EP3724735A2 - Verfahren und messvorrichtungen zum erkennen von ereignissen in einem materialbearbeitungs- oder -herstellungsprozess unter verwendung von ereignismustern - Google Patents
Verfahren und messvorrichtungen zum erkennen von ereignissen in einem materialbearbeitungs- oder -herstellungsprozess unter verwendung von ereignismusternInfo
- Publication number
- EP3724735A2 EP3724735A2 EP18830744.1A EP18830744A EP3724735A2 EP 3724735 A2 EP3724735 A2 EP 3724735A2 EP 18830744 A EP18830744 A EP 18830744A EP 3724735 A2 EP3724735 A2 EP 3724735A2
- Authority
- EP
- European Patent Office
- Prior art keywords
- operator
- pattern
- operators
- decision
- data
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012545 processing Methods 0.000 title claims abstract description 26
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 19
- 239000000463 material Substances 0.000 title claims abstract description 15
- 238000005259 measurement Methods 0.000 claims abstract description 6
- 238000001514 detection method Methods 0.000 claims abstract description 4
- 230000003287 optical effect Effects 0.000 claims abstract description 3
- 238000003909 pattern recognition Methods 0.000 claims description 23
- 230000007547 defect Effects 0.000 abstract 1
- 238000004458 analytical method Methods 0.000 description 8
- 238000005452 bending Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 230000005236 sound signal Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000001746 injection moulding Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 229910000760 Hardened steel Inorganic materials 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- ZINJLDJMHCUBIP-UHFFFAOYSA-N ethametsulfuron-methyl Chemical compound CCOC1=NC(NC)=NC(NC(=O)NS(=O)(=O)C=2C(=CC=CC=2)C(=O)OC)=N1 ZINJLDJMHCUBIP-UHFFFAOYSA-N 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005755 formation reaction Methods 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000009740 moulding (composite fabrication) Methods 0.000 description 1
- 230000008672 reprogramming Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/09—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool
- B23Q17/0952—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool during machining
- B23Q17/099—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool during machining by measuring features of the machined workpiece
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D5/00—Mechanical means for transferring the output of a sensing member; Means for converting the output of a sensing member to another variable where the form or nature of the sensing member does not constrain the means for converting; Transducers not specially adapted for a specific variable
-
- 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
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/4183—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by data acquisition, e.g. workpiece identification
-
- 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
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41875—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by quality surveillance of production
-
- 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
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/34—Graphical or visual programming
-
- 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
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
-
- 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
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/23—Pc programming
- G05B2219/23258—GUI graphical user interface, icon, function bloc editor, labview
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32368—Quality control
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/37—Measurements
- G05B2219/37435—Vibration of machine
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/20—Software design
- G06F8/24—Object-oriented
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Definitions
- the invention relates to methods (measuring) devices, and components thereof, for detecting events in a material processing or manufacturing process based on a multidimensional data stream obtained during the process with time resolved frequency and energy information using event patterns.
- the invention is applicable to all processes in which by re insbesonde acoustic and / or magnetic sensors high-frequency information currency end and / or can be obtained after a material processing or production, as in eg WO 2010/051954 and WO 2017/071812 is described, for example, when machining, injection molding, forming, inductive hardening, welding or the like.
- the invention will be described below for the purposes of illustration using the example of bending. However, the statements are also applicable to the other applications.
- a stamp When bending on a straightening press a stamp acts on a component to be straightened for the purpose of plastic deformation repeatedly and at various points until a desired concentricity is reached.
- a typical Bie-vor gang example of a trained hardened steel drive shaft for the automotive sector can last about one or two minutes with load phases in the order of magnitude of typically less than 1 second follows ge of substantially comparable length relief phases.
- the deformation energy acting on the construction part can not visually cause obvious damage, in particular microcracks, on the component and also the bending straightening device can be damaged or worn out.
- FIG. 1 illustrates the data stream detected as a function of the time t, the frequency f and the intensity I, as illustrated in WO 2010/051954.
- the exemplary three-dimensional illustrated landscape has patterns that can be assigned ver different events.
- a landscape can be discerned which deviates from the landscapes in the loading phase 2 or in the discharge phases 3. If the landscapes are compared with known patterns, for example, for a crack, it can be determined whether the component is faultless or faulty and therefore broke. Corresponds to a landscape 4 in the field of loading phase 1, for example, a pattern for a crack, the component is sorted out as faulty. On the other hand, if this landscape 4 corresponds to the pattern for an operating noise, as in the area of the preceding loading phase 2, the component is fault-free.
- Difficult is the exact discrimination.
- simple pattern recognition for example, by the known comparison of the recorded landscape with a comparison envelope of a comparison pattern, although a degree of agreement can be determined.
- the match is well below 100%, and moreover, multiple patterns for different events of the same order of magnitude can be identified, for example, 80% probability for one pattern and 65% probability for another Template. Depending on the quality requirements for the component, this leads to faultless components being incorrectly sorted out as faulty or faulty components to passing through as faultless.
- the adaptation to the respective process is complex.
- databases for the process and the respective process environment must be prepared and / or adapted.
- the individual adaptation of the comparison logic usually requires a reprogramming.
- the optimal comparison logic is always different for different processes.
- the object of the invention is to provide methods, devices and components thereof for detecting events in a material processing or manufacturing process on the basis of a multidimensional data stream with time-resolved frequency characteristics obtained during the process. and to provide energy information using event patterns that allow for improved discrimination with more flexible customizability.
- the invention provides a measuring device, e.g. a measuring device, advantageously via a graphical user interface or the like easily to the respective material processing and / or manufacturing process customizable Ope ratore nnetztechnik with at least one decision operator and preferably other, in particular cascading and / or parallel operators, in particular pattern operators, and methods based thereon and devices.
- the measuring device in some embodiments, enables fully automated decision making, e.g. OK or non-OK during or after material or component processing or manufacturing, and is intuitively, easily and accurately adaptable to the particular material, component, manufacturing, and / or processing constraints, advantageously using it as intended and / or parameterizable operators and / or operator networks and, if appropriate, use of predetermined standard parameters and / or patterns for particular materials, components, production, and / or processing standard frameworks or scenarios.
- it may be provided to adapt such predefined as a template by: maps / parameterizations; additional operators and their links; and / or redefinition of Operato ren.
- the measuring device may comprise a sensor for the high-frequency detection of a measured variable, such as sound, structure-borne noise, current, voltage, optical or magnetic measured values and the like, or may be connected thereto. be coupled and has an operator that can be bound in an operator network.
- a measured variable such as sound, structure-borne noise, current, voltage, optical or magnetic measured values and the like
- the operator system according to the invention represents quasi an own configuration environment or programming language, in particular for measuring devices.
- certain sensors or general operators are provided which provide the measured values for the processing operators.
- Support OPC-UA can be integrated via an OPC-UA operator.
- the so programmable pattern recognition allows any signals, in the case of sound or structure-borne noise, these signals can be noises and well-known work emissions of machines to recognize, to calculate their concrete expression and to eliminate in real time from the data stream.
- the invention thus makes it possible for a measuring device to precisely remove "loud” basic signals from the data stream and then to detect small peculiarities in the "remaining" data stream.
- this can be solved by searching an input sensor data stream from pattern operators for known noises, these are then eliminated and a new data stream is created, which can be analyzed and processed by subsequent and / or parallel other pattern operators until the results are ready for decision and can be fed to a decision-making operator.
- a decision operator is designed to decide whether, for example, a component in a material processing and / or production process (or the like) or the processing and / or manufacturing device is OK or not OK.
- the decision operator has an input for a disturbance pattern recognition operator, an input for an event pattern recognition operator (8) and / or an input for a free pattern operator (9), possibly also several inputs, eg for a plurality of event pattern recognition operators and / or multiple inputs eg for several free pattern recognition operators.
- An internal logic and internal parameters for parameterizable and / or programmable linkage of the input data, and with an output for an OK or non-OK signal are expediently provided.
- the decision operator may comprise a multi-dimensional, in particular two, three four- or five-dimensional decision field, in particular with one or more allocation regions.
- the decision operator can have several, in particular two, three or four, decision fields each having at least one time-varying borderline.
- a pattern recognition operator may comprise an input for a data stream and an output for a data stream and / or value corresponding to a measure of a match to a pattern of a plurality of patterns of a pattern database.
- the pattern recognition operator expediently recognizes event patterns and / or interference patterns, in particular based on a parameterization, a decision field and / or a pattern recognition.
- the pattern recognition operator comprises a two-, three-, or more-dimensional map having one or more allocation regions.
- Operator network comprising one, two or more pattern recognition operators (7, 8), possibly one or more free pattern operators (9) and at least one decision operator (6), and / or further operators.
- the operator network may include a notification operator, a machine control operator and / or a difference operator.
- operators in particular pattern operators, can be arranged in parallel or in cascading in the operator network.
- a suitably provided multiple data transformations allows the step-by-step processing of data up to two- or multi-dimensional graphs, individual values and yes / no decisions. This results in application of the operator programming and possibly the use of various ex ternal sensors quite different measuring devices, only by the imple mentation of the different analysis algorithms, which are inserted by means of drag and drop in the operator networks.
- Complete operator networks can also be stored as template networks and are available as a basis for similar or extended measuring systems.
- the operator networks can be run on any compatible hardware system (gauges), providing a general analysis layer up to graphically usable gage programming.
- connections also called connections, which transport the processed data between the individual operators.
- connections can also be configured as a buffer with a pipeline function. They thus ensure asynchronous processing of the data, which is necessary in particular for the transition between operators or data streams operating at different speeds.
- Connections are thus also able to connect distributed operator networks, which are connected on different hardware, via the Internet, with industrial bus systems or other widely connected to a complex network of analysis.
- Mobile devices that support the operators of the invention may become part of an integrated operator network, either as a sensor or as a display module.
- the invention therefore provides mobile, in particular current-autonomous devices, in particular in the form of a sensor or display module, which are designed as an operator with an input and / or output data stream for embedding in an operator network or in a measuring device.
- the communication he follows in a known manner wired or wireless via a standard protocol, such as TCP / I P or the like.
- the invention thus provides methods and apparatus, eg the measuring device, for detecting events in a material processing and / or production process on the basis of a multidimensional data stream obtained during the process (eg originating from a structure-borne sound sensor or other sensors called ge) time-resolved frequency and energy formations using disturbance and / or event patterns and / or energy data, the data passing through a pattern operator or a plurality of pattern operators arranged in parallel or successively and fed to a decision operator or to a plurality of decision operators arranged in parallel or in succession.
- a multidimensional data stream obtained during the process (eg originating from a structure-borne sound sensor or other sensors called ge) time-resolved frequency and energy formations using disturbance and / or event patterns and / or energy data, the data passing through a pattern operator or a plurality of pattern operators arranged in parallel or successively and fed to a decision operator or to a plurality of decision operators arranged in parallel or in succession.
- the invention further provides a graphical user interface for creating and / or editing an operator network according to the invention, and / or a measuring device comprising the graphical user interface, wherein the graphical positioning and connectivity of predetermined operators is made possible.
- an operator network and / or a graphical user interface are provided for the creation and / or editing of the operator network.
- An operator network 5 is shown in an exemplary configuration in FIG. 2 shown. It comprises a decision operator 6, which is here eingangssei tig with a noise pattern operator 7, an event pattern operator 8 and / or egg nem free pattern operator 9 and the output side connected to a signal operator 10, a counting operator 1 1 and / or a memory operator 12.
- Each operator is a program module with predetermined input and / or output interfaces and internal logic, for filtering data, collecting data, preparing data, making decisions, storing data, interacting with computers, databases, users and / or Like, and / or activating devices such as signals, motors, switching devices and / or the like, etc.
- the interference pattern operator 7 shown here can, as shown in Fiq. 3 shown to be constructed.
- a data stream 13 for example, as a raw data stream of a sensor, in particular special sound signal sensor, or as by particular other operators be worked, e.g. frequency-filtered and / or smoothed data stream, arrives at a position determining operator 14 which, taking into account a process time provided by a time operator 15, determines the timing of the data within the process and supplies it to a pattern comparison operator 16.
- An energy determination operator 17 is also connected to the operators 13, 15, determines the energy in the data stream, e.g. in terms of sound intensity and correlates with the process time to supply the result to the pattern comparison operator 16.
- the time component from the time operator 15 and / or pattern data from a pattern operator 18, which is connected to a geographic database before geous or otherwise Mus ter can retrieve events determined
- the pattern comparison operator 16 is a measure of the consistency of the data provided by the stream operator 13 with a pattern provided by the pattern operator 18, or multiple measures for multiple patterns.
- the measure may e.g. a number between 0% and 100% or between 0 and 255 or the like.
- the match score is provided at result output 19.
- the pattern operator 18 accesses interference patterns, such as occur during the process, such as the impact of the stamp on the component to be straightened, a buzzing noise due to vibrations of the straightening device, environmental influences such as knocking by operators, grinding noises of the tool on the workpiece etc.
- the probability of 67% can be output for the fact that a disturbance pattern has been identified.
- the event pattern operator 8 may be constructed in much the same way as the noise pattern operator 7.
- its logic may also include a data stream operator, a time operator, a position determining operator, an energy determining operator, a pattern matching operator, and / or a pattern operator, which may be similarly or identically connected and internally configured with weighting factors and the like, with the pattern operator checking for event patterns a pattern library, the disturbances represent len, such as patterns for stress cracks or tool breaks in cutting processing and the like.
- the event pattern operator 8 provides at its result output 19, see Fig. 2, a value for such an event having occurred, eg, 82%.
- the free-mode operator 9 may comprise, in addition to a data stream operator 13, a time operator 15 and a position-determining operator 14, as in FIG. 3, an energy-determination operator 20, e.g. the energy, such as the sound signal intensity, and / or duration, is calculated and provided at its result output 19.
- an energy-determination operator 20 e.g. the energy, such as the sound signal intensity, and / or duration, is calculated and provided at its result output 19.
- the energy-determination operator 20 e.g. the energy, such as the sound signal intensity, and / or duration
- the operators can be arranged and configured in a graphical user interface. So they can be dragged and dropped with the mouse or the like from a list of operators and placed on a worksheet. Data connections between the inputs and outputs illustrated as lines in FIGS. 2, 3, 4 are likewise graphically configurable. By right-clicking or the like on an operator whose internal parameters or logic can be selected and / or changed.
- the energy determination operator 20 the formula for the calculation of the energy value can be determined; in the pattern comparison operator 16, the algorithm can be selected on the basis of which the degree of correspondence between the acquired data and a pattern is determined (for example, by adding up the differences or the like), etc.
- the graphical user interface enables the user to quickly and flexibly implement, adapt and maintain an operator network tailored to the respective process, without having to rely on the manufacturer or programmer.
- the decision operator 6 is in the configuration of special significance to the effect that it allows the discrimination in error-free (OK) orCentral haf te (Not OK, NOK) components / workpieces in a reliable manner.
- OK, NOK and NO inputs 22, 23, 24 of the decision operator 6 are connected to the result outputs 19 of the operators 7, 8 and 9.
- a (probability) value along with further information is supplied by the interference pattern operator 7 for the purpose of detecting an insignificant interference signal at the time, ie the workpiece is "OK".
- the event pattern operator 8 supplies a (probability) value together with further information for the fact that a considerable event, such as a stress crack, is currently being detected, ie the workpiece is not OK ("NOK").
- Further information is provided at NO input 24 without pattern matching ("NO" pattern recognition, no pattern recognition).
- the further information may include an energy value such as the sound intensity and / or a duration, such as the temporal duration of the energy from exceeding a threshold value to below the threshold or the like.
- the decision operator 6 is configured to cascade multidimensional decision fields and, based on the result of the cascaded multidimensional decision, send a trigger signal to the signal operator 10 to reject a workpiece as faulty (or possibly error free). to mark, so that a faulty workpiece can be discharged.
- the results and / or data may be stored by passing to the memory operator 12, and the counter 11 may record the shot per unit time or in total and display it on the visualization operator 21, for example in the form of a scale to visualize trends.
- the first multidimensional decision box is shown in FIG. 5 illustrated. It applies the OK value from the disturbance operator 7 and the NOK value from the event pattern teroperator 8 against each other.
- an OK value of 67% and an NOK value of 82% has been determined for loading phase 1 in FIG. This corresponds to the data point 25, which is above a configurable via the graphical user interface limit line 26.
- Another data point 27 lies below the boundary line 26.
- the data points 25, 26 are ambiguous assignments, i. the events could most likely be either a negligible noise signal or a significant event pattern signal, while other data points 28, 29 are unique because they are either 0% NOK or 0% OK.
- the boundary line 26 serves as the first stage of discrimination.
- the uneindeuti data points are for the next stage of a multidimensional NOK decision box according to Fiq. 6.
- the data point 25 is plotted in each case with its further data, here by way of example the energy and the duration, and is located above an NOK borderline 30 in FIG. 5, below an OK borderline 31 in FIG. 6 and outside the hatched NOK boundary. Area 32 between the NO boundary lines 33, 34 in Fig. 7.
- the parameters include energy, duration, temporal position, counter, time scaling tion, amplitude scaling and the like and / or instead of Borderline, an interface can be used.
- the decision operator 6 is expediently configured to evaluate the data point 25 as NOK, since the data point 25 is in the NOK range 32 with regard to at least two of the three operators OK, NOK and NO.
- the borderlines 26, 30, 31, 33, 34 are individually passable to the respective process.
- FIG. 5 Another dimension in Figures 5, 6, 7, 8 may be time.
- the force exerted on the workpiece at the bending levels force and thus the probability of breakage low while at the end of each loading phase 1, 3 is maximum.
- it may be appropriate, at the beginning of the loading phase to set a boundary line 26 'that is more generous than the boundary line 26, while at the end of the loading phase, a boundary line 26 "is set at which, due to the high effecting force, an earlier NOK 5.
- a data point 27 may thus be OK if it is detected at the beginning of the loading phase, while at the end it is above the boundary line 26 "and NOK.
- the aforementioned operators can be arbitrarily cascaded and / or arranged in parallel.
- a difference operator may be provided.
- the difference operator is configured to have a known pattern, e.g. a more or less constant background noise or a recurring noise or other disturbances, recognizes the associated pattern as precisely as possible adapted to the magnitude of the data stream and subtracted from it with sufficient agreement. Then there remains as a difference an adjusted data stream, which can be supplied to the further operators.
- a difference operator 35 is connected downstream of the disturbance pattern operator 7 'and extracts disturbance patterns from the data stream 13 on the basis of the disturbance pattern recognition and the adjusted data stream 36 of the further processing, e.g. as the input data stream in FIG. 2 for the operators 7, 8, 9, whereby the following operator 7 - if present - can be set differently, or the disturbance pattern operator 7 'recognizes only certain disturbance patterns, such as ripples, scatters, etc.
- inventive operator model will be explained with reference to further case of games.
- it can be executed on distributed, heterogeneous and asynchronously processing hardware and information technology systems.
- Analyzes are performed in the measuring device according to the invention by a network of operators.
- a measurement stream coming from an external source can sample 4-channel sensor data with up to 10 OOM samples and 16-bit or 4-M and 24-bit real-time FFT at 25,000 spectra / s per channel, providing both as an input data stream.
- 32 digital lOs for machine control as well as Profibus and Profinet for machine communication can also be provided as inputs and outputs for the operators.
- the analysis sequences are created in the graphical operator editor according to the invention, see for example FIG. 11.
- processors At the top level, processors (clock slot) execute analysis programs (customer operators).
- Custom operators represent containers for subroutines in which complex networks of further subroutines and ready-made operators can be implemented, see FIG. 12, which exemplifies a pattern analysis and decision making network.
- the individual operators present in the editor more or less complex GUI components that define the connection to the data and parameterize the operation of the operators.
- JSON objects are also exchanged with the GUI.
- the integration of new operators can be done via plugin.
- a new data source must therefore bring along an operator plugin.
- the data are processed by the operators and, as shown in this example, the most suitable pattern is found, scaled and its counterpart analyzed in the data stream.
- a microcrack is detected in a transmission shaft. It is a 50ms long section of structure-borne noise data from an industrial Richtma machine for transmission shafts shown.
- the landscape is created on the basis of 25,000 spectra / s after FFT of the microphone data, which are evaluated in this case up to 800kHz.
- All data can be stored on RAW-format measuring instruments and in various compressions and analyzed both in real time and after process (for learning processes).
- sensors according to the invention are i.a. Structure-borne sound microphones and pmagnetic sensors, as well as broadband analogue amplifiers (> 100 MHz) for data acquisition in industrial processes.
- the operator concept can be extended to distributed, heterogeneous and asynchronous hardware and information technology systems. Individual sections of a large operator network can run on distributed systems.
- the sensors according to the invention can collect and preprocess data, ie be configured as smart sensors.
- a real-time processing system can perform spectral analysis and know patterns.
- a PC brings about complex decisions.
- the hardware used and also the software used can be very different. As long as the inter- faces of the operator system, every device, every service can be integrated into the entire processing.
- the manufacturer of a device provides not only the actual device but also a module for operator integration, via whose GUI the parameterization can be carried out, and that provides the inputs and outputs for the other participants in the network.
- the data streams can be both analog and digital and transported on different carriers and also support various protocols, their respective operator provides access to the data in a compatible form.
- an OS e.g., Linux system
- TCP / IP connectivity can run on each sensor.
- a sensor hub may be provided which incorporates the OS system and places the sensor in the network. The redirect can be wireless or wired.
- a FPGA-based smart-switch can represent a collection point and further processing stage. This smart-switch performs parallel computing on the connected data streams and then provides its results again via TCP / IP or via PCIe, USB etc.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Factory Administration (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Investigating Or Analyzing Materials By The Use Of Magnetic Means (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102017011368.8A DE102017011368A1 (de) | 2017-12-11 | 2017-12-11 | Verfahren, Vorrichtung, und Komponenten davon, zum Erkennen von Ereignissen in einem Materialbearbeitungs- und/oder Herstellungsprozess unter Verwendung von Ereignismustern |
PCT/EP2018/084411 WO2019115553A2 (de) | 2017-12-11 | 2018-12-11 | Verfahren, (mess-)vorrichtungen, und komponenten davon, zum erkennen von ereignissen in einem materialbearbeitungs- oder -herstellungsprozess unter verwendung von ereignismustern |
Publications (1)
Publication Number | Publication Date |
---|---|
EP3724735A2 true EP3724735A2 (de) | 2020-10-21 |
Family
ID=65009672
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP18830744.1A Pending EP3724735A2 (de) | 2017-12-11 | 2018-12-11 | Verfahren und messvorrichtungen zum erkennen von ereignissen in einem materialbearbeitungs- oder -herstellungsprozess unter verwendung von ereignismustern |
Country Status (6)
Country | Link |
---|---|
US (1) | US11931842B2 (de) |
EP (1) | EP3724735A2 (de) |
KR (1) | KR20200108281A (de) |
CN (1) | CN111954856A (de) |
DE (1) | DE102017011368A1 (de) |
WO (1) | WO2019115553A2 (de) |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4574633A (en) * | 1983-02-04 | 1986-03-11 | Citizen Watch Company Limited | Apparatus for detecting tool damage in automatically controlled machine tool |
US4636780A (en) * | 1984-10-24 | 1987-01-13 | General Electric Company | Acoustic monitoring of cutting conditions to detect tool break events |
KR100224379B1 (ko) * | 1997-05-29 | 1999-10-15 | 박호군 | 공정 제어 알고리즘 생성 방법 |
KR100226277B1 (ko) * | 1997-06-17 | 1999-10-15 | 토니헬샴 | 가공 공구 손상 및 마모 감시 장치 및 방법 |
EP1873634A3 (de) * | 2006-06-29 | 2013-10-09 | Rockwell Automation Technologies, Inc. | HMI-Rahmen für Engineering-Plattformen erweiterbarer Automatisierungssysteme |
DE202008014792U1 (de) | 2008-11-07 | 2010-03-25 | Qass Gmbh | Vorrichtung zum Bewerten von Zerspanungsprozessen |
GB201510220D0 (en) * | 2015-06-11 | 2015-07-29 | Renishaw Plc | Additive manufacturing apparatus and method |
WO2017071812A1 (de) | 2015-10-28 | 2017-05-04 | Qass Gmbh | Verfahren und vorrichtungen zum beobachten eines magnetfelds eines materialvolumens sowie verwendung der vorrichtung |
US20170172493A1 (en) | 2015-12-17 | 2017-06-22 | Microsoft Technology Licensing, Llc | Wearable system for predicting about-to-eat moments |
US10245698B2 (en) * | 2016-05-06 | 2019-04-02 | Massachusetts Institute Of Technology | Method and apparatus for efficient use of CNC machine shaping tool including cessation of use no later than the onset of tool deterioration by monitoring audible sound during shaping |
KR20180042557A (ko) * | 2016-10-18 | 2018-04-26 | 삼성전자주식회사 | 공작 기계의 상태를 감시하는 전자 장치 및 그의 제어 방법 |
KR20180083990A (ko) * | 2017-01-13 | 2018-07-24 | 삼미정보시스템 주식회사 | 다수 공작기계의 통합 관제 시스템 |
-
2017
- 2017-12-11 DE DE102017011368.8A patent/DE102017011368A1/de active Pending
-
2018
- 2018-12-11 WO PCT/EP2018/084411 patent/WO2019115553A2/de unknown
- 2018-12-11 CN CN201880088950.0A patent/CN111954856A/zh active Pending
- 2018-12-11 US US16/965,339 patent/US11931842B2/en active Active
- 2018-12-11 KR KR1020207020011A patent/KR20200108281A/ko not_active Application Discontinuation
- 2018-12-11 EP EP18830744.1A patent/EP3724735A2/de active Pending
Also Published As
Publication number | Publication date |
---|---|
WO2019115553A2 (de) | 2019-06-20 |
WO2019115553A3 (de) | 2019-09-19 |
KR20200108281A (ko) | 2020-09-17 |
US20210165396A1 (en) | 2021-06-03 |
CN111954856A (zh) | 2020-11-17 |
US11931842B2 (en) | 2024-03-19 |
DE102017011368A1 (de) | 2019-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102017002607B4 (de) | Bearbeitungsmaschinensystem, das über die Akzeptanz/Verwerfung von Werkstücken bestimmt | |
EP2419799A1 (de) | Verfahren zum aufbereiten von prozesszustandsdaten und/oder maschinenzustandsdaten einer werkzeugmaschine | |
EP3077878B1 (de) | Computer-implementiertes verfahren und system zur automatischen überwachung und statusermittlung ganzer prozessabschnitte in einer process unit | |
DE102019100722B4 (de) | Erkennung von Spitzen und Fehlern in Schwingungstrendddaten | |
CN101362301A (zh) | 一种基于混沌振子的刀具磨损状态检测装置及其检测方法 | |
DE102021124253A1 (de) | Maschinelles Lernverfahren zur Anomaliedetektion in einem elektrischen System | |
DE102017117991A1 (de) | Analysesystem | |
WO2021099159A1 (de) | Verfahren für die überwachung und/oder vorhersage von bearbeitungsprozessen und/oder bearbeitungsergebnissen | |
EP3665536A1 (de) | Ursachenbestimmung von anomalieereignissen | |
EP3705962A1 (de) | Verfahren und system zur qualitätskontrolle in der industriellen fertigung | |
DE19702234A1 (de) | Verfahren zur Überwachung und Qualitätsbeurteilung von sich bewegenden und/oder rotierenden Maschinenteilen insbesondere von Maschinenlagern | |
DE102005015465B4 (de) | Verfahren und Gerät zum Kategorisieren von Wälzlagerschäden | |
EP3724735A2 (de) | Verfahren und messvorrichtungen zum erkennen von ereignissen in einem materialbearbeitungs- oder -herstellungsprozess unter verwendung von ereignismustern | |
EP3268822B1 (de) | Projektgerät und verfahren zum konfigurieren und/oder parametrieren von automatisierungskomponenten eines automatisierungssystems | |
CN103473640A (zh) | 一种基于机床刀具受力状态的加工进度信息采集方法 | |
EP2419798A1 (de) | Verfahren zum bereitstellen eine information über ein verschleiss einer komponente einer maschine und verfahren zum bereitstellen eines ersatzalgorithmus | |
WO2011088935A1 (de) | Verfahren zur zustandsüberwachung einer maschine und überwachungseinrichtung hierfür | |
DE10228389A1 (de) | Schwingungssensor und Verfahren zur Zustandsüberwachung von rotierenden Bauteilen und Lagern | |
EP3792709A1 (de) | Analysevorrichtung für betriebsgeräusche einer werkzeugmaschine | |
EP3999925B1 (de) | Verfahren und vorrichtungen zum bestimmen einer produktgüte | |
WO2021123276A1 (de) | Verfahren und system zur ermittlung des dynamischen verhaltens einer maschine | |
DE102007021130A1 (de) | Verfahren zur automatischen Ermittlung von Prüfbereichen, Prüfverfahren und Prüfsystem | |
DE102009031486A1 (de) | Verfahren zum Betrieb eines Rundschalttischs | |
EP3891467B1 (de) | Verfahren zum überprüfen einer qualität eines werkstücks sowie recheneinrichtung | |
EP2158527B1 (de) | Aktionsmodule für zustandsabhängige wartungsarbeiten |
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: 20200713 |
|
AK | Designated contracting states |
Kind code of ref document: A2 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 |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
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: 20220601 |