Control Method and Device for Ball Mill

Abstract

The present invention provides a control method and device for a ball mill, including: acquiring characteristic signals of the ball mill and preprocessing the characteristic signals; wherein, the characteristic signals include: the motor current of the ball mill, the cylinder vibration signal of the ball mill, and the sound intensity of the ball mill; determining the load state corresponding to the characteristic signals of the ball mill based on the pre-set correspondence between the characteristic signals and the load state; determining the ore feeding amount of the ball mill based on the load state of the ball mill, and controlling the ore feeding operation of the ball mill based on the ore feeding amount. In this way, multiple parameters such as the motor current, cylinder vibration signal, and sound intensity of the ball mill are used as characteristic signals, and the load state of the ball mill is comprehensively judged through multiple parameters; moreover, the correspondence between the characteristic signals and the load state is determined in combination with the production situation of the concentrator and the operation experience of the post workers, realizing the effective integration of the control system of the ball mill and manual experience, and improving the efficiency, reliability, and accuracy of the judgment of the load state of the ball mill.

Description

Technical Field

[0001] The present invention relates to the technical field of ball mill control, and in particular, to a control method and device for a ball mill. Background Art

[0002] The grinding process is the core of the entire beneficiation process. Since the operation process of the mill is very complex, during the grinding process, due to the existence of numerous parameters and these parameters are extremely prone to change, coupled with the difficulty in establishing the model of the ball mill, the grinding process has the characteristics of large inertia, strong hysteresis, and easy drift of the optimal load point. At the same time, since the mill load can only be measured by an indirect method, the plant workers need to frequently observe the mill current during work, listen to the working sound of the mill from time to time, judge the load state inside the ball mill according to experience, and judge the grinding concentration by visually observing the color depth of the pulp, and adjust the feed amount and water supply according to the empirical values. However, this manual experience control is not accurate and easily leads to abnormal phenomena such as "idle grinding" and "over-grinding" of the mill, which not only increases the energy consumption of the plant but also reduces the production efficiency of the plant. Summary of the Invention

[0003] In view of this, the purpose of the present invention is to provide a control method and device for a ball mill to improve the efficiency, reliability, and accuracy of judging the load state of the ball mill.

[0004] In a first aspect, an embodiment of the present invention provides a control method for a ball mill, the method comprising: acquiring characteristic signals of the ball mill and preprocessing the characteristic signals; wherein, the characteristic signals include: the motor current of the ball mill, the cylinder vibration signal of the ball mill, and the sound intensity of the ball mill; determining the load state corresponding to the characteristic signals of the ball mill based on a pre-set correspondence between the characteristic signals and the load state; determining the feed amount of the ball mill based on the load state of the ball mill, and controlling the feeding operation of the ball mill based on the feed amount.

[0005] In an optional embodiment of the present application, the step of preprocessing the characteristic signals includes: performing mean value processing on the motor current of the ball mill within a preset time range; performing wavelet threshold denoising processing on the cylinder vibration signal and / or the sound intensity of the ball mill.

[0006] In an optional embodiment of the present application, the step of acquiring the characteristic signals of the ball mill includes: acquiring the vibration signal of the ball mill; wherein, the vibration signal of the ball mill includes the cylinder vibration signal and the mechanical vibration signal; separating the vibration signal of the ball mill to obtain the cylinder vibration signal of the ball mill.

[0007] In an alternative embodiment of the present application, the load state of the above ball mill includes a normal load state and an abnormal load state; the step of determining the ore feeding amount of the ball mill based on the load state of the ball mill includes: if the load state of the ball mill is an abnormal load state, obtaining the ore feeding amount of the ball mill through weighted processing based on the cylinder vibration signal and the sound intensity; if the load state of the ball mill is a normal load state, obtaining the ore feeding amount of the ball mill through proportional-integral-derivative control processing based on the cylinder vibration signal and the sound intensity.

[0008] In an alternative embodiment of the present application, the step of obtaining the ore feeding amount of the ball mill through weighted processing based on the cylinder vibration signal and the sound intensity includes: obtaining the target values of the cylinder vibration signal and the sound intensity, as well as the weighting coefficients of the cylinder vibration signal and the sound intensity; determining the adjustment amount of the ore feeding amount of the ball mill based on the cylinder vibration signal and the sound intensity, the target values of the cylinder vibration signal and the sound intensity, and the weighting coefficients of the cylinder vibration signal and the sound intensity; obtaining the reference value of the ore feeding amount of the ball mill, and determining the ore feeding amount of the ball mill based on the load state of the ball mill, the reference value, and the adjustment amount.

[0009] In an alternative embodiment of the present application, the above abnormal load state includes an underload state, a low load state, a high load state, and an overload state; the step of determining the ore feeding amount of the ball mill based on the load state of the ball mill, the reference value, and the adjustment amount includes: if the load state of the ball mill is an underload state or a low load state, determining the ore feeding amount of the ball mill based on the first calculation relationship, the reference value, and the adjustment amount; if the load state of the ball mill is a high load state or an overload state, determining the ore feeding amount of the ball mill based on the second calculation relationship, the reference value, and the adjustment amount.

[0010] In an alternative embodiment of the present application, the step of obtaining the ore feeding amount of the ball mill through proportional-integral-derivative control processing based on the cylinder vibration signal and the sound intensity includes: determining the first adjustment amount of the ore feeding amount of the ball mill corresponding to the cylinder vibration signal; determining the second adjustment amount of the ore feeding amount of the ball mill corresponding to the sound intensity; taking the average value of the first adjustment amount and the second adjustment amount as the target adjustment amount of the ore feeding amount of the ball mill; obtaining the reference value of the ore feeding amount of the ball mill, and determining the ore feeding amount of the ball mill based on the reference value and the target adjustment amount.

[0011] In an alternative embodiment of the present application, after the step of determining the load state corresponding to the characteristic signal of the ball mill, the method further includes: determining the ore-water ratio coefficient based on the load state; determining the water replenishment flow rate of the ball mill based on the ore-water ratio coefficient, and controlling the water replenishment operation of the ball mill based on the water replenishment flow rate.

[0012] In an alternative embodiment of the present application, the step of determining the ore-water ratio coefficient based on the load state includes: if the load state is an under-load state, determining the ore-water ratio coefficient as the maximum value set in advance; if the load state is a low-load state, a high-load state, or a normal-load state, determining the grinding concentration and the reverse sand concentration of the ball mill, and determining the ore-water ratio coefficient based on the calculation relationship set in advance, the grinding concentration, and the reverse sand concentration; if the load state is an over-load state, determining the ore-water ratio coefficient as the minimum value set in advance.

[0013] In a second aspect, an embodiment of the present invention further provides a control device for a ball mill. The device includes: a characteristic signal acquisition module, configured to acquire the characteristic signals of the ball mill and preprocess the characteristic signals; wherein the characteristic signals include: the motor current of the ball mill, the barrel vibration signal of the ball mill, and the sound intensity of the ball mill; a load state determination module, configured to determine the load state corresponding to the characteristic signals of the ball mill based on the correspondence between the characteristic signals and the load state set in advance; a feed amount control module, configured to determine the feed amount of the ball mill based on the load state of the ball mill and control the feeding operation of the ball mill based on the feed amount.

[0014] The embodiments of the present invention bring the following beneficial effects:

[0015] The embodiments of the present invention provide a control method and device for a ball mill, which can use multiple parameters such as the motor current, barrel vibration signal, and sound intensity of the ball mill as characteristic signals, and comprehensively judge the load state of the ball mill through multiple parameters; moreover, the correspondence between the characteristic signals and the load state can be determined in combination with the production situation of the concentrator and the operation experience of the operators, realizing the effective integration of the control system of the ball mill and the manual experience, and improving the efficiency, reliability, and accuracy of the load state judgment of the ball mill.

[0016] Other features and advantages of the present disclosure will be described in the following specification, or some features and advantages can be inferred from the specification without doubt, or can be known by implementing the above technologies of the present disclosure.

[0017] To make the above objects, features, and advantages of the present disclosure more obvious and understandable, the following specific preferred embodiments are given, and in conjunction with the accompanying drawings, the detailed description is as follows. Description of the Drawings

[0018] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 Flow chart of a control method for a ball mill provided by an embodiment of the present invention;

[0020] Figure 2 Schematic diagram of an ore grinding and classification process provided by an embodiment of the present invention;

[0021] Figure 3 Schematic diagram of a data processing and control unit provided by an embodiment of the present invention;

[0022] Figure 4 Flow chart of another control method for a ball mill provided by an embodiment of the present invention;

[0023] Figure 5 Schematic diagram of a ball mill load judgment and adjustment provided by an embodiment of the present invention;

[0024] Figure 6 Schematic diagram of a ball mill supplementary water addition adjustment provided by an embodiment of the present invention;

[0025] Figure 7 Schematic diagram of the structure of a control device for a ball mill provided by an embodiment of the present invention;

[0026] Figure 8 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0027] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0028] The ore grinding process is the core of the entire ore dressing process. Since the operation process of the mill is very complex, during the ore grinding process, due to the existence of numerous parameters and these parameters are extremely prone to change, and in addition, it is difficult to establish a model of the ball mill, the ore grinding process has characteristics such as large inertia, strong hysteresis, and easy drift of the optimal load point. At the same time, since the mill load can only be measured by an indirect method, the plant operators need to frequently observe the mill current during work, listen to the working sound of the mill from time to time, judge the load state inside the ball mill according to experience, and judge the grinding concentration by visually observing the color depth of the pulp, and adjust the feed amount and water supply amount according to the empirical values. However, this manual experience control is not accurate and is prone to abnormal phenomena such as "idle grinding" and "over grinding" of the mill, which not only increases the energy consumption of the plant but also reduces the production efficiency of the plant.

[0029] As a main crushing equipment, the ball mill has many advantages such as simple operation, stable performance, low manufacturing cost, large crushing ratio, and can be used for both wet grinding and dry grinding. However, the ball mill is a large energy consumer in the ore dressing process. Because the grinding process is quite complex, with many influencing factors, long lag time, and difficult online measurement of key process parameters, the grinding process is a non-linear multi-variable input-output process. The internal load parameters (such as ball addition amount, feed amount, feed particle size distribution, ball ratio, etc.) inside its cylinder cannot be explicitly described and controlled, making it difficult for various control methods to be effective and the degree of automation is very low. At present, the automation production level of most domestic ore dressing plants' ball mills is relatively backward, mainly relying on the combination of manual detection and empirical judgment to regulate the production state.

[0030] Due to the influence of many factors on the ball mill during the grinding process, it has characteristics such as non-linearity, large time lag, and strong random interference. Moreover, it rotates continuously and is closed during operation, resulting in the following characteristics of the ball mill load monitoring and control: (1) The ball mill load is difficult to directly measure. Indirect quantities such as grinding sound signals, cylinder vibration signals, and mill current signals during the grinding process can reflect the mill load to a certain extent, but the relationship between each indirect quantity and the mill load cannot be represented by an accurate mathematical model. (2) There is a correlation between the ball mill load and grinding process parameters such as feed amount and water supply amount, but it cannot be represented by an accurate mathematical model.

[0031] In recent years, for the research on the detection of the mill load state, signal decomposition methods are mostly used to extract the main components for signal reconstruction, then extract features such as power spectrum, multi-scale, singular value, and frequency spectrum, and finally use pattern recognition methods for state detection.

[0032] The main indirect detection methods for the mill load include vibration method, grinding sound method, power method, ultrasonic method, etc. At present, for the detection of the mill load state, many intelligent algorithms are widely used in the mill load modeling, such as through neural networks, support vector machines, extreme learning machines, least squares method, etc., and then combined with the method of multi-source data fusion to comprehensively consider multiple characteristic parameters generated during the grinding process to predict the mill load.

[0033] Although the above methods clarify the influence of the load on the characteristics of the cylinder vibration signal, the detection accuracy has been improved with the optimization of the algorithm and the in-depth research. However, these methods all rely too much on the computing power of the computer and the accuracy of the selected sample data. Due to the many influencing factors in the operation of the ball mill, any change in factors (such as ore properties, liner material and size, rotation speed, material-ball ratio, etc.) will cause the selected sample data to be inaccurate.

[0034] Therefore, it is necessary to frequently update the sample database to provide more characteristic parameter values as the judgment basis when performing load prediction. Moreover, the system operation time is relatively long when using these methods to judge the load, and the real-time performance of judging the mill load is poor. If a single parameter is used to judge the working load of the mill, although the efficiency can be improved, the error is relatively large.

[0035] Based on this, a control method and device for a ball mill provided by an embodiment of the present invention specifically provide a ball mill load state monitoring and automatic adjustment system and method, which can reduce the situation that the existing mill operators adjust the mill load based on manual experience, reduce the manual labor intensity, and realize the automatic control of the mill load. It can keep the ball mill load stable, avoid the interference caused by the changes in the nature of the raw ore and the mill working conditions to the grinding process, and ensure that the grinding concentration is within its target value range.

[0036] To facilitate the understanding of this embodiment, first, a control method for a ball mill disclosed by an embodiment of the present invention will be introduced in detail.

[0037] Embodiment 1:

[0038] An embodiment of the present invention provides a control method for a ball mill. Refer to Figure 1 the flowchart of a control method for a ball mill shown in

[0039] Step S102: Obtain the characteristic signals of the ball mill and preprocess the characteristic signals; wherein, the characteristic signals include: the motor current of the ball mill, the cylinder vibration signal of the ball mill, and the sound intensity of the ball mill.

[0040] The method provided in this embodiment can be applied to a ball mill load state monitoring and automatic adjustment system, which may include: a data acquisition unit, a data processing and control unit, an alarm unit, and a human-machine interaction interface. Among them, the ball mill can be abbreviated as the mill.

[0041] Refer to Figure 2 the schematic diagram of a grinding and classification process shown in

[0042] The data acquisition unit is mainly used to collect the real-time values of the ball mill motor current, the mill cylinder vibration signal, the mill sound intensity, the ore feeding amount, the grinding concentration, the return sand concentration, the mill water replenishment flow rate, and the opening degree of the water replenishment regulating valve, and transmit the real-time values to the data processing and control unit.

[0043] The sound intensity of the mill can be simply referred to as the grinding sound, which is monitored using a grinding sound measuring instrument. Its monitoring probe is installed at the position where the ore and steel ball throwings are located when the ball mill moves in a circumferential direction; the amount of incoming ore is obtained by a belt weighing feeder.

[0044] The grinding concentration is measured using an optoelectronic concentration meter, which is installed on the discharge pipeline from the mill to the pump sump; the reverse sand concentration meter is installed on the feed pipeline from the underflow of the hydrocyclone to the ball mill; the mill make-up water flowmeter and the make-up water regulating valve are installed on the make-up water pipeline at the feed end of the ball mill, and the flowmeter used is an ultrasonic flowmeter.

[0045] In this embodiment, parameters such as the motor current of the ball mill, the cylinder vibration signal of the ball mill, and the sound intensity of the ball mill can be used as characteristic signals. In addition, in this embodiment, the amount of incoming ore, the grinding concentration, the reverse sand concentration, the mill make-up water flow, and the opening degree of the make-up water regulating valve can also be used as characteristic signals.

[0046] Step S104, based on the pre-set correspondence between the characteristic signal and the load state, determine the load state corresponding to the characteristic signal of the ball mill.

[0047] See Figure 3 As shown in the schematic diagram of a data processing and control unit, the data processing and control unit consists of a knowledge base, a database, an inference engine, and a mill load controller. Among them, the knowledge base mainly stores the control logic, control indicators, and expert experience of the system (i.e., the correspondence between the characteristic signal and the load state); the database mainly stores the real-time parameters of the system, as well as the process data and result data generated during the system control process; the inference engine uses the forward reasoning method to determine the load state corresponding to the characteristic signal of the ball mill from the knowledge base according to the pre-set correspondence between the characteristic signal and the load state.

[0048] Step S106, determine the ore feeding amount of the ball mill based on the load state of the ball mill, and control the ore feeding operation of the ball mill based on the ore feeding amount.

[0049] The inference engine of this embodiment can also, after determining the load state of the ball mill, retrieve relevant control logic for logical reasoning operations to determine the ore feeding amount of the ball mill, so as to meet the requirements of the control indicators; the mill load controller includes a proportional regulation algorithm based on characteristic weighting and a fuzzy PID (Proportional Integral Derivative) control algorithm, etc., to automatically adjust the ore feeding amount according to the mill load state, thereby controlling the ore feeding operation of the ball mill. In addition, the mill load controller can also automatically adjust the make-up water amount according to the mill load state, thereby controlling the make-up water operation of the ball mill.

[0050] In addition, it should be noted that the alarm unit is mainly used to give alarm prompts according to system anomalies, including over-threshold alarm of feeding amount, abnormal alarm of grinding concentration, over-current and under-voltage alarm of the mill, abnormal alarm of mill load, and abnormal alarm of the opening degree of the water supply valve. The human-machine interaction interface includes the ball mill area, parameter setting, status control, data analysis, and statistical report. Among them, the ball mill area mainly displays the grinding concentration, the feeding amount of the ball mill, the current of the mill motor, the additional water supply amount of the mill and the opening degree of the water supply valve, as well as the operating status of the equipment; parameter setting is used to adjust the system control parameters according to the current production situation; status control is used to operate the start and stop of the control algorithm; data analysis is mainly a trend comparison chart of the real-time values and target values of the grinding concentration, mill current, feeding amount, and additional water supply amount; the statistical report mainly provides the log information management of the control mode and its operation results.

[0051] An embodiment of the present invention provides a control method for a ball mill, which can use multiple parameters such as the motor current, cylinder vibration signal, and sound intensity of the ball mill as characteristic signals, and comprehensively judge the load status of the ball mill through multiple parameters; moreover, the corresponding relationship between the characteristic signals and the load status can be determined in combination with the production situation of the concentrator and the operation experience of the operators on duty, realizing the effective integration of the control system of the ball mill and manual experience, and improving the efficiency, reliability, and accuracy of judging the load status of the ball mill.

[0052] Embodiment Two:

[0053] This embodiment provides another control method for a ball mill, which is implemented on the basis of the above embodiment. As Figure 4 shown in the flowchart of another control method for a ball mill, the control method for the ball mill in this embodiment includes the following steps:

[0054] Step S402, obtain the characteristic signals of the ball mill and preprocess the characteristic signals; wherein, the characteristic signals include: the motor current of the ball mill, the cylinder vibration signal of the ball mill, and the sound intensity of the ball mill.

[0055] Refer to Figure 5 shown in a schematic diagram of ball mill load judgment and adjustment. First, data collection and preprocessing can be carried out. First, set the mill load judgment interval period. After the interval setting period, collect the characteristic signals (motor current, cylinder vibration signal, sound intensity) of the ball mill.

[0056] Specifically, in this embodiment, the motor current of the ball mill within a preset time range can be averaged. Due to factors such as the anti-interference and stability of the current sensor itself, the monitored current value will fluctuate slightly within a short interval. Therefore, in order to study the variation law of the current signal value corresponding to the mill load, for the collected current values, the current values within every 30 seconds are averaged to obtain the current characteristic value corresponding to the mill load.

[0057] Specifically, this embodiment can acquire the vibration signal of the ball mill; among them, the vibration signal of the ball mill includes the cylinder vibration signal and the mechanical vibration signal; the vibration signal of the ball mill is separated to obtain the cylinder vibration signal of the ball mill. The vibration signal of the mill cylinder is mainly formed by the impact of steel balls on the cylinder liner, and this impact is affected by the amount of load in the cylinder. It is necessary to separate the vibration signal strongly related to the load change from these inherent mechanical vibration signals through a suitable signal decomposition method, and extract the vibration characteristics strongly related to the load change.

[0058] Specifically, this embodiment can perform wavelet threshold denoising on the cylinder vibration signal of the ball mill and / or the sound intensity of the ball mill. Since there are multiple ball mills working simultaneously in the same workshop, the mill sound measuring instrument is easily affected by adjacent mills and environmental noise, causing interference to the mill sound detector. Therefore, wavelet threshold denoising is performed on the vibration signal and the mill sound signal, and the denoised data is obtained after three-layer wavelet packet decomposition, threshold quantization, and wavelet reconstruction.

[0059] Step S304, based on the corresponding relationship between the preset characteristic signal and the load state, determine the load state corresponding to the characteristic signal of the ball mill.

[0060] As Figure 5 shown, this embodiment can identify the mill load state according to the relationship between the characteristic parameters and the mill load. That is, the mill sound signal decreases with the increase of the loading amount. When the loading amount is small, the mill sound signal is the strongest, and when the loading amount is large, the mill sound signal is the lowest; the vibration signal decreases with the increase of the loading amount; within a certain range, the current signal increases with the increase of the loading amount, but when the loading amount is too low or too high, the current signal will decrease.

[0061] Specifically, the load state of the ball mill in this embodiment includes a normal load state and an abnormal load state; the abnormal load state includes an underload state, a low load state, a high load state, and an overload state.

[0062] Combined with the production experience of the operators in dealing with fault conditions during the grinding process, the case-based reasoning method is used to divide the mill load into five conditions: underload, low load, normal load, high load, and overload, and an expert rule table for judging the mill load state is sorted out and generated. Among them, the four conditions of underload, low load, high load, and overload can be collectively referred to as the load abnormal state. The change ranges of the current, grinding sound, and vibration signals for judging the mill load and the experience of the mill load judgment rules are shown in Table 1 and Table 2 respectively.

[0063] Table 1 Change ranges of the current, grinding sound, and vibration signals for judging the mill load

[0064]

[0065] Table 2 Experience table of the mill load judgment rules

[0066]

[0067]

[0068] As shown in Table 1 and Table 2, denote the set current target value I goal , the current lower limit I min , the average current value I(t) within 30 s, the grinding sound target value B goal , the grinding sound upper limit B max , the grinding sound lower limit B min , the denoised real-time grinding sound B(t), the amplitude target value M goal , the amplitude upper limit M min , the amplitude lower limit M max , the denoised real-time amplitude M(t). Denote the underload as condition S1, the low load as condition S2, the normal load as condition S3, the high load as condition S4, and the overload as condition S5.

[0069] Due to the disadvantage of the ambiguity of the ball mill current varying with the mill loading, it is difficult to judge the corresponding relationship between the current adjustment amount and the ore quantity adjustment amount. Therefore, the mill current is only used to assist in judging the mill load interval and does not participate in the ore quantity adjustment control.

[0070] Step S406: Determine the ore feeding amount of the ball mill based on the load state of the ball mill, and control the ore feeding operation of the ball mill based on the ore feeding amount.

[0071] Specifically, if the load state of the ball mill is the load abnormal state, the ore feeding amount of the ball mill is obtained by weighted processing based on the cylinder vibration signal and the sound intensity; if the load state of the ball mill is the load normal state, the ore feeding amount of the ball mill is obtained by proportional-integral-derivative control processing based on the cylinder vibration signal and the sound intensity.

[0072] Such as Figure 5As shown, when the working condition of the ball mill is in an abnormal load (underload, low load, high load, overload) state, the proportional regulation method based on feature weighting is used to control the ore feeding amount of the mill.

[0073] Specifically, in this embodiment, the target values of the cylinder vibration signal and the sound intensity, as well as the weighting coefficients of the cylinder vibration signal and the sound intensity, can be obtained; based on the cylinder vibration signal and the sound intensity, the target values of the cylinder vibration signal and the sound intensity, and the weighting coefficients of the cylinder vibration signal and the sound intensity, the adjustment amount of the ore feeding amount of the ball mill is determined; the reference value of the ore feeding amount of the ball mill is obtained, and the ore feeding amount of the ball mill is determined based on the load state, the reference value and the adjustment amount of the ball mill.

[0074] Set the proportional regulation interval time T', and judge the mill load again at the interval time T' after executing the proportional regulation algorithm. Construct a feature weighting function of the ore feeding amount adjustment amount and the deviation amounts of the grinding sound B and the cylinder vibration signal M from the target values, and obtain: △Q' = k 1 ×a△B + k 2 ×b△M; where a and b are the proportional coefficients of the grinding sound and the vibration signal to the ore feeding amount respectively, which are set according to the production situation; k 1 , k 2 are the weighting coefficients of the grinding sound, the vibration signal to the ore amount respectively, k 1 + k 2 = 1; △B and △M are the absolute values of the deviation between the actual value and the target value.

[0075] Since the calculated ore amount adjustment amount is always different from the actually produced adjustment amount, long-term operation may lead to model imbalance. To avoid this situation, multiply the calculated adjustment amount by the correction coefficient β. At the same time, set the ore amount adjustment reference value to assist in fine-tuning the ore amount. Finally, the ore feeding amount adjustment amount △Q and the target ore amount Q are obtained: △Q = △Q'×β.

[0076] Among them, if the load state of the ball mill is in an underload state or a low load state, the ore feeding amount of the ball mill is determined based on the first calculation relationship, the reference value and the adjustment amount; if the load state of the ball mill is in a high load state or an overload state, the ore feeding amount of the ball mill is determined based on the second calculation relationship, the reference value and the adjustment amount.

[0077] In the underload or low load working condition, the first calculation formula is Q = Q 0 + △Q + A; in the high load or overload working condition, the second calculation formula is Q = Q 0 - △Q + B, Q 0 is the manually set ore amount value, and A and B are the ore amount adjustment reference values.

[0078] As Figure 5 shown, when the working condition of the mill is in the normal load range, the fuzzy PID control algorithm is executed to adjust the ore feeding amount.

[0079] Specifically, in this embodiment, the first adjustment amount of the ore feeding amount of the ball mill corresponding to the cylinder vibration signal can be determined; the second adjustment amount of the ore feeding amount of the ball mill corresponding to the sound intensity can be determined; the average value of the first adjustment amount and the second adjustment amount is used as the target adjustment amount of the ore feeding amount of the ball mill; the reference value of the ore feeding amount of the ball mill is obtained, and the ore feeding amount of the ball mill is determined based on the reference value and the target adjustment amount.

[0080] First, the input of the intelligent fuzzy PID control algorithm is the pretreated grinding sound and cylinder vibration signal, and the output is the set value of the ore feeding amount. Denote the grinding sound deviation E 1 and the deviation change rate E c1 , as well as the vibration signal deviation E 2 and the deviation change rate E c2 , and the fuzzy adjustment interval time T, that is: E 1 = B t - B goal , E 2 = M t - M goal , E c1 =(E Bt - E Bt-1 ) / T, E c2 =(EM t - EM t-1 )T. Among them, B t is the grinding sound at time t, and E Bt is the vibration signal at time t.

[0081] Secondly, combining the changing trends of the grinding sound and vibration signal with the ball mill loading amount and the manual operation experience, select the language variables describing the fuzzy states of the input quantities, that is, divide the deviation values and deviation change rates of the grinding sound and vibration signal into seven states {negative large, negative medium, negative small, zero, positive small, positive medium, positive large}, and the seven states are generally abbreviated with English letter heads as: (NB, NM, NS, O, PS, PM, PB). For the ore feeding amount adjustment amounts △Q B and △Q M corresponding to the grinding sound and vibration signal respectively, divide the universes of discourse, and the values are {-3 (negative large); -2 (negative medium); -1 (negative small); 0 (zero); 1 (positive small); 2 (positive medium); 3 (positive large)}. Finally, establish a fuzzy rule control table, and the fuzzy control rules are shown in Table 3.

[0082] Table 3 Fuzzy control rule table

[0083] E1, E2 Large negative Medium negative Small negative Zero Small positive Medium positive Large positive <![CDATA[E c1 ,E C2 > Ore feed adjustment amount ENB ENM ENS EZE EPS EPM EPB Large negative ECNB 3 2 1 0 0 0 0 Medium negative ECNM 2 2 1 0 0 0 0 Small negative ECNS 2 1 0 0 0 0 -1 Zero ECZE 1 1 0 0 0 -1 -1 Small positive ECPS 1 0 0 0 0 -1 -2 Medium positive ECPM 0 0 0 0 -1 -2 -2 Large positive ECPB 0 0 0 0 -1 -2 -3

[0084] As shown in Table 3, different change intervals can be defined for the grinding sound and the cylinder vibration signal, and corresponding ore quantity adjustment amounts can be given. The control rules adopted are as follows: calculate the second adjustment amount △Q of the ore quantity corresponding to the grinding sound B , and the linguistic rule is: if E 1i and E c1j , then △Q Bij ; i ∈ I, j ∈ J; calculate the first adjustment amount △Q of the ore quantity corresponding to the vibration signal M , and the linguistic rule is: if E 2n and E c2u , then △Q Mnu ; n ∈ N; u ∈ U. Among them, I, j, n, and u respectively represent the number of fuzzy sets, E 1i , E c1j , △Q Bij , E 2n , E c2u , △Q Mnu are any elements in (NB, NM, NS, O, PS, PM, PB) respectively.

[0085] Finally, the average method is used to calculate the final ore feeding adjustment amount, that is, the target adjustment amount △Q of the ore feeding amount of the ball mill = (△Q B + △Q M ) / 2. In addition, when adjusting the ore feeding amount, the upper and lower limit thresholds of the ore quantity are set. When the set value exceeds the threshold, the ore feeding amount of the mill is adjusted according to the set upper and lower limits of the ore quantity.

[0086] The above method provided by the embodiment of the present invention can respectively control the ore feeding amount according to the interval where the mill load is located by using the proportional adjustment algorithm based on feature weighting and the fuzzy PID control algorithm, can realize the rapid adjustment of the ore quantity when the mill load is abnormal, and realize the steady adjustment of the ore quantity when the mill load is normal, effectively avoiding production accidents such as "over-grinding" and "under-grinding" of the mill caused by excessive fluctuations in the ore feeding amount, and improving the working efficiency of the concentrator.

[0087] Step S408, determine the ore-water ratio coefficient based on the load state; determine the water replenishment flow rate of the ball mill based on the ore-water ratio coefficient, and control the water replenishment operation of the ball mill based on the water replenishment flow rate.

[0088] This embodiment can also perform the water replenishment operation of the ball mill. Specifically, if the load state is an under-load state, determine the ore-water ratio coefficient as the maximum value set in advance; if the load state is a low-load state, a high-load state, or a normal load state, determine the grinding concentration and the return sand concentration of the ball mill, and determine the ore-water ratio coefficient based on the calculation relationship set in advance, the grinding concentration, and the return sand concentration; if the load state is an over-load state, determine the ore-water ratio coefficient as the minimum value set in advance.

[0089] SeeFigure 6 Schematic diagram of supplementary water regulation for a ball mill. First, determine the mill load. When the mill is underloaded, according to the mill feed rate adjustment method in the previous steps, the feed rate increases proportionally at this time, and the proportion of feed water is adjusted to the maximum value K synchronously max , to avoid overgrinding, increase the fluidity of the pulp inside the ball mill, and enable the qualified pulp particles to be discharged from the ball mill in a timely manner; when the mill is overloaded, according to the mill feed rate adjustment method in the previous steps, the feed rate decreases proportionally at this time, and the proportion of feed water is adjusted to the minimum value K synchronously min , to increase the grinding concentration, reduce the fluidity of the pulp, and increase the grinding time of the ore in the ball mill.

[0090] Secondly, when the mill load is in three working conditions of high load, normal load, and low load, automatically adjust the water supply of the mill according to the difference between the current grinding concentration and the target concentration. The formula for calculating the grinding concentration is: C = (Q + Q s ) / (Q + W + S). Where C is the grinding concentration, Q is the real-time feed rate, W is the supplementary water volume of the mill, S is the return sand flow rate of the ball mill, and Q s is the return sand ore volume. The formula for calculating the supplementary water flow rate is: W = K × Q, where K is the proportion coefficient of feed water.

[0091] The return sand flow rate and return sand ore volume of the ball mill cannot be accurately estimated, and the return sand volume basically remains stable during the normal production process of the mill. Therefore, the return sand flow rate can be estimated according to the circulating load X of the concentrator plant, that is, the return sand ore volume Q s = X × Q, then the return sand flow rate is: S = Q s / C S , C s is the return sand concentration. After conversion, the formula for calculating the grinding concentration is: C = (Q + X × Q) / (Q + K × Q + (X × Q) / C s ). After conversion, the proportion coefficient of feed water is: K = (1 + X - C - (X × C) / C s ) / C, where X is the circulating load. K 目标 can be calculated according to the set target grinding concentration. △K = K 当前 - K 目标 , automatically adjust the proportion coefficient of feed water according to the difference △K between the calculated value and the target value, and finally obtain the target supplementary water flow rate W.

[0092] Finally, use the PID control algorithm to automatically adjust the opening of the mill water supply valve according to the difference between the target supplementary water flow rate and the real-time flow rate, control the water supply operation of the ball mill, and realize automatic water volume adjustment.

[0093] The above method provided by the embodiment of the present invention automatically adjusts the proportion coefficient of feed water according to the grinding concentration and the mill load, realizes the automatic adjustment of the additional water quantity of the mill, replaces manual operation, avoids the abnormal grinding concentration caused by inaccurate additional water quantity, and improves the grinding efficiency.

[0094] In summary, this embodiment can be a ball mill load state monitoring and automatic adjustment system, which consists of a data acquisition unit, a data processing and control unit, an alarm unit, and a human-machine interaction interface. This embodiment can judge the working load of the mill according to the grinding sound, mill current, and cylinder vibration signal, and use the case-based reasoning method to divide the mill load into five working conditions: underload, low load, normal load, high load, and overload according to production experience. This embodiment can adjust the feed quantity by using the proportional adjustment method and the intelligent fuzzy PID control method respectively according to the interval where the mill load is located. This embodiment can automatically calculate the proportion coefficient of feed water according to the grinding concentration and the mill load interval, and adjust the additional water quantity of the mill.

[0095] This embodiment provides a ball mill load state monitoring and automatic adjustment system and method, which can reduce the situation that the existing mill operators in the concentrator adjust the mill load based on manual experience, reduce the manual labor intensity, and realize the automatic control of the mill load, and has the following advantages:

[0096] (1) This embodiment can comprehensively judge the working load of the mill according to multiple parameters such as current, grinding sound, and vibration signal, avoiding the error existing in the judgment using the single-factor method only.

[0097] (2) This embodiment can divide the working load of the ball mill by using the case-based reasoning method in combination with the production situation of the concentrator and the operation experience of the operators, realizing the effective integration of the control system and manual experience. The judgment of this method has strong reliability and accuracy.

[0098] (3) This embodiment can control the feed quantity by using the proportional adjustment algorithm based on feature weighting and the fuzzy PID control algorithm respectively according to the interval where the mill load is located, which can realize the rapid adjustment of the ore quantity when the mill load is abnormal and the steady adjustment of the ore quantity when the mill load is normal, effectively avoiding production accidents such as "over-grinding" and "under-grinding" of the mill caused by excessive fluctuations in the feed quantity, and improving the working efficiency of the concentrator.

[0099] (4) This embodiment can automatically adjust the proportion coefficient of feed water according to the grinding concentration and the mill load, realizes the automatic adjustment of the additional water quantity of the mill, replaces manual operation, avoids the abnormal grinding concentration caused by inaccurate additional water quantity, and improves the grinding efficiency.

[0100] Embodiment 3:

[0101] Corresponding to the above method embodiment, the embodiment of the present invention provides a control device for a ball mill. See Figure 7Schematic structural diagram of a control device for a ball mill, the control device for the ball mill comprising:

[0102] A characteristic signal acquisition module 71, configured to acquire characteristic signals of the ball mill and preprocess the characteristic signals; wherein, the characteristic signals include: the motor current of the ball mill, the cylinder vibration signal of the ball mill, and the sound intensity of the ball mill;

[0103] A load state determination module 72, configured to determine the load state corresponding to the characteristic signal of the ball mill based on a pre-set correspondence between the characteristic signal and the load state;

[0104] A feed amount control module 73, configured to determine the feed amount of the ball mill based on the load state of the ball mill and control the feeding operation of the ball mill based on the feed amount.

[0105] An embodiment of the present invention provides a control device for a ball mill, which can use multiple parameters such as the motor current, cylinder vibration signal, and sound intensity of the ball mill as characteristic signals, and comprehensively judge the load state of the ball mill through multiple parameters; moreover, the correspondence between the characteristic signal and the load state can be determined in combination with the production situation of the concentrator and the operation experience of the post workers, realizing the effective integration of the control system of the ball mill and manual experience, and improving the efficiency, reliability, and accuracy of judging the load state of the ball mill.

[0106] The above-mentioned characteristic signal acquisition module is configured to perform mean value processing on the motor current of the ball mill within a preset time range; perform wavelet threshold denoising processing on the cylinder vibration signal of the ball mill and / or the sound intensity of the ball mill.

[0107] The above-mentioned characteristic signal acquisition module is configured to acquire the vibration signal of the ball mill; wherein, the vibration signal of the ball mill includes a cylinder vibration signal and a mechanical vibration signal; perform separation processing on the vibration signal of the ball mill to obtain the cylinder vibration signal of the ball mill.

[0108] The above-mentioned load state of the ball mill includes a normal load state and an abnormal load state; the above-mentioned feed amount control module is configured to, if the load state of the ball mill is an abnormal load state, perform weighted processing on the cylinder vibration signal and the sound intensity to obtain the feed amount of the ball mill; if the load state of the ball mill is a normal load state, perform proportional integral derivative control processing on the cylinder vibration signal and the sound intensity to obtain the feed amount of the ball mill.

[0109] The above-mentioned feed amount control module is configured to acquire the target values of the cylinder vibration signal and the sound intensity, and the weighting coefficients of the cylinder vibration signal and the sound intensity; determine the adjustment amount of the feed amount of the ball mill based on the cylinder vibration signal and the sound intensity, the target values of the cylinder vibration signal and the sound intensity, and the weighting coefficients of the cylinder vibration signal and the sound intensity; acquire the reference value of the feed amount of the ball mill, and determine the feed amount of the ball mill based on the load state, reference value, and adjustment amount of the ball mill.

[0110] The above load abnormal states include under-load state, low-load state, high-load state, and over-load state; the above ore feeding amount control module is configured to, if the load state of the ball mill is under-load state or low-load state, determine the ore feeding amount of the ball mill based on a first calculation relationship, a reference value, and an adjustment amount; if the load state of the ball mill is high-load state or over-load state, determine the ore feeding amount of the ball mill based on a second calculation relationship, a reference value, and an adjustment amount.

[0111] The above ore feeding amount control module is configured to determine a first adjustment amount of the ore feeding amount of the ball mill corresponding to the cylinder vibration signal; determine a second adjustment amount of the ore feeding amount of the ball mill corresponding to the sound intensity; take the average value of the first adjustment amount and the second adjustment amount as the target adjustment amount of the ore feeding amount of the ball mill; obtain the reference value of the ore feeding amount of the ball mill, and determine the ore feeding amount of the ball mill based on the reference value and the target adjustment amount.

[0112] The above device further includes: a makeup water flow control module, configured to determine a ore-water ratio coefficient based on the load state; determine the makeup water flow of the ball mill based on the ore-water ratio coefficient, and control the makeup water operation of the ball mill based on the makeup water flow.

[0113] The above flow control module is configured to, if the load state is under-load state, determine the ore-water ratio coefficient as the pre-set maximum value; if the load state is low-load state, high-load state, or normal load state, determine the grinding concentration and the back sand concentration of the ball mill, and determine the ore-water ratio coefficient based on a pre-set calculation relationship, the grinding concentration, and the back sand concentration; if the load state is over-load state, determine the ore-water ratio coefficient as the pre-set minimum value.

[0114] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process of the above-described control device of the ball mill can refer to the corresponding process in the embodiment of the control method of the ball mill described above, and will not be elaborated here.

[0115] Embodiment 4:

[0116] The embodiment of the present invention further provides an electronic device for running the above control method of the ball mill; refer to Figure 8 the structural schematic diagram of an electronic device shown. The electronic device includes a memory 100 and a processor 101. Among them, the memory 100 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor 101 to implement the above control method of the ball mill.

[0117] Furthermore, Figure 8 the electronic device shown further includes a bus 102 and a communication interface 103, and the processor 101, the communication interface 103, and the memory 100 are connected through the bus 102.

[0118] Among them, the memory 100 may include high-speed random access memory (RAM), and may also include non-volatile memory, such as at least one disk memory. The communication connection between this system network element and at least one other network element is realized through at least one communication interface 103 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus 102 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 8 only a bidirectional arrow is used in [description] but it does not mean that there is only one bus or one type of bus.

[0119] The processor 101 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 101 or the instructions in software form. The above-mentioned processor 101 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field programmable gate array (FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register, etc. This storage medium is located in the memory 100, and the processor 101 reads the information in the memory 100 and combines its hardware to complete the steps of the method in the foregoing embodiments.

[0120] An embodiment of the present invention further provides a computer-readable storage medium storing computer-executable instructions, which, when called and executed by a processor, cause the processor to implement the above control method of the ball mill. For specific implementation, reference may be made to the method embodiment, which will not be elaborated herein.

[0121] The control method and device of the ball mill provided by the embodiment of the present invention include a computer-readable storage medium storing program codes, and the instructions included in the program codes can be used to execute the method in the foregoing method embodiment. For specific implementation, reference may be made to the method embodiment, which will not be elaborated herein.

[0122] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described system and / or device can refer to the corresponding processes in the foregoing method embodiment, which will not be elaborated herein.

[0123] In addition, in the description of the embodiments of the present invention, unless otherwise clearly defined and limited, the terms "installation", "connection", and "connection" shall be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0124] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or a part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present invention. The foregoing storage medium includes various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0125] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0126] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present invention, used to illustrate the technical solutions of the present invention, rather than limiting it. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions described in the foregoing embodiments or easily conceive of changes, or perform equivalent replacements for some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A control method for a ball mill, characterized in that, the method includes: acquiring characteristic signals of the ball mill and preprocessing the characteristic signals; wherein, the characteristic signals include: the motor current of the ball mill, the barrel vibration signal of the ball mill, and the sound intensity of the ball mill; determining the load state corresponding to the characteristic signals of the ball mill based on a pre-set correspondence between the characteristic signals and the load state; determining the ore feeding amount of the ball mill based on the load state of the ball mill, and controlling the ore feeding operation of the ball mill based on the ore feeding amount; the load state of the ball mill includes a normal load state and an abnormal load state; the step of determining the ore feeding amount of the ball mill based on the load state of the ball mill includes: if the load state of the ball mill is the abnormal load state, obtaining the ore feeding amount of the ball mill through weighted processing based on the barrel vibration signal and the sound intensity; if the load state of the ball mill is the normal load state, obtaining the ore feeding amount of the ball mill through proportional-integral-derivative control processing based on the barrel vibration signal and the sound intensity.

2. The method according to claim 1, characterized in that, the step of preprocessing the characteristic signals includes: performing averaging processing on the motor current of the ball mill within a preset time range; performing wavelet threshold denoising processing on the barrel vibration signal of the ball mill and / or the sound intensity of the ball mill.

3. The method according to claim 1, characterized in that, the step of acquiring the characteristic signals of the ball mill includes: acquiring the vibration signal of the ball mill; wherein, the vibration signal of the ball mill includes the barrel vibration signal and the mechanical vibration signal; performing separation processing on the vibration signal of the ball mill to obtain the barrel vibration signal of the ball mill.

4. The method according to claim 1, characterized in that, the step of obtaining the ore feeding amount of the ball mill through weighted processing based on the barrel vibration signal and the sound intensity includes: acquiring the target values of the barrel vibration signal and the sound intensity, and the weighting coefficients of the barrel vibration signal and the sound intensity; determining the adjustment amount of the ore feeding amount of the ball mill based on the barrel vibration signal and the sound intensity, the target values of the barrel vibration signal and the sound intensity, and the weighting coefficients of the barrel vibration signal and the sound intensity; acquiring the reference value of the ore feeding amount of the ball mill, and determining the ore feeding amount of the ball mill based on the load state of the ball mill, the reference value, and the adjustment amount.

5. The method according to claim 4, characterized in that, the abnormal load state includes an underload state, a low load state, a high load state, and an overload state; the step of determining the ore feeding amount of the ball mill based on the load state of the ball mill, the reference value, and the adjustment amount includes: If the load state of the ball mill is an underload state or a low load state, determine the ore feeding amount of the ball mill based on the first calculation relationship, the reference value, and the adjustment amount; where the calculation is performed through the following formula: Q = Q 0 + △Q + A; Q is the ore feeding amount, △Q is the adjustment amount, Q 0 is the manually set ore amount value, and A is the reference value; If the load state of the ball mill is a high load state or an overload state, determine the ore feeding amount of the ball mill based on the second calculation relationship, the reference value, and the adjustment amount; where it is calculated by the following formula: Q = Q 0 - △Q + B; B is the reference value.

6. The method according to claim 1, characterized in that, the step of obtaining the ore feeding amount of the ball mill through proportional-integral-derivative control processing based on the barrel vibration signal and the sound intensity includes: determining the first adjustment amount of the ore feeding amount of the ball mill corresponding to the barrel vibration signal; Determine the second adjustment amount of the ore feeding amount of the ball mill corresponding to the sound intensity; Take the average value of the first adjustment amount and the second adjustment amount as the target adjustment amount of the ore feeding amount of the ball mill; Obtain the reference value of the ore feeding amount of the ball mill, and determine the ore feeding amount of the ball mill based on the reference value and the target adjustment amount; Determine the first adjustment amount of the ore feeding amount of the ball mill corresponding to the cylinder vibration signal; The step of determining the second adjustment amount of the ore feeding amount of the ball mill corresponding to the sound intensity includes: substituting the vibration signal deviation and the deviation change rate into the fuzzy control rule table to obtain the first adjustment amount; substituting the grinding sound deviation and the deviation change rate into the fuzzy control rule table to obtain the second adjustment amount.

7. According to the method described in claim 1, characterized in that, After the step of determining the load state corresponding to the characteristic signal of the ball mill, the method further includes: Determine the ore-water ratio coefficient based on the load state; Determine the water replenishment flow rate of the ball mill based on the ore-water ratio coefficient, and control the water replenishment operation of the ball mill based on the water replenishment flow rate.

8. According to the method described in claim 7, characterized in that, The step of determining the ore-water ratio coefficient based on the load state includes: If the load state is an under-load state, determine that the ore-water ratio coefficient is the maximum value set in advance; If the load state is a low-load state, a high-load state or a normal-load state, determine the grinding concentration and the reverse sand concentration of the ball mill, and determine the ore-water ratio coefficient based on the calculation relationship set in advance, the grinding concentration and the reverse sand concentration; If the load state is an over-load state, determine that the ore-water ratio coefficient is the minimum value set in advance.

9. A control device for a ball mill, characterized in that, The device includes: A characteristic signal acquisition module, configured to acquire a characteristic signal of the ball mill and preprocess the characteristic signal; wherein, the characteristic signal includes: the motor current of the ball mill, the cylinder vibration signal of the ball mill, and the sound intensity of the ball mill; A load state determination module, configured to determine the load state corresponding to the characteristic signal of the ball mill based on the corresponding relationship between the characteristic signal and the load state set in advance; An ore feeding amount control module, configured to determine the ore feeding amount of the ball mill based on the load state of the ball mill, and control the ore feeding operation of the ball mill based on the ore feeding amount; The load state of the ball mill includes a normal load state and an abnormal load state; the ore feeding amount control module is configured to, if the load state of the ball mill is the abnormal load state, perform weighted processing based on the cylinder vibration signal and the sound intensity to obtain the ore feeding amount of the ball mill; if the load state of the ball mill is the normal load state, perform proportional-integral-derivative control processing based on the cylinder vibration signal and the sound intensity to obtain the ore feeding amount of the ball mill.

Images