The over-exploitation of resources caused by the increasing
coal
demand has resulted in a sharp increase in solid waste emissions mainly
gangue, which has made the burden on the environment, economy, resources,
and society of our country heavier. In order to achieve a balance
between energy consumption and solid waste emission in the process
of top coal caving, this study carried out coal gangue recognition
research based on multi-source time–frequency domain feature
fusion (MS-TFDF-F). First, the process of coal gangue symbiosis and
the harm of gangue in top coal caving are analyzed, and the fundamental
method of comprehensive treatment of gangue is put forward, which
is the accurate recognition of the coal gangue interface. Second,
by building a top coal caving simulation test bed, the MS signals
generated in the caving process of the coal gangue mixture with a
gangue content of 0–100% are collected and the TFDFs are extracted.
Third, the MS-TFDF-F-based coal gangue recognition model is established.
Then, the recognition effect of the two TFDF-F sample sets was compared,
and the results show that the time–frequency domain feature
selection fusion method (TFDFS-FM) has higher accuracy. On this basis,
this paper studies the variation law of the number of sensors on the
coal gangue recognition accuracy of MS information fusion. Finally,
the economic, social, environmental, and resource benefits of the
model are qualitatively described. The final results show that the
MS-TFDF-F-based coal gangue recognition model has the strongest recognition
ability when fusing six sensor signals, and the recognition accuracy
reaches 99% under the AdaBoost algorithm. The establishment of this
model brings huge benefits to China’s environment, economy,
resources, and society, and it is helpful to realize the balance between
loss reduction mining and solid waste emission reduction in the process
of top coal caving.