As a highly automated carrying vehicle, an automated guided vehicle (AGV) has been widely applied in various industrial areas. The collision avoidance of AGV is always a problem in factories. Current solutions such as inertial and laser guiding have low flexibility and high environmental requirements. An INS (inertial navigation system)-UWB (ultra-wide band) based AGV collision avoidance system is introduced to improve the safety and flexibility of AGV in factories. An electronic map of the factory is established and the UWB anchor nodes are deployed in order to realize an accurate positioning. The extended Kalman filter (EKF) scheme that combines UWB with INS data is used to improve the localization accuracy. The current location of AGV and its motion state data are used to predict its next position, decrease the effect of control delay of AGV and avoid collisions among AGVs. Finally, experiments are given to show that the EKF scheme can get accurate position estimation and the collisions among AGVs can be detected and avoided in time.

AGV is an important material handling equipment for flexible, lean and intelligent production of smart factory. Because of the high cost of AGV car and the congestion of vehicles in the system, this chapter studies the waste smoke recovery path planning and material handling task scheduling strategy of multi AGV system to improve the waste smoke recovery efficiency of AGV.

In this paper, a floor fork laser guided transport vehicle is used to recover waste smoke. The advantages are obvious, small and flexible, safe and reliable, and it is widely used in working places with narrow space and high level difference. In the multi-AGV system, each AGV coordinated with each other to complete the waste smoke recovery. When multiple AGVs are running at the same time, it is necessary to consider path planning issues to avoid conflicting paths. On the one hand, the operation efficiency is affected, and on the other hand, the AGV system is paralyzed. Multiple AVGs run in the system at the same time and perform multiple handling tasks at the same time. Coordination is required to avoid or preempt the area first, avoid path conflicts, and collaborate to achieve efficient distribution.

In recent years, the industrial automation of cigarette enterprises has made great progress, and the underlying data acquisition, centralized control and condition monitoring systems have been established. The management has also established a large number of application systems. There are a large number of equipment data resources in these industrial automation systems and application systems, but incremental data value mining is difficult to really solve the problem. The exploration of big data and machine learning has gradually encountered bottlenecks and ceilings, Lack of integration of domain knowledge, it is difficult to mine high-value application scenarios. From the point of view of "semantic analysis" and "equipment management", it is necessary to establish a unified method of data collection and application, which is the basis of effective data collection and management. From the perspective of "semantic analysis" and "equipment management", it is necessary to establish a unified method of data collection and application.

Industrial anomalous sound detection (ASD) is typically trained exclusively on normal samples, making self-supervised learning a promising paradigm for label-scarce settings. However, existing discriminative ASD methods still exhibit three practical limitations. First, most methods rely on a fixed Mel-scale front end, even though fault-related frequency bands vary across machine types, potentially obscuring informative anomalous components in the mid- and high-frequency ranges. Second, spectrogram generation can attenuate long-range temporal dependencies present in raw audio, thereby reducing sensitivity to temporally evolving anomalies. Third, widely used backbone networks often fail to achieve an effective balance between representational capacity and computational efficiency, thereby limiting deployment in resource-constrained industrial environments. To address these limitations, AFSTgram-DFE is proposed as a self-supervised ASD framework that integrates adaptive filtering with dynamic feature extraction. In the spectrogram branch, the filtering strategy is adaptively selected between uniform and Mel-scale filter banks according to the fault-sensitive frequency characteristics of each machine type. In the temporal branch, an attention mechanism and an autocorrelation-based module are introduced to recover temporal cues lost during spectrogram generation. In addition, a parameter-free feature enhancement module and a dynamic feature extraction network with complementary large and small convolutional kernels are employed to enhance discriminative representation learning while preserving lightweight inference. Finally, anomaly discrimination is performed using an ArcFace-based classifier in conjunction with a Gaussian mixture model. Experiments on the DCASE 2020 Challenge Task 2 dataset show that AFSTgram-DFE achieves an average AUC of 95.10% and an average pAUC of 90.25%, outperforming existing mainstream methods.

In the process of communication of residual cigarette recycle system, due to the residual cigarette recycling bin WIFI switch with the signal strength, signal quality, distance of WIFI and other reasons. In order to keep the residual cigarette recycling bin in a non-inductive switching state, WIFI needs to adopt seamless Switching technology [1]. In which cognitive radio automatic networking (CRAN) is one of the core technologies, in order to suppress cognitive users from interfering with authorized users, it is necessary to reduce WIFI switching times as much as possible. Advance a cognitive wireless dynamic WIFI switching method based on detection of the WIFI chanel idle time (PWCIT). The theory is based on a known-state sequence hidden Markov [2] model (KSS-HMM). The selection method of the alternative WIFI is given, and the optimal channel is selected for data transmission by comparing the date transmission throughput of each candidate WIFI. The simulation results show that compared with the traditional channel selection method and the random channel [3] selection, the method can significantly reduce the number of WIFI handovers and improve the throughput of cognitive [4] users.