DE102022209247A1 - Examining components for defects using a component analyzer - Google Patents

Abstract

Method for examining components for defects using a component analyzer,
wherein the method includes an AI routine (K1) for object analysis and an AI routine (K2) for detecting and classifying defects that are known to the component analyzer from data sets, and/or an AI routine (K3) for detecting anomalies, which are not known to the component analyzer from data sets,
wherein the AI routines are fed with sensor data or processed sensor data relating to a component to be examined as input data and generate annotated data relating to the component to be examined as output data containing a result of the respective routine,
wherein at least one AI routine is trained with annotated output data of at least one of the other AI routines.

Description

FIELD OF THE INVENTION

The present invention relates to a method for examining components for defects using a component analyzer and a component analyzer.

SUMMARY OF THE INVENTION

• - ein Verfahren zur Untersuchung von Bauteilen auf Fehler mittels eines Bauteilanalysators, wobei das Verfahren eine KI-Routine zur Objektanalyse und eine KI-Routine zur Erkennung und Klassifikation von Mängeln, die dem Bauteilanalysator aus Datensätzen bekannt sind, und/oder eine KI-Routine zur Erkennung von Anomalien, die dem Bauteilanalysator aus Datensätzen nicht bekannt sind, aufweist, wobei die KI-Routinen mit Sensordaten oder verarbeiteten Sensordaten betreffend ein zu untersuchendes Bauteil als Eingangsdaten gespeist werden und als Ausgangsdaten annotierte Daten betreffend das zu untersuchende Bauteil enthaltend ein Ergebnis der jeweiligen Routine generieren, wobei wenigstens eine KI-Routine mit annotierten Ausgangsdaten wenigstens einer der anderen KI-Routinen trainiert wird; sowie
• - ein Bauteilanalysator zur Untersuchung von Bauteilen auf Fehler mit einer Aufnahme, in welcher das Bauteil während der Untersuchung positioniert ist; wenigstens einem Sensor, insbesondere optischen Sensor, um Sensordaten betreffend ein zu untersuchendes Bauteil zu generieren; einem Steuergerät, um den Sensor derart zu steuern, dass dieser die Sensordaten automatisch generiert; einer Schnittstelle zu einem KI-Modul mit wenigstens einer Kl-Routine zur Objektanalyse, wenigstens einer KI-Routine zur Erkennung und Klassifikation von Mängeln, die dem KI-Modul aus Datensätzen bekannt sind, und wenigstens einer KI-Routine zum Erkennen von Anomalien, die dem KI-Modul aus Datensätzen nicht bekannt sind, wobei die KI-Routinen des KI-Moduls miteinander in Wechselwirkung stehen; und mit Mitteln zum Sortieren von untersuchten Bauteilen entsprechend deren Untersuchungsergebnissen.

Accordingly it is provided:

• - a method for examining components for defects using a component analyzer, the method comprising an AI routine for object analysis and an AI routine for detecting and classifying defects that are known to the component analyzer from data sets and/or an AI routine for Detection of anomalies that are not known to the component analyzer from data sets, the AI routines being fed with sensor data or processed sensor data relating to a component to be examined as input data and annotated data relating to the component to be examined as output data containing a result of the respective routine generate, wherein at least one AI routine is trained with annotated output data of at least one of the other AI routines; as well as
• - a component analyzer for examining components for defects with a holder in which the component is positioned during the examination; at least one sensor, in particular an optical sensor, to generate sensor data relating to a component to be examined; a control device to control the sensor such that it automatically generates the sensor data; an interface to an AI module with at least one AI routine for object analysis, at least one AI routine for detecting and classifying defects that are known to the AI module from data sets, and at least one AI routine for detecting anomalies are not known to the AI module from data sets, whereby the AI routines of the AI module interact with each other; and with means for sorting examined components according to their examination results.

A sensor, also known as a detector, (measurement or measuring) transducer or (measuring) probe, is a technical component that detects certain physical, chemical properties or states, e.g. B. temperature, humidity, pressure, speed, brightness, acceleration, pH value, ionic strength, electrochemical potential and / or the material nature of its environment can be recorded qualitatively or quantitatively as a measurement variable. These variables are recorded using physical or chemical effects and converted into an electrical signal that can be further processed as sensor data. Sensors include camera, lidar, radar, TOF and other sensor technologies, such as acoustic sensors.

Computer program products typically include a sequence of instructions that, when the program is loaded, causes the hardware to perform a specific procedure that results in a specific result.

Machine learning or artificial intelligence (AI) is a generic term for the “artificial” generation of knowledge from experience: an artificial system learns from examples and can generalize them after the learning phase has ended. To do this, machine learning algorithms build a model that is based on training data. This means that the examples are not simply memorized, but patterns and regularities are recognized in the learning data. The system can also assess unknown data (learning transfer) or fail to learn unknown data (overfitting).

In artificial intelligence or machine learning, the type and power of knowledge representation play an important role. A distinction is made between symbolic approaches, in which the knowledge - both the examples and the induced rules - is explicitly represented, and non-symbolic approaches, such as neural networks, which are "trained" to behave in a predictable manner, but which do not provide any insight into it allow learned solutions; Knowledge is implicitly represented here.

An AI routine is a computer program section that is implemented using artificial intelligence.

Object analysis refers to determining the properties of a component. This includes, for example, object classification, i.e. the division of components into different groups/classes according to their type and/or properties, the measurement of an object, or object recognition, i.e. the classification of components according to their type and/or properties.

If defects are known to a component analyzer or an AI routine, it can be assumed that the AI routine has already processed sensor data regarding comparable defects in the past, or that the AI routine has already been trained on this.

Training manifests itself in a quantitative assessment of the distribution of training data. An AI uses the training data to learn what distribution of sensor data can be expected in the future.

Anomalies are defects that are not known to an AI routine. These can, for example, be defects that occur rarely or are caused by a change in the manufacturing process. Anomaly detection can be achieved using statistical methods in conjunction with artificial intelligence by first determining a distribution of sensor data. If the distribution deviates from the expected distribution by more than a predetermined standard deviation factor, it may be useful to detect an anomaly.

As part of anomaly detection, the distribution of expected training data, e.g. regarding error-free components or components with known errors, can be determined as a reference and/or patterns can be determined in the data based on historical data, which can be classified at least into the normal classes through appropriate annotations and optionally classified as abnormal.

One way to train an AI is error feedback. In the early training phase, an AI makes mistakes. To correct the error, the triggers of the deviations (errors) between the generated assignment (actual output data) and the solution assignment (target output data) are traced back and controlling factors are changed in such a way that the assignment errors become smaller.

In this application, training data is data pairs consisting of input data that is to be processed by the AI and target output data that is to be determined by the AI. During training, the AI is adjusted based on a comparison of target output data with the actual output data determined by the AI, which creates a training effect.

An examination result can, for example, be the classification of a component into quality classes, such as good/not good, or a probability for the quality of a component. A result space can contain any number of classes

The components of a component analyzer include hardware and/or software modules, comprising hardware and/or software modules for regulating and/or controlling industrial manufacturing processes. The hardware modules include electronic units, integrated circuits, embedded systems, microcontrollers, multiprocessor systems-on-chip, central processors and/or hardware accelerators, for example graphics processors, data storage units and connectivity elements, for example WLAN modules, RFID modules, Bluetooth modules, NFC modules . According to one aspect of the invention, the AI modules are executed as functional software in the cloud infrastructure.

The commands of the computer programs according to the invention include machine instructions, source text or object code written in assembly language, an object-oriented programming language, for example C++, or in a procedural programming language, for example C. According to one aspect of the invention, the computer programs are hardware-independent application programs that, for example, via a data carrier or a data carrier signal is provided using Software Over The Air technology.

The basic idea of the invention is a component analyzer or a method for examining components using several AI routines, each of which is specialized for individual special tasks. This includes at least one AI routine for object analysis, at least one AI routine for detecting and classifying defects that are known to the component analyzer from data sets, and/or at least one AI routine for detecting anomalies that are not known to the component analyzer from data sets are.

The basic idea of the invention is also the interaction between different AI modules. Accordingly, the invention comprises at least two AI modules -

It is intended that the AI routines interact with each other, which means that the AI routines learn from each other. For example, it can be provided that if the AI routine detects a previously unknown anomaly, this deviation will also be recognized in the future by an AI routine for detecting and classifying defects. It is also planned that the AI routines can process output data from other AI routines. For example, it can be provided that a result of an AI routine for object analysis is further processed by an AI routine for detecting and classifying defects.

Furthermore, it is envisaged that the AI routines are fed with sensor data or processed sensor data relating to a component to be examined and generate annotated output data for these sensor data with conclusions that the respective AI routine has determined.

Advantageous refinements and further developments result from the further subclaims and from the description with reference to the figures in the drawing.

According to a preferred development of the invention, the annotated data is at least partially checked by a human editor. For this purpose, the component analyzer has a human-machine interface.

It can be provided that a further AI routine is provided for determining the reliability of output data and that the annotated data is presented to a human processor for checking, provided that the reliability determined for the annotated output data falls below a predetermined threshold value.

Alternatively, it can be provided that the output data of the AI routine for detecting anomalies is generally checked by a human processor, provided that the output data contains recognized anomalies. This means that newly occurring defects can be checked and production coordinators can be informed about new defects that have arisen. The human editor can also decide whether other AI routines are trained with respective annotated source data.

According to a preferred development of the invention, a first examination result is generated by means of at least a first AI routine regarding the quality of a component, while the component analyzer has access to the component and the component is prepared by the component analyzer for sorting according to quality classes or is sorted according to quality class.

This means that the component analyzer decides on the quality of a component within the clock frequency. The component analyzer can therefore also ensure or at least prepare for the sorting out of rejects.

It is also useful if a second examination result is generated using at least a second AI routine regarding the quality of a component if the component was sorted into a positive quality class based on the first examination result, the second examination result being generated while the component analyzer does not has access to the component.

This makes it possible to carry out further examinations of the sensor data after a component is no longer in the component analyzer. This ensures that the clock frequency is not slowed down to wait for the results of the AI routines. Instead, it can be planned to carry out examinations that require a longer period of time while a component is being transported or further processed.

It is also expedient if a batch containing components that were sorted into a positive quality class based on the first test result is retrieved if a second test result corresponding to a negative quality class was generated for at least one component of the batch.

Provision can be made to discard the entire batch or to examine which component of the batch generated a negative second test result.

According to a preferred development of the invention, optical sensor data relating to a component to be examined are transformed to a predetermined size and at least one AI routine is fed with the transformed sensor data.

Image data with a fixed size is often easier to process by an AI routine. In the past, such changes to image data to a fixed size were often not considered, as this often results in the loss of interpretability for human editors, as a transformation to a fixed size causes distortions, for example. However, experiments have shown that AI routines can handle bias, and bias does not reduce the reliability of an AI routine's results.

According to a preferred development of the invention, the AI routine for object analysis is fed with optical sensor data and the fed AI routine generates image sections relating to relevant features of a component as output data. It is intended that the initial data (annotated image sections) be annotated with annotations by the AI routine for object analysis.

The annotations can, for example, contain information about which component it is. AI routines that are downstream in the investigation process of the AI routines for object analysis can use this result and, for example, assess the relevance of abnormalities in sensor data based on the object analysis.

It is also useful if at least one AI routine for detecting and classifying defects and/or at least one AI routine for detecting anomalies is fed with annotated image sections.

This can also ensure that a component analyzer examines a large number of components that are different in nature, without the need for measures to change the component analyzer.

According to a preferred development of the invention, at least two, in particular a plurality, AI routines for detecting and classifying defects are provided, each of the AI routines for detecting and classifying defects of a predetermined type and/or specialized in a predetermined location of defects is. For example, one AI routine can be specialized for detecting scratches and another AI routine can be specialized for detecting breakage damage. Alternatively or additionally, another AI routine may inspect a coating, a weld, or other local features in a specific local area of the component.

A computer program product according to a method of an embodiment of the invention carries out the steps of a method according to the preceding description when the computer program product runs on a computer. When the program in question is used on a computer, the computer program product produces an effect, namely the interaction of multiple AI routines, which improves the reliability of reject detection in a component analyzer.

CONTENTS OF THE DRAWINGS

• 1 ein schematisches Blockdiagramm einer Ausführungsform der Erfindung;
• 2 eine schematische Prinzipskizze einer Ausführungsform der Erfindung.

The present invention is explained in more detail below using the exemplary embodiments shown in the schematic figures of the drawings. It shows:

• 1 a schematic block diagram of an embodiment of the invention;
• 2 a schematic principle sketch of an embodiment of the invention.

The accompanying drawings are intended to provide further understanding of embodiments of the invention. They illustrate embodiments and, in connection with the description, serve to explain principles and concepts of the invention. Other embodiments and many of the advantages mentioned arise with regard to the drawings. The elements of the drawings are not necessarily shown to scale with each other.

In the figures of the drawings, identical, functionally identical and identically effective elements, features and components are provided with the same reference numerals - unless stated otherwise.

DESCRIPTION OF EMBODIMENTS

1 shows a schematic block diagram according to a method for examining components for errors using a component analyzer. The method includes an AI routine for object analysis K1, as well as an AI routine for detecting and classifying defects K2 and an AI routine for detecting anomalies K3. The AI routines K2 and K3 are downstream of the AI routine K1.

The AI module with the AI routines K1, K2, K3 is fed with sensor data S relating to a component to be examined and from this generates output data containing annotated data relating to the component to be examined.

Furthermore, the AI routines K2 and K3 are fed with the annotated output data of the AI routine K1.

It is also provided that at least one AI routine is trained with annotated output data from at least one other AI routine. The training can take place during ongoing operations or on an event-related basis.

2 shows a schematic block diagram of a component analyzer for examining components for errors. The component analyzer comprises a receptacle 1 in which the component is positioned during the examination, at least one sensor 2 to generate sensor data relating to a component to be examined, a control device 3 to control the sensor in such a way that it automatically generates the sensor data, an interface 4 to an AI module 5 with at least one AI routine K1 for object analysis, at least one AI routine K2 for detecting and classifying defects, and at least one AI routine K3 for detecting anomalies. Furthermore, the component analyzer has means 6 for sorting examined components according to their examination results.

Reference symbols

K1

AI routine

K2

AI routine

K3

AI routine

S

Sensor data

A

Output data

1

Recording

2

sensor

3

Control unit

4

interface

5

AI module

6

Medium

10

Component analyzer

Claims (11)

Method for examining components for defects using a component analyzer, where the procedure an AI routine (K1) for object analysis and an AI routine (K2) for detecting and classifying defects that are known to the component analyzer from data sets and/or has an AI routine (K3) for detecting anomalies that are not known to the component analyzer from data sets, wherein the AI routines are fed with sensor data or processed sensor data relating to a component to be examined as input data and generate annotated data relating to the component to be examined as output data containing a result of the respective routine, wherein at least one AI routine is trained with annotated output data of at least one of the other AI routines. Procedure according to Claim 1 , whereby the annotated data is at least partially checked by a human editor. Method according to one of the preceding claims, wherein a first examination result is generated by means of at least a first AI routine regarding the quality of a component while the component analyzer has access to the component, and the component is prepared by the component analyzer for sorting according to quality classes or according to quality classes is sorted. Procedure according to Claim 3 , wherein a second examination result is generated using at least a second AI routine regarding the quality of a component if the component has been sorted into a positive quality class based on the first examination result, the second examination result being generated while the component analyzer has no access to the component . Procedure according to Claim 4 , wherein a batch containing components that were sorted into a positive quality class based on the first test result is retrieved if a second test result corresponding to a negative quality class was generated for at least one component of the batch. Method according to one of the preceding claims, wherein optical sensor data relating to a component to be examined are transformed to a predetermined size, and at least one AI routine is fed with transformed sensor data. Method according to one of the preceding claims, wherein the AI routine for object analysis is fed with optical sensor data and image sections relating to relevant features of a component are generated as output data, the output data, hereinafter referred to as annotated image sections, being used by the AI routine for object analysis with annotations be annotated. Procedure according to Claim 7 , wherein at least one AI routine for detecting and classifying defects and/or at least one AI routine for detecting anomalies are fed with annotated image sections. Method according to one of the preceding claims, wherein at least two, in particular a plurality, AI routines are provided for detecting and classifying defects, each of the AI routines for detecting and classifying defects of a predetermined type, predetermined cause and / or due to a specialized in a predetermined location of defects. Component analyzer (10) for examining components for errors - a receptacle (1) in which the component is positioned during the examination; - at least one sensor (2), in particular an optical sensor, in order to generate sensor data relating to a component to be examined; - a control device (3) to control the sensor in such a way that it automatically generates the sensor data; - an interface (4) to an AI module (5) with at least one AI routine (K1) for object analysis, at least one AI routine (K2) for detecting and classifying defects that are known to the AI module from data sets , and at least one AI routine (K3) for detecting anomalies that are not known to the AI module from data sets, the AI routines of the AI module interacting with one another; and with - Means (6) for sorting examined components according to their examination results. Computer program product with program code means to carry out the method according to one of the Claims 1 - 9 to carry out.

Images