In the dense medium separation system of coal preparation plant, the fluctuation of raw coal ash and lag of suspension density adjustment often causes the instability of product quality. To solve this problem, this study established a suspension density prediction model for the dense medium separation system based on Long Short-Term Memory (LSTM). First, the historical data in the dense medium separation system of a coal preparation plant were collected and preprocessed. Moving average and cubic exponential smoothing methods were used to replace abnormal data and to fill in the missing data, respectively. Second, a LSTM network was used to construct the density prediction model, and the optimal number of time steps, hidden layers, and nodes was determined. Finally, the model was employed on a testing set for prediction, and a Back-Propagation (BP) network without a time series was used for comparison. Root Mean Squared Error (RMSE) were the minimum when the number of the hidden layers, nodes, and time steps was 6, 12, and 5, respectively. In this case, the RMSE and Mean Absolute Percent Error (MAPE) of the LSTM method were 0.009 and 0.007, respectively, while those of the BP method were 0.019 and 0.015, respectively. Therefore, the model established using LSTM can be used to accurately predict the suspension density of the dense medium separation system.

Triboelectrostatic beneficiation, a dry separation technology recurred to electrification properties between carbon and ash, is employed to remove unburned carbon from coal fly ash effectively. Previous works showed that the efficiency of triboelectrostatic separation was influenced by particle size of fly ash. However, the effect of specific particle size range on triboelectric separation efficiency has not received appropriate academic attention. In this paper, a model of charge-to-mass ratio (CMR) which varied with particle sizes was established by Engineering Discrete Element Method (EDEM); on this basis, the effect of particle size range on triboelectric separation of fly ash was studied via screening before and after separation. Based on the Change rule of high loss-on-ignition (LOI), yield, CMR, LOI decrease rate of clean ash (LDC) and LOI increase rate of tailing (LIT), the results were obtained and shown as follows: carbon and ash can be separated efficiently when the particle size is between 38 ~ 74 μm; separation effect is deficient when the particle size is smaller than 38 μm due to insufficient depolymerization of the particles and CMR decrease. This indicates that the separation effect of triboelectric separation is not negatively correlated with particle size. Instead, there is an appropriate optimal separation range. Triboelectrostatic separation efficiency can be improved by screening fly ash in the narrow particle size under 74 μm, and the separation effect of narrow size grain samples obtained after screening is better than the full-size grain ones. Therefore, the fly ash should be screened properly before separation.

The sedimentation process of coal slurry water is influenced by numerous factors and has complex mechanisms. Its nonlinear and large hysteresis characteristics pose great challenges to process optimization control, making it a current research hotspot. This paper takes the typical slime water treatment process of a coal preparation plant as the object, and, on the basis of selecting raw coal quantity, flocculation dosage, coagulation dosage, overflow turbidity, raw coal ash content, underflow concentration, and slime quantity as the key variables, establishes a quality control method for process detection data consisting of data acquisition → data anomaly detection → data filling and noise reduction; subsequently, different machine-learning algorithms are used to predict the performance of coal-slurry-settling agents. It was found that Long Short-Term Memory shows the highest prediction accuracy for coagulants, with corresponding root mean square errors of 2.72% and 6.23%. Finally, using iFix software (version 5.5), an intelligent control system for the settling process of coal slurry water was constructed, which reduced the usage of coagulants by 31.56% and 37.21%.