CN100394163C - Flexible measuring method for overflow particle size specification of ball mill grinding system - Google Patents

Flexible measuring method for overflow particle size specification of ball mill grinding system Download PDF

Info

Publication number
CN100394163C
CN100394163C CNB031339514A CN03133951A CN100394163C CN 100394163 C CN100394163 C CN 100394163C CN B031339514 A CNB031339514 A CN B031339514A CN 03133951 A CN03133951 A CN 03133951A CN 100394163 C CN100394163 C CN 100394163C
Authority
CN
China
Prior art keywords
neural network
soft
training
grinding
measurement
Prior art date
Application number
CNB031339514A
Other languages
Chinese (zh)
Other versions
CN1525153A (en
Inventor
岳恒
赵大勇
柴天佑
Original Assignee
东北大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 东北大学 filed Critical 东北大学
Priority to CNB031339514A priority Critical patent/CN100394163C/en
Publication of CN1525153A publication Critical patent/CN1525153A/en
Application granted granted Critical
Publication of CN100394163C publication Critical patent/CN100394163C/en

Links

Abstract

The present invention relates to the technical field of measurement in an automation technique, particularly to a soft measurement method for overflow granularity indexes of a spiral classifier of a grinding circuit used for grinding ore and composed of a ball mill and a spiral classifying machine set in an ore grinding working section in an ore dressing plant. In the method, a distributed computer control system and a conventional measuring instrument are used for providing on-line process data and combining time variables to reflect the variation of grinding media; a classifier overflow granularity soft measurement model composed of neural networks is established through a small quantity of artificial samples to realize the soft measurement of the overflow granularity of the classifier of a grinding system. Compared with the conventional granulometer, the method reduces cost and maintenance workload; compared with manual measurement, the method reduces operators' workload, reduces the indeterminacy of artificial operation and increases the timeliness of the measurement; simultaneously, the method is helpful to realize the optimization control and the optimization operation of an ore grinding process.

Description

Bowl mill grinding system overflow granularity index flexible measurement method

Technical field

The present invention relates to the field of measuring technique in a kind of automatic technology, relate to final products---the method that spiral classifier overflow granularity index is carried out soft measurement particularly the wet grinding loop of forming by bowl mill and spiral classifier that is used for ground ore in the ore dressing plant ore grinding workshop section.

Background technology

In the ore dressing industry, the wet grinding loop of being made up of bowl mill and spiral classifier is widely used in ore grinding to the particle size range of technological requirement, granularity is excessive or too smallly all the follow-up process of sorting is had a negative impact, so the final products of grinding circuit---the granularity (also claiming grinding particle size, overflow granularity) of spiral classifier overflow is to weigh the important indicator of grinding circuit riding quality.At present, the detection method of conventional grinding particle size is by two kinds: the one, and the off-line hand sampling is at the laboratory manual measurement; Another kind is to use the checkout equipment of granularity---and hondrometer carries out on-line measurement, and the deficiency of preceding a kind of method is: 1. the human factor influence is big during manually-operated, and the objectivity of measurement result is poor; The time interval of Ce Lianging long, the time of measurement feedback is also long, the information that therefore obtains lacks directive significance to operating personnel; Though the second method weak point is to access accurately objective measurement result timely of comparison, but hondrometer costs an arm and a leg, the most ore dressing plants of China are difficult to be equipped with, and the workload of field maintemance is also very huge, in sum, also there is not to add at bowl mill specially the grinding particle size employing flexible measurement method of the grinding circuit of spiral classifier formation at present both at home and abroad.

Summary of the invention

In order to solve the above deficiency that bowl mill is added the grinding particle size measurement of the grinding circuit that spiral classifier constitutes, the purpose of this invention is to provide a kind of grinding particle size flexible measurement method at this grinding circuit, be used to set up the grinding particle size soft-sensing model of realizing with neural network, the measurement parameter of the auxiliary variable that provides by conventional on-line measurement instrument, provide the estimated value of current classifier overflow granularity, moving with optimization for the Optimizing operation of time in grinding production process provides key index.

Flexible measurement method technical scheme of the present invention is achieved in that

Grinding particle size measuring method proposed by the invention is made up of hardware platform and Survey Software, and wherein the hardware platform core is made up of bowl mill and spiral classifier, has been equipped with measurement instrument simultaneously, topworks and the computer system of carrying out computed in software.The connection of its hardware is that input end and belt feeder, bowl mill inlet amount of water pipeline and the grader sand return mouth of bowl mill links, bowl mill output terminal and outlet are added water inlet and are joined with the spiral classifier input port simultaneously, spiral classifier sand return end and bowl mill inlet join detailed structure following (as shown in Figure 1):

One adds the grinding circuit that spiral classifier constitutes by bowl mill, and its measurement instrument comprises

A weighing instrument (can be uclear scale or belt conveyer scale) is used for the new mine-supplying quantity Q of on-line measurement bowl mill F, be installed on the feeding belt;

A flowmeter is used for on-line measurement bowl mill inlet amount of water W F, be installed on the bowl mill inlet filler pipe;

A densitometer is used for on-line measurement overflow concentration in classifier D OVC, be installed on the classifier overflow pipeline;

Two power meters or two galvanometer are used for on-line measurement ball mill power P WMWith the spiral classifier power P WCOr bowl mill electric current and spiral classifier electric current, the drive motor with bowl mill and grader joins respectively, because power signal and current signal equivalence, so P in this instructions WMAnd P WCAlso can be used for representing bowl mill electric current and spiral classifier current signal.

Its topworks comprises:

Two motor regulated valves are respectively applied for and regulate that the bowl mill inlet is added water and water is added in the bowl mill outlet, are installed on that the bowl mill inlet is added water pipe and the bowl mill outlet is added on the water pipe;

A frequency converter is used to regulate the batcher vibration frequency, joins with oscillating feeder;

Distributed computer control system (DCS) or programmable logic controller (PLC) (PLC) or industrial control computer (IPC) have been disposed in this grinding circuit simultaneously, or the discrete industrial regulator, and form the basic controlling loop according to following corresponding relation:

The new mine-supplying quantity Q of electric vibrating feeder frequency control F

The bowl mill inlet is added the moving variable valve control of water power bowl mill inlet and is added discharge W F

The moving variable valve control of water power spiral classifier effluent concentration D is added in the bowl mill outlet OVC

Soft Survey Software of the present invention both may operate on the supervisory control comuter of computer control system, also can run on independently on the computing machine, this software by with control loop (distributed computer control system (DCS) or programmable logic controller (PLC) (PLC) or industrial control computer (IPC), or discrete industrial regulator) carries out communication, obtain real-time process data, and provide the estimated result of grinding particle size.

Implementation method of the present invention comprises, the selection of auxiliary variable, training data obtain the study of neural network soft sensor model and use.

The selection of auxiliary variable.

After above-mentioned hardware platform has been realized the automatic control in three basic loops of bowl mill, we will add the grinding attachment that spiral classifier constitutes by bowl mill and add that control system is defined as the grinding system of the nonlinear multiple-input and multiple-output of being made up of following input/output variable:

Its input variable comprises:

But the performance variable of controlled on-line measurement (also claiming independent variable) comprises

The new mine-supplying quantity Q of bowl mill F

Bowl mill inlet amount of water W F

Overflow concentration in classifier D OVC

Uncontrollable disturbance variable that can not on-line measurement comprises

The quantity G of milling medium in the bowl mill M, the steel ball of the some of property adding once a day under the general normal running, thus this variable over time trend be roughly as shown in Figure 2 sawtooth pattern curve;

Ore hardness H D

Its output variable comprises:

But the variable of on-line measurement comprises

Ball mill power (or electric current) P WM

Screw classifying acc power (or electric current) P WC

Target variable that can not on-line measurement, promptly

Spiral classifier overflow granularity P SOV, generally adopt the off-line hand sampling, obtain data at the laboratory manual measurement;

Under stable situation, the input/output relation of this nonlinear system can be expressed as

P SOV=f 1(Q F,W F,D OV,H D,G M)

P WM=f 2(Q F,W F,D OV,H D,G M)

P WC=f 3(Q F,W F,D OV,H D,G M)

According to inverse function theorem, by f 2And f 3There is the inverse function relation in two formula as can be known between bowl mill electric current and grader electric current and milling medium quantity and the ore hardness:

H D=f 4(Q F,W F,D OV,P WM,P WC)

G M=f 5(Q F,W F,D OV,P WM,P WC)

Therefore, with last two nonlinear function substitution f 1Among, can obtain

P SOV=f 1(Q F,W F,D OV,H D,G M)

=f 1[Q F,W F,D OV,f 4(Q F,W F,D OV,P WM,P WC),f 5(Q F,W F,D OV,P WM,P WC)]

=f 6(Q F,W F,D OV,P WM,P WC)

So, spiral classifier overflow granularity P SOVCan pass through new mine-supplying quantity Q F, inlet adds discharge W F, overflow concentration in classifier D OVC, ball mill power (or electric current) P WM, grader power (or electric current) P WCInformation parameter reflect.

Notice the quantity G of milling medium in the bowl mill M, the steel ball of the some of property adding once a day under general normal running, its Changing Pattern is that the cycle is the curve of 24 hours approximate sawtooth pattern, if introduce following time variable:

T---add ball within the cycle at one, begin time span constantly to current time from adding ball

The quantity G that just can reflect milling medium in the bowl mill more sensitively MVariation (although the variation of power or electric current can reflect that susceptibility is weaker).Therefore with time variable T as one independently auxiliary variable introduce soft-sensing model:

P SOV=f 7(Q F,W F,D OV,P WM,P WC,T)

Following formula has reflected that under the steady state (SS) of grinding system these auxiliary variables that we select are with master variable spiral classifier overflow granularity P to be estimated SOVBetween the nonlinear function of outwardness.

Therefore the selected auxiliary variable of the present invention comprises

New mine-supplying quantity Q F

Inlet is added discharge W F

Overflow concentration in classifier D OVC

Ball mill power (or electric current) P WM

Grader power (or electric current) P WC

Time variable T.

Obtaining of training data.

Within the equipment ability to bear, covering normal operation range and be a bit larger tham in the scope of normal operation range, provide one group of independent variable (new mine-supplying quantity Q F, inlet adds discharge W F, overflow concentration in classifier D OVC) the combination of different setting values, the setting value set below forming

S setpoint={[Q Fi,W Fi,D OVi]|i=1,…,m}

Wherein m is the number of elements in this set, and each element comprises [a Q Fi, W Fi, D OVi] tlv triple.Each element of this setting value set is put on the grinding system successively, whenever add a minor element [Q Fi, W Fi, D OVi] treat that afterwards grinding system enters stable state, by artificial collection sample, send the size value P of laboratory measurement sample in spiral classifier overflow place SOVi, the moment T of record sampling simultaneously i(beginning metering constantly from the recent ball that adds) as the time variable of this sampling, and writes down ball mill power (or electric current) P simultaneously WMi, grader power (or electric current) P WCi, treat that this sampling and record are finished after, grinding system is applied next element.Thus, can obtain following data acquisition

S V={[Q Fi,W Fi,D OVi,P WMi,P WCi,T i,P SOVi]|i=1,…,m}

According to following rule pairing, promptly become training set with above-mentioned data acquisition

{[Q Fi,W Fi,D OVi,P WMi,P WCi,T i]|i=1,…,m}→{[P SOVi]|i=1,…,m}

Wherein, the variable on → symbol left side is the input variable (auxiliary variable just) of grinding particle size soft-sensing model, and the variable on → symbol the right carries out tutor's signal of learning training for the grinding particle size soft-sensing model.The input/output variable relation of this soft-sensing model and training patterns are as shown in Figure 3.

The training of neural network soft sensor model and use.

Flexible measurement method of the present invention is that the mode with soft Survey Software realizes its FB(flow block) (as shown in Figure 4).Be divided into training process and measuring process, its detailed step is as follows:

(A) initialization: carry out the initialization of all variablees.

(B) training or measurement? if this operates to training process, then go to step (C), use the process of the data neural network training of training set; If neural network trains, the purpose of this operational process is in order to measure the effluent concentration index under the current state, then to go to step (I);

(C) determine neural network structure and initial weight

Because neural network can be approached arbitrarily nonlinear function continuously with arbitrary accuracy, therefore any neural network with above-mentioned character can be used as soft-sensing model structure of the present invention, can adopt counterpropagation network (BP) and radial basis function (RBF) network during concrete enforcement, but be not limited to this two kinds of networks.

(D) read the data of training set: from the database at training set place, read relevant data, carry out normalized after, the input neural network soft-sensing model;

(E) calculate the output of neural network soft sensor model, and with tutor's signal relatively

The soft-sensing model that input signal in training set input is made of neural network is compared the output of current time soft-sensing model with corresponding tutor's signal, calculate current error signal;

(F) revise neural network weight

Adopt the weight matrix of the inside of relevant Learning Algorithm correction neural network according to the error signal that relatively obtains, the target of correction is to make mean square of error and decline between the output of soft-sensing model tutor's signal corresponding with it.Revise after the weights, recomputate the output of neural network, and with tutor's signal relative error;

(G) whether error qualified? if error meets preassigned, illustrate that then neural metwork training finishes, and goes to step (H); If error does not meet preassigned, explanation should continue training, goes to step (E);

(H) preserve neural network weight: training process finishes, and the neural network weight that obtains just can be used for overflow granularity is carried out soft measurement;

(I) read neural network weight: if the purpose of this operation is in order to measure the effluent concentration index under the current state, then at first will to read the neural network weight that preceding step (H) is kept;

(J) read process data

Does (K) process enter stable state? if all variablees of process have all entered stable state, then begin to carry out soft measuring process; Otherwise return step (J) wait and enter stable state;

(L) the steady-state process data are through input neural network after the normalized identical with training process.

(M) calculate neural network output: determine good neural network structure and neural network weight according to the front, calculate current output, just the estimated value of overflow granularity index.

(N) show the soft measurement result of granularity: the estimated value that on man-machine interface, shows the soft measurement index of overflow granularity.

(O) finish not? continue if desired to measure, then be back to step (J); If do not need to continue to measure, then go to step (P);

(P) finish.

In order to make soft-sensing model have certain adaptive ability, adapt to the chronic drift and the variation of the characteristic of grinding system, need neural network soft sensor model to wait where necessary and restart study, its method is, when according to the regular manual measurement classifier overflow of the operating provisions in ore dressing plant granularity the time, sampled value is compared with the output valve of neural network, if difference surpasses certain limit, remarkable drift has appearred in the characteristic that grinding system is described, so startup learning process, the data that newly collect are formed new training set, according to aforesaid learning algorithm original neural network soft sensor model is further trained, reduce to desired standard until error level.

The invention has the advantages that: the online process data of utilizing conventional computer control system and conventional measuring instrument to provide, and the binding time variable is with the variation of reflection milling medium, only, realized the soft measurement of grinding system classifier overflow granularity by a spot of artificial sample.Compare with hondrometer, reduced cost, and the situation that sampling line stops up can not take place, reduced maintenance workload, improved reliability; Compare with manual measurement, reduced operating personnel's workload, reduced the uncertainty of the measurement of manual operation introducing, improved measure ageing.This method helps to realize the optimal control of grinding system and optimizes operation.

Description of drawings

Fig. 1 is flow process and the measurement instrument topworks and the basic loop configuration figure of grinding circuit of the present invention

Fig. 2 adds the approximate change curve of the interior milling medium of bowl mill under the ball system for routine of the present invention

Fig. 3 is the input/output relation and the training patterns of grinding particle size soft-sensing model of the present invention

Fig. 4 is the FB(flow block) of the soft Survey Software of overflow granularity of the present invention

Used label symbol is as follows among Fig. 1 to Fig. 3:

Spiral classifier overflow granularity---P SOV

New mine-supplying quantity---Q F

The bowl mill inlet is added discharge---W F

Spiral classifier effluent concentration---D OVC

Ball mill power (or electric current)---P WM

Screw classifying acc power (or electric current)---P WC

Time variable---T

Power (or electric current) transmitter---PT

Consistency transmitter---DT

Flow transmitter---FT

Quality transmitter---WT

The solid line tip is represented logistics (raw ore, water and ore pulp) or signal flow;

The pecked line arrow is represented the pairing of basic control loop;

Draw dotted line and represent being connected of sensor and transmitter.

Embodiment

Embodiments of the invention are the primary grinding series of the weak magnetic roasted ore of a large-scale iron ore beneficiating factory.The main iron ore in this ore dressing plant is a pyrite, limonite, gangue is with barite, quartzy, jasper and ferrodolomite are main, the actual ferrous grade 33% of ore, behind calcining process, transport to low intensity magnetic separation cylinder ore storage bin through the weak magnetic ore deposit after the sorting, the synoptic diagram of grinding system as shown in Figure 1, roasted ore in the low intensity magnetic separation cylinder ore storage bin is by the electricity rock feeder discharge that shakes, again by sending in the bowl mill for the ore deposit belt feeder, adding water with bowl mill inlet is blended in and is ground into ore pulp in the bowl mill, this section ore grinding adopts grate ball mill, bowl mill ore discharge and bowl mill outlet are added the water bout and are entered spiral classifier, ball milling is returned in the spiral classifier sand return one time, forms closed circuit with a ball milling.After entering the pump pond, spiral classifier overflow (being the final products of this procedure) is transported to subsequent handling.

The bowl mill model is Φ 3200 * 3500, useful volume 25.3m 3, drum speed 18.5r/min, 54 tons of maximum ball loads.

Spiral classifier is a 2FLG-2400 type duplex-spiral classifier.Revolution speed of screw 3.5r/min, the tank gradient 17 degree.

At first following measurement instrument and topworks are installed, comprise in requirement according to this instructions:

Uclear scale is measured new mine-supplying quantity Q F

Electromagnetic flowmeter survey bowl mill inlet is added discharge W F

Nuclear density gauge is measured spiral classifier effluent concentration D OVC

Galvanometer is measured bowl mill electric current P WM

Galvanometer is measured spiral classifier electric current P WC

Frequency Converter Control electric vibrating feeder frequency

Two electric control valves control bowl mill inlet adds water and water is added in the bowl mill outlet

Realize the automatic control of basic control loop with Programmable Logic Controller (PLC).In slave computer, use the single-loop regulator configuration among the PLC to become following basic control loop:

The new mine-supplying quantity Q of electric vibrating feeder frequency control F

The bowl mill inlet is added the moving variable valve control of water power bowl mill inlet and is added discharge W F

The moving variable valve control of water power spiral classifier effluent concentration D is added in the bowl mill outlet OVC

Realize monitoring human-computer interface at host computer (supervisory control comuter) with RSView32 software.Provide the setting value in above-mentioned three loops on man-machine interface, basic loop control unit just can guarantee that each performance variable equals setting value separately when grinding system enters stable state, and the normal range of operation of this grinding system is:

New mine-supplying quantity---75 ± 5 tons/hour

An ore milling concentration---78%~85%

The spiral classifier effluent concentration---45%~50%

Spiral classifier overflow granularity---55%~60% (200 order)

The medium filling rate---38%~42%

Soft process of measurement moves on independent computing machine, RS Linx communication program is housed on this computing machine is responsible for carrying out data communication with PLC and host computer, carries out both-way communication by the DDE mode between RS Linx and the soft process of measurement.

According to the described step that obtains training data of this instructions, at first provide 50 groups of different independent variables (new mine-supplying quantity Q F, inlet adds discharge W F, overflow concentration in classifier D OVC) the combination of setting value, put on successively in the setpoint column of host computer, treat that grinding system enters after the stable state, overflow granularity is measured in artificial sample, and the data of record grinding system, forms by 50 training the training of forming is gathered.

Neural network adopts the single hidden layer BP network of seven inputs, one output.Seven inputs are respectively: new mine-supplying quantity Q F, inlet adds discharge W F, overflow concentration in classifier D OVC, bowl mill electric current P WM, spiral classifier electric current P WC, time variable T, constant threshold value (1).Latent first number of neural network is chosen as 60, and the structure of network is expressed as with the form of matrix:

y=NN(x)

=W 1·sig(W 2·x)

Wherein, y is the output of network, and x contains threshold value at interior augmentation input vector, and activation function is chosen as the Sigmoid function, and its expression formula is:

sig ( z ) = e z - e - z e z + e - z

Output variable and output layer weights W 1Between be linear relationship, adopt the gradient descent method to train, learning rate η gets 0.0001.When dropping to 2%, relative error stops training when following, the neural network soft sensor model of the overflow granularity that the above-mentioned learning process of process forms is at the grinding system normal operation period, can estimate the spiral classifier overflow granularity of stable state according to the stable state real time data of process, relative error is no more than 3%, become one have very high practical value, granularity measurement means cheaply.

Claims (3)

1. a bowl mill grinding system overflow granularity index flexible measurement method is characterized in that this measuring method includes the selection of auxiliary variable, training data obtain the study of neural network soft sensor model and use:
The auxiliary variable of selecting comprises: new mine-supplying quantity Q F, inlet is added discharge W F, overflow concentration in classifier D OVC, ball mill power or electric current P WM, grader power or electric current P WC, time variable T;
Obtaining of data is by providing one group of independent variable, comprising new mine-supplying quantity Q F, inlet adds discharge W F, overflow concentration in classifier D OVCThe combination of different setting values, form the setting value set, each element of this setting value set is put on the grinding system successively, treat that grinding system enters stable state, in spiral classifier overflow place by artificial collection sample and measure the size value P of sample SOViAs tutor's signal, simultaneously writing time variable T i, ball mill power or electric current P WMi, grader power or electric current P WCi, obtain the training set of neural network soft sensor model;
The study of neural network soft sensor model and use are that the weights of application training set pair neural network soft sensor model are trained and the overflow granularity index is carried out soft measurement.
2. by the described bowl mill grinding system of claim 1 overflow granularity index flexible measurement method, it is characterized in that the study and the use of described neural network soft sensor model, its specific implementation step is as follows: (A) initialization: carry out the initialization of all variablees; (B) training or measurement? if this operates to training process, then go to step (C), if neural network trains, then go to step (I); (C) determine neural network structure and initial weight; (D) read the data of training set: from the database at training set place, read relevant data, carry out normalized after, the input neural network soft-sensing model; (E) output of calculating neural network soft sensor model, and with tutor's signal relatively: the soft-sensing model that the input of the input signal in the training set is made of neural network, the output of current time soft-sensing model is compared with corresponding tutor's signal, calculated current error signal; (F) revise neural network weight: adopt the weight matrix of the inside of relevant Learning Algorithm correction neural network according to the error signal that relatively obtains, the target of correction is to make mean square of error and decline between the output of soft-sensing model tutor's signal corresponding with it; Revise after the weights, recomputate the output of neural network, and with tutor's signal relative error; (G) whether error qualified? if error meets preassigned, illustrate that then neural metwork training finishes, and goes to step (H); If error does not meet preassigned, explanation should continue training, goes to step (E); (H) preserve neural network weight: training process finishes, and the neural network weight that obtains just can be used for overflow granularity is carried out soft measurement; (I) read neural network weight: if the purpose of this operation is in order to measure the effluent concentration index under the current state, then at first will to read the neural network weight that preceding step (H) is kept; (J) read process data; Does (K) process enter stable state? if all variablees of process have all entered stable state, then begin to carry out soft measuring process; Otherwise return step (J) wait and enter stable state; (L) the steady-state process data are through input neural network after the normalized identical with training process; (M) calculate neural network output: determine good neural network structure and neural network weight according to the front, calculate current output, just the estimated value of overflow granularity index; (N) show the soft measurement result of granularity: the estimated value that on man-machine interface, shows the soft measurement index of overflow granularity; (O) finish not? continue if desired to measure, then be back to step (J); If do not need to continue to measure, then go to step (P); (P) finish.
3. by the described a kind of bowl mill grinding system overflow granularity index flexible measurement method of claim 1, it is characterized in that the new mine-supplying quantity Q in the auxiliary variable of described selection F, inlet is added discharge W F, overflow concentration in classifier D OVC,Ball mill power or electric current P WM, grader power or electric current P WCBe to record by on grinding system, installing and measuring instrument.
CNB031339514A 2003-09-12 2003-09-12 Flexible measuring method for overflow particle size specification of ball mill grinding system CN100394163C (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CNB031339514A CN100394163C (en) 2003-09-12 2003-09-12 Flexible measuring method for overflow particle size specification of ball mill grinding system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CNB031339514A CN100394163C (en) 2003-09-12 2003-09-12 Flexible measuring method for overflow particle size specification of ball mill grinding system

Publications (2)

Publication Number Publication Date
CN1525153A CN1525153A (en) 2004-09-01
CN100394163C true CN100394163C (en) 2008-06-11

Family

ID=34286086

Family Applications (1)

Application Number Title Priority Date Filing Date
CNB031339514A CN100394163C (en) 2003-09-12 2003-09-12 Flexible measuring method for overflow particle size specification of ball mill grinding system

Country Status (1)

Country Link
CN (1) CN100394163C (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106485326A (en) * 2016-10-17 2017-03-08 鞍钢集团矿业有限公司 A kind of hardness detection method in ore reduction production process
CN109142167A (en) * 2018-06-26 2019-01-04 中国矿业大学 A kind of method for building up of the online robust canonical soft-sensing model of grinding particle size

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101244403B (en) * 2008-03-17 2011-07-20 西安艾贝尔科技发展有限公司 Optimization control method for grind grading process
CN101569869A (en) * 2009-05-31 2009-11-04 内蒙古华生高岭土有限责任公司 Coal-measure hard kaolin wet method stripping monocular tertiary circular grinding method
CN101776531B (en) * 2010-02-10 2013-07-10 东北大学 Soft sensing method for load parameter of ball mill
CN102169077B (en) * 2010-12-28 2013-04-17 东北大学 Hybrid intelligent soft measuring method of overflow granularity index in wet grinding process
CN102357395A (en) * 2011-10-27 2012-02-22 东南大学 Obscure monitoring control device and method in ore grinding grading process
CN103344530B (en) * 2013-04-18 2014-05-07 中国科学院沈阳自动化研究所 Soft measurement method for granularity of cement raw material grinded by ball mill
CN104028364A (en) * 2014-04-30 2014-09-10 江西理工大学 Multi-metal ore-separating and ore-grinding grading optimization test method
CN105528636B (en) * 2015-12-04 2018-06-15 中国人民解放军61599部队计算所 A kind of mill load parameter soft measurement method based on fuzzy reasoning
CN107451386A (en) * 2016-05-31 2017-12-08 丹东东方测控技术股份有限公司 Grinding process mill power online soft sensor method
CN109482330B (en) * 2018-11-02 2020-06-30 北矿智云科技(北京)有限公司 Total water balance control method and device for SABC ore grinding

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN87108168A (en) * 1987-12-19 1988-07-27 沈阳矿山机器厂 A kind of method of controlling grinding particle size
CN1032978A (en) * 1987-11-04 1989-05-17 冶金工业部马鞍山矿山研究院 The method and apparatus of ultrasound examination pulp granularity
FR2690745A1 (en) * 1992-04-30 1993-11-05 Lorraine Laminage Acoustic method of particle size evaluation - e.g. of iron ore delivered into blast furnace charging hopper

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1032978A (en) * 1987-11-04 1989-05-17 冶金工业部马鞍山矿山研究院 The method and apparatus of ultrasound examination pulp granularity
CN87108168A (en) * 1987-12-19 1988-07-27 沈阳矿山机器厂 A kind of method of controlling grinding particle size
FR2690745A1 (en) * 1992-04-30 1993-11-05 Lorraine Laminage Acoustic method of particle size evaluation - e.g. of iron ore delivered into blast furnace charging hopper

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106485326A (en) * 2016-10-17 2017-03-08 鞍钢集团矿业有限公司 A kind of hardness detection method in ore reduction production process
CN106485326B (en) * 2016-10-17 2019-02-05 鞍钢集团矿业有限公司 A kind of hardness detection method in ore reduction production process
CN109142167A (en) * 2018-06-26 2019-01-04 中国矿业大学 A kind of method for building up of the online robust canonical soft-sensing model of grinding particle size

Also Published As

Publication number Publication date
CN1525153A (en) 2004-09-01

Similar Documents

Publication Publication Date Title
Zhou et al. Intelligent optimal-setting control for grinding circuits of mineral processing process
CN104458316B (en) Overall physical model test platform for transient process of hydropower station
CN102183621B (en) Aquaculture dissolved oxygen concentration online forecasting method and system
CN101498457B (en) Boiler combustion optimizing method
US8156017B2 (en) System and method for real-time activity-based accounting
CN1280685C (en) Fluid regultion
CN1940781B (en) Method and system for controlling a batch process
CN103011356B (en) Method for controlling automatic chemical dosing of high-turbidity water system
CN102902257B (en) sewage treatment process optimization and energy-saving control system and method
CN105223937B (en) Hydropower Stations ecological regulation and control intelligence control system and method
CN101226377B (en) Robust control method for asphalt mixing plant batching error
CN102817335B (en) Method and system for optimal scheduling on joint flood control for cascade reservoir groups
CN203830127U (en) Closed type automatic control system for ore grinding classification
CN102789447B (en) Based on the icing of grey multiple linear regression and the analytical approach of meteorological relation
CN103912966A (en) Optimal control method for ground source heat pump refrigerating system
CN102411305B (en) Design method of comprehensive disturbance rejection control system for single-rotor wing helicopter/turboshaft engine
CN100561383C (en) The cooling of sheet billet continuous casting secondary reaches dynamically gently depresses off-line emulation system
CN105046953A (en) Short-time traffic-flow combination prediction method
CN102184490A (en) System and system for real-time monitoring and managing urban water resources
CN101038277B (en) Soft measurement method for coal power fineness in powdering producer
CN101923083B (en) Sewage chemical oxygen demand soft measuring method based on support vector machine and neural network
CN101382801B (en) Optimum soft measuring instrument based on EGA-optimized polymerization of propylene production process and method
CN100577272C (en) Dynamic batching digital control system and method
CN101371164A (en) Dynamic production system management
CN101315557B (en) Propylene polymerization production process optimal soft survey instrument and method based on genetic algorithm optimization BP neural network

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
EXPY Termination of patent right or utility model
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20080611

Termination date: 20150912