EP3914974A1 - Procédé et dispositif pour déterminer ou prédire une position d'une rupture de bande, programme informatique et installation industrielle - Google Patents

Procédé et dispositif pour déterminer ou prédire une position d'une rupture de bande, programme informatique et installation industrielle

Info

Publication number
EP3914974A1
EP3914974A1 EP20710774.9A EP20710774A EP3914974A1 EP 3914974 A1 EP3914974 A1 EP 3914974A1 EP 20710774 A EP20710774 A EP 20710774A EP 3914974 A1 EP3914974 A1 EP 3914974A1
Authority
EP
European Patent Office
Prior art keywords
parameter
web
deviation
web break
determined
Prior art date
Legal status (The legal status 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 status listed.)
Pending
Application number
EP20710774.9A
Other languages
German (de)
English (en)
Inventor
Konrad Moritz Grießinger
Sarah Osterburg
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Siemens Energy Global GmbH and Co KG
Original Assignee
Siemens AG
Siemens Energy Global GmbH and Co KG
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 AG, Siemens Energy Global GmbH and Co KG filed Critical Siemens AG
Publication of EP3914974A1 publication Critical patent/EP3914974A1/fr
Pending legal-status Critical Current

Links

Classifications

    • 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
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
    • G05B19/406—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by monitoring or safety
    • 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
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
    • B65H26/00—Warning or safety devices, e.g. automatic fault detectors, stop-motions, for web-advancing mechanisms
    • B65H26/02—Warning or safety devices, e.g. automatic fault detectors, stop-motions, for web-advancing mechanisms responsive to presence of irregularities in running webs
    • B65H26/025—Warning or safety devices, e.g. automatic fault detectors, stop-motions, for web-advancing mechanisms responsive to presence of irregularities in running webs responsive to web breakage
    • D—TEXTILES; PAPER
    • D21—PAPER-MAKING; PRODUCTION OF CELLULOSE
    • D21F—PAPER-MAKING MACHINES; METHODS OF PRODUCING PAPER THEREON
    • D21F7/00—Other details of machines for making continuous webs of paper
    • D21F7/04—Paper-break control devices
    • 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
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
    • G05B23/0267—Fault communication, e.g. human machine interface [HMI]
    • G05B23/0272—Presentation of monitored results, e.g. selection of status reports to be displayed; Filtering information to the user

Definitions

  • the invention relates to a method and a device, in particular for determining and predicting a position of a web break that has occurred or is threatened in a fiber-containing web.
  • the invention also relates to a computer program product and an industrial plant.
  • Industrial plants for the production and / or processing of a fiber-containing web are, for example, paper machines or printing machines.
  • a tear in the fiber-containing material web a so-called web tear.
  • the object of the invention is to avoid or at least shorten downtimes in an industrial plant.
  • the method is used in particular to determine and predict a position of a completed or threatened web breakage of a fibrous web in an industrial plant, the industrial plant having a plurality of rollers, the rollers being provided for transporting the fibrous web in the industrial plant , wherein the method comprises at least the following first steps:
  • the time course of the parameter is checked for a first deviation.
  • the parameters are advantageously examined for a difference from the predefinable distribution.
  • the respective parameter is advantageously checked periodically for a difference with respect to the predefinable distribution.
  • the parameters are advantageously determined by a sensor or an encoder.
  • the parameters can also be provided by a control device for the respective motor.
  • the parameters are advantageously stored in a data memory in the form of a time series.
  • the data memory can be designed locally or be assigned to a decentralized computing unit, for example a cloud.
  • parameters are determined which represent a (rotary) movement of a roller.
  • one parameter is the speed of rotation of the respective roller, the torque which the motor has to apply to rotate the roller and / or a position of the respective roller, insofar as the position of the roller can be displaced.
  • the parameters are advantageously stored as time series.
  • the predeterminable distribution can be a Gaussian distribution or some other statistical normal distribution.
  • the parameters are each advantageously stored with a time stamp.
  • the parameters can be compared with one another as time series.
  • the respective parameter such as a speed or a torque of a motor
  • Noise means that the value of the respective parameter fluctuates as a function of time.
  • the fluctuation is such that the values fluctuate around a mean value in accordance with a normal distribution, in particular a Gaussian distribution. A check is therefore carried out to determine whether the fluctuation of the respective parameter is within the scope of the distribution.
  • All parameters provided are advantageously checked for a predefinable distribution.
  • the test can be used to determine whether the fluctuation occurs due to an imminent or occurred web break or whether it is a "normal" fluctuation within the scope of a predeterminable distribution. If the parameter, in particular the time profile of the parameter, deviates from the predefinable distribution, the parameter is further searched for a first deviation.
  • the parameter the course of which over time does not behave in accordance with a predeterminable distribution, can be examined for the second deviation.
  • a second deviation is, for example, a peak in the time course of the respective parameter.
  • the time course of the respective parameter can be examined with regard to a second deviation of the parameter from its time mean value.
  • a first deviation can be a changed difference between two parameters.
  • the role that is assigned to the respective parameter is advantageously assigned.
  • the position of the web break in the industrial system can be determined quickly and reliably via the position of the respective determined role.
  • the method advantageously runs during the operation of the industrial plant and examines the determined parameters at least irregularly. So the first deviation can be parameters can be determined quickly and reliably.
  • the first discrepancy he recognized advantageously forms the basis for recognizing an impending web break in the industrial facility.
  • the method comprises the following second steps:
  • the second deviation is recognized and / or the second deviation is assigned to at least one role for the web breakage that has occurred or is imminent in the fibrous web.
  • First steps and second steps to determine a position of a web break that has taken place or a threatened web break are advantageous.
  • the respective parameter is advantageously examined for a first deviation, the respective parameter not necessarily having been found to be significant for determining a position of a web break through a comparison with a predeterminable distribution.
  • a second deviation can also be a deviation of the respective parameter beyond a usual fluctuation of the respective parameter.
  • a second deviation is, for example, a deviation of the respective parameter from a time average of the respective particular parameter beyond a small fluctuation range of the parameter.
  • a criterion for a first and second deviation can be that the respective parameter shows the deviation from the temporal mean value of the respective parameter for at least a period of time. Such a period of time preferably lasts from 1 millisecond to 1 second.
  • a limit value is used to decide whether a parameter deviates from a time average.
  • the limit value can be 1% to 10% of the respective parameter.
  • a role of the industrial plant is usually assigned to a parameter. Since the position of the respective role in the industrial plant is generally known, an assignment of an imminent or already existing web tear of the fibrous web can be done quickly and safely.
  • the second deviation is advantageously recognized with the aid of a learning algorithm.
  • the first deviation can preferably also be recognized with the aid of a learning algorithm.
  • the adaptive algorithm can preferably provide the period of time which a deviation lasts in order not to be classified as random deviation / noise.
  • the predefinable distribution can be adapted with the aid of the adaptive algorithm.
  • the adaptive algorithm is advantageously learned with the aid of the parameters provided in each case, the deviation determined in each case and with the aid of information from web breaks that have occurred.
  • a neural network a support vector machine or some other algorithm based on artificial intelligence (AI), in particular a random forest tree, is suitable as a learning algorithm. Both monitored and unsupervised adaptive algorithms can advantageously be provided.
  • the self-learning algorithm is preferably designed to locate abnormalities in the respective parameters that differ from normal operation of the industrial plant.
  • Time series of the respective parameters are advantageously provided to the self-learning algorithm.
  • the self-learning algorithm uses the time series to determine first deviations and / or second deviations.
  • the respective behavior of the respective role is assigned to the respective deviations in the parameters.
  • such a method can operate largely independently, so that an operator of the industrial plant can be relieved.
  • the first deviation of the respective parameter is determined with the first steps and the second deviation with the aid of the second steps, with the aid of the first deviation a first position of the web break that has occurred or is threatened and with With the help of the second deviation, a second position of the threatened or completed web break is determined, with the respective posi tion being displayed to a user if the first position and the second position match.
  • first steps and second method steps are advantageously carried out using the same parameters.
  • first steps and the second steps each determine different roles or a different position of a web break that has occurred or is imminent, the actual position of the web break can be made available to the self-learning algorithm.
  • the provision is made with the aim of improving the learning of the self-learning algorithm.
  • this position can be displayed to the operator of the industrial plant.
  • the position of the web break is determined, preferably with the aid of visual monitoring, the determined position of the web break being performed by the adaptive algorithm is provided so that the adaptive algorithm is improved based on the position of the web break.
  • Visual monitoring can take place with the help of one or more camera modules or other sensors which are directed at the fiber-containing material web.
  • visual monitoring by an operator can take place.
  • the position of the web break determined by the visual monitoring is advantageously provided to the self-learning algorithm in order to improve the determination of the position of an imminent or occurred web break.
  • the advantageous level of a limit value for a first and / or second deviation can be improved.
  • the adaptive algorithm is provided with the parameters, the determined position of the web break and / or the respectively determined first and / or second deviation.
  • the adaptive algorithm can be learned quickly and efficiently by comparing the respective parameters and the information on the respective web break with the parameters.
  • An efficiently learned algorithm enables the position of the impending or current web break to be determined quickly and reliably.
  • the first steps and / or the second steps run repeatedly, in particular periodically, to determine an impending web break.
  • the determined and provided parameters are advantageously continuously examined with the aid of the first and / or second steps.
  • all parameters are repeatedly examined for the predefinable distribution.
  • the parameters are advantageously examined with the aid of the first and second steps.
  • the first and / or second steps are preferably carried out periodically as long as the industrial plant is in operation.
  • the subsequent analysis of the parameters can determine the exact position of the web break.
  • the first steps and / or the second steps are carried out after the web tear has taken place to determine the position of the web tear that has taken place.
  • a separate examination of the parameters is carried out in the event of a web break in a time range before the web break.
  • the separate examination takes place with the first and / or second steps.
  • the self-learning algorithm can advantageously be increased in its efficiency with a precise examination after a web break has occurred.
  • the respectively stored parameter is examined in a time range for a first deviation, the time range being arranged immediately before the web break.
  • the time range can be 1 to 10 minutes.
  • the parameters are advantageously examined in a time range, the end of the time range advantageously coinciding with the web break.
  • the examination is preferably carried out with first steps and / or with second steps.
  • the deviation of the respective parameter is determined on the basis of a difference of the respective parameter from a respective time mean value of the respective parameter.
  • a time average of the respective parameter can be determined by integrating the parameter over the operating time and then dividing it by the operating time.
  • a parameter such as the speed of a roller is largely constant during the operation of the industrial system.
  • a deviation from the constant value which can be determined by its mean value over time, therefore indicates an impending web break.
  • a deviation can also be due to a change in the type of paper or a change in the operating mode of the industrial plant. This should advantageously be taken into account as part of the procedure described here
  • a plurality of parameters increase together. For example, adjacent rollers can jointly assume a higher speed without increasing the risk of a web break between the rollers. Such a problem can be avoided by considering the web tension as a parameter. By considering the deviation of the respective parameter from its mean value over time, a malfunction of a roller or of an associated drive can be determined quickly and easily.
  • the respective parameter is assigned to a plurality of roles, the respective parameter mapping the movement of adjacent roles.
  • Such a parameter can be a web tension of the fibrous web between two adjacent rolls.
  • the web tension can be proportional to a difference in the speeds of the respective adjacent rollers.
  • the learning algorithm is learned on the basis of a comparison of the respective parameter in a time range before a web break occurred with the respective parameter in a time range during normal operation of the industrial plant.
  • the distribution and / or the time average of the respective parameter is advantageously determined during normal operation of the industrial plant.
  • the time course of the respective parameter in the time range before the web tear can be compared with the time average.
  • the respective parameter is:
  • rollers which are each adjacent in the context of the transport of the fiber-containing web.
  • the web tension can be determined from the difference between the speeds of the respective rollers, between which the web tension is to be determined.
  • the web tension is additionally determined with the aid of a tension measuring cell, the tension measuring cell being designed as a sensor for the web tension of the fiber-containing material web.
  • the second deviation is only determined after the web break has occurred, the first deviation being determined repeatedly, preferably repeated periodically.
  • a first deviation is preferably used to determine short-term deviations of the respective parameter from its a time average.
  • a first deviation does not necessarily lead to a web break.
  • a first deviation of a parameter from the time average can increase the probability of a web break.
  • the first steps to determine the first discrepancy are thus carried out during the operation of the industrial plant.
  • the second deviation is advantageously determined in order to predict an impending web break.
  • the determination of the second deviation is advantageously used to determine a longer deviation of the respective parameter from its mean value over time.
  • Second deviations are often an indicator of a web break.
  • the role that is assigned to the parameter can be determined using the parameter. Based on the position of the corresponding roll in the industrial plant, the position of the web break can easily be determined.
  • At least one first role is assigned to a first group, with at least one second role being assigned to a second group,
  • Rolls of a drying unit are preferably combined to form a group.
  • the rollers in the respective group often have essentially the same speed or an essentially identical torque.
  • web breaks in the fiber-containing web occur at points which are outside the respective groups of rolls.
  • each group advantageously represents a drying section, the fiber-containing material web passing through a plurality of such drying sections until a winding device winds the fiber-containing material web onto a roll.
  • the roles are advantageously combined as a group, where in a first run of the first steps and / or the second steps the group of roles is treated as a single role, i.e. a parameter is assigned to the respective group.
  • the device is used in particular to determine a web break he has followed or threatened with a fiber-containing Wa ren web in an industrial plant.
  • the device includes:
  • the device is assigned a computing unit, where the computing unit for determining the position of an impending or occurred web break can be carried out with the aid of a method according to a method described above.
  • the device is advantageously designed as a control device for an industrial plant, in particular for part of a paper machine.
  • a detection means for a parameter is, for example, a sensor for determining a torque, a transmitter for determining a speed, a sensor for determining a web tension of the fiber-containing material web, in particular designed as a tensile load cell.
  • a detection means can be an interface for detecting a speed, the interface being assigned to a power supply of the respective motor.
  • the interface can be a sensor for a voltage or a current that is made available to the respective motor.
  • the display can be designed as a screen, the screen preferably being assigned to a control station.
  • the display is advantageously connected to the computing unit, the computing unit being designed to carry out the first steps and / or the second steps.
  • the computing unit can be designed as an edge device or as a decentralized server.
  • An image of the industrial plant is advantageously displayed, the roles and their positions being marked. By identifying the respective role or the respective roles in or between which the web break has occurred or is threatened, the position of the success th or threatened web break can be determined at a glance.
  • the computer program product is provided to run on a computing unit, wherein the computer program product is designed to run on a computing unit to carry out the above existing method.
  • the computer program product can advantageously be transferred to a working memory of a computing unit and can be executed from there with the aid of at least one CPU.
  • the computer program product can advantageously be stored on a data storage medium such as a USB stick, a hard disk or a CD-ROM / DVD-ROM and can be called up or installed from there on the processing unit.
  • the computer program advantageously has at least one input interface for the respective parameter.
  • the computer program product also advantageously comprises output interfaces for providing the position of the threatened or occurred web break.
  • the computer program advantageously includes an interface for connection to a data memory for storing the parameters and / or for reading in the respective parameters.
  • the parameters are advantageously stored in a database.
  • the industrial plant is preferably designed as a dry part of a paper machine or a paper machine.
  • the industrial plant advantageously comprises a device as described above.
  • 1 shows an exemplary industrial plant 100.
  • the plant comprises rollers 3, 3 ', the rollers 3, 3' being designed to transport a fiber-containing web 1, in particular a paper web.
  • a motor 5 is assigned to each roller 3, 3 '.
  • the motor 5 is used for Drehbewe movement of the respective associated roller 3, 3 '.
  • sensors 9 are used be.
  • the detection means can be assigned to a roller 3, 3 ′ or a motor 5.
  • the industrial system shown here comprises first roles 3, the first roles being summarized in a first group 4.
  • the industrial installation 100 shown here also comprises second rollers 3 ′, the second rollers 3 ′ being assigned to a second group 4.
  • the first roles advantageously have essentially the same values as parameters x1, x2, x3. Accordingly, there is a web tear BA of the fiber-containing web 1 between each be adjacent first rollers 3 and second rollers 3 '.
  • the motors 5 are each connected to a power supply 8.
  • the power supply 8 is advantageously designed as a frequency converter.
  • the power supply 8 is coupled to a control device 7.
  • the control device is used to control and / or regulate the torques D, the speed w of the respective roller 3,3 '.
  • the control device 7 is assigned a computing unit RE.
  • the computing unit includes an interface for receiving the parameters xl, x2, x3.
  • the speeds w of the respective roller 3, 3 ′ and / or its torques D are advantageously stored in the arithmetic unit RE using the parameters x1, x2, x3.
  • the computing unit RE is assigned a further computing unit.
  • the other arithmetic unit is preferably designed as a cloud and is used to collect the parameters xl, x2, x3 stored as time series A, B, C.
  • the adaptive algorithm A is preferably installed on the computing unit RE.
  • a further arithmetic unit is preferably used to teach in the adaptive algorithm Alg.
  • Parameters xl, x2, x3 can be torques D, speeds w and / or the web tension BS detected by means of sensors 9.
  • the torque D and / or the speed w is advantageously provided to the power supply for the respective motors.
  • Parameters x1, x2, x3 can also be control variables and / or control variables that are provided by the control device 7, for example.
  • the exemplary method is used to determine the position of a web tear BA of a fiber-containing web 1.
  • a first step V101 the parameters xl, x2, x3, in particular the speeds w and the torques D of the respective roller 3, 3 'are recorded.
  • the web tension BS is optionally determined on the basis of the rotational speed w of two adjacent rollers 3, 3 '.
  • the web tension BS or some other parameter Xl, x2, x3 is optionally stored as time series A, B, C.
  • a first deviation D1 and / or a second deviation D2 is determined.
  • the first deviation D1 is determined with the aid of first steps (VI 02, V702).
  • the second deviation D2 is determined with the aid of second steps (VI 03, V603).
  • First steps (VI 02, V702) and second steps (VI 03, V603) advantageously run together in order to determine the position of a web break that has occurred or is threatened.
  • the first and second discrepancies D1, D2 are, for example, a difference between a value of a web tension BS and an averaged web tension ⁇ BS>.
  • the respective deviation D1, D2 can also be a difference between two speeds w, in particular a speed w of a first roller 3 from the speed w of a second roller 3 '.
  • the deviation D can be a difference in torques D of a first roller 3 and a second roller 3 '.
  • the position of the web break BA is advantageously determined on the basis of the at least one deviation D1, D2.
  • the position of the web break BA is preferably displayed to a user with the help of a display.
  • the display is advantageously designed to be mobile, for example as a tablet or handheld device.
  • the further exemplary method is preferably used to predict the position of a web break BA that has occurred or is imminent.
  • a first step V102 the parameters xl, x2, x3 are recorded by the industrial installation 100.
  • the parameters xl, x2, x3 are advantageously detected by sensors 9. With the aid of the parameters xl, x2, x3, the movement of the respective roller 3, 3 'in the industrial installation 100 is described in each case.
  • the parameters xl, x2, x3 are advantageously stored in the form of time series A, B, C. They are advantageously stored in a database that is stored on a further computing unit, in particular a cloud.
  • a second step V202 it is checked whether a parameter xl, x2, x3 has changed at all. If the parameter xl, x2, x3 has not changed, a new parameter is ter xl, x2, x3 selected and checked for a change. This is in particular a test of whether the respective parameter xl, x2, x3 corresponds to the predefinable distribution Vert.
  • the parameter xl, x2, x3 can be examined in such a way whether the respective parameter xl, x2, x3 corresponds to a predeterminable distribution, for example a Gaussian normal distribution. In this way, natural fluctuations in the respective parameters xl, x2, x3 can be taken into account.
  • a fourth step V402 those parameters x1, x2, x3 that have changed over time t and / or do not correspond to the predefinable distribution are examined for a first discrepancy D1 and the first discrepancy D1 is determined and stored.
  • a fifth step V502 it is checked whether the respective first deviations D1 are similar for a plurality of roles 3, 3 'in a group 4, 4'.
  • the parameters xl, x2, x3 of a first roll 3 are advantageously compared with the parameters xl, x2, x3 of a second roll 3 '.
  • a deviation D1 can be determined in a plurality of first rollers 3. In the event of a deviation D1 in the case of only one first roller 3 or a single second roller 3 ', a measurement error can generally be assumed.
  • the first deviations D1 are determined with the aid of an adaptive algorithm Alg asked whether a web break BA of the fibrous web 1 threatens or has already occurred. On the basis of an assignment of the first deviation D1 to a roller 3, 3 'of the area between two adjacent groups 4, 4' it can be determined where a web break BA will occur or has occurred.
  • a warning signal is advantageously given.
  • the expected position of the web break BA is also advantageously shared with the receiver of the warning signal.
  • the user advantageously provides the information as to whether the displayed position of the web break BA was correct and / or whether a web break BA has actually occurred.
  • the learning algorithm Alg is advantageously learned.
  • the learning algorithm Alg is learned on the basis of a comparison of the parameters x1, x2, x3 with the web breaks BA that have occurred.
  • the recognition of the web break BA of the adaptive algorithm Alg can be improved.
  • the time series A, B, C of the respective parameters x1, x2, x3 are made available to the adaptive algorithm.
  • the adaptive algorithm can be learned in an improved manner and patterns or peaks can be recognized more easily and with greater reliability.
  • a start signal occurs in a first step V103.
  • the start signal can be the occurrence of a web break BA. Age- natively or additionally, the start signal can represent a regular repeating time signal.
  • a second step V203 the time series A, B, C and thus the parameters x1, x2, x3 are read in.
  • the time series A, B, C are usually stored parameters xl, x2, x3 as a function of time t.
  • a third step V303 the parameters xl, x2, x3 provided are used to determine the respective web tensions BS of the fiber-containing material web 1.
  • the web tension BS is in each case a region of the fiber-containing material web 1 between two adjacent rollers 3, 3 'and / or an area between two groups 4,4 'of roles 3,3' zugeord net.
  • the areas of the fibrous web 1 are determined in which the web tension BS is greatly reduced.
  • Points in time are optionally determined at which at least one parameter xl, x2, x3 is subject to a significant change.
  • a fourth step V403 it is determined whether there are time ranges dt in which a plurality of parameters
  • xl, x2, x3 show a corresponding behavior pattern.
  • One behavior is in particular the occurrence of a second deviation D2, the second deviation D2 being a deviation of the respective parameter xl, x2, x3 from the respective temporal mean value ⁇ xl>, ⁇ x2>, ⁇ x3> of the parameter xl, x2, x3 is.
  • the web tension BS between two rollers 3, 3 ' serves as a well-suited parameter xl, x2, x3.
  • a web break BA of the fibrous web 1 Based on the behavior pattern it can be determined whether and where a web break BA of the fibrous web 1 has occurred and threatens to occur.
  • a fifth step V503 the position of the web break BA that has occurred or the web break BA of the fiber-containing web 1 is indicated to a user.
  • a learnable algorithm Alg is taught on the basis of the determined or expected position of the web break BA. Before geous a user gives information about whether and / or at what position in the industrial installation 100 the web tear BA has occurred.
  • a first time series A shows a course of a parameter xl, x2, x3 as a function of time t.
  • a brief increase in the parameter xl, x2, x3 is visible.
  • the parameter xl, x2, x3 does not exceed the predefinable limit value GR at any further time range dt.
  • a predefinable distribution Vert of the parameters x1, x2, x3 is assigned for the respective time series A, B, C. Such a deviation can be a first deviation D1.
  • a predefinable distribution Vert is also shown, according to which the noise of the respective parameter x1, x2, x3 can be written.
  • the second time series B shows a behavior corresponding to a web break BA.
  • a linear drift of one parameter xl, x2, x3 is characteristic of the path break BA.
  • a drift can also be non-linear.
  • the drift occurs in the time range dt above the limit value GR.
  • the second deviation D2 increases during the drift.
  • Such a parameter xl, x2, x3 can be the Web tension BS of the fiber-containing web 1 between two groups 4, 4 '.
  • This drop is an identifier for a web break BA and this behavior is advantageously recognized by an adaptive algorithm Alg and communicated to the user.
  • the third time series C shows a course of a parameter xl, x2, x3 over time t. Except for minor deviations, the respective parameters xl, x2, x3 correspond to the respective mean values ⁇ xl>, ⁇ x2>, ⁇ x3>.
  • the invention relates to a method and a device, in particular for predicting a position of an existing or impending web break BA of a fiber-containing web 1. Furthermore, the invention relates to a computer program product and an industrial plant 100, in particular a paper machine.
  • the method comprises the acquisition of parameters x1, x2, x3, in particular speeds w of rollers 3, 3 'for transporting the fiber-containing web 1 or a web tension BS of the same.
  • the parameters xl, x2, x3 are advantageously stored in the form of time series A, B, C.
  • a self-learning algorithm Alg serves to recognize the threatening web break BA and to determine the position of the threatening and / or occurred web break BA.
  • the basis for the detection or the determination is a deviation D of the respective parameter xl, x2, x3, for example from a time mean value ⁇ xl>, ⁇ x2>, ⁇ x3> of the respective parameter xl, x2, x3.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Human Computer Interaction (AREA)
  • Manufacturing & Machinery (AREA)
  • Controlling Rewinding, Feeding, Winding, Or Abnormalities Of Webs (AREA)
  • Nonwoven Fabrics (AREA)

Abstract

L'invention concerne un procédé et un dispositif, destinés en particulier à prédire une position d'une rupture de bande (BA) intervenue ou imminente d'une bande de matière (1) contenant des fibres. L'invention concerne également un produit-programme informatique et une installation industrielle (100), en particulier une machine à papier. Le procédé comprend la détection de paramètres (x1, x2, x3), en particulier de vitesses de rotation (w) de rouleaux pour transporter la bande de matière (1) contenant des fibres ou une tension de bande (BS) de ladite bande de matière (1). Les paramètres (x1, x2, x3) sont enregistrés avantageusement sous forme de séries chronologiques (A, B, C). Un algorithme (Alg) à auto-apprentissage sert à identifier la rupture de bande (BA) imminente ainsi qu'à déterminer la position de la rupture de bande (BA) imminente et/ou intervenue. Un écart (Δ) de chaque paramètre (x1,x2,x3), par exemple d'une moyenne temporelle (<x1>,<x2>,<x3>) de chaque paramètre (x1,x2,x3) sert de base pour déceler ou déterminer la rupture de bande.
EP20710774.9A 2019-02-25 2020-02-24 Procédé et dispositif pour déterminer ou prédire une position d'une rupture de bande, programme informatique et installation industrielle Pending EP3914974A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP19159055.3A EP3699701A1 (fr) 2019-02-25 2019-02-25 Procédé et dispositif de détermination ou de prédiction d'une position d'une déchirure de la bande, programme informatique et installation industrielle
PCT/EP2020/054783 WO2020173880A1 (fr) 2019-02-25 2020-02-24 Procédé et dispositif pour déterminer ou prédire une position d'une rupture de bande, programme informatique et installation industrielle

Publications (1)

Publication Number Publication Date
EP3914974A1 true EP3914974A1 (fr) 2021-12-01

Family

ID=65628561

Family Applications (2)

Application Number Title Priority Date Filing Date
EP19159055.3A Withdrawn EP3699701A1 (fr) 2019-02-25 2019-02-25 Procédé et dispositif de détermination ou de prédiction d'une position d'une déchirure de la bande, programme informatique et installation industrielle
EP20710774.9A Pending EP3914974A1 (fr) 2019-02-25 2020-02-24 Procédé et dispositif pour déterminer ou prédire une position d'une rupture de bande, programme informatique et installation industrielle

Family Applications Before (1)

Application Number Title Priority Date Filing Date
EP19159055.3A Withdrawn EP3699701A1 (fr) 2019-02-25 2019-02-25 Procédé et dispositif de détermination ou de prédiction d'une position d'une déchirure de la bande, programme informatique et installation industrielle

Country Status (4)

Country Link
US (1) US20220147033A1 (fr)
EP (2) EP3699701A1 (fr)
CN (1) CN113490893B (fr)
WO (1) WO2020173880A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102021123077A1 (de) 2021-09-07 2023-03-09 Voith Patent Gmbh Verfahren und Vorrichtung zur Verbesserung des Trocknungsprozesses in einer Papiermaschine

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19827190A1 (de) * 1998-06-18 1999-12-23 Koenig & Bauer Ag Verfahren und Vorrichtung zur Überwachung einer Materialbahn
DE10318428A1 (de) * 2003-04-23 2004-11-25 Siemens Ag Echtzeit-gesteuerte optimierte Magnet-Resonanz-Bildgebung unter Berücksichtigung von Geräte- und Patienten-spezifischen Grenzwerten
US8157199B2 (en) * 2005-08-31 2012-04-17 Kimberly-Clark Worldwide, Inc. Rewinder web chop with early detection and web diversion to eliminate equipment damage
DE102006011201B4 (de) * 2006-03-10 2011-12-01 Koenig & Bauer Aktiengesellschaft Druckmaschine mit mehreren Antriebseinheiten
FI119980B (fi) * 2006-11-13 2009-05-29 Metso Paper Inc Menetelmä kuiturainakoneen rullaimen yhteydessä
DE102009022962A1 (de) * 2009-05-28 2010-12-02 Siemens Aktiengesellschaft Überwachungssystem und Vorrichtung mit einem solchen Überwachungssystem
RU2627061C2 (ru) * 2011-09-09 2017-08-03 Конинклейке Филипс Н.В. Устройство оптического мониторинга для мониторинга значения кривизны гибкого медицинского инструмента
EP3392405A1 (fr) * 2017-04-18 2018-10-24 Siemens Aktiengesellschaft Procédé de fonctionnement d'une machine à papier, système d'entraînement et machine à papier

Also Published As

Publication number Publication date
CN113490893B (zh) 2024-05-14
CN113490893A (zh) 2021-10-08
WO2020173880A1 (fr) 2020-09-03
EP3699701A1 (fr) 2020-08-26
US20220147033A1 (en) 2022-05-12

Similar Documents

Publication Publication Date Title
EP1607192B1 (fr) Méthode et système pour estimer l&#39;usure des articulations d&#39;un bras de robot
DE102011053145A1 (de) Fehlerdiagnoseverfahren für Rollenförderer, Rollenförderer und Steuerung für Förderer
DE102005040978A1 (de) Verfahren zur Überwachung des Betriebszustandes rotierender Walzen in einer industriellen Anlage
EP1975857A2 (fr) Procédé de traitement assisté par ordinateur de valeurs de mesure établies dans un réseau de capteurs
DE102009022962A1 (de) Überwachungssystem und Vorrichtung mit einem solchen Überwachungssystem
AT502431B1 (de) Verfahren und system zur durchführung und verwendung von belastungsmessungen zur wartung von maschinenkomponenten und -vorrichtungen in bezug auf papierherstellung
EP2334454B1 (fr) Système et procédé de détection de l état de fonctionnement d&#39;un guidage de barre
WO2020173880A1 (fr) Procédé et dispositif pour déterminer ou prédire une position d&#39;une rupture de bande, programme informatique et installation industrielle
EP1795893A1 (fr) Méthode pour la détermination d&#39;une propriété de dilatation d&#39;une bande
EP1070280B1 (fr) Procede et dispositif pour technique neuronale de modelisation d&#39;une bobineuse pour papier
EP4068018A1 (fr) Dispositif et procédé de surveillance d&#39;un processus de poinçonnage
EP3122483A1 (fr) Procédé permettant de positionner un galet de dressage d&#39;une installation de dressage à galets
WO2021069258A1 (fr) Procédé de détermination et/ou de classification d&#39;un état de bande d&#39;une bande de matériau, produit de programme informatique, appareil de production et installation industrielle
WO2020173701A1 (fr) Procédé et dispositif pour déceler une rupture de bande d&#39;une bande fibreuse, installation industrielle et produit-programme informatique
DE102015207383B4 (de) Verfahren und Vorrichtung zur Überwachung einer Dichtungseinrichtung
AT519777B1 (de) Verfahren zur Erkennung des normalen Betriebszustands eines Arbeitsprozesses
EP3286375B1 (fr) Procédé de surveillance d&#39;un dispositif d&#39;étanchéité et dispositif d&#39;étanchéité
DE102017108496B4 (de) Verfahren und Vorrichtungen sowie System zum Auf- und Abwickeln eines Wickels
DE19814407B4 (de) Verfahren und Anordnung zur neuronalen Modellierung einer Papierwickelvorrichtung
DE102013224626A1 (de) Anordnung und Verfahren zur Detektierung eines Betriebszustandes
EP0431481A1 (fr) Méthode pour déterminer en continu la finesse des fibres dans des fils et appareil pour la mise en oeuvre de cette méthode
DE102018117579A1 (de) Identifikation eines Schienenfahrzeugrades
WO2009059860A1 (fr) Procédé et dispositif de relevé d&#39;une déchirure et/ou d&#39;un module d&#39;élasticité d&#39;une bande de matériau
DE102019122578B4 (de) Verfahren zum Prüfen, Markieren und Sortieren von Einzelobjekten
EP4356209A1 (fr) Surveillance de la production de panneaux de matériau, en particulier de panneaux en matériau dérivé du bois, en particulier à l&#39;aide d&#39;une carte auto-organisatrice

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: UNKNOWN

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20210824

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DAV Request for validation of the european patent (deleted)
DAX Request for extension of the european patent (deleted)
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: EXAMINATION IS IN PROGRESS

17Q First examination report despatched

Effective date: 20230508