Mill Load Research Articles

ОПРЕДЕЛЕНИЕ МЕХАНИЗМА РАСКРЫТИЯ ЧАСТИЦ КВАРЦА ПРИ ИЗМЕЛЬЧЕНИИ КВАРЦСОДЕРЖАЩИХ ПРОДУКТОВ В ЦЕНТРОБЕЖНОЙ МЕЛЬНИЦЕ

Introduction. Currently used grinding machines, among which drum mills are the most widely used, have a low efficiency, are bulky, are characterized by low specific productivity, significant consumption of steel for grinding bodies and lining, high noise level, and high energy consumption of the grinding process. The most promising devices of a new type that can effectively perform grinding operations at high technological rates are centrifugal mills. The centrifugal mill developed at SKGMI operates on the principle of self-grinding of pieces and particles of crushed mineral raw materials, when they collide and RUB in a mobile toroidal flow formed when the material moves between a rotating Cup-shaped rotor, a fixed body and the overlying layers of the crushed material. Grinding occurs due to the appearance of a gradient of particle velocities over the working body, due to their impact and, to a greater extent, abrasion. The tests of these mills for grinding various materials have shown high efficiency in operation, but until now, the issues of determining the physical and mechanical properties of the crushed material based on the establishment of the particle opening mechanism remain unresolved. The purpose of the tests. Determination of the physical and mechanical properties of the crushed material in a centrifugal mill based on the establishment of the particle opening mechanism. Test procedure. To solve this problem, a vertical centrifugal mill MC-600 with a rotor diameter of 600 mm was used. Tests of the centrifugal mill were carried out according to the following method. The speed of rotation of the rotor was 4.8 and 8.4 s-1, the height of the material column above the rotor was at the level of 250 and 350 mm; 6 radial ribs were installed in the rotor cavity of the mill. The time of each test was 4 hours. The tests were repeated 3–5 times for each mode of operation of the mill. Quartz was used as a reference material for determining the relative pulverizability coefficient. The research was carried out in the production conditions of the Izhevsk machinebuilding plant during the regeneration of spent molding quartz mixtures. Pieces of a liquid-glass mixture based on quartz sand with strength of 1.3 MPa and 4.25 MPa were used as the crushed material. The crushed material was dispersed according to the standard method for each hour of operation of the mill. Samples were taken in the size class -0.200 + 0.074 mm for their fractional analysis by size. Test result. 1. It was Found that the maximum productivity of a centrifugal mill when grinding pieces of material with a strength of 1.3 MPa was achieved with a loading weight of 90–100 kg, and with a strength of 4.25 MPa – 100–110 kg, which indicates the need to create an increased normal pressure of the layers of crushed material located above the mill rotor. It was found that the maximum productivity of a centrifugal mill when grinding pieces of material with a strength of 1.3 MPa and a rotor rotation frequency of 8.4 s-1 was 13.16 t/h, and when grinding pieces of material with a strength of 4.25 MPa – 10.0 t/h. 2. The Dependence of power consumption on the weight of the mill load and the rotor speed increases when the load weight is more than 100 kg. 3. The Highest fraction content of class -0.4 +0.16 mm is 72.14 %, and the content of class -0.074 mm is 3.9 %, i.e. there is no re-grinding of the source material. 4. The specific productivity of the centrifugal mill for the newly formed calculated size classes -0.074 mm and -0.200 mm was 1.28 t/h and 13.0 t/h, respectively. 5. Microscopic study of anshlifov showed that quartz grains in the crushed material mostly have a rounded shape, on average 90–95 % of the grains. In the initial material, about 90% of quartz joints with a binder, and in the crushed material, the number of joints does not exceed 3–5%. Thus, the degree of expansion of quartz reaches to 0.87. Conclusions. The paper presents the results of studies of a centrifugal mill in the conditions of the Izhevsk machinebuilding plant when grinding quartz-containing products. The physical and mechanical properties of the crushed material that significantly affect the efficiency of grinding are determined. The mechanism of the disclosure particles of quartz, which is primarily the mineral content of many ores and defined particle size obtained by grinding. At the same time, it was found that a large yield of thin classes significantly reduces the efficiency of further technology.

Experimental analysis of wet mill load parameter based on multiple channel mechanical signals under multiple grinding conditions

Online monitoring load parameters inside the ball mill is the key to improving the production quality and quantity of the mineral grinding process. In this paper, the experimental analysis of wet mill load parameter (MLPs) based on multiple channel mechanical signals is presented. A series of experiments is conducted to investigate the mechanical frequency spectrum characteristics in terms of different grinding conditions, such as only-ball, -mineral, or –water load change. Based on power spectra density (PowSD), multiple channel mechanical signals are interpreted for different MLPs, i.e., mineral-to-ball volume ratio (MBVR), pulp density (PD), and charge volume ratio (CVR), in detail. Experimental results show that the PowSDs of these mechanical signals are positively correlated with CVR and negatively correlated with MBVR and PD.Further, the generation mechanism of these mechanical signals is qualitatively analyzed, and a new measurement method for the contribution rate of multiple channel mechanical signals, i.e., combination estimation index, is proposed. The results show the different contribution rates of these signals to various MLPs under varied grinding conditions. Appropriate mechanical channels for different MLPs must be selected to construct an effective MLP forecasting model.

Features of the rolling-separation technology development on operating continuous small-grade mill

Аt present, there is a steady tendency to increase volume of i dustrial and civil construction in Russia and abroad. This in turn makes it necessary to enhance production of structural sections and in particular – reinforcing bar. One of the promising ways to increase production of reinforcing bar at existing rolling mills is development of rollingseparation technology. This technology provides growth in productivity of existing small-grade mills and reduces energy costs without large capital expenditures. However, despite its apparent simplicity, introduction of rolling-separation technology at existing enterprises causes difficulties associated with insufficient coverage of this experience in literature. The article presents experience of introduction of the rolling-separation technology on operating continuous small-grade mill. The research was carried out on equipment available in the workshop and used to monitor load of the main engines. Features of energy costs distribution on stands were studied at classical rolling and with the use of technology of rolling-separation of reinforcing bar No. 10, No. 14 made of 35GS and 3PS steel. Experimental graphs of the main engines of the rolling mill load show redistribution of energy consumption in stands for roughing, intermediate and finishing groups when using rolling-separation technology. Data on application of the main engine power and distribution of the specific load on the stands in classical rolling method and using rolling-separation technology are presented in graphic form. Analysis of the received data allowed us to reveal features of energy consumption at development of rolling-separation technology during operation. It is shown that use of this technology leads to additional load on stands of finishing groups. Energy savings during introduction of rolling-separation technology were quantified, and it was found that with a decrease of the rebar number, efficiency increases. Reduction of energy consumption during development of this technology in current production is associated with a decrease in machine time.

Feature Extraction Method of Ball Mill Load Based on Adaptive Variational Mode Decomposition and Improved Power Spectrum Analysis

The real-time working conditions of the ball mill in the grinding process are complicated, which makes it difficult to accurately obtain the internal load status of the ball mill. In this paper, the energy difference between the original cylinder vibration signal and the intrinsic mode function is proposed as the evaluation parameter of the adaptive variational mode decomposition (VMD) layer number, and a new autocorrelation function is constructed. The intrinsic mode function is processed by introducing the energy centrobaric method of the Nuttall self-convolution window. Accordingly, a ball mill load feature extraction method based on adaptive VMD and improved power spectrum estimation is proposed, and the ball mill load identification system based on LabVIEW is developed. The number of layers of intrinsic mode function could be adaptively determined. And the algorithm’s ability to resist mode aliasing and false components of this method is improved, which improves the accuracy of ball mill load detection. The measured results show that internal load features of ball mill during the grinding process are effectively extracted, and the mill load status is accurately identified, which provide an accurate and reliable basis for grinding optimization control and efficiency.

Neural simulation of ball mill grinding process

This study is aimed at getting simplified model of mill filling technological process of fine crushing in a closed-circuit grinding with screen separation. Optimal and simple model structure are supposed to be used in adaptive predictive control loop. The minor factors that directly affect the mill load indicator are not taken into account, since some of them cannot be directly measured, and other ones affect the process only in the long term. In this paper the athors considered mill filling process identification in the center-discharge ball mill by the method of neural networks (NN). The method includes the identification of the nonlinear process using nonlinear autoregressive with external input (NARX) neural network. The most accurate model was found by varying the structural parameters of the network. The best models were tested in the course of the actual grinding process. The best estimation of the NN model to the real object is obtained with 72.1% match.

Load State Identification Method for Wet Ball Mills Based on the MEEMD Singular Value Entropy and PNN Classification

To overcome the difficulty of accurately judging the load state of a wet ball mill during the grinding process, a method of mill load identification based on the singular value entropy of the modified ensemble empirical mode decomposition (MEEMD) and a probabilistic neural network (PNN) classifier is proposed. First, the MEEMD algorithm is used to decompose the vibration signals recorded under different load states to obtain the intrinsic mode components, and a correlation coefficient threshold is used to select the sensitive mode components that characterize the state of the original signal. Second, singular value decomposition is used to obtain the singular value entropy. Finally, the load state of the wet ball mill is judged based on the magnitude of the singular value entropy. A characteristic mill load vector is constructed from the singular value entropies of the cylinder vibration signals recorded under different load conditions and is used as the input to a PNN, which then outputs the predicted ball mill load state; in this way, a load state identification model is established. Grinding experiments are presented to verify the effectiveness of the proposed method, showing that the method can accurately identify the load state of a wet ball mill.

Soft measurement of ball mill load based on multi-classifier ensemble modelling and multi-sensor fusion with improved evidence combination

Aiming at the problem that the traditional Dempster–Shafer (D–S) evidence theory obtains counter-intuitive results when dealing with conflicting evidences, a new index of evidence dissimilarity measure and an improved evidence combination method are proposed in this paper, which are verified through numerical examples and UCI datasets by comparing with other methods. Then, based on the improved evidence combination method, an improved multi-classifier ensemble modelling is proposed in this paper, which is applied to the soft measurement of ball mill load. Experiments are performed with a laboratory ball mill, and the vibration signals of bearing seats are used as auxiliary variables for the mill load. The recognition results of multiple classifiers and multiple sensors are fused in turn. The recognition accuracy of the proposed method in multi-sensor fusion is significantly higher than that of a single sensor, and the overall classification accuracy is higher than that of other combination methods, which can be found that the proposed method effectively improves the accuracy of soft measurement of ball mill load.

Load State Identification Method for Ball Mills Based on Improved EWT, Multiscale Fuzzy Entropy and AEPSO_PNN Classification

To overcome the difficulty of accurately determining the load state of a wet ball mill during the grinding process, a method of mill load identification based on improved empirical wavelet transform (EWT), multiscale fuzzy entropy (MFE), and adaptive evolution particle swarm optimization probabilistic neural network (AEPSO_PNN) classification is proposed. First, the concept of a sliding frequency window is introduced based on EWT, and the adaptive frequency window EWT algorithm, which is used to decompose the vibration signals recorded under different load states to obtain the intrinsic mode components, is proposed. Second, a correlation coefficient threshold is used to select the sensitive mode components that characterize the state of the original signal for signal reconstruction. Finally, the MFE of the reconstructed signal is used as the characteristic vector to characterize the load state of the mill, and the partial mean value of MFE is calculated. The results show that the mean value of MFE under different load states varies. To further identify the load state, a characteristic mill load vector is constructed from the MFE values of the reconstructed signal under different load conditions and is used as the input of the AEPSO_PNN model, which then outputs the predicted ball mill load state. Thus, a load state identification model is established. The feasibility of the method is verified based on grinding experiments. The results show that the overall recognition rate of the proposed method is as high as 97.3%. Compared with the back propagation (BP) neural network, Bayes discriminant method, and PNN classification, AEPSO_PNN classification increases the overall recognition rate by 8%, 5.3%, and 3.3%, respectively, which indicates that this method can be used to accurately identify the different load states of a ball mill.

Dual-layer optimized selective information fusion using multi-source multi-component mechanical signals for mill load parameters forecasting

Abstract Ball mill is a heavy mechanical device necessary for grinding. Mill load parameters (MLP) relate to production economic indices and process safety. Mechanical signals of the ball mill are used to estimate MLP by domain experts. However, they can only estimate familiar mills effectively in certain time because of human limitation. A new dual-layer optimized selective information fusion is proposed based on the analysis of the characteristics of mill mechanical signals and cognitive behavior of the domain expert for MLP forecasting (MLPF). An ensemble construction strategy based on multi-component mechanical signals adaptive decomposition is employed to build candidate sub-models by using kernel partial least squares (KPLS). The dual-layer optimization strategy is proposed to build selective ensemble (SEN) KPLS (SENKPLS) with optimized ensemble sub-models and their coefficients, thus realizing the trade-off between prediction accuracies and diversity implicitly. The MLPF models based on SENKPLS are constructed by selective fusion multi-source multi-scale frequency spectral information in terms of the auditory perception process of the simulation domain experts. Results show that the proposed strategy can obtain better forecasting results than other state-of-the-art methods.

Analysis of load sharing capability of a series-connected twin synchronous motor drive coupled to a common load shaft by gearing

Torque limitations on gear teeth led to the use of two motors on opposite sides of the gear to drive large grinding mills. For such systems, motor overheating and rapid gear-teeth wear have been observed, especially when using synchronous motors due to load imbalance between the two motors. This paper studied a drive system consisting of two separate three-phase synchronous motors whose phase windings are split into two sections in a manner that makes them appear as six-winding machines, and then each of the resulting six windings of one motor are connected in series with those of the other motor, with no phase transposition, such that only three terminals of each motor are available to be connected to supply. The field windings are connected in parallel to the same source. Again, the motors, running on separate shafts, are connected to a common load shaft through a speed reduction gear driven through pinions. A detailed mathematical model is developed in the q-d axis, and the system is implemented on the MATLAB/ SIMULINK environment. A circumferential error in the girth gear was modeled to introduce load imbalance. It is observed that despite the load imbalance, the stator currents and the load torque seen by the two motors are the same. However, a variation is observed in their rotor angles. This suggests that while the motor units inherently share the mill load equally thereby removing the possibility of motor overheating, the varying rotor angle may represent a problem for the motor shafts. Keywords: Six-winding Machine, Synchronous Motors, Series-Connected, Common Load Shaft, Speed Reduction Gear, q-d Axis

Cement Particle Size Modeling for Cement Combined Grinding System Based on LS-SVM

Aiming at the problem that the mechanism model of cement grinding process is difficult to be established due to its comprehensive complexity, a modeling method of cement particle size based on LS-SVM algorithm is proposed by analyzing its dynamic characteristic and manual operation mode. The model can reflect the relationship between mill load and particle size, reveal the dynamic change process of cement particle size, and lay a foundation for the optimal control of cement quality. The simulation results show that the model is reasonable and effective.

Application of Fractional Fourier Transform for Prediction of Ball Mill Loads Using Acoustic Signals

In cement plant and power plant, ball mills remain in current and widespread use. The load parameter inside a ball mill directly impacts the stability of the production process, the grinding production rate, and the quality of the product in the grinding process. Accurately predicting the load from acoustic signals remains a challenging problem because of the nonlinearity and high dimensions of spectral data. In this paper, the application of fractional Fourier transforms on acoustic signals for estimating mill load parameter was researched. A fractional Fourier transform can give intermediate time-frequency representations by controlling an additional order, and the acoustical frequency spectra in the fractional Fourier domain can provide more information about the load parameters. According to the distribution of acoustic frequency spectra in the fractional Fourier domain, the strategies of predicting ball mill loads were divided into three segments, namely feature extraction, offline modeling, and online monitoring. These techniques included an acoustic signal analysis in different fractional orders, feature extracted based on mutual information and kernel principal component analysis, offline soft measuring modeling compared with other regression models, and online adaptive monitoring based on the optimal fractional order. The experimental investigation of the proposed method demonstrates its effectiveness for estimating mill loads in the fractional Fourier domain by comparing with the result in the Fourier domain.

Controller Maintenance Prioritisation with LoopRank for a Milling and Flotation Plant

Abstract This paper describes the use of the LoopRank algorithm to determine the importance of control loops in large operating plants. Defining control loop importance is an important step towards the prioritization of control loop maintenance efforts, building on extensive existing research into controller performance monitoring, which can identify poorly-performing control loops. LoopRank uses a connectivity matrix, which can be extracted from operating data using techniques such as partial correlation or Granger causality. The algorithm was applied to synthetic data from a simulated tank network, and to industrial data from a minerals processing plant. For the simulated data, LoopRank with Granger causality provided no significant improvement over LoopRank with the relatively simple partial correlation results. However, for the industrial data, LoopRank with partial correlation was not able to correctly assign importance to variables which are critical to advanced process control, such as mill load, power and speed. LoopRank with Granger causality was able to identify these variables, suggesting that incorporating lagged information in the connectivity matrix provides better importance rankings than using simpler methods.

Mill Load Parameter Forecasting Based on Multi-source Single-scale Mechanical Frequency Spectral Multiple feature Subsets

Multi-source mechanical signals at different locations of the ball mill system have different contributions for constructing mill load parameter forecasting (MLPF) model. It is necessary to select suitable multi-source mechanical signals and their frequency spectral feature subsets. Aim at these problems, a new MLPF approach based on LASSO algorithm and selective ensemble (SEN) modeling strategy by using multi-source single-scale mechanical frequency spectrum is proposed. At first, Fast Fourier transformer (FFT) is used to obtain single-scale frequency spectrum of these multi-source (channel) mechanical signals. Then, SEN-LASSO modeling approach based on candidate regularization parameter set is used to obtain single-scale frequency spectral feature subsets and to build single-channel SEN MLPF model jointly. Finally, SEN strategy is employed again to construct the final MLPF model by selecting and combining these single-channel SEN MLPF models. Simulation results based on a laboratory-scale ball mill validate effectiveness of this approach.

基于混合神经遗传算法的半自磨机功率预测

There are few methods of semi-autogenous (SAG) mill power prediction in the full-scale without using long experiments. In this work, the effects of different operating parameters such as feed moisture, mass flowrate, mill load cell mass, SAG mill solid percentage, inlet and outlet water to the SAG mill and work index are studied. A total number of 185 full-scale SAG mill works are utilized to develop the artificial neural network (ANN) and the hybrid of ANN and genetic algorithm (GANN) models with relations of input and output data in the full-scale. The results show that the GANN model is more efficient than the ANN model in predicting SAG mill power. The sensitivity analysis was also performed to determine the most effective input parameters on SAG mill power. The sensitivity analysis of the GANN model shows that the work index, inlet water to the SAG mill, mill load cell weight, SAG mill solid percentage, mass flowrate and feed moisture have a direct relationship with mill power, while outlet water to the SAG mill has an inverse relationship with mill power. The results show that the GANN model could be useful to evaluate a good output to changes in input operation parameters.

Mill Load Control System Based on the Improved Ant Colony Neural Network

Mill Load Control System Based on the Improved Ant Colony Neural Network

Reconstruct the Support Vectors to Improve LSSVM Sparseness for Mill Load Prediction

The sparse strategy plays a significant role in the application of the least square support vector machine (LSSVM), to alleviate the condition that the solution of LSSVM is lacking sparseness and robustness. In this paper, a sparse method using reconstructed support vectors is proposed, which has also been successfully applied to mill load prediction. Different from other sparse algorithms, it no longer selects the support vectors from training data set according to the ranked contributions for optimization of LSSVM. Instead, the reconstructed data is obtained first based on the initial model with all training data. Then, select support vectors from reconstructed data set according to the location information of density clustering in training data set, and the process of selecting is terminated after traversing the total training data set. Finally, the training model could be built based on the optimal reconstructed support vectors and the hyperparameter tuned subsequently. What is more, the paper puts forward a supplemental algorithm to subtract the redundancy support vectors of previous model. Lots of experiments on synthetic data sets, benchmark data sets, and mill load data sets are carried out, and the results illustrate the effectiveness of the proposed sparse method for LSSVM.

Semi-autogenous mill power model development using gene expression programming

Predicting the performance of the semi-autogenous (SAG) mill is necessary for the best circuit design which is possible by suitable modeling and simulation. Numerous models of the SAG mill are studied in the literature, but the majority of them do not evaluate the predicted model for full-scale mill performance. Mill powers of the semi-autogenous mill have an effective influence on the mill performance. In this regard, a new predictive model based on gene expression programming (GEP) was developed to predict the mill power of the SAG mill. To achieve this purpose, a total number of 186 full-scale SAG mill works were investigated and the most effective parameters on SAG mill power, i.e., feed moisture, mass flowrate, mill load cell weight, SAG mill solid percentage, inlet and outlet water to the SAG mill and work index were measured and utilized to develop the GEP model. In order to determine the relationship between the input and output parameters, the GEP model was developed and the results were compared with non-linear multiple regression (NLMR) method. The results show the capability of the GEP model in predicting the mill power. It shows that the mill power is more sensitive to mass flowrate and work index than other input parameters.

Effect of undersize misplacement on product size distribution of Bond’s ball mill test

The standard Bond ball mill grindability test determines the ore grindability (g rev−1) and work index on an ore which gives the ball mill power consumption. The test is carried out on a standard sample and the number of revolutions per minute (rev min−1) required for the next cycle is determined after screening out and weighing the undersize fraction from a screen of a mesh the same size as the intended product passing size. The standard procedure assumes 100% efficiency in screening out the undersize fraction. However in plant grinding and classification circuits especially those based on dry grinding and classification, the efficiency of classifiers will be less than 100%. The misplacement of undersize particles in the oversize recirculating load is a practical reality which cannot be avoided. The aim of this study was to examine the effect of misplaced undersize particles on the P80 of product. The P80 values obtained from the standard Bond ball mill procedure and those of an inefficient ball mill grinding – classifier circuit were compared. The P80 values obtained with an inefficient classification were lower than the values obtained from the standard Bond ball mill procedure. The relationship between standard P80 values and those obtained with inefficient classification can be used as a guide to adjust operating parameters such as mill load and mill speed to produce the desired product size.

球磨机信号分析和关键参数预报系统

为了实现磨矿过程球磨机负荷参数的在线检测，采用MATLAB和C#.net混合编程方式，开发实现了球磨机振动、振声信号分析和关键参数预报的软测量系统。该系统基于集合经验模态分解(Ensemble Empirical Mode Decomposition, EEMD)技术和区间偏最小二乘(interval partial least-squares, iPLS)技术提取与磨机负荷参数密切相关的本征模态函数(intrinsic mode functions, IMF)频域特征，构建基于本征模态函数特征空间的选择性集成模型，实现磨机负荷参数的测量。MATLAB的Deploytool工具将信号EEMD分解、IMF频谱变换、iPLS特征选择、关键参数模型训练和模型预测一系列m函数编译生成DLL程序集合，在C#.net编程环境中，通过调用上述程序实现球磨机信号分析和关键参数预报软件系统的快速开发。系统测试结果表明该系统能够有效选择筒体振动和振声信号IMF频谱特征，系统准确性和可靠性较高，对改进磨矿过程控制和优化具有重要意义。 Due to the difficult of the ball mill load to measure directly, we combined matlab language with c#.net programming to develop a signal analysis and key parameters prediction system of ball mill. The vibration and acoustic signals are decomposed a series of Intrinsic Mode Functions (IMFs) by using Ensemble Empirical Mode Decomposition (EEMD). The frequency domain characteristics of the IMFs were chosen based on interval Partial Least-Squares (iPLS) and forecast model of key load parameters were built based on extreme learning machine ensemble modeling. In order to solve the problem of monitoring and estimating the critical parameters of the ball mill’s running state. Use the Deploytool tool of Matlab to compile a series of M function of signal EEMD decomposition, IMF transform spectrum, iPLS feature selection and the model training and prediction of the key parameters into C#.NET DLL assemblies, and then call them in C#. The software system of signal analysis and key parameters prediction of ball mill is developed, which has the function of signal decomposition, feature selection, model training and parameter prediction. System test results show that the system can effectively select the cylinder vibration and noise signal IMF spectrum characteristics closely related to the ratio of material ball, grinding concentration and filling rate. In addition, the mill load parameters forecasting system based on spectral characteristics has good generalization performance.