EP1984795A1

EP1984795A1 - Method and apparatus for monitoring a production line

Info

Publication number: EP1984795A1
Application number: EP06819009A
Authority: EP
Inventors: Martin KÄSEMANN; Stefan Strathmann; Helmut Herrmann
Original assignee: Henkel AG and Co KGaA
Current assignee: Henkel AG and Co KGaA
Priority date: 2006-01-19
Filing date: 2006-12-08
Publication date: 2008-10-29
Also published as: US20110019877A1; DE102006002704A1; WO2007082575A1; WO2007082575A9

Abstract

The invention relates to a method and an apparatus for monitoring a production line on which objects (5) are transported between machines (2, 3) using transport paths (4). In order to accurately detect faults early, a method having the following method steps is proposed: (a) a reference image sequence which maps at least one transport path (4) to be monitored between machines (2, 3) is generated; (b) a statistical characteristic variable which is derived from the movement of the objects (5) which are transported between the machines (2, 3) is determined; (c) a test image sequence which maps the same transport paths (4) between the machines (2, 3) is generated; (d) a statistical characteristic variable which is derived from the movement of an object (5) is determined for each of the mapped objects (5); (e) the statistical characteristic variable determined for the test image sequence is compared with the statistical characteristic variable determined for the reference image sequence.

Description

Method and device for monitoring a production line

The invention relates to a method and a device for monitoring a production line.

In the production of liquid or solid consumer goods, these are usually filled into containers in the course of the production process in order to bring them to the retail trade in such a packaged state. In the filling and packaging processes, a large number of containers of the same type are filled, closed, labeled and then packed or collected in further outer packaging at the highest possible speed.

The individual steps of filling, closing, labeling and further packaging are usually carried out in a production line by several machines. The containers are transported from one machine to the next. Transport belts, screw conveyors or similar devices are used for the transport, with which the containers or products are transported individually from one machine to the next.

The solid or liquid products are filled into the containers at the highest possible cycle rate. With known production systems, several hundred containers are filled, labeled and packed per minute and, accordingly, transported quickly between the individual machines.

For the trouble-free operation of such a production plant, trouble-free transport of the products or containers is essential. If, for example, containers are transported to a machine by means of a conveyor belt and if one of the containers is not delivered to the machine in a position from which the machine can further process the container, the machine and thus the production line can be blocked by this container.

Typical malfunctions when transporting the containers or products between the machines are, for example, placement outside the permissible limits on the conveyor belt or twisting or tilting or overturning on a conveyor belt Conveyor belt. The causes of such faults can be, for example, unexpectedly high tolerances in the geometric dimensions of the objects to be transported, incorrect setting of transport or handling systems or causes that change over time, such as vibrations, fluctuating climatic conditions or signs of wear.

An analysis of the causes of a malfunction in the production line is often carried out by trained people who are familiar with the production line and who try to identify the triggers based on the damage that has occurred. Such a manual error analysis is on the one hand time and personnel and thus expensive, on the other hand the damage that has occurred only allows the determination of the actual triggers to a very limited extent.

Various devices and methods are known for detecting and analyzing faults on conveyor belts in production lines, which enable automated and permanent monitoring of a production line.

WO01 / 50204 describes a method and system for monitoring a production line, in which sensors on the production line to be monitored record production data and deliver it to a computer system which compares the supplied data with preset limit values and, in the event of deviations, in a suitable manner on a screen for these displays the monitored production line. The system records, for example, the quantity of goods ejected from a machine or a conveyor belt and reports this to the computer system. This method and system thus enables a deviation to be determined quickly and conveniently, without however determining the causes of the deviation.

KR 2003053731 describes a device for monitoring a conveyor belt on which objects are transported. To monitor the conveyor belt, it has a current measuring device on its electric drive. A deviation in the current strength is interpreted as an indicator of a fault.

The methods and systems for monitoring a production line known from the prior art thus already detect the effects of a malfunction, for example a reduction in the output of a conveyor belt or a change in the operating parameters of a machine. Although this information is helpful for determining the cause, it is only possible to draw a limited conclusion about the cause of the fault.

The object of the invention is therefore to propose a method and a device with which the causes of a fault in a production line can be detected.

To solve this problem, a method for monitoring a production line, in which objects are transported between machines via transport routes, is proposed, which has at least the following method steps:

(1) generation of a reference image sequence, which images at least one region of a transport path to be monitored between the machines;

(2) determining a statistical parameter derived from the movement of an object transported between the machines;

(3) generating a test image sequence, which images the same area of a transport route between the machines;

(4) determining the statistical parameter derived from the movement of an object for at least one of the objects depicted in the test image sequence;

(5) Comparing the statistical parameter determined for the test image sequence with the statistical parameter determined for the reference image sequence.

In the first method step, a reference image sequence is first generated, which maps at least one area of a transport path to be monitored between the machines of a production line. This reference image sequence shows the trouble-free operation of the part of a production line to be monitored in a period of suitable length. Ideally, the reference image sequence not only captures a period of time in which the production line to be monitored is operated without problems, but in which the area to be monitored is operated with ideal parameters, so that it is ensured that the system is not operated at the limit of an operating parameter becomes.

A digital camera with a CCD or CMOS chip, for example, can be used to generate the reference image sequence, with which the desired part of a production line is captured in an image-generating manner and from which the individual images of an image sequence are supplied to a connected computer via a connection will. As an alternative to a digital camera, an image sequence could initially also be generated with a conventional analog camera, the images being digitized in a later method step. An image sequence could furthermore be composed of several partial sequences that cover different areas of a production line at a time in order to be subsequently processed as a whole. In this way, a production line could be completely recorded and monitored.

The reference image sequence generated in this way is first stored on the computer and evaluated in a subsequent method step.

This evaluation in a later method step includes the determination of a statistical parameter derived from the movement of the objects, for example the speeds of the objects transported between the machines, that is to say the products to be packaged or the packagings or the packaged and further processed products.

In a preferred embodiment, the statistical parameter derived from the movement of an object is the speed of an object.

Alternatively, the acceleration, as occurs, for example, when the direction of a movement of an object changes, can be determined and processed as a statistical parameter derived from the movement of an object. For the sake of simplicity, however, the speed of an object is assumed below as the statistical parameter derived from the movement of the object.

The statistical parameter, for example the speed of a moving object in one direction, is determined using known algorithms by first determining corresponding pixels in successive images, for example on the basis of their color or gray value. Since the time period between the successive images is known, the speed of the imaged object can be determined by moving the image points. The determined speeds of the transported objects are then saved for further use. In this way, for each place the whole in the Transport image shown in the reference image sequence determines the speed of a transported product.

The statistical parameter of an object is advantageously determined for each location on the transport route, so that the entire length of the transport route is monitored without gaps.

Furthermore, it is advantageous if the statistical parameter for each object, which is shown in the test image sequence, is determined and compared with the corresponding parameter of the reference image sequence.

The reference image sequence must record a sufficiently long period of trouble-free operation so that a sufficiently large amount of data is available for the determination of the speeds in order to be able to calculate temporal averages of the speeds.

In a next process step, a test pattern sequence is generated. For this purpose, the camera delivers the generated images to the computer, which summarizes them in test image sequences of a predetermined length. The test pattern sequence starts the operation of the production line within a period of time, which may have a situation that can be recognized as different below. This divides the entire monitoring time into sections. A test pattern sequence is generated for each time period, which is further processed in the further steps of the test method.

Since the method compares information from the test image sequence with corresponding information from the reference image sequence in a later method step in order to determine a deviation of the test image sequence from the ideal state or fault-free state, the test image sequence must map the same machines and conveyor belts as the reference image sequence.

The image sections when generating the reference and test image sequence and the image repetition rates of the camera are advantageously identical. Based on the test pattern sequence, the speeds of the objects in the test pattern sequence are now determined in a further method step analogous to the determination of the speeds in the reference image sequence. For each transported object, the speed at the current location of the object is determined. For this purpose, the same algorithm is preferably used as was used to determine the speeds in the reference image sequence.

The determined speeds of the objects in the test image sequence are compared in a further method step with the speed values determined for the reference image sequence. If deviations between the speeds are determined in this comparison, this indicates a possible cause of a fault. Such a deviation in the speed of an object can be, for example, a jam of objects in front of a machine that takes the objects off the belt.

By comparing the speeds of the objects, the method thus determines those locations where the actual speed of an object deviates from that which the object had at this location during the trouble-free reference operation, namely during the generation of the reference image sequence.

The process thus enables permanent automatic monitoring of a production line.

In a preferred embodiment, a deviation is only evaluated as a deviation in the comparison if the size of the deviation exceeds a preset limit value. A detected deviation that is below the preset limit value is therefore not considered a relevant deviation. The result of this is that a tolerance range is defined for the speeds, so that only the speed deviations that are known from experience are evaluated as relevant and treated accordingly.

Speed deviations are advantageously marked in the test pattern sequence in such a way that each location of a test pattern sequence is marked at which a deviation in the speed between objects of the test sequence and the reference image sequence was determined. The location can, for example, by specifying the X and Y coordinates in the Image can be given. Alternatively or additionally, the location of a deviation on a display screen can also be marked in color by the location of the deviation being highlighted in a striking color. If, for example, the image area in which no deviation was found is highlighted in green, this area can be highlighted in red to indicate a detected speed deviation.

The ascertained speed deviation can advantageously be displayed by specifying the direction and the amount of the determined deviation and / or by specifying the speed components in the X and Y axis directions, the X and Y axes of the generated images being used as a coordinate system for display serve the speed deviations.

A test pattern sequence for which a relevant speed deviation has been determined is then saved. If several test pattern sequences with relevant speed deviations are determined in quick succession, the last determined test pattern sequence can always be shown on a display. Older test pattern sequences can, however, also be displayed, if desired, so that the information is available for a later error analysis over several test pattern sequences. Test pattern sequences for which no relevant speed deviations have been determined can, however, be deleted or are not saved.

The method can advantageously have the method step that, after the generation of the reference image sequence, the largest contiguous moving image area is determined therein and subsequent method steps are carried out exclusively for this image area. When generating the reference and test image sequences, the camera typically cannot only record only those areas in which objects are transported from one machine to another. In order to keep the amount of data to be processed in the subsequent method steps as small as possible and thus to enable the image sequences to be processed as quickly and promptly as possible, the largest contiguous area in which objects are moved is determined after the generation of the reference image sequence. This is the area of the conveyor belt to be monitored. Other areas where, for example, machine parts are moving and people move are not considered any further. On the one hand, this results in a reduction in the amount of data to be processed, and on the other hand, the method is thus insensitive to movements that do not take place in the area to be checked, that is to say in the area of the conveyor belt.

To determine the image areas and the largest coherent image area in which objects are moved, the temporal variance of the color or gray value is determined for each pixel of all images in an image sequence by measuring the color or gray value. Only if this is significantly above the statistical noise level is this regarded as the movement of objects and the area is treated accordingly. Image areas in which the temporal variance of color or gray values of pixels lies below the statistical noise level are masked for the subsequent method steps and are not taken into account.

The largest coherent moving image area determined can be marked in the reference and test image sequences, in particular highlighted in color. When the image sequences are displayed, this enables a simple and quick check as to whether the image section determined as relevant has been correctly determined.

In a further method step, those image areas in which the color values of individual pixels fluctuate considerably over time can advantageously be marked as not relevant and thus be disregarded in subsequent method steps. In such image areas, it is only possible with a disproportionately high amount of computation and thus time to determine the movement of an object and thus its speed of movement. However, since the monitoring system should process the evaluation of the generated test image sequences as quickly and as quickly as possible, so that a display or other reaction to a determined speed deviation can occur as soon as possible, complex algorithms for determining the speed of an object in a region of strongly changing colors are unsuitable here . Such image areas are therefore advantageously marked as irrelevant for subsequent process steps. Typically, such areas are caused by light reflections on the transported objects or by moving surfaces of liquids in transparent containers. To carry out the method, a device is used which has at least one camera for generating the images and a computer connected to the camera. The camera can be controlled via the connection to the computer in such a way that the generation of the images is triggered and controlled by the computer and the images are then transferred to the computer. All further processing steps are carried out on the computer.

The method can be represented in a computer program which can carry out all method steps of the method, trigger the generation of the images in the camera and control the image settings. The generated images or image sequences as well as determined speed deviations can be displayed on a screen. You can manually intervene in the program at any time. For example, the evaluation of the reference image sequence, in particular the determination of the largest contiguous moving area, can be checked by one person.

The repeated generation and evaluation of test image sequences following the evaluation of the reference image sequence then take place automatically.

The computer program can be designed in such a way that the images for the next test pattern sequence are already generated and transmitted to the computer during the processing of a test pattern sequence, so that continuous monitoring is possible.

In practice, a portable computer, for example a laptop, in connection with a portable black and white CCD camera, which can be used together as a mobile system without a time-consuming installation, has proven itself as a computer. In particular, this mobile system enables monitoring of machines or conveyor belts that have not yet been monitored or for which a permanently installed monitoring system is too complex and whose economic benefits are therefore questionable. The method according to the invention is described in more detail below using an exemplary embodiment. Show it:

Fig. 1 is a schematic representation of a production line

Monitoring device Fig. 2 is a schematic representation of the largest contiguous moving

3 shows a graphical representation of the determined speed and a

Deviation from this

Fig. 1 shows a schematic representation of a production line 1 with the monitoring system. The production line has a first machine 2 and a second machine 3, which in this exemplary embodiment are a filling machine 2 and a labeling machine 3. The filling machine 2 fills the bottles 5 with a liquid. A conveyor belt 4 transports objects 5, here transparent bottles 5, in the direction indicated by arrow 6 first to the filling machine 2, then to the labeling machine 3.

The monitoring system has a camera 7 for generating the reference and test image sequences, which is connected to a computer 8. The camera 7 is positioned such that it captures the section of the conveyor belt 4 to be monitored from a position elevated relative to the conveyor belt 4. The generated image sequences thus show a supervision of the part of the production line 1 to be monitored or the part of the conveyor belt 4 to be monitored.

In this exemplary embodiment, the camera 7 records the area delimited by the frame 9 drawn in broken lines, which comprises a piece of the conveyor belt 4 which transports bottles 5 from the filling machine 2 to the labeling machine 3. The image sequences generated by the camera 7 thus represent the section of the conveyor belt 4 to be monitored between the machines 2, 3.

At the beginning of the method, the camera 7 generates the images for the reference image sequence, which reproduces the trouble-free and ideally possible transportation of the bottles 5. The reference image sequence usually has a duration of a few seconds to a few minutes, typically 60 seconds. For this period of time is through Manual checking ensures that the transport of the bottles 5 by means of the conveyor belt 4 runs smoothly and with ideal parameters.

The camera 7 is set so that it generates the images for the reference image sequence with a sufficiently high image frequency so that the movement of the bottles 5, which are the objects of interest here, can be clearly tracked on the conveyor belt 4 to be monitored using the images . In practice, it has been shown that the image frequency should preferably be set so that an object moves by a maximum of 4 pixels between two images.

With conventional conveyor belts and a camera distance that ensures a sufficient size of the moving objects, the camera should generate the image sequences with more than 50 images per second.

It is also sufficient if the image sequences are generated in black and white, so that colors are displayed as gray values. The mapping of the area to be monitored in black and white images, in which the colors are recorded as gray values, results in a smaller amount of data, but at the same time it is ensured that the generated images have sufficient information content to determine an object and its respective speed can.

The images of the reference image sequence are transmitted from the camera 7 to the computer 8, which takes over the entire further processing of the images.

In the reference image sequence, the computer first determines the areas in which any movement takes place. On the one hand, this is the area in which the bottles 5 are moved by means of the conveyor belt 4. On the other hand, moving machine parts or a moving person can be depicted in the image sequences. The image sections recognized as moving image areas can be displayed on the screen of the computer 8 so that they can be checked so that they can be checked.

FIG. 2 shows the image section delimited by the dashed frame 9, which the camera 7 records from its position. The computer 8 has determined the largest contiguous moving image area 10 for all images and thus all image sequences that are generated from this position of the camera 7. This image area 10 is marked visibly on the screen of the computer 8, for example by the background being colored. In Fig. 2, the largest contiguous moving image area 10 is marked by hatching.

The marking of this image section, which the computer 8 has determined as the largest contiguous moving area 10, applies to all images of the reference image sequence and the test image sequences, so that the determination of this area only has to be carried out once at the beginning of the method using the reference image sequence.

All subsequent method steps are only carried out for the largest coherent moving area identified. This has the effect that the computer 8 only has to process a partial section of the image and consequently only a part of the image data, so that the amount of data to be processed is considerably reduced and further processing can take place promptly.

FIG. 3 shows a graphic representation of the determined speeds of the transported bottles 5 in the horizontal direction of the image and along the transport path. The X axis of the coordinate system indicates the location in the X direction along the conveyor belt 4. The value of the speed in the X direction, that is to say the speed component Vx, is indicated on the Y axis of the graphic.

The hatched line 11 indicates the speeds Vx of the bottles 6, which were determined on the basis of the reference image sequence. The entire length of the conveyor belt 4 shown in the pictures is divided into sections 4a to 4e by the curves 12a to 12d. On the first route section 4a and the sections 4c and 4e parallel thereto, the speeds of the bottles 5 are greatest and almost the same in the reference image sequence. In the curves 12a to 12d, the magnitude of the speed in the X direction decreases sharply. On the route sections 4b and 4d running in depth in the drawing, the speeds of the bottles 5 are considerably lower, but not zero, since the camera captures an oblique view of these route sections. Analogously to the determination of the speeds in the X direction, the speeds are also determined in the transport direction perpendicular thereto, which runs into the paper plane in the representations and is not shown here.

The speeds are averaged over time. As an alternative to a temporal averaging of the speeds, a spatial averaging is also conceivable, in which the averaging or the determination of a statistical parameter takes place over an image area defined around a pixel to be considered. In a further alternative, a spatio-temporal averaging could be carried out in which a plurality of successive images of a sequence and of these an image area around a pixel to be considered are used to determine the statistical parameter.

Instead of such a first-order statistical parameter, i.e. a temporal averaging of the speed value, statistical parameters of a higher order, for example the standard deviation or variance, or statistical parameters of a third or even higher order can be used as a reference value for determining a deviation from the ideal case. For the sake of simplicity, however, the invention is explained below on the basis of speed deviations.

The speeds determined in this way on the basis of the reference image sequence are stored and serve as reference values for the test image sequences to be subsequently generated.

After the reference speed values in the X and Y directions have each been determined from the reference image sequence, the test image sequences can subsequently be generated and evaluated. To monitor the normal operation of the conveyor belt, test image sequences are now generated which show the conveyor belt during normal operation. The faults should be recognized early on using the test pattern sequences.

The test image sequences are generated with the same camera settings and from the same position as the reference sequence, so that the test image sequences can be compared with the reference image sequence. A test pattern sequence has a duration of a few seconds to a few minutes, the duration of the test pattern sequence being able to deviate from the duration of the reference pattern sequence. The Test image sequences are contiguous to one another so that the area to be monitored is monitored without interruption during monitoring.

The speeds of the bottles 5 along the transport path are then determined on the basis of the test image sequences. The speeds or the speed components are preferably determined using the same algorithm that was used for the evaluation of the reference image sequence, so that deviations in speed values due to different determination methods can be excluded.

The speeds determined for a test image sequence are then compared with those of the reference image sequence in order to reveal deviations. A determined speed deviation is shown in FIG. 3 as a solid line 13. This indicates that the speed of the bottles 5 in the X direction in front of the curve 12d and on the subsequent conveyor belt section 4e is lower than the reference speed. This means that the bottles 5 are transported from the location before the change of direction 12d to the labeling machine 2 more slowly than in the reference image sequence. However, since bottles 5 are transported at the reference speed to the location from which the transport speed is lower in the route sections lying in front of them, the bottles jam before the direction change 12d of the conveyor belt 4. As a further consequence of such a jam of bottles 5, they can jam or fall over, for example, and thereby trigger a fault in production line 1.

The speeds per se and the deviations of the speeds do not have to be converted into a physical unit. The absolute size of the speeds is irrelevant for the comparison of the speeds. Therefore, both the speeds themselves and the deviations can be specified in the pseudo-unit "pixel between successive images". This simplified consideration of the speeds and the deviations considerably simplifies the evaluation of the image sequences and thus reduces the computational effort required for the evaluation. Such a deviation in speed can arise, for example, in that the bottles rub along a guide rail at one point on the conveyor belt 4 and are thereby braked.

Another possible source for a speed deviation can be, for example, a transfer station that places the objects from a first to a second conveyor belt. Such a station can, for example, essentially be designed as a rotating disk on which the objects are placed and are transported in a rotating manner to be placed on the second conveyor belt. If the rotational speed of the disc deviates from the ideal value, the bottles are thereby placed, for example, on an edge of the second conveyor belt. This position of a bottle 5 on a conveyor belt 4 which deviates from the ideal state can, for example, cause a guide rail to touch, which could brake the bottle or not match the position of the bottle 5 expected by a further processing machine, so that this would cause malfunctions. The non-ideal position of the bottle on the second conveyor belt can therefore be a result of a speed deviation on the one hand, and can also trigger a - further - speed deviation on the other.

The comparison of the speeds of the bottles 5 from the test image sequences with those from the reference image sequence over the observed transport route thus enables the exact determination of all locations at which the speeds differ from one another. In particular, the location at which the speed of an object deviates from the reference speed for the first time and at which the chain of subsequent deviations and faults begins can thus be determined.

Test pattern sequences that have a deviation of the speeds from the reference speeds are permanently stored on a data carrier so that they are permanently available. Those test pattern sequences in which no speed deviation was found are deleted or not saved, since these only show the trouble-free operation and therefore do not provide any relevant information. Since a test pattern sequence lasts from a few seconds to a few minutes, the data volume to be saved is limited. Stored reference image sequences can be reloaded into the computer at a later time and can be used as a comparison for further test image sequences, which may be generated considerably later. However, the prerequisite for this is that the test image sequences are created with the camera settings with which the reference image sequence was created. In this way, a reference image sequence can again serve as a reference after a longer time, for example a few days, weeks or months, in order, for example, to determine the changes in the speed values of a production line 1 between two points in time that are relatively long apart. For example, it can thus be determined for an uninterrupted production line 1 whether and, if so, which speed changes can be determined if it is operated over a long period of time.

The method thus enables permanent monitoring of a production line or a section thereof, the time and location of the first deviation being ascertained and stored as an image sequence. Furthermore, further measures can be triggered in the event of a detected fault. For example, the computer can be connected to a control system that controls production line 1, so that an alarm can be triggered in it or the machines of the production line can be influenced directly.

Claims

Process for monitoring a production line (1), in which objects (5) are transported between machines (2, 3) via transport routes (4), with the following process steps:

(a) generating a reference image sequence, said image sequence representing at least one area of a transport path (4) to be monitored between machines (2, 3);

(b) determining a statistical parameter derived from the movement of an object (5) transported between the machines (2, 3);

(c) generating a test image sequence, which images the same area of a transport route (4) between the machines (2, 3);

(d) determining the statistical parameter derived from the movement of an object (5) for at least one of the objects (5) depicted in the test image sequence;

(e) comparing the statistical parameter determined for the test image sequence with the statistical parameter determined for the reference image sequence.

2. The method according to claim 1, wherein the statistical parameter derived from the movement of an object (5) is the speed of the object.

3. The method according to any one of the preceding claims, wherein the statistical parameter for each location of the transport route (4) is determined.

4. The method according to any one of the preceding claims, wherein the statistical parameter for each of the objects (5) shown in the test image sequence is determined.

5. The method according to any one of the preceding claims, wherein a deviation of the statistical parameter is evaluated as a deviation only if the deviation exceeds a preset limit.

6. The method according to any one of the preceding claims, wherein each location is marked in the test image sequence at which a deviation of the statistical parameter between the objects (5) of the test and the reference image sequence was determined.

7. The method according to claim 6, wherein the determined parameter deviation is shown in its X-axis component and its Y-axis component.

8. The method according to claim 6, wherein the location of a determined parameter deviation in the test image sequence is marked in color.

9. The method according to any one of the preceding claims, wherein a test image sequence is stored if a parameter deviation between the test image sequence and the reference image sequence has been determined.

10. The method according to any one of the preceding claims, wherein the method further comprises the step that, after the generation of the reference image sequence, the largest contiguous moving image area (10) is determined in this and subsequent method steps are carried out exclusively for this image area.

11. The method according to claim 10, wherein the determined largest coherent moving image area (10) is marked in the reference and test image sequences.

12. The method according to claim 10 or 11, wherein the determined image area (10) is highlighted in color in the reference and test image sequences.

13. The method according to any one of the preceding claims, wherein image areas are determined for the reference and the test image sequence and are not taken into account in the further method steps in which the color values of pixels have large temporal fluctuations.

14. The method according to any one of the preceding claims, wherein an average value is formed for each location when determining the speeds of the transported objects (5).

15. The method according to any one of the preceding claims, wherein the reference and test image sequences is generated from an elevated position relative to the transport path (4).

16. The method according to any one of the preceding claims, wherein the reference and the test image sequences are generated by means of a digital camera (7) and from the same camera position.

17. The method according to claim 16, wherein the camera position and the camera settings are selected such that the transported objects (5) have a shift due to their movement of a maximum of 4 pixels in the trouble-free operation between two successive images.

18. Device for monitoring a production line (1) with a method according to one of the preceding claims, wherein the device comprises at least:

(a) means (7) for generating image sequences which represent the transport path (4) to be monitored;

(b) a computer (8) for determining and comparing statistical parameters which are derived from the movement of the objects (5) by evaluating the image sequences.

19. The apparatus of claim 17, wherein the means (7) for generating the image sequences is a digital camera and the computer (8) is a portable computer.

20. Device according to one of the preceding claims 17 or 18, wherein the device for transmitting control signals is connected to a control unit of the production line (1).