The various industrial sectors stand to gain significant advantages from the implementation of the Industrial Internet of Things (IIoT). Furthermore, given restricted channel materials, it is challenging to make the globe’s most effective choice in distributed wireless sensor networks (DWSN). Industrial sensor networks are susceptible to complicated industrial circumstances which are susceptible to an integration of various signal patterns. The complex interference from multiple signals can significantly lower the effectiveness of the classification of signals on industrial equipment, requiring a significant process of training that characteristics can be obtained. Furthermore, generalized envelope squared spectrum (GESS) is supplied for increased reconstruction of transmission signals. In this study, we propose a machine learning-based model an adaptive modulation-based simplified deep convolutional neural network (AM-SDCNN) for classifying signal nodes DWSN. Frequency reduction and sampling conditioning are implemented to receive signals from nodes, enabling the generation of intelligent signal representations. The aggregation center gets the output of the signal categorization process carried out by every single sensor node over a network. The simulation demonstrates that the suggested AM-SDCNN technique has beneficial performance in signal classification. Particularly, the suggested technique does not need transmitting signals from nodes to the aggregation center, which can preserve the privacy of industrial information.