EP4526746A1 - Detektion von anomalien in einem technischen system durch überwachung mit mehreren sensoren - Google Patents
Detektion von anomalien in einem technischen system durch überwachung mit mehreren sensorenInfo
- Publication number
- EP4526746A1 EP4526746A1 EP23723927.2A EP23723927A EP4526746A1 EP 4526746 A1 EP4526746 A1 EP 4526746A1 EP 23723927 A EP23723927 A EP 23723927A EP 4526746 A1 EP4526746 A1 EP 4526746A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- technical system
- sensors
- machine learning
- learning model
- behavior
- 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- Withdrawn
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
- 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
Definitions
- the present invention relates to the sensory monitoring of technical systems for detecting known and unknown anomalies.
- the invention provides a method for detecting anomalies in a technical system whose behavior is monitored by an arrangement of n sensors.
- a parameter KP is determined, which represents a pairwise conditional probability distribution P D (i
- j) describes probabilities that sensor i delivers certain concrete observations.
- KP can be determined as the mean of a distribution of observations from sensor i for all time steps at which the observation from sensor j has the same value as in journal t.
- the parameter can alternatively or in combination also be: any other properties of the pairwise conditional probability distribution P D (i
- j) can also be determined or approximated in any other way, and the parameter KP can then be determined from this.
- a tensor K* of all parameters KP is therefore a “fingerprint” of the behavior of the technical system, which records the inherent correlations between the individual sensor modalities.
- This “fingerprint” K* that is mapped by a trained machine learning model to a classification as to whether the behavior of the technical system is normal or abnormal.
- This classification can take any form. For example, it can be binary or contain one or more real-valued scores related to certain aspects of the business.
- At least two sensors are advantageously selected for measured variables between which the physical configuration of the technical system in the nominal state of this system mediates a physical interaction.
- the one measurement variable can in particular be, for example, a measure of an amount of energy supplied to the technical system or present in it, and the other measurement variable can then be a measure of the existing amount of energy or an energy output by the technical system.
- a warm fluid supplied at one end of the pipeline introduces energy into the pipeline, and when the pipeline is heated by this, it in turn radiates energy.
- an increased motor current of an electrical machine will also manifest itself in an increased amplitude of vibrations of this machine. Since energy is a physical conserved quantity, in many technical systems there are temporal correlations between measured values provided by different sensors. These correlations do not have to be explicitly analyzed and formulated in order to use them to monitor the technical system for normal function. It is sufficient that the correlations simply exist physically during normal operation so that they can be learned by the machine learning model.
- At least two further sensors are selected for further measured variables, between which the physical configuration of the technical system in the nominal state of this system is one excludes physical interaction. For example, pressures in areas or containers that are not connected to one another should not be correlated with one another. However, if such a correlation does exist, it may indicate that there is an undesirable leak between the areas or containers.
- the further sensors can be arranged on different sides of a barrier which prevents the physical interaction between the further measured variables in the nominal state of the technical system.
- the machine learning module can, for example, learn the normal behavior of the technical system and then classify everything that is “different in some way” as an anomaly, even if the anomaly is only in a small portion of the signal from one or more sensors recorded measurement signals.
- This is somewhat analogous to the fact that a burglar alarm system does not trigger an alarm if the legitimate occupant of the house drives a nail into the wall with a hammer, while at the same time it recognizes the working noises caused by manual manipulation of the door lock with unlocking tools as an attempted break-in and triggers an alarm.
- the technical system can in particular be, for example, a vehicle or an industrial plant that processes one or more educts into one or more products through one or more processing steps.
- a vehicle in particular conveys a multitude of correlations through its body, in and on which the sensors are distributed in a comparatively small space, which can be used to detect anomalies.
- correlations are mediated, for example, by material flows of reactants and/or products through the plant.
- Control devices in vehicles, as well as “plant historians” in industrial plants also automatically log a large number of measured values.
- These protocols can be used, for example, to obtain labeled training data for both the normal state and the abnormal state in conjunction with the knowledge that there were or were not anomalies at certain times.
- the machine learning model can be trained in a monitored manner using this labeled training data.
- j) can be determined and/or approximated with the help of training data. How far into the past a machine learning model can look is determined by the architectural parameters chosen, such as the widths of filter kernels in convolution layers.
- a control signal is formed from the classification provided by the machine learning model.
- the technical system is controlled with this control signal.
- the maximum speed can be reduced, the execution of certain risky driving maneuvers (such as overtaking maneuvers) can be prevented, or the vehicle can be brought to a stop on a pre-planned emergency stop trajectory.
- an industrial plant can be switched to a safe mode in which the throughput of the plant is reduced to a minimum. In this safe mode, the system can then also be operated manually, for example if the automatic control fails.
- the machine learning model can be trained with labeled training examples of tensors K*.
- specially labeled training examples for anomalies are often scarce because the technical systems usually work so well that anomalies are rare.
- the invention therefore provides a method for training a machine learning model for use in the method described above, which requires only a few labeled training examples.
- training examples for tensors K* of parameters KP which characterize pairwise conditional probability distributions P D (i
- a distribution of disturbances p is provided which is known to only change a tensor K* in a way that can also happen during normal operation of the technical system.
- An example of such disturbances p is additive, normally distributed noise, which can also be contained in the observations provided by the sensors.
- Further examples include a stochastic zeroing of off-diagonal elements of the tensor K*, a replacement of elements on the level t by elements on the levels t + 1 or t - 1, and/or an interchange of levels t, t' of the tensor K*.
- These disturbances simulate errors that can occur during sensory acquisition and the transmission of measurement data over a network. This allows a mixing of elements on level t with elements at levels t + 1 or t - 1, for example, can be caused by inaccurate time synchronization between sensors. Poor time synchronization or problems in transmitting the measurement data over a network can, for example, lead to levels t, t' being swapped. Sporadic sensor errors can manifest themselves, for example, in missing off-diagonal elements in the tensor K*.
- Contrastive learning is self-supervised learning using positive and negative examples that are known to be similar or dissimilar to each other.
- the modifications and these pairs differ not only in the usual disorders mentioned, but are also variations of two completely different examples. Therefore, the machine learning model should recognize these variations and as dissimilar to each other.
- the machine learning model to be trained is made from the modifications and K*" each processing products and generated. This does not have to be the final output of the machine learning model that shows the classification regarding the normal or abnormal state.
- the machine learning model can include, for example, a feature extractor that extracts features from the tensor K*, and a classification head that maps these features to the desired classification of the behavior of the technical system.
- the feature extractor can in particular, for example, comprise a sequence of several convolution layers that convert their respective input into a dimensionally reduced feature map by applying one or more filter kernels. The processing products and can then be formed by the feature extractor.
- the feature extractor of the machine learning model is trained to process products in the latent space of its output and that go back to positive couples, close to each other place. It is simultaneously trained to process products in this latent space and to negative pairs go back, place far away from each other.
- the processing product can therefore correspond to a point z i in latent space, and that Processing product to the same positive pair can become one Correspond to point Zj in latent space.
- An example cost function that measures whether the points z ; and z, are close to each other, is the NT-Xent-Loss C, normalized temperature-scaled cross entropy): where the function ⁇ measures similarity and ⁇ is a temperature parameter.
- the temperature parameter ⁇ can in particular be varied, for example, according to an “annealing plan” as a function of the number of epochs.
- the machine learning model can therefore complete a large part of its training in a self-monitored manner without having to use labeled training examples.
- the classification head can then be trained in a monitored manner with training examples K* that are labeled with target classifications. Since the classification head only makes up a small portion of the machine learning model, especially in terms of the number of parameters to be optimized, a comparatively small number of labeled training examples is sufficient for this training. In this context, it is also particularly advantageous that the classification head receives as input a processing product that has already been well pre-sorted as a result of the self-monitored training. The classification head does not have to do something that was previously neglected through increased training effort.
- the invention provides yet another method for training a machine learning method for use in the method described above.
- this method uses normal supervised training.
- training examples are provided for tensors K* of parameters that provide pairwise conditional probability characterize distributions P D (i
- These training examples K* refer to normal behavior of the technical system.
- a distribution of disturbances p* is now provided which is known to change a tensor K* in a way that is not to be expected in the normal operation of the technical system.
- An example of such interference is uniformly distributed noise.
- modifications K* are generated.
- the machine learning model is trained in a monitored manner with the training examples K* for normal behavior of the technical system on the one hand and with the modifications K* as training examples for abnormal behavior of the technical system on the other hand.
- the machine learning model can be trained directly on the desired classification task in one step, provided that a suitable distribution of disturbances p* is available for the respective application.
- a suitable distribution of disturbances p* is available for the respective application.
- the contrastive learning approach described above can be used.
- An important advantage of contrastive learning is that it does not rely on modeling the perturbations p*.
- the training examples K* can be augmented into further modifications by applying the disturbances p discussed in connection with contrastive learning, which can then be used as further training examples for normal behavior within the framework of supervised learning. Further measures improving the invention are shown in more detail below together with the description of the preferred exemplary embodiments of the invention using figures
- Figure 1 exemplary embodiment of the method 100 for detecting anomalies in a technical system 1;
- Figure 3 exemplary embodiment of the method 200 for training a machine learning model 2
- Figure 4 exemplary embodiment of the method 300 for training a machine learning model 2.
- Figure 1 is a schematic flow diagram of an exemplary embodiment of the method 100 for detecting anomalies in a technical system 1.
- the behavior of this system 1 is monitored by an arrangement of n sensors.
- At least two sensors can be selected for measured variables between which the physical configuration of the technical system 1 in the nominal state of this system 1 mediates a physical interaction.
- at least two further sensors can then optionally be selected for further measured variables, between which the physical configuration of the technical system 1 can be selected Nominal state of this system 1 excludes a physical interaction.
- step 130 a tensor K* of all parameters is trained by one Machine learning model 2 is mapped to the desired classification 3 as to whether the behavior of the technical system 1 is normal or abnormal.
- a control signal 4 is formed from the classification 3 provided by the machine learning model 2.
- step 150 the technical system 1 is controlled with the control signal 4.
- Figure 2 illustrates the formation of the tensor K* using a simple example with three time-dependent observations x(t), y(t) and z(t). For each point in time t, conditional probabilities can be given, assuming that one of the three values x(t), y(t) and z(t) is given Specify the values of all variables (t), y(t) and z(t). Parameters the distributions of these in pairs conditional probabilities are compiled in a two-dimensional matrix. All such matrices for all times t together form the tensor K*.
- step 210 training examples for tensors K* of parameters which characterize pairwise conditional probability distributions P D (i
- step 220 a distribution of disturbances p is provided which is known to only change a tensor K* in a way that can also happen in normal operation of the technical system.
- step 230 positive pairs of variations and generated by applying two perturbations p 1 and p 2 sampled from the distribution to one and the same training example K*. These modifications therefore only differ in terms of disturbances p, which also occur with normal behavior of the technical system 1 and the sensory data acquisition.
- step 240 negative pairs of variations generated by applying two perturbations p 1 and p 2 sampled from the distribution to two different training examples K*' and K*". These modifications therefore differ in more ways than just "normal" perturbations p.
- step 250 the machine learning model (2) to be trained is selected from the modifications each processing products and generated.
- the machine learning model 2 may include a feature extractor
- step 260 parameters 2a, which characterize the behavior of the machine learning model 2, are optimized with the aim of maximum similarity between and at the same time minimal similarity between and These parameters can in particular be the parameters 21 a of the feature extractor 21.
- the fully optimized state of the parameters 2a, 21a is designated by the reference number 2a*, 21a*.
- step 270 the classification head 22 is trained in a monitored manner with training examples K* that are labeled with target classifications. This means that the parameters 22a, which characterize the behavior of the classification head 22, are optimized with the aim of mapping the training examples K* from the machine learning model 2 to the respective target classifications.
- the fully optimized state of these parameters is designated by reference number 22a*.
- FIG. 4 is a schematic flow diagram of an exemplary embodiment of the method 300 for training a machine learning model 2 for use in the method 100 described in connection with FIG. 1. In contrast to the method 200, this method is based on supervised training.
- step 310 training examples for tensors K* of parameters which characterize pairwise conditional probability distributions P D (i
- step 320 a distribution of perturbations p* is provided that are known to modify a tensor K* in a way that is not expected in normal operation of the technical system.
- step 330 modifications K* are generated by applying perturbations p* sampled from the distribution to training examples K*.
- the machine learning model 2 is created with the training examples K* for normal behavior of the technical system 1 on the one hand and with the modifications * As training examples for an abnormal behavior of the technical system 1, on the other hand, trained in a monitored manner.
- the parameters 2a which characterize the behavior of the machine learning model 2, are optimized directly with the aim of ensuring that the training examples K* are classified as normal and the modifications are classified as normal classification as abnormal.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
Description
Claims
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102022204863.6A DE102022204863B4 (de) | 2022-05-17 | 2022-05-17 | Detektion von Anomalien in einem technischen System durch Überwachung mit mehreren Sensoren |
| PCT/EP2023/061648 WO2023222381A1 (de) | 2022-05-17 | 2023-05-03 | Detektion von anomalien in einem technischen system durch überwachung mit mehreren sensoren |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP4526746A1 true EP4526746A1 (de) | 2025-03-26 |
Family
ID=86382810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP23723927.2A Withdrawn EP4526746A1 (de) | 2022-05-17 | 2023-05-03 | Detektion von anomalien in einem technischen system durch überwachung mit mehreren sensoren |
Country Status (5)
| Country | Link |
|---|---|
| EP (1) | EP4526746A1 (de) |
| JP (1) | JP2025516803A (de) |
| CN (1) | CN119213380A (de) |
| DE (1) | DE102022204863B4 (de) |
| WO (1) | WO2023222381A1 (de) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010092203A (ja) * | 2008-10-07 | 2010-04-22 | Nec Corp | 異常検出装置および異常検出方法 |
| JP6404889B2 (ja) * | 2015-11-13 | 2018-10-17 | タタ コンサルタンシー サービシズ リミテッドTATA Consultancy Services Limited | マルチセンサビジュアルアナリティクスのためのプロセッサ実装方法、マルチセンサデータを要約するシステム、及びマルチセンサビジュアルアナリティクスのための方法を実行するためのコンピュータプログラムを具現化した非一時的なコンピュータ可読媒体 |
| JP7040851B2 (ja) * | 2018-03-09 | 2022-03-23 | 株式会社インテック | 異常検知装置、異常検知方法及び異常検知プログラム |
| US10754310B2 (en) * | 2018-10-18 | 2020-08-25 | International Business Machines Corporation | Incorporating change diagnosis using probabilistic tensor regression model for improving processing of materials |
| US12031733B2 (en) | 2019-12-17 | 2024-07-09 | Tignis, Inc. | Method for physical system anomaly detection |
| JP7222939B2 (ja) * | 2020-02-03 | 2023-02-15 | 株式会社日立製作所 | 時系列パターンの説明情報生成装置 |
| US11175973B1 (en) | 2020-05-11 | 2021-11-16 | International Business Machines Corporation | Prediction of performance degradation with non-linear characteristics |
| JP2021192155A (ja) * | 2020-06-05 | 2021-12-16 | 富士通株式会社 | 異常検知支援プログラム、異常検知支援方法および異常検知支援システム |
| US12025528B2 (en) | 2020-07-16 | 2024-07-02 | INDIAN INSTITUTE OF TECHNOLOGY MADRAS (IIT Madras) | Device and method to predict the onset of oscillatory instabilities in systems with turbulent flow |
-
2022
- 2022-05-17 DE DE102022204863.6A patent/DE102022204863B4/de active Active
-
2023
- 2023-05-03 WO PCT/EP2023/061648 patent/WO2023222381A1/de not_active Ceased
- 2023-05-03 JP JP2024568441A patent/JP2025516803A/ja active Pending
- 2023-05-03 CN CN202380040461.9A patent/CN119213380A/zh active Pending
- 2023-05-03 EP EP23723927.2A patent/EP4526746A1/de not_active Withdrawn
Also Published As
| Publication number | Publication date |
|---|---|
| CN119213380A (zh) | 2024-12-27 |
| DE102022204863A1 (de) | 2023-11-23 |
| WO2023222381A1 (de) | 2023-11-23 |
| DE102022204863B4 (de) | 2025-02-06 |
| JP2025516803A (ja) | 2025-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE19743600B4 (de) | Verfahren zur Überwachung eines zyklischen Produktionsprozesses | |
| DE102017000287B4 (de) | Zellensteuerung und produktionssystem zum verwalten der arbeitssituation einer vielzahl von fertigungsmaschinen in einer fertigungszelle | |
| EP3077878B1 (de) | Computer-implementiertes verfahren und system zur automatischen überwachung und statusermittlung ganzer prozessabschnitte in einer process unit | |
| EP3282399B1 (de) | Verfahren zur verbesserten erkennung von prozessanomalien einer technischen anlage sowie entsprechendes diagnosesystem | |
| EP3853778B1 (de) | Verfahren und vorrichtung zum betreiben eines steuerungssystems | |
| DE102018221002A1 (de) | Steuereinrichtung zur Steuerung einer Fertigungsanlage sowie Fertigungsanlage und Verfahren | |
| EP3825796A1 (de) | Verfahren und vorrichtung zum ki-basierten betreiben eines automatisierungssystems | |
| DE102021204040A1 (de) | Verfahren, Vorrichtung und Computerprogramm zur Erstellung von Trainingsdaten im Fahrzeug | |
| DE102018129563A1 (de) | Verfahren zum Bestimmen des Steuermodus eines Lenkrads | |
| EP3625629B1 (de) | Vorrichtung und verfahren zur bestimmung des zustands einer spindel einer werkzeugmaschine | |
| WO2021089591A1 (de) | Verfahren zum trainieren eines künstlichen neuronalen netzes, computerprogramm, speichermedium, vorrichtung, künstliches neuronales netz und anwendung des künstlichen neuronalen netzes | |
| DE102019208922A1 (de) | Verfahren und Vorrichtung zum Kontrollieren eines Produktionsprozesses | |
| DE69811088T2 (de) | Klassifizieranlage und klassifizierverfahren unter verwendung einer kombination von warscheinlichkeitsverfahren und neuronalen netzwerken | |
| EP4673875A1 (de) | Verfahren und vorrichtung zur erkennung einer anomalie im verhalten eines dynamischen systems | |
| DE102008032885A1 (de) | Verfahren und Vorrichtung zur Überprüfung und Feststellung von Zuständen eines Sensors | |
| DE102022204863B4 (de) | Detektion von Anomalien in einem technischen System durch Überwachung mit mehreren Sensoren | |
| DE102022110130A1 (de) | Verfahren zum Überwachen eines Betriebs einer autonomen landwirtschaftlichen Arbeitsmaschine | |
| DE19612465C2 (de) | Automatisches Optimieren von Objekt-Erkennungssystemen | |
| EP3629252A1 (de) | Verfahren und vorrichtung zum betreiben eines steuerungssystems | |
| EP3816673A1 (de) | Verfahren zum betreiben eines metalldetektors | |
| DE112023005124T5 (de) | Verfahren und system zur anomalie-erfassung in einem betrieblichen asset und verfahren zum reparieren eines betrieblichen assets | |
| DE102018216079A1 (de) | Verfahren und Vorrichtung zum Betreiben eines Steuerungssystems | |
| EP3701428B1 (de) | Verfahren und vorrichtung zum verbessern der robustheit eines maschinellen lernsystems | |
| EP3483513B1 (de) | Verfahren zum betreiben einer heizungsanlage und heizungsanlage | |
| DE102021207493A1 (de) | Verfahren zur Unterstützung eines Betriebs eines Fahrzeuges mit einer Sensoreinheit, Computerprogrammprodukt sowie System |
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: 20241217 |
|
| 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 ME 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: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
| 18D | Application deemed to be withdrawn |
Effective date: 20251014 |