lots of security solution providers are focusing on the network side security assurance without involving the SCADA communication level protection. This paper investigates a new trusted-ID referenced key scheme for securing SCADA communications efficiently. The AES (Advanced Encryption Standard) algorithm is used in the data transmission for its fast calculating speed, and the ECCDSA (Elliptic Curve Cryptography Digital Signature Algorithm) is used to confirm the data package that is from the right ID which can avoid the measured values and the control instructions to be maliciously modified by attacker. This solution for securing SCADA communication provides an efficient way to protect the data and protocol between the controllers and the RTUs (Remote Terminal Unit), and offers an authentication for the communication, which can avoid MITM (Man-In-The-Middle) Attack. Random numbers are used as session key that can avoid the Replay Attack. CBC-MAC(Cipher-Block Chaining mode Message Authentication Code) calculation is used to meet the data integrity requirement. GNY (Gong Needham Yahalom) logic is used to prove the security of this solution, and an example is given to verify its validity.

In this paper, we investigate the adaptive robust visual servoing/force control problem for the uncertain robot manipulator. The robot is considered to work with an unknown constraint surface and the unknown depth of feature point in image plane is assumed to be time-varying. The unknown constraint surface is linearly parameterized, and new adaptive laws are designed to estimate the unknown parameters online. In image based visual servoing control, the unknown time-varying depth plays a special role as it appears nonlinearly in the overall Jacobian matrix and cannot be adapted together with other uncertain kinematic parameters. To handle this problem, a compensatory depth-independent interaction matrix framework and the corresponding adaptive laws are proposed to compensate for the depth in the closed-loop dynamics. Moreover, the dead-zone input constraint is considered and handled by designing the robust compensatory terms and adaptive laws. With the proposed control scheme, it is proved that the image position and force tracking errors converge to zero asymptotically. Finally, numerical simulation and experimental results illustrate the effectiveness of the proposed approach.

Aiming to address the issue of low accuracy in industrial network traffic anomaly detection, we propose an improved DeepFM model for multi-type anomaly detection. The dataset undergoes preprocessing, including encoding and non-string numerical operations. The SMOTE-ENN algorithm is utilized to balance the data through oversampling and undersampling. The improved DeepFM model is employed to extract linear, non-linear, and temporal features from the industrial network traffic data. These features are then fed into an anomaly detector classifier constructed based on Softmax to achieve high-performance detection of traffic attacks. The effectiveness of the model is verified using the UNSW-NB15 dataset, with experimental results demonstrating a detection accuracy of 0.95 for DoS attacks, 0.94 for Fuzzers attacks, and 0.92 for Worms attacks, significantly surpassing other algorithms, which confirms the effective utilization of the proposed model for industrial network traffic anomaly detection.