Multi-channel monitoring data compression method for industrial robot based on compressed sensing

Long-term monitoring of satellite microvibrations generates a significant amount of data streams, placing strain on satellites with limited transmission capacity. To relieve this transmission strain, a dynamic compressed sensing (CS) framework is proposed for satellite microvibration measurements. Microvibration streams are measured block by block and then reconstructed by a dynamic recovery algorithm. The recovery solution of one block can be used as a priori knowledge for the next block, allowing for faster updates. However, the existing dynamic recovery algorithms are only applicable to the real domain and cannot be applied to the microvibrations projected on a Fourier basis in the complex domain. In light of this, the dynamic homotopy algorithm is expanded to the complex domain to deal with microvibration signals that are sparse on the Fourier basis. In comparison to the traditional uniform sampling methods, the experimental results show that the dynamic CS with the expanded recovery algorithm can achieve a maximum root-mean-square acceleration (Grms) deviation of 4% in power spectrum density (PSD) with 1/5 sampling points. Compared with recovery algorithms applicable to fixed measurements, the dynamic algorithm can achieve comparable accuracy in about 1/3 of computation time. The experimental results demonstrate the feasibility of satellite microvibrations measurement using dynamic CS.

Section: Introductionmentioning

confidence: 99%

Microvibration streaming measurements using dynamic compressed sensing for satellites

Zhou

Zhu

et al. 2023

“…Modern industrial production is increasingly dependent on industrial robots, which play a crucial role in the development of intelligent manufacturing. In the scenario of processing, such as welding and transporting, industrial robots have proven to be a highly effective, flexible, and safe solution [1]. With the proliferation of industrial robots, their maintenance has become a critical issue.…”

Section: Introductionmentioning

confidence: 99%

An attention-enhanced multi-modal deep learning algorithm for robotic compound fault diagnosis

Zhou

Zeng²,

Chen³

et al. 2022

Compound fault diagnosis plays a critical role in lowering the maintenance time and cost of industrial robots. With the advance of deep learning and industrial big data, the compound fault diagnosis model can be established through a data-driven approach. However, current methods mainly focus on the single fault diagnosis of assets, which cannot achieve satisfactory performance of compound fault diagnosis. This study proposes a compound fault diagnosis algorithm for the industrial robot based on multimodal feature extraction and fusion. Firstly, the multi-head self-attention enhanced convolution neural network (CNN) module and long short-term memory (LSTM) network module are adopted to learn the fault-related features from different perspectives simultaneously. The local and global features extracted by the aforementioned modules are then fused for subsequent compound fault classification. An experimental study was implemented based on the real-world robotic sensor data. The experimental results indicated that the proposed multi-modal algorithm shows merits in compound fault diagnosis in comparison with other state-of-the-art methods.

“…However, this data is bandwidth intensive, an especially challenging problem for low-gain antenna-dependent systems. This fact motivates distinct studies in vibration data compression, using different strategies [10][11][12][13][14]. In the case of space missions, as posted in [15], data compression has been used since the late 1960s.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of lossy compression algorithms using discrete cosine transform for sounding rocket vibration data

Pinto¹,

Maciel²,

Pinho³

et al. 2022

This work evaluates the performance of compression algorithms based on Discrete Cosine Transform when used to encode sounding rockets' vibration signals. Different compression methods that use the three-step strategy (transform, quantization, and entropy encoder) are presented. The performances are evaluated using the relationship between the compression rate and distortion, the latter being measured using the Peak Signal-to-Noise Ratio (PSNR) and the difference observed in the Power Spectral Density (PSD). The focus of the work is on vibration signals from rocket launches conducted by the Institute of Aeronautics and Space of the Brazilian Air Force. The obtained results present a great variation for the vibration data in the test set. Compressors operating with PSNR close to 50 dB can achieve very high compression rates (over 100) for low power signals. However, if the vibration signal strength increases significantly, the compression rate can be much lower. For the worst case in the test set (signal with the highest power), the work shows that the best proposed method needs a rate of 9.8 to achieve a PSNR of 48.2 dB. When compared to the performance of recently published DCT-based compression algorithms, the proposed technique shows significant improvements. Given a PSNR around 50 dB, for signal with moderate power, improvements above 100% are observed in compression rate.