WO2007124981A1 - Procede pour faire fonctionner un systeme de broyeur - Google Patents

Procede pour faire fonctionner un systeme de broyeur Download PDF

Info

Publication number
WO2007124981A1
WO2007124981A1 PCT/EP2007/052494 EP2007052494W WO2007124981A1 WO 2007124981 A1 WO2007124981 A1 WO 2007124981A1 EP 2007052494 W EP2007052494 W EP 2007052494W WO 2007124981 A1 WO2007124981 A1 WO 2007124981A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
mill system
operating
mill
unit
Prior art date
Application number
PCT/EP2007/052494
Other languages
German (de)
English (en)
Inventor
Norbert Becker
Rüdiger DÖLL
Hans-Ulrich LÖFFLER
Robert Wagner
Original Assignee
Siemens Aktiengesellschaft
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 Siemens Aktiengesellschaft filed Critical Siemens Aktiengesellschaft
Publication of WO2007124981A1 publication Critical patent/WO2007124981A1/fr

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B02—CRUSHING, PULVERISING, OR DISINTEGRATING; PREPARATORY TREATMENT OF GRAIN FOR MILLING
    • B02C—CRUSHING, PULVERISING, OR DISINTEGRATING IN GENERAL; MILLING GRAIN
    • B02C25/00—Control arrangements specially adapted for crushing or disintegrating
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/048—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators using a predictor

Definitions

  • the invention relates to a method for operating a mill system.
  • Such a mill system may be, for example, a ball mill (ball mill) or even a SAG (semi-autogenously grinding) mill, which is suitable for grinding coarse-grained materials, such as. As ores or cement, etc., is determined.
  • the throughput by means of dividing different control or reference variables, such. B. a rotational speed of the mill drum, a supply of coarse-grained starting material, a Wasserzu ⁇ drove an ore mill and / or a discharge rate of the ground material present at the output controlled.
  • An important quality feature is the particle size distribution of the crushing material. It influences the yield of the mill system further downstream components such.
  • the aim is to achieve the highest possible throughput with high product quality and at low costs. The latter are significantly determined by the energy and / or material ⁇ required.
  • the object of the invention is therefore to provide a method of the type described, which allows a fast Ie and stable adjustment of the mill system.
  • the method according to the invention is one in which a) model parameters of a model of the mill system are calculated, b) on the basis of the model updated with the calculated model parameters for at least one operating variable of the mill system is detected, a predicted value for a current operation phase, c) correcting or command variables of the mill system set on the basis of the updated model and used during the aktuel ⁇ len operating phase, d) a measured value of the operating variable during the current operating phase determined is e) determining a deviation between the predictive value and the measured ⁇ value, f) the model parameters based on the deviation adapted and used with the model to predict the operating quantity and to the actuator or control variables setting for a future operating state of w earth.
  • the operating method according to the invention is based on an adaptive model-predictive controller.
  • an overall model of the complete mill system is created and taken into account in the adaptive control.
  • the model parameters of the overall model are tracked as a function of a comparison between the prediction and the actually measured value of one or more operating variables. Since the operating variables are preferably immediately measured, they can also directly to the adaptation of the model parameters, and thus also of the model used for the control Hérange ⁇ subjected. The tracking is done very quickly. Since the control is based on predictions of future operating size values, rule dead times play virtually no role. Therefore, feedback and instabilities, which are often due to dead-times, are largely avoided.
  • the inventive method responds quickly to changing Pro ⁇ zess crab, such as a change in the quality of the supplied material, and regulates the desired throughput with the required product quality an immediate new.
  • a bottom unit and a hydrocyclone unit Submo ⁇ delle at least unit for a central Mühlenein ⁇ , situated. They are the three most important subunits of the mill system. If required, however, a submodel can also be set up for other subunits, such as the pipelines, the pumps and also the mill contents, for example, and taken into account in the overall model.
  • the proportion of currently entered in the grinding drum steel balls, engine torque, engine speed, material supply, the water supply of material and water discharge to standardize the Sumpfein- and find the specific design of the grinding drum A ⁇ gang.
  • the modeling of the sump unit can take place taking into account the fresh water supply and the fill level. Overall, in this way a very accurate Abbil ⁇ -making reality possible.
  • it may also include at Radio Grö ⁇ SSE, the predicted and measured flow to a transit, a density, a weight, a pressure, a power, a torque, speed, or graininess act.
  • the operating procedure can be very wide
  • the semiconductor device has a particle size distribution in a discharge line to an output of the mill system, in a bottom unit of the mill system or in a return loss to a hydro-cyclone unit.
  • the grain size ⁇ distribution provides a particularly good insight into the processes of the mill system. Your good knowledge enables the ⁇ after a particularly efficient control of Mühlensys ⁇ tems.
  • the particle size distribution can be measured in real time, ie in particular online and / or directly.
  • the detection of the particle size distribution is by means of an optical, an acoustic, or magnetic ⁇ tables measurement method.
  • the detection location also has an influence on the respectively suitable measuring method.
  • a laser diffractometer with online dilution or an in situ measurement by means of a fingerprint sensor is suitable for recording the
  • the adaptation of the model parameters is carried out by means of an optimization or minimization method oriented on at least one predefinable target function, wherein the deviation between the predicted value and the measured value is included in the target function.
  • an optimization or minimization method oriented on at least one predefinable target function, wherein the deviation between the predicted value and the measured value is included in the target function.
  • the setting of the manipulated or control variables by means of at least one predetermined target oriented optimization method is performed, wherein m istsvon wherein Opti ⁇ secondary conditions are taken into account.
  • m istsvon wherein Opti ⁇ secondary conditions are taken into account.
  • the optimization process provides very good, in particular the current conditions adapted model parameters. The consideration of the secondary conditions not only enables throughput optimization, but also at the same time energy and / or quality-optimized operation of the mill system.
  • SQP Simential Quadratic Programming
  • optimization method is used as target and in particular a system present within the mill grain ⁇ size or grain size distribution of the material to be ground or a load condition of the mill system into consideration.
  • the particle size distribution is determined such that at least two partial regions with different grain sizes are distinguished. It is therefore provided at least one Operabe ⁇ rich for smaller and a second portion of larger grain sizes.
  • a further division into several subsections is possible in principle. This refines the gradation of the control attitude. The more subregions that are provided for the particle sizes for determining the particle size distribution, the more sensitive and accurate the optimization and control method reacts.
  • a model further comprises a data-driven model, preferably a neural network provided in the ⁇ .
  • the model parameters correspond in particular to the network weights and the measured values of the operating variable (s) to the training values.
  • the identification and adaptation of the Model1 parameters then takes place, for example, as part of the network training.
  • a system based on a neural network model requires only a few, perhaps even no metallic on the physika ⁇ conditions of the mill system based specifications.
  • FIG 1 shows an embodiment of a mill system with egg ⁇ ner adaptive model predictive control unit
  • FIG 2 is a block diagram showing the control unit of Figure 1 with an adaptive model of the mill system and an operating variable forecast as well as a derived therefrom optimization of model parameters.
  • FIG. 1 shows an embodiment of a mill system 1 is shown. It is an ore mill, which is designed as a ball mill or SAG mill. It is wired with a ven adapti ⁇ model predictive control unit 2 which controls the operation of the mill system. 1
  • the mill system 1 includes a central mill unit 3 with a drum 3a for milling the supplied guide ⁇ th ore material and having a drum 3a driving particular gearless motor 3b, a fed from the central mill unit 3 sump unit 4, and a hydro cyclone unit 5
  • the sump unit 4 and the hydrocyclone unit 5 are connected to each other by means of a hydrocyclone inflow line 6.
  • a separation takes place in finely ground and coarse-grained material.
  • the finely ground material passes into an outlet-side outflow line 7, which is connected to a non-illustrated the mill system 1 downstream Kompo ⁇ nent.
  • the coarse-grained material is returned to an inlet 9 of the central mill unit 3 via a return line 8.
  • the inlet 9 is also connected to conveyor belts 10, by means of which unground ore material from an ore supply 11 is supplied. Instead of the conveyor belts 10 may also be provided another feed unit. Furthermore, the input 9 is connected to a water inlet 12. Another water inlet 13 is provided on the sump unit 4.
  • the mill system 1 also contains a multiplicity of transducers which detect measured values for different operating variables B and supply them to the control unit 2 by means of measuring lines 14.
  • a weight meter 15 on the conveyor belts 10 a flow meter 16 on the water inlet 12, a power and torque meter 17 on the motor 3b, a
  • Weight meter 18 for detecting a load of the drum 3a a flow meter 19 at the water inlet 13, a level gauge 20 at the sump unit 4, a grain size meter 21, a flow meter 22 and a pressure gauge 23 are each provided on the hydrocyclone supply line 6, a density meter 24 on the return flow line i and a particle size meter 25 on the outflow line 7.
  • This list is to be understood as an example. In principle, further transducers can be provided. The respective measurements always take place online and in real time, so that always up-to-date measured values are available in the control unit 2.
  • the mill system 1 and a plurality of local controllers which are connected by means of control lines 26 to the Re ⁇ gelungsaku 2 has.
  • a weight regulator 27 on the conveyor belts 10 a flow regulator 28 on the water inlet 12, a (rotary) speed regulator 29 on the motor 3b, a flow regulator 30 on the water inlet 13 and on the hydrocyclone inflow line 6, a level controller 31 on the sump unit 4 and a density controller 32 at the remindyaklei ⁇ device 8 is provided.
  • transducers and local controllers are only to be understood as examples. In individual cases, other such components may be provided.
  • additional information about the nature of the supplied unmilled ore material can be obtained, for example, by means of a laser measurement or by means of video recording.
  • GE in the embodiment ⁇ Switzerlandss FIG measuring sensor 1 shown and local controller possible.
  • the actually of interest secondary operating variable is determined from the measured values by means of an evaluation algorithm, a current value is powered on sizes detectable primary Be ⁇ resorted to.
  • the evaluation software used for this purpose may also include a neural network.
  • an adjustment for the different process parameters of the mill system 1 is determined such that a good, constant throughput results with the lowest possible energy consumption and the highest possible product quality.
  • a high product quality means a certain , relatively small particle size of the milled material guided in the outlet-side outflow line 7.
  • control unit 2 shows a block diagram of the control unit 2 with its essential components. It comprises an adaptive overall model 33 of the mill system 1, a prediction unit 34, a comparison unit 35, a parameter iden- taimss- and adaptation unit 36 and an optimization unit 37. ⁇ approximately These components are in particular realized as software modules.
  • a measuring unit 38 is representative of the multiplicity of measuring transducers shown in FIG.
  • the measuring unit 38 can also be realized as a software module and thus as an integral part of the control unit 2. Otherwise, however, it is also possible that the measuring unit 38 is physically separate from the control unit 2.
  • control unit 2 In the following, the operation of the control unit 2 will be described in more detail.
  • the input quantities E can therefore refer to process parameters, to the design of the mill system 1, in particular to the central mill unit 3, or to the material.
  • control unit 2 On the output side, the control unit 2 provides output variables A, which are used to control the process sequence.
  • these are around the guide ⁇ sizes for the different local controller as shown in FIG 1.
  • the regulation ⁇ unit 2 on the output side manipulated variables available to the un- indirectly thus also act without the interposition of a local controller, to actuators ,
  • the adaptive model 33 describes the mill system is one in ⁇ ner entirety. In the exemplary embodiment, it is composed of a coupling of several submodels.
  • the sub-models be ⁇ write the central mill unit 3, the sump unit 4 and the hydrocyclones unit 5. Further sub-models for ande ⁇ re components of the mill system 1 can be added as needed.
  • the model 33 can be adapted to the currently prevailing process conditions by means of the model parameter P, wherein it is also determined in the parameter identification and adaptation unit 36 whether this adaptation takes place by means of all or only part of the model parameter P. If necessary, therefore, a relevant subset of the model parameters P is identified. The thus selected model parameters P are then particularly well suited for model adaptation.
  • the model 33 is based on the embodiment physi ⁇ 's specifications, which can be at least partially supplemented by empirical experience.
  • the model 33 and in particular ⁇ its adaptation by means of the model parameters P are calculated in real time. This contributes to the fact that no significant rule dead times arise.
  • a prediction value B v is determined in the prediction unit 34 for one or more operating variables (B).
  • a detected deviation F is the parameter identification and adaptation unit 36 to the He ⁇ averaging an improved rate for the model parameters P provided.
  • the thus adjusted model parameters P are then used to adapt the model 33.
  • the adapted model 33 is then used to determine the outputs A and also the predicted value B v for a coming phase of operation.
  • control unit 2 based on a forecast of the value that will take on the size of company B in the future, ⁇ ent drop-dead rule broadly.
  • the control unit 2 is therefore very stable and reacts very quickly to changed process conditions.
  • an SQP optimization method is used in which a predefinable target function is minimized while maintaining constraints and used to determine the improved parameter (partial) set for the model parameter P.
  • the objective function minimization and thus the parameter adaptation are carried out such that the adapted model 33 emulates the past behavior of the mill system 3 as well as possible.
  • Model 33 optimally describes reality in the past with this adapted parameter set.
  • the target function for example, is the deviation between measured and calculated particle size distribution.
  • Possible constraints are then produced in particular from a transition matrix indicating the coefficients of the probability with which a material particle, the len in aktuel ⁇ cycle in a certain partial area of the grain size distribution falls after the next cycle in a certain (different) part range of the grain size distribution falls.
  • Values that can take the coefficients of this transition matrix are subject to certain mathematical or physical constraints. It is possible to specify limits for the individual coefficients but also for combinations, for example sums of several coefficients.
  • the deviation between measured and calculated density in the reflux line 8 can also be defined as the objective function.
  • the optimization of adaptation SQP- ⁇ unit 36, a combination of multiple objective functions are used in the parameter identification and.
  • the recovered based on the past viewing adapted model 33 is used in a further process step to be ⁇ future scheme, ie for controlling the coming cycle. This takes place in the optimization unit 37. It is a second optimization, for which in turn, in particular, an SQP optimization method is used. Again, a target size is optimized in compliance with constraints. The aim is now particularly optimal He ⁇ mediation of the local regulator output variables A, so the correcting or command sizes, so for example, a superiors given particle size distribution at a certain point of the mill system 3, in particular at the output, is achieved. The target size can therefore be the product quality in this second optimization. As secondary conditions, the material requirements and the energy requirements come into question.
  • the consideration of secondary conditions also contributes to the set operating mode of the mill system 1 fulfilling several requirements in equal measure.
  • the mill speed, the supply of fresh water to the central mill unit 3 and into the sump unit 4 as well as the energy consumption can be optimized in this way, while at the same time maintaining the throughput and the product quality achieved at a predetermined level.

Landscapes

  • Engineering & Computer Science (AREA)
  • Food Science & Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Disintegrating Or Milling (AREA)
  • Feedback Control In General (AREA)

Abstract

L'invention concerne un procédé pour faire fonctionner un système de broyeur, qui calcule des paramètres de modélisation (P) d'un modèle (33) du système de broyeur. Sur la base du modèle (33) mis à jour avec les paramètres de modélisation (P) calculés, on détermine pour au moins une valeur fonctionnelle (B) du système de broyeur une valeur de prédiction (Bv) pour une phase de fonctionnement actuelle. Des valeurs de commande ou de guidage (A) du système de broyeur sont ajustées sur la base du modèle (33) mis à jour et sont utilisées pendant la phase de fonctionnement actuelle. Une valeur de mesure (BM) de la valeur fonctionnelle (B) est déterminée pendant la phase de fonctionnement actuelle. Un écart (F) entre la valeur de prédiction (Bv) et la valeur de mesure (BM) est déterminé. Les paramètres de modélisation (P) sont adaptés sur la base de l'écart (F) et sont utilisés conjointement avec le modèle (33) pour prédire la valeur fonctionnelle (B) ainsi que pour ajuster les valeurs de commande ou de guidage (A) pour un état fonctionnel ultérieur.
PCT/EP2007/052494 2006-04-26 2007-03-16 Procede pour faire fonctionner un systeme de broyeur WO2007124981A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102006019417.9 2006-04-26
DE200610019417 DE102006019417A1 (de) 2006-04-26 2006-04-26 Verfahren zum Betrieb eines Mühlensystems

Publications (1)

Publication Number Publication Date
WO2007124981A1 true WO2007124981A1 (fr) 2007-11-08

Family

ID=38137851

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2007/052494 WO2007124981A1 (fr) 2006-04-26 2007-03-16 Procede pour faire fonctionner un systeme de broyeur

Country Status (2)

Country Link
DE (1) DE102006019417A1 (fr)
WO (1) WO2007124981A1 (fr)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101244403B (zh) * 2008-03-17 2011-07-20 西安艾贝尔科技发展有限公司 一种磨矿分级过程优化控制方法
WO2012028384A1 (fr) 2010-09-02 2012-03-08 Siemens Aktiengesellschaft Procédé pour commander un système de broyeur comprenant au moins un broyeur, en particulier un broyeur à minerai ou à ciment
WO2012072315A3 (fr) * 2010-11-30 2012-07-26 Siemens Aktiengesellschaft Utilisation de mesures de température pour la mesure indirecte de variables de processus dans des installations de concassage
IT201800010468A1 (it) * 2018-11-20 2020-05-20 Aixprocess Gmbh Metodo e dispositivo per controllare un processo all'interno di un sistema, in particolare un processo di combustione all'interno di una centrale elettrica
EP4268963A1 (fr) * 2022-04-26 2023-11-01 Siemens Aktiengesellschaft Procédé et dispositif de fabrication à l'échelle industrielle d'une suspension pour une batterie
GB2619744A (en) * 2022-06-15 2023-12-20 Intellisense Io Ltd System and method for continuous optimization of mineral processing operations

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102008040095A1 (de) * 2008-07-02 2010-01-07 Bühler AG Regelsystem für Getreide-Verarbeitungsanlage
DE102008047418A1 (de) * 2008-09-16 2010-04-08 Siemens Aktiengesellschaft Online-Systemidentifikation und Online-Systemsteuerung
DE102010012620A1 (de) 2010-03-24 2011-09-29 Siemens Aktiengesellschaft Verfahren zum Betrieb einer Mühle
EP3456417A1 (fr) 2017-09-18 2019-03-20 ABB Schweiz AG Procédé de fonctionnement d'un circuit de broyage et circuit de broyage respectif
CN112317110A (zh) * 2020-09-27 2021-02-05 鞍钢集团矿业有限公司 基于深度学习的磨矿粒度预测系统及方法

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050154477A1 (en) * 1996-05-06 2005-07-14 Martin Gregory D. Kiln control and upset recovery using a model predictive control in series with forward chaining

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19629703A1 (de) * 1996-07-24 1998-01-29 Schenck Process Gmbh Verfahren zur Steuerung eines Mühlensystems
DE19922449B4 (de) * 1999-05-11 2010-01-21 Bartsch, Thomas, Dr.-Ing. Verfahren zur Durchsatzregelung einer Mahlanlage
DE19931181B4 (de) * 1999-07-07 2004-12-09 Bühler AG Verfahren und Vorrichtung zur Optimierung der Prozessführung sowie Prozessüberwachung in einer Anlage zur Schokoladeherstellung

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050154477A1 (en) * 1996-05-06 2005-07-14 Martin Gregory D. Kiln control and upset recovery using a model predictive control in series with forward chaining

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
K.SANKAR, P. KALE, R.A. SOMANI, R. SOMANI: "Online-Steuerung und Optimierung des Mahlvorgangs in Kugelmühlen", ZKG INTERNATIONAL, vol. 55, no. 11/2002, 2002, pages 92 - 99, XP002438577 *
M. RAMASAMY, S.S. NARAYANAN, CH.D.P. RAO: "Controll of ball mill grinding circuit using model predictive control scheme", JOURNAL PF PROCESS CONTROL, vol. 15, no. 3, April 2005 (2005-04-01), pages 273 - 283, XP002438578 *

Cited By (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101244403B (zh) * 2008-03-17 2011-07-20 西安艾贝尔科技发展有限公司 一种磨矿分级过程优化控制方法
WO2012028384A1 (fr) 2010-09-02 2012-03-08 Siemens Aktiengesellschaft Procédé pour commander un système de broyeur comprenant au moins un broyeur, en particulier un broyeur à minerai ou à ciment
CN103068489A (zh) * 2010-09-02 2013-04-24 西门子公司 对具有至少一台磨机尤其矿磨机或者水泥磨机的磨机系统进行控制的方法
WO2012072315A3 (fr) * 2010-11-30 2012-07-26 Siemens Aktiengesellschaft Utilisation de mesures de température pour la mesure indirecte de variables de processus dans des installations de concassage
AU2011335385B2 (en) * 2010-11-30 2014-10-30 Siemens Aktiengesellschaft Method for the operation of a mill at continuous input and output mass flows
DE102010062204B4 (de) * 2010-11-30 2015-06-18 Siemens Aktiengesellschaft Nutzung von Temperaturmessungen zur indirekten Messung von Prozessvariablen in Mahlanlagen
US9486809B2 (en) 2010-11-30 2016-11-08 Siemens Aktiengesellschaft Use of temperature measurements for indirect measurement of process variables in milling systems
WO2020104255A1 (fr) * 2018-11-20 2020-05-28 Aixprocess Gmbh Procédé et dispositif de régulation d'un processus à l'intérieur d'un système, en particulier d'un processus de combustion à l'intérieur d'une centrale électrique
IT201800010468A1 (it) * 2018-11-20 2020-05-20 Aixprocess Gmbh Metodo e dispositivo per controllare un processo all'interno di un sistema, in particolare un processo di combustione all'interno di una centrale elettrica
CN113167473A (zh) * 2018-11-20 2021-07-23 Aix制程有限公司 用于调控系统内过程、特别是发电站内燃烧过程的方法和装置
CN113167473B (zh) * 2018-11-20 2024-05-28 Aix制程有限公司 一种对系统内燃烧过程进行调控的方法及装置
US12031717B2 (en) 2018-11-20 2024-07-09 Aixprocess Gmbh Method and device for regulating a process within a system, in particular a combustion process in a power station
EP4268963A1 (fr) * 2022-04-26 2023-11-01 Siemens Aktiengesellschaft Procédé et dispositif de fabrication à l'échelle industrielle d'une suspension pour une batterie
GB2619744A (en) * 2022-06-15 2023-12-20 Intellisense Io Ltd System and method for continuous optimization of mineral processing operations
WO2023242752A1 (fr) * 2022-06-15 2023-12-21 Intellisense.Io Système et procédé d'optimisation continue d'opérations de traitement de minéraux
GB2619744B (en) * 2022-06-15 2024-09-18 Intellisense Io Ltd System and method for continuous optimization of mineral processing operations

Also Published As

Publication number Publication date
DE102006019417A1 (de) 2007-11-15

Similar Documents

Publication Publication Date Title
WO2007124981A1 (fr) Procede pour faire fonctionner un systeme de broyeur
DE102016011532B4 (de) Maschinenlernvorrichtung und Maschinenlernverfahren zum Optimieren der Häufigkeit einer Werkzeugkorrektur einer Werkzeugmaschine und Werkzeugmaschine mit der Maschinenlernvorrichtung
DE102016117773B4 (de) Werkzeugmaschine, die eine optimale Beschleunigung/Verlangsamung erzeugt, Simulationsvorrichtung und Maschinenlernvorrichtung
DE102016011402A1 (de) Maschinelles Lernverfahren und maschinelle Lernvorrichtung zum Einlernen von Betriebsbefehlen für einen Elektromotor und Werkzeugmaschine mit maschineller Lernvorrichtung
DE102017130429A1 (de) Numerische Steuerung und maschinelle Lernvorrichtung
DE102018004048B4 (de) Steuerung und Maschinenlernvorrichtung
DE102017011544A1 (de) Steuerung und maschinelle Lernvorrichtung
DE102018108778B4 (de) Beschleunigungs- und verzögerungssteuereinheit, maschinenlernvorrichtung und maschinenlernverfahren
DE102017011896A1 (de) Vorrichtung zum Schätzen einer Werkzeuglebenszeit
WO2016038705A1 (fr) Dispositif de simulation de laminage
DE102019003601A1 (de) Vorrichtung zur Lebensdauervorhersage und Vorrichtung für maschinelles Lernen
DE102018004330B4 (de) Steuerung und maschinelle Lernvorrichtung
DE102018010054A1 (de) Steuerung und maschinelle Lernvorrichtung
EP2582458A1 (fr) Procédé pour commander un système de broyeur comprenant au moins un broyeur, en particulier un broyeur à minerai ou à ciment
DE4325187A1 (de) Verfahren zur Steuerung einer Walzenmühle sowie eine Steuerung zur Ausführung des Verfahrens
DE102016009106A1 (de) Mit Steuerung ausgerüstete Bearbeitungsvorrichtung mit Bearbeitungszeit- Messfunktion und Messfunktion auf der Maschine
DE102018000342A1 (de) Numerische steuerung und maschinelle lernvorrichtung
DE102019102250A1 (de) Vorhersagen der Abnutzung des Polierwerkzeugs, Maschinenlernvorrichtung und System
DE102018126429A1 (de) Bearbeitungsbedingungsanpassungsvorrichtung und Maschinenlernvorrichtung
DE112011101443T5 (de) Servoregler
DE102019001783A1 (de) Steuerung, maschinelle lernvorrichtung und system
DE102019001044A1 (de) Steuervorrichtung und maschinelle lernvorrichtung
DE102019106939A1 (de) Bearbeitungszustandsanpassungsvorrichtung und maschinenlernvorrichtung
DE102019001177B4 (de) Steuergerät, maschinelle Lernvorrichtung und System
EP1055180B1 (fr) Procede et dispositif de conception d'un systeme technique

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 07712536

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 07712536

Country of ref document: EP

Kind code of ref document: A1