In order to ensure the stable operation, improve efficiency, and enhance sustainability of wastewater treatment systems, this paper investigates the fault detection problem in wastewater treatment process based on an improved kernel extreme learning machine method. Firstly, a kernel extreme learning machine (KELM) model optimized by an improved mutation bald eagle search (IMBES) optimizer is proposed to generate point predictions of effluent quality parameters. Then, based on the point prediction results, the confidence interval of effluent quality parameters is calculated using kernel density estimation (KDE) method. This interval represents the bounds of system uncertainty and unknown disturbance at normal conditions and can be treated as the threshold for fault diagnosis. Finally, the effectiveness of the proposed method is illustrated by two datasets obtained from the BSM1 wastewater simulation platform and an actual water platform. Experimental results show that compared with other methods such as CNN, LSTM, and IBES-LSSVM, this method has a significant improvement in prediction accuracy, and at the same confidence level, it ensures fault detection rate while generating smaller confidence intervals.

This paper proposes a speech recognition method based on a domain-specific language speech network (DSL-Net) and a confidence decision network (CD-Net). The method involves automatically training a domain-specific dataset, using pre-trained model parameters for migration learning, and obtaining a domain-specific speech model. Importance sampling weights were set for the trained domain-specific speech model, which was then integrated with the trained speech model from the benchmark dataset. This integration automatically expands the lexical content of the model to accommodate the input speech based on the lexicon and language model. The adaptation attempts to address the issue of out-of-vocabulary words that are likely to arise in most realistic scenarios and utilizes external knowledge sources to extend the existing language model. By doing so, the approach enhances the adaptability of the language model in new domains or scenarios and improves the prediction accuracy of the model. For domain-specific vocabulary recognition, a deep fully convolutional neural network (DFCNN) and a candidate temporal classification (CTC)-based approach were employed to achieve effective recognition of domain-specific vocabulary. Furthermore, a confidence-based classifier was added to enhance the accuracy and robustness of the overall approach. In the experiments, the method was tested on a proprietary domain audio dataset and compared with an automatic speech recognition (ASR) system trained on a large-scale dataset. Based on experimental verification, the model achieved an accuracy improvement from 82% to 91% in the medical domain. The inclusion of domain-specific datasets resulted in a 5% to 7% enhancement over the baseline, while the introduction of model confidence further improved the baseline by 3% to 5%. These findings demonstrate the significance of incorporating domain-specific datasets and model confidence in advancing speech recognition technology.

From the perspective of teaching and researching, we developed a manipulator digital twin experiment platform (named the remote experience platform, REP) based on a rapid control prototype (RCP). The platform consisted of a controlled target, a real-time controller, rapid prototype configuration software, and supervisory control software. The controlled target was a 6-DOF manipulator, divided into a physical entity and its digital twin. The 3D model and mathematical model of the manipulator were constructed as an experimental entity in a digital space. The whole system provided flexible and intuitive experimental scenes without the restraints of time and place. Based on RCP technology, students can design various complex control strategies using simulation tools such as Matlab/Simulink, then convert the graphical model into executable code to be performed in target hardware. The framework and development methods of the proposed system are elaborated in this paper. An example is demonstrated, including invocation of algorithms, one-click code generation and compilation, real-time verification and online parameter adjustment, and more. The feasibility and practicability of the system are verified through the PID control experiment of the manipulator.

The fluctuations of the Pipe-to-Soil Potential (PSP) in buried pipes are influenced by the geoelectric field induced by changes in the Earth's magnetic field, which can accelerate pipeline corrosion. Monitoring data of PSP along China's West–East Gas Pipeline near the lake indicates obvious tidal changes. This study proposes that the periodic movement of the conductivity boundary of the seepage area near the lake shore caused by tides is the fundamental cause of the tidal changes in PSP. The movement of the boundary changes the range of the H polarization of the geoelectric field, resulting in periodic changes in the PSP of the pipeline outside the seepage area. To investigate this mechanism, a dynamic boundary model of conductivity in the seepage area of Sailimu Lake in Xinjiang was established, and the characteristics of PSP at different distances from the boundary were analyzed using electromagnetic field finite element method and DSTL pipeline model. The study compared the simulation results of the model with the PSP data of the cathodic protection station and PSP monitoring station near Sailimu Lake, during a geomagnetic disturbance on September 23–24, 2016. The results of the study, as well as the corrosion of the test strips along the lake, verified the validity of the boundary change mechanism and model of the seepage zone. This study provides a theoretical basis for corrosion protection of pipelines near the lake’s edge.

Industrial robot after-sales question answering often depends on multimodal evidence, such as error screenshots, interface displays, and wiring diagrams, which are difficult for conventional text-based retrieval-augmented generation (RAG) systems to exploit effectively. To address this issue, we design a dual-channel multimodal RAG system that converts image content into retrievable textual knowledge through the collaboration of optical character recognition (OCR) and structured semantic description. In the proposed system, OCR is used to extract explicit textual cues, such as error codes, parameter fields, and interface prompts, while expert-authored semantic descriptions complement implicit visual evidence, including device parts, fault phenomena, and contextual scene information. The transformed knowledge is further integrated into a hybrid retrieval pipeline that combines dense retrieval and BM25, followed by Reciprocal Rank Fusion (RRF) and Maximal Marginal Relevance (MMR) reordering to improve both relevance and contextual diversity. Experiments on a real-world industrial robot after-sales dataset show that the proposed method achieves an overall question-answering accuracy of 87.9%, outperforming the LLM-only baseline by 35.6 percentage points. For image-related questions, accuracy improves from 46.7% to 83.3%. These results indicate that the proposed framework provides a deployment-friendly and interpretable system-level alternative to end-to-end multimodal model fine-tuning for industrial after-sales question answering.

Semantic segmentation of large-scale 3D point clouds is a fundamental task in robotic perception, semantic mapping, and urban scene understanding. Existing methods mainly rely on geometric information, which limits their ability to distinguish semantic categories with similar spatial structures. To address this issue, this paper proposes a lightweight cross-modal feature learning framework that adaptively integrates geometric coordinates and RGB color information. By exploiting the complementary characteristics of spatial structure and visual appearance during feature encoding, the proposed method enhances feature discriminability while maintaining a compact model scale. Experiments on the Semantic3D dataset show that the proposed method achieves an mIoU of 87.1%, outperforming the original RandLA-Net and several representative approaches. Additional runtime and LiDAR-only cross-dataset experiments indicate the potential of the proposed structure for online outdoor point cloud perception.