EP1134712B1 - Method for the processing of the signal in a danger detector, and detector with means for the implementation of such method - Google Patents
Method for the processing of the signal in a danger detector, and detector with means for the implementation of such method Download PDFInfo
- Publication number
- EP1134712B1 EP1134712B1 EP00105438A EP00105438A EP1134712B1 EP 1134712 B1 EP1134712 B1 EP 1134712B1 EP 00105438 A EP00105438 A EP 00105438A EP 00105438 A EP00105438 A EP 00105438A EP 1134712 B1 EP1134712 B1 EP 1134712B1
- Authority
- EP
- European Patent Office
- Prior art keywords
- signals
- sensor
- analysis
- wavelets
- detector
- 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.)
- Expired - Lifetime
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/20—Calibration, including self-calibrating arrangements
- G08B29/24—Self-calibration, e.g. compensating for environmental drift or ageing of components
- G08B29/26—Self-calibration, e.g. compensating for environmental drift or ageing of components by updating and storing reference thresholds
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B29/00—Checking or monitoring of signalling or alarm systems; Prevention or correction of operating errors, e.g. preventing unauthorised operation
- G08B29/18—Prevention or correction of operating errors
- G08B29/185—Signal analysis techniques for reducing or preventing false alarms or for enhancing the reliability of the system
- G08B29/186—Fuzzy logic; neural networks
Definitions
- the present invention relates to a method for processing the signals of a hazard detector, which has at least one sensor for monitoring risk parameters and the at least one sensor associated evaluation, wherein the monitoring of the hazard parameters by comparing the signals of at least one sensor with predetermined parameters by means.
- the hazard detector can be, for example, a smoke detector, a flame detector, a passive infrared detector, a microwave detector, a dual detector (passive infrared + microwave sensor), or a sound detector.
- the US 6011464 describes how, in a method for frequency analysis of a signal of a hazard detector, a wavelet transformation is combined with a fuzzy logic evaluation.
- the original signal is fed to a multi-level filter cascade of high / low pass filter pairs.
- a membership function is generated from results of the high pass filter, wavelet coefficients and values of the original signal.
- These functions are normalized and are used in this form for further evaluation according to fuzzy logic rules.
- the method is particularly suitable for the evaluation of the output signal of hazard detectors such as flame detectors, noise detectors and the like.
- the wavelet transformation and fuzzy logic evaluation is performed by a small number of lines of processor code, whereby the evaluation can be realized with a low-cost processor and accelerated at the same or increased accuracy.
- fuzzy logic is well known. With regard to the evaluation of the signals from hazard detectors, it should be emphasized that signal values are assigned to so-called fuzzy sets, or fuzzy sets, according to a membership function, the value of the membership function, or the degree of belonging to a fuzzy set, being between zero and one. Importantly, the membership function is normalizable, i. the sum of all values of the membership function is equal to one, whereby the fuzzy logic evaluation allows a clear interpretation of the signal.
- the inventive method is characterized in that the signals of the at least one sensor are analyzed as to whether they occur more frequently or regularly, and that increasingly or regularly occurring signals are classified as interference signals.
- a first preferred development of the method according to the invention is characterized in that the classification of signals as interference signals triggers a corresponding adaptation of the parameters.
- the method according to the invention is based on the new knowledge that, for example, a fire detector never "sees" more than a few real fires between two revisions or two power failures, and that increasingly or regularly occurring signals indicate the presence of sources of interference.
- the interference caused by the sources of interference are recognized as such and the detector parameters are adjusted accordingly.
- the detectors operated by the method according to the invention are capable of learning and can better distinguish between real danger signals and interference signals.
- a second preferred embodiment of the method according to the invention is characterized in that the occurrence of interference signals before the adaptation of the parameters, the result of the analysis of the signals of the at least one sensor is checked for its validity, and that the adjustment of the parameters in dependence on the result of this validity check ,
- a third preferred development is characterized in that the validity check is carried out by means of methods based on multiple resolution.
- a fourth preferred development of the method according to the invention is characterized in that wavelets, preferably “biorthogonal” or “second generation” wavelets or “lifting scheme", are used for the validation.
- the wavelet transformation is a transformation or mapping of a signal from the time domain into the frequency domain (see, for example, " The Fast Wavelet Transform "by MacA Cody in Dr. Dobb's Journal, April 1992 ); it is basically similar to Fourier transform and Fast Fourier transform. It differs from these, however, by the basic function of the transformation, after which the signal is developed.
- a Fourier transform uses a sine and cosine function that is sharply localized in the frequency domain and indefinite in the time domain.
- a so-called wavelet or wave packet is used. There are various types of these, such as a Gaussian, spline or hair wavelet, which can be arbitrarily shifted in the time domain by two parameters and stretched or compressed in the frequency domain. More recently, new wavelet methods have been introduced, often referred to as "second generation". Such wavelets are constructed with the so-called “lifting-scheme” (Sweldens).
- the result is a series of approximations of the original signal, each of which has a coarser resolution than the previous one.
- the number of operations required for the transformation is in each case proportional to the length of the original signal, while in the Fourier transformation this number is disproportionate to the signal length.
- the fast wavelet transform can also be performed inversely by restoring the original signal from the approximated values and coefficients for reconstruction.
- the algorithm for the decomposition and reconstruction of the signal and a table of the coefficients of decomposition and reconstruction are exemplified for a spline wavelet in " An Introduction to Wavelets "by Charles K. Chui (Academic Press, San Diego, 1992 ). See also on this topic “ A Wavelet Tour of Signal Processing "by S. Mallat (Academic Press, 1998 ).
- a further preferred development of the method according to the invention is characterized in that the expected values for the approximation or the approximation and detail coefficients of the wavelets are determined and compared at different resolutions.
- the determination of said coefficients preferably takes place in an estimator or by means of a neural network.
- the invention further relates to a hazard detector with means for carrying out said method, with at least one sensor for a hazard parameter and with a microprocessor-containing evaluation for the evaluation and analysis of the signals of the at least one sensor.
- the danger detector according to the invention is characterized in that the microprocessor contains a software program with a multi-resolution learning algorithm for the analysis of the signals of the at least one sensor.
- a first preferred embodiment of the inventive hazard alarm is characterized in that the learning algorithm on the one hand, an analysis of said sensor signals on their repeated or regular occurrence and on the other hand, a validity check of the result of the analysis, and that the learning algorithm for validating wavelets, preferably "biorthogonal" or "second generation” wavelets.
- a second preferred embodiment of the inventive hazard detector is characterized in that the learning algorithm uses neuro-fuzzy methods.
- ⁇ m, n wavelet scaling functions, ⁇ m, n approximation coefficients and y k denote the k-th input point of the neural network
- ⁇ m, n the dual function (definition see S. Mallat) of ⁇ m, n is.
- the inventive method the signals of a hazard detector are processed so that typical noise signals are detected and characterized. If in the present description is mainly mentioned by Brandmeldem, this does not mean that the inventive method is limited to fire detectors. The method is rather suitable for hazard detectors of all kinds, especially for burglar and motion detectors.
- the mentioned interference signals are analyzed with a simple and reliable method.
- An important feature of this method is that it not only detects and characterizes the interfering signals, but verifies the result of the analysis.
- wavelet theory and multiresolution analysis is used.
- the parameters of the detector or the algorithms are adjusted. This means, for example, that the sensitivity is reduced or that certain automatic switching between different parameter sets is locked.
- a fire detector which has a scattered light optical sensor, a temperature sensor and a fire gas sensor.
- the evaluation electronics of the detector contains a fuzzy controller in which the signals of the individual sensors and a diagnosis of the respective type of fire are linked. For each type of fire, a special application-specific algorithm is provided and can be selected based on the diagnosis.
- the detector contains various parameter sets for personal protection and property protection, between which an online switchover normally takes place. If interference signals are now diagnosed in the case of the temperature and / or the fire gas sensor, switching between these parameter sets is interlocked.
- Fig. 1 a diagram of such a multiple resolution is shown.
- Line a shows the course of a signal whose amplitude moves in the areas of small, medium and large.
- the membership functions c1 are "fairly small", c2 "medium” and c3 "rather large”.
- These membership functions form a multiple resolution, meaning that each membership function can be decomposed into a sum of membership functions of a higher resolution level.
- the triangular spline function c2 can be decomposed into the sum of the translated triangular functions of the higher level of line c.
- a i linguistic expressions x is the linguistic input variable and y is the output variable.
- the value of the input linguistic variables can be sharp or fuzzy. For example, if x i is a linguistic variable for the temperature, then x may be a sharp number such as "30 (° C)" or a fuzzy size such as "about 25 (° C)", with "about 25” itself Fuzzy set is.
- the output y is a linear sum of translated and extended spline functions.
- the Tagaki-Sugeno model is equivalent to a multi-resolution spline model.
- wavelet techniques can be used here.
- Fig. 2 shows a block diagram of a equipped with a Neurofuzzy learning algorithm hazard detector.
- the detector designated by the reference M is, for example, a fire detector and has three sensors 2 to 4 for fire parameters.
- an optical sensor 2 for scattered light or transmitted light measurement, a temperature sensor 3 and a fire gas, such as a CO sensor 4 is provided.
- the output signals of the sensors 2 to 4 are fed to a processing stage 1, which has suitable means for processing the signals, such as amplifiers, and passes from this to a microprocessor or microcontroller, hereinafter referred to as ⁇ P 6.
- the sensor signals are compared with each other as well as individually with specific parameter sets for the individual fire parameters.
- the number of sensors is not limited to three. Thus, only a single sensor can be provided, in which case various properties, for example the signal gradient or the signal fluctuation, are extracted and examined from the signal of the one sensor.
- a neuro-fuzzy network 7 and a validity check (validation) 8 are integrated into the ⁇ P 6 by software. If the signal resulting from the neuro-fuzzy network 7 is evaluated as an alarm signal, a corresponding alarm signal is sent to an alarm output device 9 or an alarm center. If the validation 8 shows that interference signals occur repeatedly or regularly, then the parameter sets stored in ⁇ P 6 are corrected accordingly.
- the scaling functions are such that ⁇ ( ⁇ m, n (x) ⁇ form a multiple resolution
- Each neural network uses activation functions of a given resolution
- the m th neural network optimizes the coefficients ⁇ m, n with f m (x) , the output of the mth neural network.
- f m x ⁇ ⁇ c ⁇ m . n ⁇ ⁇ m . n x ⁇ over all n
- the two equations (5) and (6) form the main algorithm of the neuro-fuzzy network.
- the values of the various neural networks are cross checked (validated), including a property of the wavelet decomposition, namely that the approximation coefficients ⁇ m, n of a level m from the approximation and wavelet coefficients of the level m-1 can be obtained by using the reconstruction or decomposition algorithm.
- ⁇ m, n (x) is a second-order spline function and ⁇ m, n (x) is an interpolation function.
- ⁇ m, n (x) is a spline function and ⁇ m, n (x) is the dual function of ⁇ m, n (x).
- ⁇ m , n (x) ⁇ m, n (x), where ⁇ m, n (x) is the hair function.
- FIGS. 3a and 3b Two variants of a neuro-fuzzy network 7 and the associated validation stage 8 are shown.
- the input signal is approximated in different resolution levels as a weighted sum of wavelets ⁇ m, n and scaling functions ⁇ m, n with a given resolution.
- the validation stage 8 compares the approximation coefficients ⁇ m, n with the approximation and detail coefficients of the wavelets at the level of the next lower resolution level.
- P and q denote wavelet reconstruction filter coefficients.
- the input signal is approximated in different resolution levels as a weighted sum of scaling functions ⁇ m, n with a given resolution.
- the validation stage 8 compares the approximation coefficients ⁇ m, n with the approximation coefficients at the level of the next lower resolution stage. With g, wavelet are called low-pass decomposition coefficients.
- Wavelet spline estimators are used to adaptively determine the appropriate resolution to locally describe an underlying hypersurface in an online learning process.
- Nadaraya-Watson estimators have two interesting properties, they are estimators of the local mean square deviation and it can be shown that in the case of a random design they are so-called Bayesian estimators of (x k , y k ), where (x k , y k ) are iid copies of a continuous random variable (X, Y).
- the available data are indicated by a small square, their projection onto dual spline functions with a small circle and the estimation on a regular grid with a cross.
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Automation & Control Theory (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Alarm Systems (AREA)
- Fire Alarms (AREA)
- Geophysics And Detection Of Objects (AREA)
- Radar Systems Or Details Thereof (AREA)
- Indication And Recording Devices For Special Purposes And Tariff Metering Devices (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
- Complex Calculations (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
- Fire-Detection Mechanisms (AREA)
- Constituent Portions Of Griding Lathes, Driving, Sensing And Control (AREA)
- Pinball Game Machines (AREA)
Abstract
Description
Die vorliegende Erfindung betrifft ein Verfahren zur Verarbeitung der Signale eines Gefahrenmelders, welcher mindestens einen Sensor zur Überwachung von Gefahrenkenngrössen und eine dem mindestens einen Sensor zugeordnete Auswerteelektronik aufweist, wobei die Überwachung der Gefahrenkenngrössen durch Vergleich der Signale des mindestens einen Sensors mit vorgegebenen Parametern mittels erfolgt. Der Gefahrenmelder kann beispielsweise ein Rauchmelder, ein Flammenmelder, ein Passiv-Infrarotmelder, ein Mikrowellenmelder, ein Dualmelder (Passiv-Infrarot- + Mikrowellensensor), oder ein Geräuschmelder sein.The present invention relates to a method for processing the signals of a hazard detector, which has at least one sensor for monitoring risk parameters and the at least one sensor associated evaluation, wherein the monitoring of the hazard parameters by comparing the signals of at least one sensor with predetermined parameters by means. The hazard detector can be, for example, a smoke detector, a flame detector, a passive infrared detector, a microwave detector, a dual detector (passive infrared + microwave sensor), or a sound detector.
Die
Heutige Gefahrenmelder haben bezüglich der Detektion von Gefahrenkenngrössen eine solche Empfindlichkeit erreicht, dass das Hauptproblem nicht mehr darin besteht, eine Gefahrenkenngrösse möglichst frühzeitig zu detektieren, sondern darin, Störsignale von echten Gefahrensignalen sicher zu unterscheiden und dadurch Fehlalarme zu vermeiden. Die Unterscheidung zwischen Gefahren- und Störsignalen erfolgt dabei im wesentlichen durch die Verwendung mehrerer verschiedener Sensoren und Korrelation von deren Signalen oder durch die Analyse verschiedener Merkmale der Signale eines einzigen Sensors und/oder durch eine entsprechende Signalverarbeitung, wobei in jüngster Zeit durch die Verwendung von Fuzzy-Logik schon eine wesentliche Verbesserung der Störsicherheit erreicht worden ist.Today's hazard detectors have reached such a sensitivity with respect to the detection of hazard parameters that the main problem is no longer to detect a hazard parameter as early as possible, but to reliably distinguish interference signals from true danger signals and thereby avoid false alarms. The distinction between danger and interference signals is made essentially by the use of several different sensors and correlation of their signals or by the analysis various features of the signals of a single sensor and / or by a corresponding signal processing, which has already been achieved by the use of fuzzy logic already a significant improvement in noise immunity.
Die Fuzzy-Logik ist allgemein bekannt. In bezug auf die Auswertung der Signale von Gefahrenmeldern ist hervorzuheben, dass Signalwerte sogenannten Fuzzy sets, oder unscharfen Mengen, gemäss einer Zugehörigkeitsfunktion zugeteilt werden, wobei der Wert der Zugehörigkeitsfunktion, oder der Grad der Zugehörigkeit zu einer unscharfen Menge, zwischen null und eins beträgt. Wichtig dabei ist, dass die Zugehörigkeitsfunktion normalisierbar sind, d.h. die Summe aller Werte der Zugehörigkeitsfunktion gleich eins ist, wodurch die Fuzzy-Logik-Auswertung eine eindeutige Interpretation des Signals erlaubt.The fuzzy logic is well known. With regard to the evaluation of the signals from hazard detectors, it should be emphasized that signal values are assigned to so-called fuzzy sets, or fuzzy sets, according to a membership function, the value of the membership function, or the degree of belonging to a fuzzy set, being between zero and one. Importantly, the membership function is normalizable, i. the sum of all values of the membership function is equal to one, whereby the fuzzy logic evaluation allows a clear interpretation of the signal.
Durch die vorliegende Erfindung soll nun ein Verfahren der eingangs genannten Art zur Verarbeitung der Signale eines Gefahrenmelders angegeben werden, das bezüglich Störunempfindlichkeit und Störsicherheit weiter verbessert ist.By the present invention, a method of the type mentioned above for processing the signals of a hazard detector will now be given, which is further improved in terms of noise immunity and noise immunity.
Das erfindungsgemässe Verfahren ist dadurch gekennzeichnet, dass die Signale des mindestens einen Sensors daraufhin analysiert werden, ob sie vermehrt oder regelmässig auftreten, und dass vermehrt oder regelmässig auftretende Signale als Störsignale klassiert werden.The inventive method is characterized in that the signals of the at least one sensor are analyzed as to whether they occur more frequently or regularly, and that increasingly or regularly occurring signals are classified as interference signals.
Eine erste bevorzugte Weiterbildung des erfindungsgemässen Verfahrens ist dadurch gekennzeichnet, dass die Klassierung von Signalen als Störsignale eine entsprechende Anpassung der Parameter auslöst.A first preferred development of the method according to the invention is characterized in that the classification of signals as interference signals triggers a corresponding adaptation of the parameters.
Das erfindungsgemässe Verfahren beruht auf der neuen Erkenntnis, dass beispielsweise ein Brandmelder zwischen zwei Revisionen oder zwei Stromausfällen nie mehr als einige wenige echte Brände "sieht", und dass vermehrt oder regelmässig auftretende Signale auf das Vorhandensein von Störquellen hindeuten. Die durch die Störquellen verursachten Störsignale werden als solche erkannt und die Melderparameter werden entsprechend angepasst. Auf diese Weise sind die nach dem erfindungsgemässen Verfahren betriebenen Melder lernfähig und können zwischen echten Gefahrensignalen und Störsignalen besser unterscheiden.The method according to the invention is based on the new knowledge that, for example, a fire detector never "sees" more than a few real fires between two revisions or two power failures, and that increasingly or regularly occurring signals indicate the presence of sources of interference. The interference caused by the sources of interference are recognized as such and the detector parameters are adjusted accordingly. In this way, the detectors operated by the method according to the invention are capable of learning and can better distinguish between real danger signals and interference signals.
Eine zweite bevorzugte Weiterbildung des erfindungsgemässen Verfahrens ist dadurch gekennzeichnet, dass beim Auftreten von Störsignalen vor der Anpassung der Parameter das Ergebnis der Analyse der Signale des mindestens einen Sensors auf seine Gültigkeit überprüft wird, und dass die Anpassung der Parameter in Abhängigkeit vom Ergebnis dieser Gültigkeitsprüfung erfolgt.A second preferred embodiment of the method according to the invention is characterized in that the occurrence of interference signals before the adaptation of the parameters, the result of the analysis of the signals of the at least one sensor is checked for its validity, and that the adjustment of the parameters in dependence on the result of this validity check ,
Eine dritte bevorzugte Weiterbildung ist dadurch gekennzeichnet, dass die Gültigkeitsprüfung mittels Methoden erfolgt, welche auf Mehrfachauflösung beruhen.A third preferred development is characterized in that the validity check is carried out by means of methods based on multiple resolution.
Eine vierte bevorzugte Weiterbildung des erfindungsgemässen Verfahrens ist dadurch gekennzeichnet, dass für die Gültigkeitsprüfung Wavelets, vorzugsweise "biorthogonal" oder "second generation" wavelets oder "lifting scheme" verwendet werden.A fourth preferred development of the method according to the invention is characterized in that wavelets, preferably "biorthogonal" or "second generation" wavelets or "lifting scheme", are used for the validation.
Die Wavelet-Transformation ist eine Transformation oder Abbildung eines Signals vom Zeitbereich in den Frequenzbereich (siehe dazu beispielsweise "
Es resultiert eine Reihe von Approximationen des ursprünglichen Signals, wovon jede eine gröbere Auflösung besitzt als die vorhergehende. Die Anzahl Operationen, die für die Transformation erforderlich sind, ist jeweils proportional zur Länge des ursprünglichen Signals, während bei der Fourier-Transformation diese Anzahl überproportional zur Signallänge ist. Die schnelle Wavelet-Transformation kann auch invers durchgeführt werden, indem das ursprüngliche Signal aus den approximierten Werten und Koeffizienten für die Rekonstruktion wiederhergestellt wird. Der Algorithmus für die Zerlegung und Rekonstruktion des Signals und eine Tabelle der Koeffizienten der Zerlegung und Rekonstruktion sind am Beispiel für ein Spline Wavelet in "
Eine weitere bevorzugte Weiterbildung des erfindungsgemässen Verfahrens ist dadurch gekennzeichnet, dass die Erwartungswerte für die Approximations- oder die Approximations- und Detailkoeffizienten der Wavelets bestimmt und bei verschiedenen Auflösungen verglichen werden. Vorzugsweise erfolgt die Bestimmung der genannten Koeffizienten in einem Schätzer oder mittels eines neuronalen Netzes.A further preferred development of the method according to the invention is characterized in that the expected values for the approximation or the approximation and detail coefficients of the wavelets are determined and compared at different resolutions. The determination of said coefficients preferably takes place in an estimator or by means of a neural network.
Die Erfindung betrifft weiter einen Gefahrenmelder mit Mitteln zur Durchführung des genannten Verfahrens, mit mindestens einem Sensor für eine Gefahrenkenngrösse und mit einer einen Mikroprozessor enthaltenden Auswerteelektronik zur Auswertung und Analyse der Signale des mindestens einen Sensors.The invention further relates to a hazard detector with means for carrying out said method, with at least one sensor for a hazard parameter and with a microprocessor-containing evaluation for the evaluation and analysis of the signals of the at least one sensor.
Der erfindungsgemässe Gefahrenmelder ist dadurch gekennzeichnet, dass der Mikroprozessor ein Software-Programm mit einem auf Mehrfachauflösung beruhenden Lernalgorithmus für die Analyse der Signale des mindestens einen Sensors enthält.The danger detector according to the invention is characterized in that the microprocessor contains a software program with a multi-resolution learning algorithm for the analysis of the signals of the at least one sensor.
Eine erste bevorzugte Ausführungsform des erfindungsgemässen Gefahrenmelders ist dadurch gekennzeichnet, dass durch den Lernalgorithmus einerseits eine Analyse der genannten Sensorsignale auf deren wiederholtes oder regelmässiges Auftreten und andererseits eine Gültigkeitsprüfung des Ergebnisses der Analyse erfolgt, und dass der Lernalgorithmus für die Gültigkeitsprüfung Wavelets, vorzugsweise "biorthogonal" oder "second generation" wavelets, verwendet.A first preferred embodiment of the inventive hazard alarm is characterized in that the learning algorithm on the one hand, an analysis of said sensor signals on their repeated or regular occurrence and on the other hand, a validity check of the result of the analysis, and that the learning algorithm for validating wavelets, preferably "biorthogonal" or "second generation" wavelets.
Eine zweite bevorzugte Ausführungsform des erfindungsgemässen Gefahrenmelders ist dadurch gekennzeichnet, dass der Lernalgorithmus Neuro-Fuzzy-Methoden verwendet.A second preferred embodiment of the inventive hazard detector is characterized in that the learning algorithm uses neuro-fuzzy methods.
Eine dritte bevorzugte Ausführungsform des erfindungsgemässen Gefahrenmelders ist dadurch gekennzeichnet, dass der Lernalgorithmus die beiden Gleichungen
Im folgenden wird die Erfindung anhand von Ausführungsbeispielen und der Zeichnungen näher erläutert; es zeigt:
- Fig. 1
- ein Diagramm zur Funktionserläuterung,
- Fig. 2
- ein Blockschema eines mit Mitteln zur Durchführung des erfindungsgemässen Verfahrens ausgerüsteten Gefahrenmelders,
- Fig. 3a, 3b
- zwei Varianten eines Details des Gefahrenmelders von
Fig. 2 ; und - Fig. 4
- eine weitere Variante eines Details des Gefahrenmelders von
Fig. 3 .
- Fig. 1
- a diagram to explain the function,
- Fig. 2
- 1 is a block diagram of a hazard detector equipped with means for carrying out the method according to the invention;
- Fig. 3a, 3b
- two variants of a detail of the danger detector of
Fig. 2 ; and - Fig. 4
- another variant of a detail of the hazard detector of
Fig. 3 ,
Durch das erfindungsgemässe Verfahren werden die Signale eines Gefahrenmelders so verarbeitet, dass typische Störsignale erfasst und charakterisiert werden. Wenn in der vorliegenden Beschreibung vorwiegend von Brandmeldem die Rede ist, bedeutet das nicht, dass das erfindungsgemässe Verfahren auf Brandmelder beschränkt ist. Das Verfahren ist vielmehr für Gefahrenmelder aller Art geeignet, insbesondere auch für Einbruch- und Bewegungsmelder.The inventive method, the signals of a hazard detector are processed so that typical noise signals are detected and characterized. If in the present description is mainly mentioned by Brandmeldem, this does not mean that the inventive method is limited to fire detectors. The method is rather suitable for hazard detectors of all kinds, especially for burglar and motion detectors.
Die erwähnten Störsignale werden mit einer einfachen und zuverlässigen Methode analysiert. Ein wichtiges Merkmal dieser Methode besteht darin, dass die Störsignale nicht nur erfasst und charakterisiert werden, sondern dass das Ergebnis der Analyse überprüft wird. Dazu wird Wavelet-Theorie und Mehrfachauflösungs-Analyse (multiresolution analysis) verwendet. Je nach dem Ergebnis der Überprüfung werden die Parameter des Melders oder die Algorithmen angepasst. Das bedeutet, dass bei-spielsweise die Empfindlichkeit verringert oder dass gewisse automatische Umschaltungen zwischen verschiedenen Parametersätzen verriegelt werden.The mentioned interference signals are analyzed with a simple and reliable method. An important feature of this method is that it not only detects and characterizes the interfering signals, but verifies the result of the analysis. For this purpose wavelet theory and multiresolution analysis is used. Depending on the result of the check, the parameters of the detector or the algorithms are adjusted. This means, for example, that the sensitivity is reduced or that certain automatic switching between different parameter sets is locked.
Letzteres sei an einem Beispiel erläutert: In der
Bei der Verwendung von Fuzzy-Logik besteht eines der zu lösenden Probleme in der Übersetzung des in einer Datenbank gespeicherten Wissens in linguistisch interpretierbare Fuzzy-Regeln. Zu diesem Zweck entwickelte Neurofuzzy-Methoden vermochten nicht zu überzeugen, weil sie teilweise nur sehr schwierig interpretierbare Fuzzy-Regeln liefern. Eine Möglichkeit zur Gewinnung interpretierbarer Fuzzy-Regeln bieten hingegen sogenannte Mehrfachauflösungs-Techniken. Deren Idee besteht darin, ein Wörterbuch von Zugehörigkeitsfunktionen zu verwenden, welche eine Mehrfachauflösung bilden, und zu bestimmen, welches die für die Beschreibung einer Steuerfläche geeigneten Zugehörigkeitsfunktionen sind.When using fuzzy logic, one of the problems to be solved in translating the knowledge stored in a database into linguistically interpretable fuzzy rules. Neurofuzzy methods developed for this purpose were not convincing because they sometimes provide very difficult to interpret fuzzy rules. One way to However, obtaining interpretable fuzzy rules offers so-called multi-resolution techniques. Their idea is to use a dictionary of membership functions which form a multi-resolution and to determine which are the membership functions suitable for the description of a control surface.
In
Im Tagaki-Sugeno Modell werden die Fuzzy Regeln nach der Gleichung
Für einen scharfen Eingangswert ist der Ausgangswert des Fuzzy-Systems gegeben durch:
Wenn Spline-Funktionen Nk genommen werden, beispielsweise als Zugehörigkeitsfunktion µAi(x̂) = Nk [2m(x̂-n)], dann ist das System von Gleichung (3) äquivalent mit
In diesem speziellen Fall ist der Ausgang y eine lineare Summe von übersetzten und ausgedehnten Splinefunktionen. Und das bedeutet, dass unter Gleichung (4) das Tagaki-Sugeno Modell einem Mehrfachauflösungs-Spline Modell äquivalent ist. Und daraus folgt, dass hier Wavelet-Techniken angewendet werden können.In this particular case, the output y is a linear sum of translated and extended spline functions. And that means that under equation (4) the Tagaki-Sugeno model is equivalent to a multi-resolution spline model. And it follows that wavelet techniques can be used here.
Im µP 6 werden die Sensorsignale sowohl untereinander als auch einzeln mit bestimmten Parametersätzen für die einzelnen Brandkenngrössen verglichen. Selbstverständlich ist die Anzahl der Sensoren nicht auf drei beschränkt. So kann auch nur ein einziger Sensor vorgesehen sein, wobei in diesem Fall aus dem Signal des einen Sensors verschiedene Eigenschaften, beispielsweise der Signalgradient oder die Signalfluktuation, extrahiert und untersucht werden. In den µP 6 sind softwaremässig ein Neuro-Fuzzy-Netz 7 und eine Gültigkeitsprüfung (Validierung) 8 integriert. Wenn das aus dem Neuro-Fuzzy-Netz 7 resultierende Signal als Alarmsignal gewertet wird, wird einer Alarmabgabevorrichtung 9 oder einer Alarmzentrale ein entsprechendes Alarmsignal zugeführt. Sollte die Validierung 8 ergeben, dass wiederholt oder regelmässig Störsignale auftreten, dann werden die im µP 6 gespeicherten Parametersätze entsprechend korrigiert.In
Das Neuro-Fuzzy-Netz 7 ist eine Serie neuronaler Netze, welche die symmetrischen Skalierfunktionen ϕm,n(x) = ϕm,n(x) = ϕ[(x-n)·2m] als Aktivierungsfunktion verwenden. Die Skalierfunktionen sind derart, dass {(ϕm,n(x)} eine Mehrfachauflösung bilden. Jedes neuronale Netz benutzt Aktivierungsfunktionen einer gegebenen Auflösung. Das m-te neuronale Netz optimiert die Koeffi-zienten ĉm,n mit fm(x), dem Ausgang des m-ten neuronalen Netzes.
Die Koeffizienten ĉm,n werden mit der folgenden Gleichung berechnet:
wobei yk(x) der k-te Eingangspunkt und ϕ̃m,n(x) die duale Funktion von ϕm,n(x) ist. Die beiden Gleichungen (5) und (6) bilden den Hauptalgorithmus des Neuro-Fuzzy-Netzes.The coefficients ĉ m, n are calculated using the following equation:
where y k (x) is the k th entry point and φ m, n (x) is the dual function of φ m, n (x). The two equations (5) and (6) form the main algorithm of the neuro-fuzzy network.
Bei jedem Iterationsschritt werden die Werte der verschiedenen neuronalen Netze kreuzweise überprüft (validiert), wozu eine Eigenschaft der Wavelet-Zerlegung, nämlich diejenige, dass die Approximationskoeffizienten ĉm,n eines Niveaus m aus den Approximations- und Wavelet-Koeffizienten des Niveaus m-1 durch Verwendung des Rekonstruktions- oder Zerlegungsalgorithmus gewonnen werden können.At each iteration step, the values of the various neural networks are cross checked (validated), including a property of the wavelet decomposition, namely that the approximation coefficients ĉ m, n of a level m from the approximation and wavelet coefficients of the level m-1 can be obtained by using the reconstruction or decomposition algorithm.
Bei einer bevorzugten Ausführung ist ϕ̃m,n(x) eine Spline-Funktion zweiter Ordnung und ϕm,n(x) eine Interpolationsfunktion. Bei einer zweiten Ausführung ist ϕm,n(x) eine Spline-Funktion und ϕ̃m,n(x) die duale Funktion von ϕm,n(x). In einer dritten Ausführung ist ϕ̃m,n(x) = ϕm,n(x), wobei ϕm,n(x) die Haar-Funktion ist. In diesen Fällen ist die Implementierung des Lernalgorithmus in einen einfachen Mikroprozessor möglich.In a preferred embodiment, φ m, n (x) is a second-order spline function and φ m, n (x) is an interpolation function. In a second embodiment, φ m, n (x) is a spline function and φ m, n (x) is the dual function of φ m, n (x). In a third embodiment, φ m , n (x) = φ m, n (x), where φ m, n (x) is the hair function. In these cases, the implementation of the learning algorithm in a simple microprocessor is possible.
In den
Beim Beispiel von
Anstatt in einem Neuro-Fuzzy-Netz 7 kann die Bestimmung der genannten Koeffizienten in einem Schätzer (estimator) der in
Nadaraya-Watson-Estimatoren haben zwei interessante Eigenschaften, sie sind Schätzer der lokalen mittleren quadratischen Abweichung und es kann gezeigt werden, dass sie im Fall eines Zufallsdesigns sogenannten Bayes'sche-Schätzer von (xk,yk) sind, wobei (xk,yk) iid-Kopien einer kontinuierlichen Zufallsvariablen (X, Y) sind.Nadaraya-Watson estimators have two interesting properties, they are estimators of the local mean square deviation and it can be shown that in the case of a random design they are so-called Bayesian estimators of (x k , y k ), where (x k , y k ) are iid copies of a continuous random variable (X, Y).
Die Spline-Funktionen ϕ(x) und ihre Dualfunktion ϕ̃(x) können als Schätzer verwendet werden. Wir verwenden zuerst die Funktion ϕ̃(x)zur Abschätzung von f(x) mit λ = 2-m (m ist eine ganze Zahl) an xn mit xn · 2m ∈ Z:The spline functions φ (x) and their dual function φ (x) can be used as estimators. We first use the function φ (x) to estimate f (x) with λ = 2 -m (m is an integer) at x n with x n · 2 m ∈ Z:
Mit Verwendung der Symmetrie von ϕ̃(x) ist Gleichung (6) für die duale Spline-Funktion äqivalent zur Verwendung eines bei xn zentrierten Schätzers:
Der Erwartungswert des Zählers in Gleichung (7) ist proportional zum Approximationskoeffizienten cm,n. Gleichung (6) liefert eine Schätzung von ĉm,n in fm(x) = Σĉm,n ˙ ϕm,n(x):
In der
Zur Validierung des Koeffizienten ĉm,n sind zwei Bedingungen notwendig:
wobei die Filterkoeffizienten g dem Tiefpass-Zerlegungs-Koeffizienten für Spline-Funktionen entsprechen. Ausserdem wird gefordert, dass
wherein the filter coefficients g correspond to the low-pass decomposition coefficient for spline functions. In addition, it is demanded that
Die Stärke dieser Methode liegt darin, dass die Berechnung eines Koeffizienten ĉm,n die Speicherung von lediglich zwei Werten erfordert, des Zählers und des Nenners in Gleichung (7). Das Verfahren ist daher sehr gut für online-Lernen mit einem einfachen Mikroprozessor mit geringer Speicherkapazität geeignet.The strength of this method is that the calculation of a coefficient ĉ m, n requires the storage of only two values of the numerator and the denominator in equation (7). The method is therefore very well suited for online learning with a simple low memory microprocessor.
Das Verfahren ist leicht an Dichte-Abschätzung anpassbar, indem die Gleichung (7) und (8) durch die folgende Gleichung ersetzt werden:
Claims (10)
- Method for processing the signals of a danger detector, which features at least one sensor (2, 3, 4) for monitoring characteristic danger values and features evaluation electronics assigned to the at least one sensor (2, 3, 4), in which the signals of the at least one sensor (2, 3, 4) are compared with predetermined parameters, characterized in that the signals of the at least one sensor (2, 3, 4) are analysed to establish whether they are occurring more than once or regularly so that signals occurring more than once or regularly can be classed as interference signals and that the result of the analysis of the signals as to their validity is checked by methods which are based on multi-resolution.
- Method according to claim 1, characterised in that the classification of signals as interference signals triggers a corresponding adaptation of the parameters,
- Method according to claim 2, characterised in that, on occurrence of interference signals, before the parameters are adapted, the result of the analysis of the signals of the at least one sensor (2, 3, 4) is validated, and that the parameters are adapted depending on the result of this validation,
- Method according to claim 3, characterised in that wavelets, preferably "biorthogonal" or "second generation" wavelets or a "lifting scheme" are used for the validation.
- Method according to claim 4, characterised in that the expected values are determined for the approximation coefficients or the approximation and detailed coefficients of the wavelets and are compared at different resolutions.
- Method according to claim 5, characterised in that the said coefficients are determined in an estimator or by means of a neuronal network.
- Danger detector with means for executing the method as claimed in claim 1, with at least one sensor (2, 3, 4) for a characteristic danger value and with evaluation electronics (1) containing a microprocessor (6) for evaluation and analysis of the signals of the at least one sensor (2, 3, 4), characterized in that the microprocessor (6) contains a software program with a learning algorithm based on multi-resolution for the analysis of the signals of the at least one sensor (2, 3, 4).
- Danger detector according to claim 7, characterised in that, through the learning algorithm, on the one hand an analysis of the said sensor signal as to its repeated or regular occurrence and on the other hand a validation of the result of the analysis is undertaken, and that the learning uses wavelets, preferably "biorthogonal" or "second generation" wavelets for the validation.
- Danger detector according to claim 8, characterised in that the learning algorithm uses neuro-fuzzy methods.
Priority Applications (15)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/019,362 US6879253B1 (en) | 2000-03-15 | 2000-03-06 | Method for the processing of a signal from an alarm and alarms with means for carrying out said method |
AT00105438T ATE394767T1 (en) | 2000-03-15 | 2000-03-15 | METHOD FOR PROCESSING THE SIGNALS OF A HAZARD DETECTOR AND HAZARD DETECTOR WITH MEANS FOR IMPLEMENTING THE METHOD |
ES00105438T ES2304919T3 (en) | 2000-03-15 | 2000-03-15 | PROCEDURE FOR PROCESSING THE SIGNS OF A DANGER AND DANGER NOTICE WITH MEANS TO PERFORM THE PROCEDURE. |
EP00105438A EP1134712B1 (en) | 2000-03-15 | 2000-03-15 | Method for the processing of the signal in a danger detector, and detector with means for the implementation of such method |
DE50015145T DE50015145D1 (en) | 2000-03-15 | 2000-03-15 | Method for processing the signals of a danger detector and danger detector with means for carrying out the method |
PL01350725A PL350725A1 (en) | 2000-03-15 | 2001-03-06 | Method for the processing of a signal from an alarm and alarms with means for carrying out said method |
JP2001567562A JP2003527702A (en) | 2000-03-15 | 2001-03-06 | Danger detector having a method of processing a signal of a danger detector and means for performing the method |
CNB018005322A CN1187723C (en) | 2000-03-15 | 2001-03-06 | Method for processing of signal from alarm and alarms with means for carrying out said method |
KR1020017014423A KR100776063B1 (en) | 2000-03-15 | 2001-03-06 | Method for the processing of a signal from an alarm and alarms with means for carrying out said method |
AU35304/01A AU776482B2 (en) | 2000-03-15 | 2001-03-06 | Method for the processing of a signal from an alarm and alarms with means for carrying out said method |
CZ20014105A CZ20014105A3 (en) | 2000-03-15 | 2001-03-06 | Method for the processing of the signal in a danger detector, and detector with means for the implementation of such method |
HU0201180A HUP0201180A2 (en) | 2000-03-15 | 2001-03-06 | Method for the processing of a signal from an alarm and alarms with means for carrying out said method |
PCT/CH2001/000136 WO2001069566A1 (en) | 2000-03-15 | 2001-03-06 | Method for the processing of a signal from an alarm and alarms with means for carrying out said method |
NO20015566A NO20015566L (en) | 2000-03-15 | 2001-11-14 | Method of processing the signals from a risk alert, and risk alerts with means for carrying out the method |
HK02108442.5A HK1046978B (en) | 2000-03-15 | 2002-11-21 | Method for processing the signal of a danger detector and danger detector |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP00105438A EP1134712B1 (en) | 2000-03-15 | 2000-03-15 | Method for the processing of the signal in a danger detector, and detector with means for the implementation of such method |
Publications (2)
Publication Number | Publication Date |
---|---|
EP1134712A1 EP1134712A1 (en) | 2001-09-19 |
EP1134712B1 true EP1134712B1 (en) | 2008-05-07 |
Family
ID=8168099
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP00105438A Expired - Lifetime EP1134712B1 (en) | 2000-03-15 | 2000-03-15 | Method for the processing of the signal in a danger detector, and detector with means for the implementation of such method |
Country Status (15)
Country | Link |
---|---|
US (1) | US6879253B1 (en) |
EP (1) | EP1134712B1 (en) |
JP (1) | JP2003527702A (en) |
KR (1) | KR100776063B1 (en) |
CN (1) | CN1187723C (en) |
AT (1) | ATE394767T1 (en) |
AU (1) | AU776482B2 (en) |
CZ (1) | CZ20014105A3 (en) |
DE (1) | DE50015145D1 (en) |
ES (1) | ES2304919T3 (en) |
HK (1) | HK1046978B (en) |
HU (1) | HUP0201180A2 (en) |
NO (1) | NO20015566L (en) |
PL (1) | PL350725A1 (en) |
WO (1) | WO2001069566A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107180521A (en) * | 2017-04-19 | 2017-09-19 | 天津大学 | Optical fiber perimeter security protection intrusion event recognition methods and device based on comprehensive characteristics |
Families Citing this family (30)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7068177B2 (en) * | 2002-09-19 | 2006-06-27 | Honeywell International, Inc. | Multi-sensor device and methods for fire detection |
US7202794B2 (en) * | 2004-07-20 | 2007-04-10 | General Monitors, Inc. | Flame detection system |
FI117878B3 (en) * | 2006-01-20 | 2019-01-31 | Innohome Oy | Alarm device for a kitchen range or range hood |
US8819562B2 (en) | 2010-09-30 | 2014-08-26 | Honeywell International Inc. | Quick connect and disconnect, base line configuration, and style configurator |
US20110093493A1 (en) | 2008-10-28 | 2011-04-21 | Honeywell International Inc. | Building management system site categories |
US20100106543A1 (en) * | 2008-10-28 | 2010-04-29 | Honeywell International Inc. | Building management configuration system |
US8719385B2 (en) * | 2008-10-28 | 2014-05-06 | Honeywell International Inc. | Site controller discovery and import system |
US8850347B2 (en) | 2010-09-30 | 2014-09-30 | Honeywell International Inc. | User interface list control system |
US8572502B2 (en) * | 2008-11-21 | 2013-10-29 | Honeywell International Inc. | Building control system user interface with docking feature |
US9471202B2 (en) * | 2008-11-21 | 2016-10-18 | Honeywell International Inc. | Building control system user interface with pinned display feature |
US8224763B2 (en) | 2009-05-11 | 2012-07-17 | Honeywell International Inc. | Signal management system for building systems |
US8554714B2 (en) * | 2009-05-11 | 2013-10-08 | Honeywell International Inc. | High volume alarm management system |
US8352047B2 (en) | 2009-12-21 | 2013-01-08 | Honeywell International Inc. | Approaches for shifting a schedule |
US20110196539A1 (en) * | 2010-02-10 | 2011-08-11 | Honeywell International Inc. | Multi-site controller batch update system |
US8640098B2 (en) * | 2010-03-11 | 2014-01-28 | Honeywell International Inc. | Offline configuration and download approach |
US8890675B2 (en) | 2010-06-02 | 2014-11-18 | Honeywell International Inc. | Site and alarm prioritization system |
US8648706B2 (en) | 2010-06-24 | 2014-02-11 | Honeywell International Inc. | Alarm management system having an escalation strategy |
US9213539B2 (en) | 2010-12-23 | 2015-12-15 | Honeywell International Inc. | System having a building control device with on-demand outside server functionality |
US9223839B2 (en) | 2012-02-22 | 2015-12-29 | Honeywell International Inc. | Supervisor history view wizard |
US9529349B2 (en) | 2012-10-22 | 2016-12-27 | Honeywell International Inc. | Supervisor user management system |
US9971977B2 (en) | 2013-10-21 | 2018-05-15 | Honeywell International Inc. | Opus enterprise report system |
US9933762B2 (en) | 2014-07-09 | 2018-04-03 | Honeywell International Inc. | Multisite version and upgrade management system |
CN105067025A (en) * | 2015-07-31 | 2015-11-18 | 西南科技大学 | Method for utilizing monostable system stochastic resonance effect to detect weak signals |
US10362104B2 (en) | 2015-09-23 | 2019-07-23 | Honeywell International Inc. | Data manager |
US10209689B2 (en) | 2015-09-23 | 2019-02-19 | Honeywell International Inc. | Supervisor history service import manager |
US10957176B2 (en) | 2016-11-11 | 2021-03-23 | Carrier Corporation | High sensitivity fiber optic based detection |
US11127270B2 (en) | 2016-11-11 | 2021-09-21 | Carrier Corporation | High sensitivity fiber optic based detection |
ES2919300T3 (en) | 2016-11-11 | 2022-07-22 | Carrier Corp | High sensitivity fiber optic based detection |
EP3539108B1 (en) | 2016-11-11 | 2020-08-12 | Carrier Corporation | High sensitivity fiber optic based detection |
US11151853B2 (en) | 2016-11-11 | 2021-10-19 | Carrier Corporation | High sensitivity fiber optic based detection |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CH686914A5 (en) * | 1993-12-20 | 1996-07-31 | Cerberus Ag | Fire detection system for early detection of fires. |
EP0718814B1 (en) * | 1994-12-19 | 2001-07-11 | Siemens Building Technologies AG | Method and device for flame detection |
JP3251799B2 (en) * | 1995-02-13 | 2002-01-28 | 三菱電機株式会社 | Equipment diagnostic equipment |
EP0834845A1 (en) * | 1996-10-04 | 1998-04-08 | Cerberus Ag | Method for frequency analysis of a signal |
US6150935A (en) * | 1997-05-09 | 2000-11-21 | Pittway Corporation | Fire alarm system with discrimination between smoke and non-smoke phenomena |
JP3827426B2 (en) * | 1997-11-06 | 2006-09-27 | 能美防災株式会社 | Fire detection equipment |
-
2000
- 2000-03-06 US US10/019,362 patent/US6879253B1/en not_active Expired - Lifetime
- 2000-03-15 DE DE50015145T patent/DE50015145D1/en not_active Expired - Lifetime
- 2000-03-15 EP EP00105438A patent/EP1134712B1/en not_active Expired - Lifetime
- 2000-03-15 AT AT00105438T patent/ATE394767T1/en active
- 2000-03-15 ES ES00105438T patent/ES2304919T3/en not_active Expired - Lifetime
-
2001
- 2001-03-06 KR KR1020017014423A patent/KR100776063B1/en not_active IP Right Cessation
- 2001-03-06 CN CNB018005322A patent/CN1187723C/en not_active Expired - Fee Related
- 2001-03-06 AU AU35304/01A patent/AU776482B2/en not_active Ceased
- 2001-03-06 PL PL01350725A patent/PL350725A1/en not_active Application Discontinuation
- 2001-03-06 JP JP2001567562A patent/JP2003527702A/en active Pending
- 2001-03-06 CZ CZ20014105A patent/CZ20014105A3/en unknown
- 2001-03-06 WO PCT/CH2001/000136 patent/WO2001069566A1/en active IP Right Grant
- 2001-03-06 HU HU0201180A patent/HUP0201180A2/en unknown
- 2001-11-14 NO NO20015566A patent/NO20015566L/en not_active Application Discontinuation
-
2002
- 2002-11-21 HK HK02108442.5A patent/HK1046978B/en not_active IP Right Cessation
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107180521A (en) * | 2017-04-19 | 2017-09-19 | 天津大学 | Optical fiber perimeter security protection intrusion event recognition methods and device based on comprehensive characteristics |
Also Published As
Publication number | Publication date |
---|---|
PL350725A1 (en) | 2003-01-27 |
US6879253B1 (en) | 2005-04-12 |
NO20015566D0 (en) | 2001-11-14 |
KR20020042764A (en) | 2002-06-07 |
NO20015566L (en) | 2001-11-14 |
EP1134712A1 (en) | 2001-09-19 |
CN1187723C (en) | 2005-02-02 |
ES2304919T3 (en) | 2008-11-01 |
DE50015145D1 (en) | 2008-06-19 |
AU3530401A (en) | 2001-09-24 |
HK1046978A1 (en) | 2003-01-30 |
AU776482B2 (en) | 2004-09-09 |
HUP0201180A2 (en) | 2003-03-28 |
CZ20014105A3 (en) | 2002-05-15 |
ATE394767T1 (en) | 2008-05-15 |
WO2001069566A1 (en) | 2001-09-20 |
HK1046978B (en) | 2005-09-23 |
CN1364283A (en) | 2002-08-14 |
KR100776063B1 (en) | 2007-11-15 |
JP2003527702A (en) | 2003-09-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP1134712B1 (en) | Method for the processing of the signal in a danger detector, and detector with means for the implementation of such method | |
DE102019209565A1 (en) | Method and device for checking the robustness of an artificial neural network | |
DE69309300T2 (en) | METHOD AND DEVICE FOR ITEM CLASSIFICATION | |
EP0780002B1 (en) | Process and apparatus for reconstructing raster-shaped line structures | |
EP0865646B1 (en) | Method for analyzing the signals of a danger alarm system and danger alarm system for implementing said method | |
DE102019209566A1 (en) | Method and device for training a machine learning system | |
EP3707496B1 (en) | Identification of one or more spectral features in a spectrum of a sample for a constituent analysis | |
DE102018216078A1 (en) | Method and device for operating a control system | |
DE102021204040A1 (en) | Method, device and computer program for creating training data in the vehicle | |
DE102020208828A1 (en) | Method and device for creating a machine learning system | |
EP3659887A1 (en) | Method and device for estimating a load state of a vehicle | |
DE68925937T2 (en) | Detection and processing of waveforms | |
EP1376286B1 (en) | System and method for monitoring a process | |
AT507266B1 (en) | METHOD FOR AUTOMATICALLY DETECTING A DEFECT IN AN ELECTRONIC REPRESENTATION | |
DE102016113310A1 (en) | A method for evaluating statements of a plurality of sources about a plurality of facts | |
EP0863485B1 (en) | Method of reconstruction of patterns | |
WO2023046653A1 (en) | Method for determining whether a predetermined good to be transported is arranged in a monitoring region | |
DE102021210775A1 (en) | Method and device for machine learning from a small number of training data samples | |
DE102020211714A1 (en) | Method and device for creating a machine learning system | |
WO2022237930A1 (en) | Component-classifying apparatus, method for classifying components, and method for training a component-classifying apparatus | |
AT413248B (en) | METHOD FOR COMPARING A REQUEST FINGER PRINT WITH A REFERENCE FINGERPRINT | |
DE102021205897A1 (en) | Examine a training data set | |
DE102022211293A1 (en) | Method for identifying anomalies and thus also actual processing positions of a web and for classifying these anomalies, system and computer program product | |
WO2023156312A1 (en) | Method and system for detecting a seat occupancy state of a seating arrangement on the basis of radar point clouds | |
DE102022204863A1 (en) | Detection of anomalies in a technical system through monitoring with multiple sensors |
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 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE |
|
AX | Request for extension of the european patent |
Free format text: AL;LT;LV;MK;RO;SI |
|
17P | Request for examination filed |
Effective date: 20020312 |
|
AKX | Designation fees paid |
Free format text: AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: SIEMENS SCHWEIZ AG |
|
17Q | First examination report despatched |
Effective date: 20070102 |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
RAP1 | Party data changed (applicant data changed or rights of an application transferred) |
Owner name: SIEMENS AKTIENGESELLSCHAFT |
|
GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LI LU MC NL PT SE |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D Free format text: NOT ENGLISH |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: EP |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D Free format text: LANGUAGE OF EP DOCUMENT: GERMAN |
|
REF | Corresponds to: |
Ref document number: 50015145 Country of ref document: DE Date of ref document: 20080619 Kind code of ref document: P |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: NV Representative=s name: SIEMENS SCHWEIZ AG |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: NL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20080507 Ref country code: FI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20080507 |
|
REG | Reference to a national code |
Ref country code: ES Ref legal event code: FG2A Ref document number: 2304919 Country of ref document: ES Kind code of ref document: T3 |
|
NLV1 | Nl: lapsed or annulled due to failure to fulfill the requirements of art. 29p and 29m of the patents act | ||
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FD4D |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: DK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20080507 Ref country code: PT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20081007 Ref country code: SE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20080807 Ref country code: IE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20080507 |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: PCAR Free format text: SIEMENS SCHWEIZ AG;INTELLECTUAL PROPERTY FREILAGERSTRASSE 40;8047 ZUERICH (CH) |
|
26N | No opposition filed |
Effective date: 20090210 |
|
BERE | Be: lapsed |
Owner name: SIEMENS A.G. Effective date: 20090331 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MC Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20090331 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: BE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20090331 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20080808 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LU Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20090315 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CY Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20080507 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20111001 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: AT Payment date: 20120207 Year of fee payment: 13 |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: MM01 Ref document number: 394767 Country of ref document: AT Kind code of ref document: T Effective date: 20130315 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: AT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20130315 |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: PUE Owner name: SIEMENS SCHWEIZ AG, CH Free format text: FORMER OWNER: SIEMENS AKTIENGESELLSCHAFT, DE |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: PLFP Year of fee payment: 16 |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: 732E Free format text: REGISTERED BETWEEN 20150220 AND 20150225 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: IT Payment date: 20150328 Year of fee payment: 16 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R081 Ref document number: 50015145 Country of ref document: DE Owner name: SIEMENS SCHWEIZ AG, CH Free format text: FORMER OWNER: SIEMENS AKTIENGESELLSCHAFT, 80333 MUENCHEN, DE Effective date: 20150407 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: FR Payment date: 20150311 Year of fee payment: 16 Ref country code: GB Payment date: 20150312 Year of fee payment: 16 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: CH Payment date: 20150602 Year of fee payment: 16 Ref country code: ES Payment date: 20150427 Year of fee payment: 16 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: TP Owner name: SIEMENS SCHWEIZ AG, CH Effective date: 20150916 |
|
REG | Reference to a national code |
Ref country code: ES Ref legal event code: PC2A Owner name: SIEMENS SCHWEIZ AG Effective date: 20160406 |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: PL |
|
GBPC | Gb: european patent ceased through non-payment of renewal fee |
Effective date: 20160315 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: ST Effective date: 20161130 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CH Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20160331 Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20160331 Ref country code: GB Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20160315 Ref country code: LI Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20160331 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IT Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20160315 |
|
REG | Reference to a national code |
Ref country code: ES Ref legal event code: FD2A Effective date: 20170428 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: ES Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20160316 |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: DE Payment date: 20180518 Year of fee payment: 19 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R119 Ref document number: 50015145 Country of ref document: DE |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: DE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20191001 |