EP2483755A1 - Représentation acoustique des états d'une installation industrielle - Google Patents

Représentation acoustique des états d'une installation industrielle

Info

Publication number
EP2483755A1
EP2483755A1 EP10760595A EP10760595A EP2483755A1 EP 2483755 A1 EP2483755 A1 EP 2483755A1 EP 10760595 A EP10760595 A EP 10760595A EP 10760595 A EP10760595 A EP 10760595A EP 2483755 A1 EP2483755 A1 EP 2483755A1
Authority
EP
European Patent Office
Prior art keywords
industrial plant
plant
acoustic signal
audio
profile
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.)
Withdrawn
Application number
EP10760595A
Other languages
German (de)
English (en)
Inventor
Matthias Dürr
Norbert Gewald
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
Original Assignee
Siemens AG
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 filed Critical Siemens AG
Publication of EP2483755A1 publication Critical patent/EP2483755A1/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10K—SOUND-PRODUCING DEVICES; METHODS OR DEVICES FOR PROTECTING AGAINST, OR FOR DAMPING, NOISE OR OTHER ACOUSTIC WAVES IN GENERAL; ACOUSTICS NOT OTHERWISE PROVIDED FOR
    • G10K15/00—Acoustics not otherwise provided for
    • G10K15/02—Synthesis of acoustic waves
    • 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]
    • G05B23/027—Alarm generation, e.g. communication protocol; Forms of alarm

Definitions

  • industrial plants such as power plants or factories today have human-machine interfaces via which a plant operator monitors the industrial plant.
  • the man-machine interface enables the plant operator to control the plant.
  • signals e.g. Sensor messages, operating states and other data processed and visually z. B. issued via monitors to the plant driver.
  • certain operating states of the industrial plant can only be measured via sensors and displayed only visually on the monitors.
  • audible warnings are emitted on the audio channel.
  • a method for outputting an audible signal (e.g., blinker noise) depending on a condition of a motor vehicle (such as overspeed, blinker set).
  • the state here includes an operating state and a driving state.
  • the assignment of the states to the acoustic signals is implemented as a tabular assignment.
  • a method is known to produce and output an artificial engine noise as an acoustic signal for a motor vehicle with electric drive.
  • properties of the acoustic signal are set in direct dependence on a speed of the motor vehicle.
  • the object is to provide a method and an arrangement for representing states of an industrial plant, which monitor the state of the industrial plant. simplify and, if necessary, improve
  • This object is achieved according to the invention by processing signals from an industrial plant with a machine classifier, wherein a current state of the industrial plant is determined as the result. Based on the current state, a computer-aided audio profile is selected from a set of audio profiles. The audio profile is converted into an acoustic signal, which is then output to a system operator.
  • the arrangement for acoustically representing states of an industrial plant includes a machine classifier programmed to process industrial plant signals and to determine a current state of the industrial plant.
  • the arrangement further includes a first arithmetic unit programmed to select an audio profile from a set of audio profiles based on the current state.
  • the arrangement includes a second arithmetic unit programmed to convert the audio profile to an audible signal. Furthermore, the arrangement includes an interface to a sound generator, which is connected to an acoustic output means and designed for outputting the acoustic signal to a plant driver.
  • the plant operator can hear the state of the industrial plant again by listening.
  • the acoustic signal changes, the attention of the plant driver is automatically aroused, such as the change of driving noise in a motor vehicle alerts the driver and, for example, indicates that a gasoline pump unusually loud or no longer buzz or the brakes squeak unusually.
  • a plant operator could listen to the acoustic signal several times a day for a few minutes, or continuously in the background, thus revealing irregularities in a mere visual observation of his attention would escape.
  • Another advantage is that the system operator can now continuously provide a reference signal in the form of the acoustic signal on a little overloaded sensory channel. so that even a small change in the acoustic signal can cause a lot of attention on the plant operator.
  • the machine classifier is a plant automation program, an expert system, a neural network, or a support vector machine.
  • This embodiment has the advantage that well over 1000 signals, which usually have to be evaluated in the industrial plant, can be processed by the mechanical classifier.
  • the signals come from over 1000 different sources. Furthermore, these signals are filtered, weighted, aggregated and / or abstracted before or during processing with the machine classifier. In addition to the signals, the machine classifier also processes trends in the signals, key operational key figures and / or information from a production control system, a company resource planning system, a system for production planning and control and / or archives.
  • the filtering, weighting, aggregation and abstraction of the signals mentioned in this development has the effect of simplifying the acoustic signal which is output to the system operator.
  • a direct interconnection of the individual signals to the dynamically generated acoustic signal would overwhelm the system operator because of the large number of signals. Instead, a state is determined (from a limited set of states) whose audio profile is easily recognizable to the plant operator.
  • the current state is a normal operation, startup, shutdown, standby state, idle state or malfunction of the industrial plant.
  • the audio profiles are standardized from the set of audio profiles.
  • These execution form has the advantage that the plant operator can visit all under ⁇ Kunststoffliche industrial plants and still see from the acoustic signal, what the situation is. This results in a similar effect to Airbus cockpits, which are very similar on all Airbus aircraft, for example the A380 and the A319.
  • the standardization thus offers the advantage that states of the industrial plant can be recognized immediately on different plants. This facilitates training and deployment of employees for plant control.
  • the invention further includes a computer readable medium having stored thereon a computer program which executes the method just described when executed in a computer.
  • the invention comprises a computer program that is processed in a computer and thereby carries out the method described above.
  • FIG. 1 shows an acoustic representation of states of an industrial plant
  • Figure 2 is a detailed view of the generation and output of an acoustic signal.
  • FIG. 1 shows an acoustic representation of states of an industrial plant 100.
  • a machine classifier 9 processes signals 101 of the industrial plant 100 and as a result determines a current state of the industrial plant 100.
  • an audio profile 2 from a lot of audio Profiles 2 chosen.
  • the selected audio profile 2 is then converted into an acoustic signal and output to a plant driver. The last steps are shown in detail in FIG.
  • FIG. 1 also shows a first link 111 which links one of the audio profiles 2 to a specific state of the industrial plant 100. For example, this could be the "start up" state.
  • a second link 112 links three characteristics of an audio profile 2 to a further state of the industrial plant 100. This could be, for example, a state "normal operation" of the industrial plant 100.
  • the audio profiles 2 each have an interface 201. Via the interface 201, profile parameters of the audio profiles 2 can be adapted to properties of the respective state. So could a property of the state
  • Normal operation indicate whether the industrial plant 100 is operating at low, medium or high utilization.
  • an associated profile parameter of the assigned audio profile 2 could be set via the interface 201 such that a slow, medium-fast or fast piece of music is played depending on the characteristic.
  • the three overlapping embodiments of the audio profile 2 can be different instances of the same audio profile 2, which differ only by values of their profile parameters.
  • a third link 113 links a further audio profile 2 with a further state of the industrial system 100, for example the state "shutdown".
  • a fourth link 114 is shown, which links several instances of an audio profile 2 with a further state, for example "malfunction”.
  • the state "accident” can in turn be characterized by different properties which, for example, the severity of the accident. differ.
  • corresponding parameters are again transmitted to the audio profile 2 via the interface 201, whereby one of the possible instances is formed on the basis of the corresponding profile parameters.
  • FIG. 1 also shows a development phase 110, represented by an arrow, which is drawn from right to left.
  • the audio profiles 2 are started. These are ideally already in a standardized form, that is, they are standardized for typical conditions of industrial plants. This has the advantage that a plant operator can visit different industrial plants and can orientate immediately, because everywhere acoustic signals are output with the same audio profiles 2.
  • the audio profiles 2 already present are linked backwards to the states of the industrial plant 100. This also determines how properties of the states should affect profile parameters of the audio profiles 2.
  • the states of the industrial plant 100 must be derived from their individual signals 101.
  • a filter 91 is used which precedes the machine classifier 9 or is a component of the machine classifier 9.
  • the signals 101 which can come from more than thousand different sources, are filtered, weighted, aggregated and / or abstracted before or during processing with the machine classifier 9.
  • the machine classifier 9 can also display, in addition to the signals 101, trends in the signals 101, key operational indicators (KPI) and / or information from a production control system (MES, "Manufacturing Execution System"), a corporate resource Planning system (English term ERP, “Enterprise Resource Planning”), a system for production planning and control (English term PPS, "Production Planning System”) and / or archives process. It is also possible to fall back on data such as quality data or availability, which can be inferred from the systems mentioned, in order to determine the properties of the states.
  • the signals 101 and the numerous other information sources mentioned are thus assigned to states, which is an m: n assignment.
  • this information is classified by the machine classifier 9 in order to recognize a current state and to determine its properties.
  • the opposite approach is taken by first defining states of the industrial plant 100. These are then linked to the abstracted signals of industrial plant 100.
  • the audio profiles 2 remain the same in the development phase 110, that is, an audio profile 2 for normal operation is not changed. Instead, the definition of the state "normal operation" is adapted to the respective design of the industrial plant 100.
  • the audio profiles 2 may be implemented as noise, one-tone noise, parameter-dependent tone noise, or pieces of music.
  • the machine classifier 9 can be implemented, for example, as a program of a plant automation, as an expert system, as a neural network or as a support vector machine.
  • the plant automation is programmed as appropriate to those previously described Perform process steps.
  • a neural network has the advantage that on the one hand it is very well suited for filtering, weighting, aggregation and abstraction of the signals 101. Therefore, a neural network is also particularly suitable for the filter 91.
  • the filter 91 can also be an input layer of a neural network which implements the machine classifier 9.
  • Another advantage of a neural network is that the classification can be learned automatically based on data sets. In this case, it is not necessary to explicitly state according to which rules the over thousand signals 101 are to be classified as states. Instead, data sets for different states of the industrial plant 100 are collected. The data records are annotated with the respective state. Subsequently, the neural network is trained with the data sets and is then able to classify the state independently.
  • FIG. 2 shows a detailed view of the generation and output of an acoustic signal 5.
  • an audio profile 2 is initially selected as a function of a current state 1, profile parameter 3 of the audio profile 2 being dependent on properties of the current state 1 be set.
  • the aim now is to make the current state 1 of the industrial plant 100, which was previously only visually displayed, acoustically accessible to the plant operator.
  • the current state 1 of the industrial plant 100 is thus acoustically processed and reproduced.
  • One possibility for this is a generation of an acoustic backdrop as an acoustic signal 5, which changes in the case of deviations from a normal case as a function of parameters of the industrial plant 100 which are changed in this case.
  • FIG. 2 shows an acoustic signal 5 which is output to the system operator via a sound generator 6 and an acoustic output means 7, for example a loudspeaker.
  • the acoustic signal 5 is generated here synthe ⁇ table, for example, by a sequencer. 8 Alternatively, a synthesizer or sampler can be used.
  • the acoustic signal 5 affects the current state 1 in ⁇ industrial plant 100, the acoustic signal 5.
  • the influence of the acoustic signal 5 by the current 1 state takes place here continuously, that is the current state 1
  • the industrial plant 100 is continuously determined or evaluated and used continuously to adapt the acoustic signal 5. This relates in particular to periods in which there is no fault in the industrial plant 100 or at least no fault is detected in the industrial plant 100.
  • a sampler is an electronic musical instrument that is often controlled via the data transfer protocol MIDI. It can record sounds of any kind and can play them at different pitches, for example, at the touch of a button.
  • a sequencer is an electronic device or computer program for recording, playing back and editing music.
  • a synthesizer is a musical instrument that produces sounds electronically through sound synthesis.
  • MIDI abbreviation of the musical instrument digital interface
  • MIDI abbreviation of the musical instrument digital interface
  • FIG. 2 thus shows an acoustic construction of the acoustic signal 5 as well as a manipulation of the individual tracks 4.
  • An implementation of the sequencer 8 takes place here, for example, based on sequencers for the generation of music.
  • Corresponding sequencers in hardware or software are well-known and make it possible to manage samples or synthesized signals on the different tracks 4 and to play them together as the acoustic signal 5.
  • the played tracks 4 can be manipulated by a variety of methods. For example, it is possible to change the pitch, response time, volume, etc. dynamically.
  • the individual profile parameters 3, which correlate with selected properties of the current state 1 of the industrial plant 100, are coupled to the sequencer 8.
  • Each relevant profile parameter 3 thus influences a control variable of the assigned track 4 in the sequencer 8.
  • a profile parameter 3 can also influence a control variable for several or all tracks 4, for example the volume or speed of all tracks 4.
  • the tracks 4 and the acoustic signal 5 form a piece of music.
  • the mapping of the profile parameter 3 to control variables (pitch, response time, volume, etc.) for the tracks 4 by the sequencer 8 is here calibrated so that the piece of music in the form of the acoustic signal 5 at a normal or error-free current state 1 of the industrial Annex 100 is played normally.
  • properties or the profile parameters 3 correlated therewith depart from the normal operation of the industrial plant 100, they influence the respective control variables (pitch, response time, volume, etc.) of the respective track 4 with the aid of the sequencer 8 Change the pitch of the melody of the piece of music or even its rhythm slightly get out of rhythm.
  • one of the synthetically synthesized instruments for example, can become louder and stand out.
  • the audio profile 2 is changed immediately in a state change of the industrial plant 100, so that the plant operator immediately receives a clear acoustic feedback on the state change.
  • the acoustic signal 5 does not represent a piece of music, but rather is an abstract acoustic signal.
  • the abstract acoustic signal can be implemented as noise, for example.
  • a decomposition of the abstract acoustic signal or its formation from different tracks 4 is optional and can be omitted.
  • the acoustic signal 5 does not necessarily have to be composed of several tracks 4. In principle, a single track 4, which can then be regarded as identical to the acoustic signal 5, is already sufficient.

Abstract

Un classificateur automatique classifie les signaux d'une installation industrielle et produit comme résultat un état instantané. Au moyen de l'état instantané, un profil audio est sélectionné dans une certaine quantité de profils audio et transmis à un conducteur de l'installation sous la forme d'un signal acoustique généré synthétiquement. A cet effet, l'état de l'installation industrielle est évalué en continu, et utilisé par exemple à l'aide d'un séquenceur MIDI pour la manipulation de différentes pistes d'un morceau de musique ou d'un fond sonore artificiel produit synthétiquement. Le conducteur de l'installation peut ainsi avoir une perception intuitive ou même le cas échéant subliminale des déviations de l'installation industrielle par rapport au fonctionnement normal qui ne lui sont pas accessibles ou ne le sont que difficilement sur le canal visuel surchargé. Le conducteur de l'installation peut également se rendre compte à l'écoute ou être confronté au fait que l'installation industrielle n'est plus correctement audible dans certaines situations. Etant donné que le canal sensoriel utilisé à cet effet est comparativement peu exploité par la perception acoustique, des changements minimes dans le signal acoustique suffisent à attirer fortement l'attention du conducteur de l'installation.
EP10760595A 2009-09-30 2010-09-15 Représentation acoustique des états d'une installation industrielle Withdrawn EP2483755A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102009047783 2009-09-30
PCT/EP2010/005674 WO2011038838A1 (fr) 2009-09-30 2010-09-15 Représentation acoustique des états d'une installation industrielle

Publications (1)

Publication Number Publication Date
EP2483755A1 true EP2483755A1 (fr) 2012-08-08

Family

ID=43500417

Family Applications (1)

Application Number Title Priority Date Filing Date
EP10760595A Withdrawn EP2483755A1 (fr) 2009-09-30 2010-09-15 Représentation acoustique des états d'une installation industrielle

Country Status (3)

Country Link
US (1) US20120206261A1 (fr)
EP (1) EP2483755A1 (fr)
WO (1) WO2011038838A1 (fr)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102011102709B4 (de) 2011-05-20 2020-08-06 RocketAudio Traffic GmbH Einrichtung zur simulierenden Erzeugung von Betriebsgeräuschen eines Fahrzeuges, insbesondere eines Kraftfahrzeuges
EP2690517B1 (fr) * 2012-07-26 2016-04-13 ABB Research Ltd. Procédé et système de protection des oreilles pour surveiller un processus industriel
DE102014004599A1 (de) * 2014-03-26 2015-10-01 Constanze Holzhey Verfahren, Vorrichtung oder Computerprogrammprodukt zum Abspielen eines Musikstücks im Fahrzeug.
US10024823B2 (en) * 2016-07-11 2018-07-17 General Electric Company Evaluating condition of components using acoustic sensor in lighting device

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19701801C2 (de) 1996-12-20 1998-10-29 Aarcon Prauss Arminius Gmbh Vorrichtung zur Imitation von Motor- und Fahrzeuggeräuschen
JP3033531B2 (ja) * 1997-07-11 2000-04-17 株式会社日立製作所 プラント運転監視装置
US6140568A (en) * 1997-11-06 2000-10-31 Innovative Music Systems, Inc. System and method for automatically detecting a set of fundamental frequencies simultaneously present in an audio signal
US6609036B1 (en) * 2000-06-09 2003-08-19 Randall L. Bickford Surveillance system and method having parameter estimation and operating mode partitioning
JP2004051081A (ja) 2002-05-27 2004-02-19 Yamaha Corp 車両及びその音響発生方法
SE0502857L (sv) * 2005-12-22 2007-06-23 Abb Research Ltd Ljudbaserat informationssystem
US8326582B2 (en) * 2008-12-18 2012-12-04 International Electronic Machines Corporation Acoustic-based rotating component analysis

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO2011038838A1 *

Also Published As

Publication number Publication date
WO2011038838A1 (fr) 2011-04-07
US20120206261A1 (en) 2012-08-16

Similar Documents

Publication Publication Date Title
EP1703350B1 (fr) Diagnostic d'un système d'automatisation
EP1855172A1 (fr) Procédé destiné au filtrage d'alarmes dans une installation industrielle
DE10346478A1 (de) Flexibler Softwareupdate für Automatisierungssysteme über Internet
EP2483755A1 (fr) Représentation acoustique des états d'une installation industrielle
DE102014012184A1 (de) Vorrichtung und Verfahren zur automatischen Erkennung und Klassifizierung von akustischen Signalen in einem Überwachungsbereich
EP1296207B1 (fr) Appareil HMI et procédé de commande d'une installation technique, système d'automatisation avec cet appareil HMI et produit de programme informatique avec un programme pour la mise en oeuvre de ce procédé dans un appareil HMI ou dans un système d'automatisation
EP1950639A1 (fr) Procédé destiné au fonctionnement d'une installation de processus, installation de processus et produit de programme informatique
DE102021112855A1 (de) Verfahren zur identifizierung einer anormalen geräuschquelle, system zur identifizierung einer anormalen geräuschquelle, vorrichtung zur identifizierung einer anormalen geräuschquelle, benachrichtigungsvorrichtung von einer anormalen geräuschquelle und bordvorrichtung
EP3047341B1 (fr) Système de création informatisée de règles de surveillance et/ou de diagnostic d'une installation technique
DE102015205042A1 (de) Verfahren zur Steuerung einer Audiosignalausgabe für ein Fahrzeug
WO2010118864A1 (fr) Procédé permettant d'obtenir une information concernant l'usure d'un composant d'une machine et procédé de préparation d'un algorithme alternatif
EP2642359A1 (fr) Dispositif de développement et méthode pour créer un programme de calculateur embarqué
DE112017006946B4 (de) Maschinenklangsteuerungsvorrichtung, maschinenklangsteuerungsverfahren und maschinenklangsteuerungsprogramm
EP1960854B1 (fr) Procede et dispositif de diagnostic oriente fonction d'un systeme comportant des composants mis en reseau
DE202021101570U1 (de) System zur Zustandsdarstellung für eine Automatisierungsanlage
WO2022096525A1 (fr) Système de capteur
DE102008060194A1 (de) Verfahren und Kraftfahrzeug für ein Fahrzeugflotten-Qualifikationsmanagement
EP1353529B1 (fr) Auralisation basée sur internet de la déficience auditive
DE102019111558A1 (de) Verfahren und system zum testen von systemen
DE102009055649A1 (de) Verfahren und Vorrichtung zum Betreiben einer Parkhilfeeinrichtung
DE102005042384A1 (de) Entscheidersystem und Entscheidungsverfahren zum Steuern der Wechselwirkung von Komponenten mittels einer Vorrichtungslogik
DE102019006676B3 (de) Verfahren zur Überwachung von Funktionen eines Systems und Überwachungssystems
EP2965157A1 (fr) Procédé et dispositif permettant de faire fonctionner une installation de traitement et/ou de fabrication
DE102015213269A1 (de) Modulares Baukastensystem für eine Steuereinrichtung einer Magnetresonanzeinrichtung und Verfahren zur Herstellung einer Steuereinrichtung einer Magnetresonanzeinrichtung
DE102007042580A1 (de) Verfahren zur Kommunikation zwischen einer natürlichen Person und einem künstlichen Sprachsystem sowie Kommunikationssystem

Legal Events

Date Code Title Description
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

17P Request for examination filed

Effective date: 20120316

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 SE SI SK SM TR

DAX Request for extension of the european patent (deleted)
RAP1 Party data changed (applicant data changed or rights of an application transferred)

Owner name: SIEMENS AKTIENGESELLSCHAFT

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

INTG Intention to grant announced

Effective date: 20140729

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

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20141209