EP0995156A2 - Procede et structure pour la modelisation neuronale d'un systeme dynamique dans un ordinateur - Google Patents

Procede et structure pour la modelisation neuronale d'un systeme dynamique dans un ordinateur

Info

Publication number
EP0995156A2
EP0995156A2 EP98943653A EP98943653A EP0995156A2 EP 0995156 A2 EP0995156 A2 EP 0995156A2 EP 98943653 A EP98943653 A EP 98943653A EP 98943653 A EP98943653 A EP 98943653A EP 0995156 A2 EP0995156 A2 EP 0995156A2
Authority
EP
European Patent Office
Prior art keywords
layer
influencing
variable
variables
output
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP98943653A
Other languages
German (de)
English (en)
Inventor
Hans-Georg Zimmermann
Ralf Neuneier
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Siemens AG
Original Assignee
Siemens AG
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Siemens AG filed Critical Siemens AG
Publication of EP0995156A2 publication Critical patent/EP0995156A2/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks

Definitions

  • the invention relates to a method and a layer arrangement for a neural network, with which in particular dynamic systems can be modeled well, such as technical systems or economic systems.
  • This publication proposes a six-layer model for a neural network to measure the dynamics of a technical system, or a system that predicts stock data by means of a dynamic characterization of the For the purpose of better modeling of a time series, several neighboring values of the time series are trained there separately in different branches of the neural network as targets and later combined by averaging to the desired output quantity Net at the exit dur ch imprinted a so-called interaction layer.
  • a branch is to be understood as a part of the neural network, which is itself an artificial neural network with inputs, at least one output and adaptable weights when individual neurons are coupled.
  • AI discloses a learning method and a learning arrangement for emulating a dynamic process by learning at least two time series together.
  • a separate learnable component is provided for each time series, to which historical values of the time series used are added.
  • Time series is decorrelated from its historical values and the historical values of the other time series. From US 5 479 571 A a neural network with two hidden layers is known.
  • the object on which the invention is based is to specify a further method and a further structure with which dynamic systems can be modeled neuronally on a computer.
  • the method for neural modeling of a dynamic system on a computer comprises the following features: a) Influencing variables of the dynamic system are used to emulate at least one first output variable into at least one first influencing variable, which determines the inertia of the dynamic system and into at least a second influencing variable, which determines the acceleration of the dynamic system groups; b) in a neural network (NN) at least a first (ZI) and a second (Z2) parallel branch of the neural network (NN) are trained separately with the behavior of the first influencing variable or second influencing variable; c) to form a first output variable (AD) depending on the influencing variables (ED), the or all outputs of the parallel branches (ZI, Z2) of the neural network (NN) are combined.
  • a) Influencing variables of the dynamic system are used to emulate at least one first output variable into at least one first influencing variable, which determines the inertia of the dynamic system and into at least a second influencing variable, which determines the acceleration of the dynamic system groups; b
  • the layer arrangement for a neural network for simulating a dynamic system has the following features: a) for simulating at least one first influencing variable, which determines the inertia of the dynamic system, and a second influencing variable, which determines the acceleration of the dynamic system, there are at least one hidden first (4000) or second (4500) neuron layer, as well as a first (5000) or second (5500) output layer; b) there is a combination layer (6000) for combining the simulated first influencing variable (610) and second influencing variable (620) into output variables.
  • Time series in the form of time series vectors of various influencing variables can advantageously be supplied to the neural network, and the output variable formed is combined into a single output variable by weighted averaging, since this reduces the noise component in the input variables and a more accurate replication by modeling different input variables the output size is possible.
  • the incoming signals are preprocessed by neuron-weighting them, these neuron weights being determined by subordinate positions of the neuron signals.
  • len network can be set in order to filter out undesirable influencing variables that have nothing to do with the dynamic system to be modeled.
  • the branches of the neural network can radial through implementation 'Ba are supplied, since thus the neural network to carry out different cases the possibility is also given in addition to determine sisfunktionen similarities within the pattern not only with linear predictors, but also with square weighted predictors.
  • the dynamic parameter to be supplied to the respective neural network i.e., inertia parameters or acceleration parameters
  • a plurality of indicators are formed, so that a larger amount of error return is generated within the network by a plurality of target variables, and thus a more accurate replication of the respective dynamic variable is possible.
  • the mean value or the curvature is preferably modeled with several defined interval distances around the target value.
  • the input variables for the method can be prepared in the form of the selected indicators in order to show the network a clear picture of the internal state of the dynamic system to be modeled.
  • a dynamic system is characterized by the momentarily acting inertia and influencing forces. From the input time series offered, one can now draw conclusions about the acting inertia and the forces by using the first and second differences of the time series. To normalize the order of magnitude of the input indicators, we also divide by the time series, which leads to relative changes.
  • the dynamic system is movement characterized by a balance.
  • the distance between a point in the time series and the equilibrium is a better characterization of the acting force than the description in the form of an acceleration.
  • the mean value of the last values of the time series can be used. If you now choose the difference between the current value of the time series and the mean value as equilibrium, you have used the latest point information but compared it with an outdated estimate of the equilibrium. It proves to be more advantageous in the difference to choose a past value of the time series such that the averaging for estimating the equilibrium is arranged symmetrically about this point. In this way, a better characterization of the tension between point and equilibrium of the dynamic system to be characterized is obtained.
  • a layer arrangement for a neural network for simulating a dynamic system can be provided, because there is a separate branch in the neural network for each dynamic parameter to be simulated, and an increased error reflux is generated by checking the hidden positions with an output layer, by means of which the The information about the dependence of neighboring time series values is imprinted on the neural network.
  • a preprocessing layer which serves both or the respective network branches together, since, for example, no two different preprocessing stages have to be provided and since the weights in the preprocessing layer are set by the error feedback from the respective branches of the neural network, in order to filter out undesired influencing variables and thus a more precise filtering out of disturbance variables can take place.
  • a square layer is particularly advantageously provided, which square-weighted the input values or the values supplied by the preprocessing layer. This enables the subsequent layers to simulate radial basic functions and thus to establish similarity references and not just case distinctions of incoming patterns.
  • the combination layer, the individual branches of the layer arrangement can be followed by a possibly weighted mean value layer in order to form an average value from the vectors of the prediction variable and thus to minimize the noise within the individual values.
  • Control layers which model the interval distances of the individual indicators from the respective dynamic parameter to be reproduced and which prevent the neural network or the respective branch of the neural network from taking place, are particularly advantageous in the layer arrangement of the respective branches of the neural network as output layers different indicators modeled only one.
  • FIG. 1 shows an example of a block diagram of a method according to the invention.
  • FIG. 2 shows an example of a neural network with a neuron layer arrangement according to the invention.
  • a method EV has, for example, processing blocks, a first processing block ZI and a second processing block Z2, and a further processing block 3000.
  • the processing blocks ZI and Z2 denote two separate branches, a first branch ZI and a second branch Z2 of a neural network NN.
  • the first processing block ZI and the second processing block Z2 receive input data in the form of time series which are taken from a real system, i.e. were measured.
  • a plurality of processing layers, a first processing layer 1000 and a second processing layer 2000 of the first processing block ZI or a first processing layer 1500 and a second processing layer 2500 of the second processing block Z2 are provided in the first and second processing blocks ZI and Z2 in the neural network NN, respectively are interconnected by signal lines 110 and 120.
  • acceleration parameters such as the force which causes a reset or a dynamic in the system, are described.
  • inertia parameters of the dynamic system are simulated.
  • the input data of the time series with which these respective processing blocks are supplied identically according to the method are processed in relation to identical indicators for these respective dynamic parameters.
  • the second processing block Z2 it is provided to emulate an average value around a prediction value by drawing time series values at various intervals around this value from this prediction value for averaging.
  • the output variables are fed via connecting lines 210 and 220 to a combination module 3000, which uses them to generate output data, ie the prediction value. It is achieved by the method that separate target sizes are defined for a respective dynamic parameter and these are simulated in different branches of a neural network. In this way, a strict separation of these dynamics-characterizing variables is achieved in the modeling, in that separate indicators are also learned during the training by the neural network.
  • a neural layer model for the neural modeling of a dynamic system has a plurality of layers 1000, 2000, 3000, 4000, 4500, 5000, 5500, 6000, 7000, 75000, the respective thousands indicating the numbering of the layers .
  • a preprocessing of the time series data of the dynamic system is carried out in front of the input neuron layer 1000 of the neural network NN.
  • the preprocessing shows the network a picture of the momentum and forces currently effective in the markets.
  • input variables can optionally be equilibrium variables, the restoring force of which depends on a distance between the current state and the respective state of equilibrium. In a mechanical system, this is the deflection of a spring pendulum from the idle state. In an economic system, for example, this observation quantity is a price that is derived from a process of equilibrium between supply and demand.
  • the following way is preferred to reset the point value to be predicted to such an extent that it becomes possible to compare a central mean value of the point information.
  • This concept can be understood using the following examples, where the index t denotes the current period, t-6 e.g. the time 6 steps earlier and aver (x (t), 12) indicates the averaging over the most recent 12 data.
  • x inflation indicator (e.g. a time series that does not originate from an equilibrium process)
  • INPUT (x (t) - x (t-6)) / x (t-6)
  • INPUT (x (t) - 2 * x (t-6) + x (t-12)) / x (t-6)
  • y US- $ (example of a time series defined by a supply - demand balance)
  • INPUT (y (t) - y ( t-6)) / y (t-6)
  • INPUT (y (t-6) - aver (y (t), 12)) / y (t-6)
  • a preprocessing layer 2000 is provided for the neural layer arrangement, with which the problem caused by the neural network NN interna- is achieved by the unknown damping constants appearing as learnable parameters in the network.
  • the internal preprocessing of the signals offered to the neural network NN is carried out by means of a weight matrix between the input layer 1000 and the preprocessing layer 2000, which consists of a diagonal matrix, which is denoted by 200.
  • the hyperbolic tangent (tanh) is used for the activation function of the first inner layer. This procedure and layer arrangement limit outliers in the values. Weight-based checking of inputs is also advantageously supported by this weight matrix.
  • the weights should preferably be initialized with 1 in the preprocessing layer 2000 and the weights should preferably be limited to values between 0 and 1.
  • the output signals of the preprocessing layer 2000 are forwarded to three further neuron layers 3000, 4000 and 4500. While a pure copy of the signals is forwarded to layer 3000, so that 300 denotes an identity image, the subsequent layers 4000 and 5000 or 4500 and 5500 receive the signals derived from preprocessing layer 2000 and transforms them linearly and squared, which is indicated by arrows 400 to 450 is indicated.
  • the neural network can also implement radial basic functions and thus can not only make case distinctions, but can also learn similarities in the patterns offered.
  • the signals 400, 410 or 420 and 450 generated in this way are then weighted in the neuron layers 4000 and 5000 or 4500 and 5500 multiplied, the layers 5500 and 5000 representing output layers of the neural network NN, while the layers 4000 and 4500 represent hidden neuron layers.
  • This part of the neural layer arrangement combines the classic concepts of a multilayer perceptron with a sigmoid inner layer of neurons and a classic radial basis function network. This connects the global and local approaches to these approximation approaches.
  • the activation function for the preprocessing layer 2000 and the hidden layer 4500 is chosen as the hyperbolic tangent. It may be helpful to add a Softmax function to the activation function.
  • Layers 5000 and 5500 identify the underlying dynamic system. For this purpose, these two layers are provided as the first starting layers in the neural layer arrangement and have target values that are to be learned.
  • the weights of layers 4000 to 5500 can be adapted here, as already indicated in the explanation of the arrow strengths.
  • the layer 5500 which is intended to model, for example, the inertia component of the dynamic system, 3-point averages and balance information of the time series to be approximated are offered as target values. Some examples of such target values are given below.
  • TARGET (x (t + 5) + x (t + 6) + x (t + 7)) / (3 * x (t)) - 1)
  • TARGET (x (t + 4) + x (t + 6) + x (t + 8)) / (3 * x (t)) - 1) or
  • TARGET (aver (x (t + 7), 3) - x (t)) / x (t)
  • TARGET (aver (x (t + 8), 5) - x (t)) / x (t)
  • Layer 5000 which acceleration properties of the system should learn, is offered so-called forces or mean-inverting information. The following characterizations are available for the forces that are offered as target or target values of the output layer 5000:
  • TARGET (-x (t + 4) + 2 * x (t + 6) - x (t + 8)) / ' (3 * x (t))) or
  • each average specialist can select other averages or other target sizes and combine them accordingly in order to emulate a predicted target value without being inventive or without proceeding in the sense of the invention. Since many characterizations of the dynamics can preferably be represented and thus learned through different embeddings and different ranges of the associated forces, 4500, 5500 or 4000 and 5000 are created in the replication of the dynamic branches. co co MM I- 1 P 1

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Feedback Control In General (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

L'invention concerne un procédé et un système à couches de neurones pour la modélisation neuronale de systèmes dynamiques. A cet effet, on procède à l'apprentissage et au traitement, séparément dans le réseau, de paramètres décrivant l'inertie et de paramètres décrivant l'accélération des séries chronologiques du système. Les valeurs prédictives ainsi obtenues sont regroupées en une grandeur prédictive désirée. On peut, en définissant différents indicateurs par paramètre dynamique, obtenir différentes grandeurs cibles sous forme de valeurs moyennes ayant une base de largeur différente et dont l'apprentissage génère un courant d'erreurs plus important à renvoyer dans le réseau, ce qui permet d'atteindre une simulation précise des différents paramètres dynamiques. On utilisera, de préférence, le système et le procédé selon l'invention pour des prévisions boursières et d'autres systèmes dynamiques.
EP98943653A 1997-07-09 1998-07-08 Procede et structure pour la modelisation neuronale d'un systeme dynamique dans un ordinateur Withdrawn EP0995156A2 (fr)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
DE19729391 1997-07-09
DE19729391 1997-07-09
PCT/DE1998/001887 WO1999003043A2 (fr) 1997-07-09 1998-07-08 Procede et structure pour la modelisation neuronale d'un systeme dynamique dans un ordinateur

Publications (1)

Publication Number Publication Date
EP0995156A2 true EP0995156A2 (fr) 2000-04-26

Family

ID=7835168

Family Applications (1)

Application Number Title Priority Date Filing Date
EP98943653A Withdrawn EP0995156A2 (fr) 1997-07-09 1998-07-08 Procede et structure pour la modelisation neuronale d'un systeme dynamique dans un ordinateur

Country Status (3)

Country Link
EP (1) EP0995156A2 (fr)
JP (1) JP2001509623A (fr)
WO (1) WO1999003043A2 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110070228A (zh) * 2019-04-25 2019-07-30 中国人民解放军国防科技大学 一种神经元分支进化的bp神经网络风速预测方法

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102017118996B3 (de) * 2017-05-11 2018-07-26 Schaeffler Technologies AG & Co. KG Verfahren zur Bestimmung von einflussführenden Parameterkombinationen eines physikalischen Simulationsmodells

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH04133601A (ja) * 1990-09-21 1992-05-07 Toshiba Corp 保安機能付自動運転制御装置
DE4419925A1 (de) * 1994-06-08 1995-12-14 Bodenseewerk Geraetetech Inertialsensor-Einheit

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO9903043A2 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110070228A (zh) * 2019-04-25 2019-07-30 中国人民解放军国防科技大学 一种神经元分支进化的bp神经网络风速预测方法
CN110070228B (zh) * 2019-04-25 2021-06-15 中国人民解放军国防科技大学 一种神经元分支进化的bp神经网络风速预测方法

Also Published As

Publication number Publication date
WO1999003043A3 (fr) 1999-04-01
JP2001509623A (ja) 2001-07-24
WO1999003043A2 (fr) 1999-01-21

Similar Documents

Publication Publication Date Title
EP2649567B1 (fr) Procédée pour la modélisation sur ordinateur d'un système technique
DE102007001025A1 (de) Verfahren zur rechnergestützten Steuerung und/oder Regelung eines technischen Systems
DE102008020379A1 (de) Verfahren zur rechnergestützten Steuerung und/oder Regelung eines technischen Systems
DE4217832A1 (de) Mustererkennungs- und musterlerngeraet
EP0663632A1 (fr) Méthode et dispositif pour la comande d'un processus
EP1021793A2 (fr) Ensemble d'elements de calcul relies les uns aux autres, procede de determination assistee par ordinateur d'une dynamique a la base d'un processus dynamique, et procede d'entrainement assiste par ordinateur pour un ensemble d'elements de calcul relies les uns aux autres
DE102020105785A1 (de) Verfahren zur Erzeugung eines reduzierten neuronalen Netzes für ein Steuergerät eines Fahrzeuges mithilfe von Eigenvektoren
DE102020201133A1 (de) Verfahren und Vorrichtung zur Modellwertbildung, insbesondere zur Sensordatenfusion
DE19504664C2 (de) Chaotisches rekurrentes neuronales Netz und Lernverfahren dafür
EP0901658A1 (fr) Procede d'optimisation d'un ensemble de regles floues au moyen d'un ordinateur
DE10201018A1 (de) Neuronales Netz zur Modellierung eines physikalischen Systems sowie Verfahren zur Bildung eines solchen neuronalen Netzes
EP0956531B1 (fr) Procede et dispositif pour la transformation d'une logique floue servant a la simulation d'un processus technique en un reseau neuronal
WO1999003043A2 (fr) Procede et structure pour la modelisation neuronale d'un systeme dynamique dans un ordinateur
DE4417932B4 (de) Verfahren und ein System zum Erhalten von Zieleinstellbeträgen für Ausführungsparameter durch Lernen einer Mehrzahl von Sätzen von Muster-Eingabedaten und Muster-Ausgabedaten
DE102020105783A1 (de) Verfahren zur Erzeugung eines reduzierten neuronalen Netzes
WO1997036248A1 (fr) Procede de determination de poids aptes a etre elimines, d'un reseau neuronal, au moyen d'un ordinateur
WO1998032079A1 (fr) Procede pour la detection, par ordinateur, de la synchronicite entre plusieurs series de mesures numeriques
EP0548127B1 (fr) Réseau neuronal et dispositiv de mise en oeuvre de réseaux neuronaux de type ADALINE
DE102019113958A1 (de) Verfahren zur Leistungssteigerung eines Fahrzeugsystems mit einem neuronalen Netz zum Steuern einer Fahrzeugkomponente
DE102011076969B4 (de) Verfahren zum rechnergestützten Lernen einer Regelung und/oder Steuerung eines technischen Systems
EP1344125A2 (fr) Procede de production orientee besoins de nombres aleatoires individuels d'une suite de nombres aleatoires d'un bruit en 1/f
DE102016113310A1 (de) Verfahren zur Bewertung von Aussagen einer Mehrzahl von Quellen zu einer Mehrzahl von Fakten
WO1993000652A1 (fr) Procede de traitement d'incertitudes dans des donnees d'entree dans des reseaux neuroniques
DE19748718A1 (de) Regler - Selbsteinstellungseinrichtung auf der Grundlage Neuronaler Netze
DE4228703A1 (de) Verfahren zum Entwurf eines neuronalen Netzes

Legal Events

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

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 19991217

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): DE FR GB IT

GRAG Despatch of communication of intention to grant

Free format text: ORIGINAL CODE: EPIDOS AGRA

GRAG Despatch of communication of intention to grant

Free format text: ORIGINAL CODE: EPIDOS AGRA

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

17Q First examination report despatched

Effective date: 20011220

GRAH Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOS IGRA

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: 20030201