EP3446216A1

EP3446216A1 - Real-time environment and programmable logic controller

Info

Publication number: EP3446216A1
Application number: EP17720035.9A
Authority: EP
Inventors: Marko TSCHEREPANOW; Dirk Janssen; Andre FOLKERS
Original assignee: Beckhoff Automation GmbH and Co KG
Current assignee: Beckhoff Automation GmbH and Co KG
Priority date: 2016-04-22
Filing date: 2017-04-18
Publication date: 2019-02-27
Also published as: DE102016107527A1; US20190033814A1; US10782667B2; WO2017182467A1; CN109074279A; CN109074279B

Abstract

At least one task with a pre-defined task run-time is executed in a real-time environment, wherein at least one auxiliary function with an undetermined function run-time should be processed within the pre-defined task run-time. To process the function, a time monitoring function is started, said function defining a termination time for the function within the pre-defined task run-time, and then the function is executed. The time monitoring function monitors the function run-time and if the pre-defined termination time is passed, the termination of the function is initiated. The time monitoring function is subsequently ended.

Description

description

Real-time environment and programmable logic controller The invention relates to a real-time environment and a SpeI ^¬ logic controller.

The control of actuators and sensors of a production plant usually takes place with the aid of a programmable logic controller (PLC), which can be present both as an external device and as a software PLC. The PLC controls via a suitable communication interface, as in ^¬ to play a field bus, the respective actuators and Senso ^¬ ren.

The control of actuators and sensors takes place on the PLC in the form of tasks, so-called tasks. The tasks are often executed cyclically. For faster processing, a PLC can also distribute tasks across multiple cores of a processor or multiple processors. A central task of the PLC in controlling the actuators and sensors is synchronization with the production process.

In order to realize real-time control, it must be ensured that the task to be executed within a specified ^differently surrounded maximum time, for example within the standing for one cycle time available, is processed. Wei ^¬ terhin has to be performed the cyclic execution of the task without time variation (jitter) with a predictable response time (latency). EP 2568346 Bl is known to cancel a task if the execution time of the task is longer than a previously de ^¬ finierte maximum execution time. If the task was not executed due to a timeout, the input variables are output as output variables of the task.

In DE 102 43 856 B4, a controller with function blocks is also described, wherein the function blocks can contain a real ^¬ time function. The real-time function is off, broken when the computing time exceeds a predetermined Re ^¬ conference time.

DE 10 2009 055 752 A1 further discloses a method in which a task can be interrupted in favor of another task.

From US Pat. No. 7,207,045 B2 a monitoring of the runtime of tasks with the aid of time windows assigned to the tasks is known.

In addition to the actuators and sensors that are controlled by the PLC, a production system usually has a large number of other systems whose functions must be synchronized with the production process and its control by the PLC.

For example, vision systems an essential Be ^¬ stand part of modern production facilities. They serve for object recognition, surface inspection, measurement or identification. In vision systems have a variety of image processing and image analysis operations are performed, which are preferably to be in synchronism with the production process Runaway ^¬ leads. Another additional function to be synchronized with the production process is condition monitoring, in which a regular or permanent recording and evaluation of the condition of the production plant is carried out by measuring and analyzing machine parameters that reflect the current state of the production process. Also in the field of machine learning, a synchronization of additional functions with the production process is desirable. The same applies to the numerical control, in which a program code is converted into working or movement sequences for a machine.

Vision systems as well as the other additional systems mentioned Condition Monitoring, Machine Learning and Numerical Control are usually in the form of separate software components separated from the PLC. In vision systems usually separate image processing computer or smart cameras are used, which are connected to the PLC via a Kom ^¬ munikationsmedium for example the Ethernet, I / Os or egg NEN field bus, to transmit the calculation results to the PLC.

When the vision function runs on an image processing computer, the connected cameras transmit the images or image regions to the image processing computer, which then carries out the problem-specific image analysis. The vision function can also be performed directly on the camera. The cameras can also have their own I / Os to communicate directly with the actuators and sensors of the production plant after appropriate configuration. It is then for the actuators and sensors of the production plant, the Mög ^¬ friendliness to trip over hardware trigger image capture by the cameras or to control the lighting. When using a software PLC can be used for control and image processing same hardware ^¬ to. When using an intelligent camera, in addition to the vision function, the software PLC can also run on the camera, which additionally limits the usually limited computing capacity of the intelligent camera. This approach is therefore only feasible for simple control and vision tasks.

Typically, data transfer between a normal user environment running the Vision component software and the PLC real-time environment is used to communicate the image analysis results from the vision component to the PLC. It consuming communication and synchronization steps in the Da ^¬ tenübertragung but are then required. Furthermore, the calculations required for the image analysis take place outside the real-time environment of the PLC and thus also asynchronously to the production process.

A data processing method is described in EP 1 312 990 A2 with which image and audio data relating to the movement sequence of a machine can be linked to the data of the movement and drive control of the machine. For this purpose, the image and audio data are provided with a time stamp generated by the motion and drive control. The image and audio data synchronized in time to the data of the movement and drive control of the machine can then be further processed or displayed. A significant problem in the synchronization of additional functions, such as vision systems, the production process is that their maturity strongly with output data is affected by a ^¬. The reason for this can analysis by the vision systems such as the Weiterver ^¬ processing after detection of relevant structures, the iterative application of an algorithm as a function of a con ^¬ vergenzkriteriums, alternative search strategies or so-called regions-of-interest in the image of variable size in the image be. The calculation results are then available at variable times. However, this contradicts the requirement of the PLC, a zyk ^¬ metallic execution of the task without a time fluctuation (jitter-ter) with a predictable response time (latency) to ge ^¬ währleisten, thus allowing easy integration of vision function in the real-time environment of the PLC prevents becomes.

The same applies to the other additional functions mentioned. In condition monitoring, time series are often analyzed with the aid of iterative methods whose duration depends on the achievement of a quality criterion. For machine learning, too, the required computation time, for example for training and the application of classifiers or function approximators, depends significantly on the input data. The numerical control uses complex iterative optimization algorithms whose runtime varies.

The object of the present invention is to provide a real-time environment and a programmable logic controller bereitzustel ^¬ len that allow integration of additional functions with an undefined function term in the real-time environment. This object is achieved with a real-time system according to claim 1 and with a programmable logic controller according to claim 12Q. Preferred developments are specified in the dependent claims.

According to the invention, at least one task is executed in the real-time environment with a predetermined task runtime, wherein at least one function is to be executed within the specified task runtime. The execution of the function takes place by starting a time monitoring function, which determines a termination time for the function within the specified task runtime, and then ^executing the function. The time monitoring function monitors the function run time, wherein a function abort is initiated when the predetermined abort time is exceeded. On closing ^¬ the time monitoring function is terminated.

By providing the time monitoring function, the execution of the additional function is designed such that the functional runtime can be controlled in dependence on the computing time still available in the current cycle of the task. The additional function can therefore be executed directly in the real-time environment of the PLC. Data processing of the additional function outside of the real-time environment and its einherge- Henden communication and synchronization steps entfal ^¬ len. Furthermore, a time-exact coupling of additional function to the timing of the production process is achieved.

In the real-time environment, an abort function is also provided, which is called when the predetermined abort time is exceeded by the function runtime in order to execute the abort function. In such an approach way, within the given task runtime ab ^¬ working additional function is timely terminated after exceeding the termination time. Alternatively, the function may include an abort condition which, when the predetermined abort time is exceeded by the functional run time, ^aborts the execution of the function and ^returns a processing result. Such a procedure ensures a controlled abort of the function. The results of the additional function at the cut-off time can then be fully continue USAGE ^¬ det.

The time monitoring function can determine the given abort time when called as the sum of the current time and a maximum allowed time. The termination time can then be determined dynamically and flexibly adjusted. Further, the time monitoring function when quitting may output a parameter indicating the fraction of the carried Funktionsaus ^¬ management. Alternatively or additionally, the parameter may indicate the number of accumulated functional elements. The parameter represents a measure of confidence in the corresponding calculation results of the additional function. The parameter can also be used to carry out an adaptation of the additional function.

The function can have a plurality of functional elements, wherein the characteristic value output when terminating the time monitoring function indicates the accumulated component of the execution of the functional elements. With this hens as is possible functional elements to bün ^¬ spindles to monitor their maturity together. Furthermore, loops, for example, which call functional elements iteratively, can also be included in runtime monitoring in a simple manner. The accumulation then calculates the parameters of the transit time monitoring of the individual functional elements to a total result over the entire monitored period of time. Furthermore, the time monitoring function can output a time value when ending, which indicates the time difference between the current time and the predetermined abort time. This determined remaining time can be used, for example, to optimize the execution of the additional function in the real-time environment. Furthermore, a use of a computing time interval in the length of the remaining time by other components of the real-time system is conceivable.

The time monitoring function can return an error code representative of an error condition in the exporting ^¬ tion of the time monitoring function when closing further.

The time monitoring function may include at least one subordinate time monitoring function element that sets an abort time for an associated function within the predetermined task run time prior to the abort time point of the time monitoring function. With such interleaved time monitoring function elements, individual functional elements of the additional function, ie program code areas such as loops, can be ^monitored separately with respect to their running time. The time monitoring function is managed using a stack. The stack provides an easy way of forming hierarchical levels of the individual time monitoring function elements by means of an appropriate positioning on the stack.

A programmable logic controller is connected via a fieldbus with actuators and sensors of a production plant. The programmable logic controller in this case comprises a real-time environment in the previously explained form whose task is to control actuators and sensors, the execution of the function being synchronized with the control by the time-monitoring function. The programmable logic controller may be connected to a functi ^¬ onseinheit for image acquisition, in order to transmit the image data in the real-time environment, wherein the function is a vision function for processing and / or analysis of image data.

The invention will be explained in more detail with reference to the accompanying drawings.

Figure 1 shows schematically a structure of a programmable logic controller according to the invention for a production plant, the actuators and sensors and an image ^{detection unit} has on ^¬ .

Figure 2 shows a structure of a data structure of a time monitoring function, which is executed in a real-time environment according to the invention. 3 shows a structure of a stack with time monitoring ^¬ functions.

FIG. 4 shows a possible program flow chart for starting a time monitoring function, which is executed in a real-time environment according to the invention.

Figure 5 shows a possible program flow chart for performing a vision function executed in a real-time environment according to the invention.

FIG. 6 shows a possible program flow chart for starting a time monitoring function, which is executed in a real-time environment according to the invention.

Figure 7 shows an example of propagating the remaining time when performing multiple interleaved time monitoring functions. In a production plant, a programmable logic controller (PLC) 3 is used to control sensors 1 and actuators 2, which, as shown in FIG. 1, is connected via a field bus 4 to the sensors 1 and actuators 2. The PLC can be designed as an independent data processing unit, for example in the form of an industrial PC 5, as shown in FIG. 1, or run as a software PLC additionally on an already existing unit of the production plant. As an alternative to a field bus 4 is a differently configured communica tion ^¬ compound 3 can be inserted for data exchange between the sensors 1 and actuators 2 and the PLC. The processing of the data from or for the sensors 1 and actuators 2 takes place on the PLC 3 in the form of tasks, so-called tasks. The tasks are executed for control of the sensors 1 and actuators 2 generally cyclically, said safety must be provided that the tasks are guaranteed to within ei ^¬ ner predetermined maximum time, for example within the standing for one cycle time available, processed. Furthermore, the cyclic execution of the tasks without jitter must be guaranteed with a predictable response time (latency). This Anforderun ^¬ gen to the PLC 3 are implemented by a real-time environment.

In addition to the actuators 2 and sensors 1, production plants usually have a large number of other systems whose functions must be synchronized with the production process and its control with the aid of the sensors 1 and actuators 2 by the PLC 3. Vision systems pose a sol ^¬ ches auxiliary system. With vision systems object detection, surface inspection, a survey or an identification can be performed beispiels- example. To achieve these objectives, the vision systems must perform a multi ^¬ number of image processing and analysis operations. Such image processing and image analysis operations may include, for example, filters, thresholds, morphological

Includes operators, geometric transformations, color space transformations, segmentation techniques, contour searching, and texture and shape analysis methods. According to the invention, the PLC 3, as Fig. 1 shows extended so that image data of a functional unit 6 for Bil ^¬ derfassung such as a camera of the vision system di- enter directly into a memory space of the PLC 3. The functional unit 6 for image acquisition is also referred to below as the image acquisition unit 6. In the exemplary implementation shown in FIG. 1, which uses Ethernet 7 as the communication medium between the image acquisition unit 6 and the PLC 3, Ethernet packets of the image acquisition unit 6 are transmitted directly from a network adapter into the real-time environment of the PLC 3. In the real-time environment of the PLC 3, a protocol-specific processing of the Ethernet packets takes place in order to process and analyze the image data in the real-time environment with the help of vision functions.

Instead of using Ethernet 7 for image data transmission, other data bus systems can also be used. In the case of the Vision functions, the functional run times depend essentially on the available data volume. Thus, the processing time can vary greatly in identifying relevant structures within a topological structure analysis, for example, a con ^¬ tures seeking. The iterative application of an algorithm as a function of a convergence criterion, for example an iterative filter or a subpixel optimization, can also lead to a fluctuating functional runtime. The same applies to the use of alternative search strategies, for example, that if a first sub-algorithm is unsuccessful, a second sub-algorithm is attempted. Also, a so-called region-of-interest variable size leads to different functional maturity. Consequently, the results of the respective functional operations are available at variable times. However, this conflicts with the requirement for the real-time environment of the PLC 3, which must guarantee the cyclical execution of the task without fluctuations over time (jitter) with a foreseeable response time (latency). Also, an integration of other auxiliary functions, which are to be syn chronized ^¬ with the production process and its control by the PLC 3, in the real-time environment of the PLC 3, is the unknown function runtime counter. Such an additional function, for example, the condition monitoring (condition monitoring), in which a regular or continuous detection and evaluation of the state of the production ^¬ plant is carried out by measurement and analysis of machine parameters that reflect the current status of the production process. In condition monitoring, iterative methods are often used to analyze the recorded data, whereby the running time depends on the achievement of a quality criterion and is therefore not fixed from the outset. Also in the field of machine learning and numerical control and other additional functions to be synchronized with the production process, the functional runtime varies.

In order to be able to integrate an additional function with an indeterminate functional runtime into a real-time environment in which at least one task is executed with a predetermined task runtime, a time-monitoring function is provided according to the invention, which defines an abort time for the function within the specified task runtime. When a function within the given task runtime to be abgearbei ^¬ tet, the time monitoring function is started. The time monitoring function then monitors the functional runtime, wherein a function abort is initiated when the predetermined abortive ^¬ time point is exceeded.

By providing the time monitoring function, the execution of the additional function is designed such that the functional ^¬ running time depending on the current cycle of the task still available computing time can be controlled. The additional function can be executed directly in the real-time environment of the PLC 3, as the cyclic execution of the task can be guaranteed with a predictable response time with the aid of the time monitoring function. Furthermore, a time ^¬ precise coupling of the algorithms performed by the additional function is achieved at the timing of the production process.

In the following, the invention will be explained using the example of the vision function. But the versions can be transferred to other additional functions, in particular the above genann ^¬ th additional functions transferred.

The time monitoring function, also referred to below as a watchdog, can be designed as a wrapper function, which surrounds the additional function. The time monitoring function is executed as a program code which surrounds the Funktionsssoft ^¬ ware. With the development of the time monitoring function as a wrapper, it is possible to easily expand the software of the additional function without having to intervene extensively in the program code of the additional function. The program code of the additional function then runs within the Pro ^¬ program codes of the time monitoring function. The watchdog can be realized both preemptively and cooperatively. In a preemptive Watchdog the to be executed within the given task runtime ^¬ additional function is temporarily stopped just after exceeding the termination timing. The watchdog ensures continuous monitoring of the functional runtime. When exceeding the specified ^differently surrounded abort time point by the function of maturity an abort function is called to the function abort perform. For this purpose, an interrupt program can be set up outside the watchdogs and the per ^¬ weiligen additional function that is executed to termination date. Alterna tively ^¬ the abort function can also be part of the watchdog, in which the watchdog program code branches, when the termination condition is satisfied ^¬ by exceeding the predefined termination timing.

Aborting the execution of the additional function can be done, for example, via interrupts. For example, in the case of a preemptive watchdog, a timer is started when starting, which triggers the interrupt on execution, which terminates the additional function to be monitored. In the case of the preemptive watchdog, the abort of the additional function usually takes place at an unknown program position within the additional function, so that the additional function can be in an undefined state, as a result of which the results of the additional function can often only be used to a limited extent at the abort time. In contrast to the preemptive watchdog of koopera ^¬ tive watchdog allows a controlled function abort. For this purpose, preferably the program code of the additional function is erwei ^¬ tert by an additional condition is inserted, for example, to function ^¬ specific central processing loops. The additional condition checks the computing time consumed for the algorithm of the additional function at fixed times, for example at the end of the associated processing loop. If it is determined during the review that the function ^¬ term has exceeded the cut-off time, the associated processing loop of the additional function leaving ^¬ sen is. Already existing results of the additional function can be ge ^¬ uses, since the additional function is stopped in a controlled manner by branching out at the end of a processing loop. The abort of the additional function in the cooperative watchdog is, however, generally less accurate than the preemptive watchdog, since only aborts to those times defined by the additional function.

The time monitoring function can determine the predetermined termination time t _A break when called as the sum of the current time taktueii and a maximum allowable time period At _max . The current time t _a ktueii can be related to the beginning of lukewarm ^¬ fenden task cycle while: ^ ^ -Abort -News ^ t _max (1)

Watchdogs which dynamically determine their termination time in accordance with equation (1) are also referred to below as time span watchdogs.

Furthermore, the time monitoring function can output a parameter on termination that indicates the proportion of the ^executed function ^execution . The indicator while a numerical value can be used by the watchdog function that reflects the purchase in part a _f the already completed processing steps in Behaves ^¬ nis to complete processing an additional function f. The calculation of the parameter depends on the algorithmic ^¬ mus the additional function from f. Exemplary variants for calculating the proportion a _f for a vision function as an additional function are current share of processed ROI

Total size of the processed ROI desired accuracy

max (desired accuracy, current accuracy)

Number of executed partial algorithms

Number of possible subalgorithms

Equation (2) is suitable for algorithms which process all pixels of a region-of-interest (ROI) sequentially, wherein the ROI can also include the entire image. The algorithms used may be, for example, simple convolution filters or threshold operators. Even for more complex algorithms such as labeling or contour search, equation (2) is suitable for calculating the fraction a _f . The field of application of equation (3) are mainly itera ^¬ tive algorithms where additional iterations are performed until a desired accuracy is reached. In this case, the accuracy can be specified, for example, by the absolute value of the change in one or more variables to be optimized between two successive iterations of the algorithm.

Equation (4) is suitable for complex algorithms that perform alternative processing strategies depending on the results. For example, an algorithm for license plate recognition can only try Data Matrix codes to identify and, if that fails, then another search for QR codes and then perform possibly after eindimen ^¬ dimensional barcodes. Combinations of the above equations for determining the proportion a _f for a vision function are also conceivable. The determined characteristic variable, which shows the share of the carried radio ^¬ tion execution when the function is canceled, then available in addition to the calculation results of the additional function. The indicator provides a measure of the Ver ^¬ trust in the corresponding calculation results. Based on the respective share a _f the already completed processing steps in relation to the complete processing of the additional function f less trustworthy calculation results from further proces ^¬ equipment, may for example be excluded or these are incorporated with a low weighting. Alternatively, the ascertained characteristic variable, which indicates the proportion of the performed function execution in the case of the aborted function, can also be used to carry out an adaptation of the additional function. A lesser processing component a _f for a vision function could be increased, for example, by adapting the image acquisition parameters or the processing strategy in the next task cycle. By outputting the parameter, the programmer of the PLC obtains the possibility of recognizing problems during the execution of the additional function during a running task cycle and to prevent discontinuations of vision functions and timeouts in the future by subsequent modifications.

The time monitoring function as a wrapper function can be called immediately before and immediately after the vision function to be controlled. One possible command structure is: err = StartWatchdog (t _A break)

Vision function (); (n, a, At _Res t _/ err) = StoppeWatchDog () tAbstract indicates the abort time relative to the current task cycle. err denotes an error code whose values serve to indicate error conditions in the execution of the time monitoring function. In one possible implementation, err = 0 may mean that no error has occurred in the execution of the time monitoring function, whereas err + 0 signals an error.

The element n of the tuple (n, a, At _Res t, err) indicates the number of executed functional elements of the additional function. The meaning of the functional elements will be explained in connection with FIG. 2.

Further, in the tuple (n, a, At _Res t, err) further beside the Bear beitungsanteil ^¬ a (in percent), the time difference At _Res t of ak ^¬ tual time t _a ktueii to abort time point t _A bbruch:

At _Rest = t _Abort - t _act u (5)

If an additional function, in the example the vision function, is aborted prematurely, 0% ^ a _f <100% and At _Res t - 0.

If an additional function is completely executed, ie terminated before reaching the termination time t _A break, then a _f = 100% and At _Rest > 0.

In addition to the parameter a _f , which indicates the proportion of the executed func ^¬ onsausführung in the abort function, the watchdog determined residual time At _Res t is to optimize the execution of the additional function in the real-time environment. The residual time At _Res t can be used in particular for evaluating the execution of the additional function by software components outside the current task. For example, a PLC program which is part of a further task of the Echtzeitumge- is advertising, the residual time determined by the watchdog At _{Re s} t abfra ^¬ gene to determine what proportion consumes available STE Henden computing time actually executing the additional function of has been. If there is unused computing ^¬ time available, this computation time can then be used dyna ^¬ mixed for other, less time-critical tasks such as exporting images of the vision function of a man-machine interface outside the real-time environment.

By implementing the watchdog as the additional function supplementary functional element, for example in the form of a wrapper command structure, the watchdogs can be constructed in a standardized manner, which allows a simple modification and adaptation. The monitoring of the time behavior ei ^¬ ner specific additional function, for example, the vision function can be adjusted without changing the additional function itself or their function parameters.

A possible data structure for a watchdog 200 is shown in FIG. The watchdog data structure has several data fields containing watchdog parameters. A first data field 210 can indicate the watchdog type. Of the

Watchdog type can indicate, for example, whether a preemptive watchdog or a cooperative watchdog is used. As a further data field 220, the watchdog data structure contains the termination time point t _Fig ruc _h - Further, a data field 230 for the number of accumulated functional elements is n, a data field

240 for the accumulated processing rate a and a data field 250 for the accumulated remaining time At _Rest provided. With the watchdog data structure shown in FIG. 2, monitoring of larger program code areas, including loops and branches, referred to below as function elements, can be implemented in the case of an additional function. It is advantageous to check at the beginning of the execution of each function ^¬ elements of the additional function, whether the termination time t _Abb ruc _{h was} exceeded. If this is the case, then the processing of further functional elements is omitted. Functional ^elements that do not support partial processing are included in the calculation either with the processing component a _f = 0% or a _f = 100%.

If the results of the monitored additional functional elements are largely independent of each other, the accumulated machining portion can ä approximately as incremental With ^¬ average value of the processing units of all the called function ^¬ elements are determined, a _f the machining portion of the current function element f and n the number of previously called functional elements indicating :

On the other hand, if the calculation results of the functional elements of the monitored additional function are based on one another, equation (6) provides for the calculation of the calculation proportions to optimistic values for the accumulated calculation proportion a, since the current functional element can only use the successfully calculated proportion of results of the preceding functional elements. In this case, a multiplicative calculation is suitable, as indicated in equation (7) below: cif, if n

α (n + 1) = [(7)

ä (n) ^■ üf, otherwise

As an alternative to the equations (6) and (7), other types of calculation for determining the accumulated processing fraction a are also conceivable. What type of calculation to be used in each case can be decided by selecting a parent to ^¬ watchdog type. For example, WatchdogType A can determine the accumulated processing fraction a with equation (6) and WatchdogTypB with equation (7). The choice of to-use watchdogs can be re ^¬ alisiert example, using the commands to start and stop. For example, the commands StarteWatchdogTypA and StoppeWatchdogTypA can be used to start and stop a watchdog of type A and the commands StartWatchdogTypB and StopWatchdogTypB to start and stop a watchdog of type B.

Further, the time monitoring function (watchdog), at least one child timing function element, hereinafter also referred to as a subordinate watchdog exhibit ^¬, which defines a cut-off time for an auxiliary function within the given task runtime before the termination time ^¬ point of the time monitoring function. By such an interleaving, the watchdogs can form a hierarchy which allows a more precise time monitoring of the additional function.

Nesting causes one or more child watchdogs to be called while a watchdog is running using startup and stop commands. The number of commands already executed to start watchdogs, for the no corresponding command is still done to stop the started watchdogs, indicates the hierarchical level of per ^¬ weiligen watchdog. One possible implementation may be, for example, a LIFO (last in, first out), also called a stack, as shown in FIG.

In the example in FIG. 3, the stack has two watchdogs, with the higher-level watchdog being a type A watchdog and the subordinate watchdog being a type B watchdog. Is to be ^¬ monitors the timing of a vision function, which includes three functional elements VisionFunktionl VF1, VisionFunk- tion2 VF2 and VF3 VisionFunktion3. Fig. 3 shows in the left part of the program sequence for monitoring the vision function with the two interleaved watchdogs and parallel to the individual program steps in the right part of the respective active watchdogs in the stack. After program start, the higher-level watchdog type A is started in program step 100 with the command StartWatchdogTypA. The watchdog type A is an periods watchdog, the termination time according to equation (1) from the economic refreshes ^¬ time t _a k ll _do and the maximum allowable time period At _max, which is ys, for example, 5000 is determined. After the start of the watchdog type A vision function is called and then one after the vision function elements VisionFunktionl VF1, VF2 and VisionFunktion2 abgearbei tet ^¬ VisionFunktion3 VF3.

Between the vision function elements VisionFunctionl VF1 and VisionFunction2 VF2 continues in program step 200 the subordinate watchdog type B is started with the command StartWatchdogTypB. The subordinate watchdog type B is formed as ^¬ derum as periods watchdog, the t _a k _doing the demolition ^¬ time when called from the sum of the current time ii and the maximum allowable time period At _max, which ys, for example, 4000 is determined. The subordinate watchdog type B monitors the operating times of the vision function elements VisionFunction2 VF2 and VisionFunction3 VF3. Thereafter, in program step 300, the subordinate watchdog type B is stopped with the command StopWatchdogTypB. Then, in the program step 400, the superordinate watchdog type B is terminated with the command StopWatchdogTypA. In the watchdog stack shown further in FIG. 3, the active watchdogs are respectively marked for the individual program steps. The command StarteWatchdogTypA the parent watchdog Type A is stored in the watchdog stack in program step 100 and remains active until the command StoppeWatch- dogTypA in program step 400. In the active übergeordne ^¬ th watchdog type A is in program step 200 with the command StarteWatchdogTypB in Watchdog Stack then the subordinate watchdog type B put on. The subordinate watchdog type B remains active above the higher-level watchdog type A until the command StopWatchdogTypB in the program step 300.

With the watchdog stack and the nested watchdogs contained in it, individual function elements of the additional function, ie program code areas such as loops, can be monitored separately with respect to their runtime. In the program flow shown in Fig. 3 monitors the subordinate

Watchdog type B the timing of the vision function elements VisionFunktion2 VF2 and VisionFunktion3 VF3, during the higher-level watchdog type A monitors the time behavior of the entire vision function, including the vision function element VisionFunctionl VF1 that was executed before the start of the subordinate watchdog type B.

In the real-time environment, each task that supports watchdogs gets its own stack. The hierarchy level of a ^¬ individual watchdog is represented by the position of the watchdog on the stack. For reasons of efficiency, it is possible for the time monitoring of an additional function to always use only the highest and thus the hierarchically highest ranked watchdog in the stack of the task. In an alternative implementation, however, the termination time of all watchdogs on the stack can also be checked.

When nesting watchdogs, the processing shares of the individual watchdogs can be offset against each other. In one possible implementation, the processing shares of all watchdogs on the stack can be adapted. In addition to a possible redundancy of performed

Can calculations such an implementation but at different allocation rules for the accumulated percentage working of the different watchdogs, as indicated at ^¬ play, in the equations (6) and (7), lead to inconsistent results.

Alternatively, the billing can also be designed so that only the processing share of the highest and thus the hierarchically highest ranked watchdog is adjusted on the stack. The accumulated processing proportion a and the number of accumulated function elements n of the additional function are then called upon calling the command to stop the Watchdogs propagated to the underlying and thus hierarchically deeper classified watchdog. In this way, multiple and possibly different allocations of the processing content of individual functional elements are the avoided to ^¬ set function.

The propagation of the accumulated processing shares can be done analogously to the calculation of the processing shares, as indicated in equations (6) and (7). In the propagation of the accumulated machining portions of a watchdog Wi to an overlying and thus a hierarchically higher watchdog W2 of the accumulated machining ^¬ tung proportion of W2 is for example adjusted as follows:

W. if W ₂ . n = 0

w ₂ .nW ₂ .a + Wn-W (8)

- -, else

W ₂ .n + W ₁ .n or

(W _1, a, if W _2, n = 0

W ₂ . a =] ", *", - _R (9)

2 {W ₂ . a (n) ^■ W ₁ . a (n), otherwise

The notation W _X .Y denotes the data field Y of Watch ^¬ dog W _x . The equation (8) corresponds to a calculation analogous to the equation (6) and the equation (9) a calculation analogous to the equation (7).

In addition to the propagation of the processing components, the number of accumulated functional elements n can also be propagated from the watchdog Wi to the underlying hierarchical watchdog W2:

W ₂ . n = W ₂ . n + W ₁ . n (10) In addition to monitoring the time behavior of added features make the watchdogs, are as described and for optimization ^¬ tion of the PLC. This is especially true for the additionally determined by the watchdog accumulated remaining time At _rest, which is stored in the watchdog data structure shown in Fig. 2 in a data field and can be queried from outside. In the accumulated remaining time At _Rest , the unused computing time of the watchdogs of the various hierarchy levels can be collected in a stack. When the instruction for stopping the watchdog Wi is called, the residual time At _Rest , which results as W ₁ .At _remainder = t _remainder , can be propagated to the watchdog W 2 of the lower hierarchical level. W2 can the propagation of the remaining time of the watchdog Wi to the watchdog as be ^¬ carried out at follows:

W ₂ .At _rest = W ₁ .At _rest (11)

For periods watchdogs that determine the cut-off time on call as the sum of the current time and a maximum he ^¬ laubten time, this kind of calculation, however, is not sufficient as a time saver in a previously executed Watchdog automatically t in the calculation of termination points in time _A Breaking the following time-span Watch ^¬ dogs flows, as can be seen from the above equation (1). The remaining time of previous watchdogs must be explicitly collected at time ^¬ tension watchdogs so. For this purpose, the following rule can be used to propagate the time span watchdog Wi to the watchdog W2:

W ₂ .At _rest = W ₂ .At _rest + Wi.d (12) The sum of the accumulated remaining time Δΐ _{Κβ5ί of} all watchdogs on the stack indicates in both variants the unused computation time and can then be read out and further processed by software components of other tasks from the watchdog data structure in order to optimize the behavior of the PLC's real-time environment.

4 to 6 is a possible program sequence of a time monitoring function with a watchdog stack, as

Wrapper function is executed for a vision function and the command structure already explained with the commands err = StartWatchdog (t _A break); Vision function (); (n / A,

AtRest _/ err) = uses StoppeWatchDog (). In the program sequence, an oval represents a control point such as start and stop, a rectangle represents a program step, and a rhombus is a branch step in which a decision must be made. Furthermore, arrows represent the connections between the program and branch steps. In FIGS. 4 to 6, | S | In addition to the number of watchdog on the watchdog stack and W _s for the top watchdog of the watchdog stack.

Fig. 4 shows an example for the command err = StarteWatch- dogTypA (t _A bbruch) the program sequence, wherein a watchdog W started by the watchdog type A in the context of a watchdog stacks who should ^¬.

In a first program step SP1, the watchdog W initializes its data structure shown in FIG. The watchdog W, which is a time spans watchdog determines the ^¬ From break time point t _A bbruch from the current time t _a ktueii and maximum permitted time span At _max . Further, the data fields are accumulated number n of functional elements, accumulated percentage working, etc., and accumulated time remaining At _Rest set to 0.

In a first decision step SZ1 it is then determined whether watchdogs are already active in the watchdog stack.

If the query determines that a watchdog is already active, ie | S | Is> 0, it is checked in a second decision step SZ2 whether the Ab ^¬ break time of the watchdog W is less than or equal to the Ab ^¬ break time of the uppermost watchdog W _s in the watchdog stack. If this is the case, the watchdog W is placed at the top of the watchdog stack in a second program step SP2.

Optionally, if the watchdog W is a preemptive watchdog, it prepares an abort function in a third program step SP3.

Subsequently, in a fourth program step SP4, an error code err = 0 is set to indicate that no error has occurred during program execution.

If it is determined in the first decision step SZ1 that no watchdog is active in the watchdog stack, ie | S | = 0, the program branches and bypasses a second decision-making ^¬ step SZ2 and drives directly to the second program step SP2 continues.

If it is determined in a second decision step SZ2 that the cancellation time of the watchdog W is greater than that Cancellation time of the top watchdog W _s in the watchdog stack, ie the termination time of the top watchdog W _s in the watchdog stack before the termination time of the watchdog to be started W is diverted from the program and set in a fifth program step SP5 an error code err = 1 to indicate ^¬ that there is an error in the watchdog start.

After the fourth programming step SP4 in which the error code err = 0 is set, or to the fifth program step SP5, in which the error code ERR is set = 1, the Pro ^¬ program sequence of the command err = StarteWatchdog (t _A bbruch) ended.

Fig. 5 shows an example of the program flow of the vision function () command for execution and time monitoring of the Vi sion functional element vision function which is called by the command err = StarteWatchdog (t _A bbruch), the program flow is shown in Fig. 4 ,

In the program sequence of the command VisionFunktion (), an initialization takes place in a first program step VP1, in which the processing fraction a _{f is set} to 0 and the abort time t interrupt is set to infinity.

In a subsequent first decision step VEl is then checked whether there is an active watchdog in the watchdog stack.

If it is determined in the inquiry that a watchdog is ak ^¬ tive, so ISI> 0, in a second decision is dung step VE2 checked whether the current time t _ak tueii time ^¬ Lich before the termination time t _A bbruch the topmost active Watchdogs W _{s is} in the watchdog stack. If this is the case, in a second program step VP2 the termination time t _A break is set to the termination time t _A interruption of the uppermost active watchdog W _s . Subsequently, the vision algorithm VA of the vision function element VisionFunktion is executed. At the end of each loop of the vision algorithm, the respective loop condition is checked in decision step VA1. At the same time, the current time t _a ktueii ^m is continuously compared with the termination time t _A break. The vision algorithmic ^¬ mechanism is executed until a loop condition is he fills ^¬ or the current time talking ent ^¬ the termination date.

When the active watchdog is a preemptive watchdog, wherein exceeding the termination timing called a termination function by the functi ^¬ onslaufzeit of the vision algorithm VA to cancel the vision algorithm VA. In a cooperative watchdog as an active watchdog Pro ^¬ program code of the vision algorithm VA is extended by an additional condition. The additional condition compares ^¬ step VA1 the current time t _a ktueii ^w ith t demolition time ^¬ point _A bbruch at the end of each processing loop in the decision. If it is determined during the review that the cut-off time on ^¬ steps, the processing loop is left and the vision algorithm VA so controlled ended.

When the execution of the vision algorithm VA of the vision function element VisionFunktion has ended, a third decision step VE3 checks again whether there is an active watchdog in the watchdog stack. If this is the case, in a third program step VP3 processing share a _f of the vision function ^¬ elements vision function is determined. The calculation rule is predefined by the vision algorithm VA, where, for example, equations (2), (3) or (4) can be used.

The percentage working a _f is then charged in a fourth Pro ^¬ program step VP4 with the accumulated the watchdog stack processing units, to determine the processing content for the entire vision function, for example, the equations (8) or (9) can be used , Then the program sequence of the command VisionFunktion () is ended. If it is determined in the first decision step VE1 that no watchdog is active, ie | S | = 0, is passed directly to the execution of the vision algorithm VA of the vision functi ^¬ onselements vision function. Since no time monitoring is then carried out with a watchdog, the originally initialized termination time remains at infinity and only the loop condition is checked during execution.

If it is determined in the second decision step VE2 that the current time t _ak tueii temporally after the Abbruchzeit ^¬ point t _Fig ruc _h the topmost active watchdog W _s in the watchdog stack, the vision algorithm VA of the vision func ^¬ tion element VisionFunktion not performed and the Pro ^¬ program sequence continues with the fourth program step VP4. The initialized percentage working a _f = 0 is then charged with the accumulated the watchdog stack processing units and then ends the routine of the Visi ^¬ onFunktion () command. If in the third decision step VE3 it is determined that no further active watchdog is contained in the watchdog stack, the program branches off and the program sequence of the command VisionFunction () is ended immediately.

6 shows, by way of example for the instruction (n, a, At _Res t, err) = StopPatchDogTypA (), the program sequence with which the watchdog W of the watchdog type A is again terminated. The command (n, a, At _R est _/ err) = StoppeWatchDogTypA () is after the command Visi ^¬ onFunktion (), the program flow is shown in Fig. 5, called.

In a first decision step EE1 it is checked whether a watchdog to be terminated is in the watchdog stack.

If the query determines that a watchdog is active in the watchdog stack, it is checked in a second decision step EE2 whether it is a type A watchdog.

If it is determined that the watchdog W _s active in the watchdog stack is such a type A watchdog, the watchdog is removed from the stack in a first program step EP 1.

In a second program step EP2, the data structure of the watchdog W removed from the stack is then updated. The processing component a is set to the value determined in the fourth program step VP4 of the program sequence of the command VisionFunktion (), as has been described with reference to FIG. The remaining time At _Res t is with of equation (5), which determines the time difference from current time t _ak tueii to abort time t _Abb ruc _h .

If the watchdog W is a preemptive watchdog, the abort function is then removed in a third program step EP3.

Subsequently, in a third decision step EE3, it is checked whether, after removal of the watchdog W, further

Watchdogs are in the watchdog stack.

If it is determined in the third decision step EE3 that further watchdogs are active in the watchdog stack, ie | S | > 0, it is battery- phrased the remaining time found in a fourth program step EP4 At _Rest for the watchdog W to the detected in the second program step EP2 At remaining time t _{Re s.}

In a fifth program step EP5, the number of accumulated functional elements Wn, which accumulate on profiled W.ä percentage working, and the accumulated time remaining W.At _rest on the top that are available in the watchdog active stack watchdog W _s is then propagated by the watchdog W.

Subsequently, in a sixth program step EP6, an error code err = 0 is set to indicate that no error has occurred during program execution.

If it is determined in the first decision step EE1 that no watchdog is active in the watchdog stack, ie | S | = 0, the program branches and sets in a seventh program step EP7 an error code err = 1 to indicate that an error has occurred during watchdog stop. If it is determined in the second decision step EE2 that lying in the watchdog stack above active watchdog W _s no watchdog type A, the program flow is just ^¬ if continued with the seventh program step EP7, which sets the error code ERR 1 by a Display execution error.

If it is determined in the third decision step EE3 that no watchdog is active in the watchdog stack, ie | S | = 0, the sixth program step is then EP6 out ^¬ leads and an error code err set = 0th

After the sixth program step EP6, which sets the error code err = 0, or the seventh program step EP7, in which the error code err = 1 is set, the program sequence of the command (a, At _Rest , err) = StopPatchDogTypA () is ended.

Fig. 7 shows an example of the propagation of the remaining time in a watchdog stack with five watchdog 701-705, which are distributed on three hierarchical levels 1, 2, 3, wherein to ei ^¬ nem time at each level of the hierarchy most one Watch ^¬ dog active is. In the illustration in FIG. 7, the three hierarchy levels 1, 2, 3 are entered on the Y-axis. In the hierarchically lowest hierarchical level 1, the watchdog is 701. In the next hierarchical level 2 of the Watchdog 702 Watchdog 703 and the watchdog are 705 arranged ^¬. At the top hierarchy level 3 is the watchdog 704.

The time sequence of the five watchdogs 701 to 705 in the watchdog stack is indicated on the X-axis in FIG. The numbering of the watchdogs corresponds to the start time of the watchdog respective watchdogs. The arrow from the lower hierarchy level to the next higher hierarchical level always indicates the call of the watchdog. The arrow from the higher hierarchical level to the next lower hierarchy level indicates the end of the watchdog.

The watchdog 701 located in the hierarchy level 1 starts at the time 0 ms and terminates its execution at the time 100 ms. The watchdog 702, which is located in the hierarchy level 2, starts at the time 10 ms and ends its execution at the time 20 ms. Which are currently looking Dende in the hierarchy level 2 ^¬ Watchdog 703 starts 40ms at the time and ended his execution at the time of 70ms. Watchdog 705, which is in hierarchy level 2, starts at time 80 ms and terminates its execution at the time

90ms. The watchdog 704 located in the hierarchy level 3 starts at the time 50 ms and ends its execution at the time 60 ms. The five watchdog 701-705 are each Zeitspannen- watchdog, wherein in Fig. 7, the actual running time of the watchdog, which results from the specified start and stop newspaper th and to be monitored by the function of duration of the fed arrange ^¬ th functional elements determined becomes. The watchdog 702 has a termination period of 15ms, the watch dog ^¬ 703 has a termination period of Iliad, the watchdog 704 has a termination period of 37 ms and the Watchdog 705 has a termination period of 18ms. It therefore remain residual ^¬ times for the watchdog 702 of 5ms, the watchdog 703 of 7 ms, the watchdog 704 of 1ms and for the watchdog 705 of 8ms. When a propagation of the remaining time, for example for time ^¬ point 65 ms, which is shown as a dashed line in FIG. 7 is to be performed, results on the Hierar ^¬ chieebene 3 is a time saving by the watchdog 704 of 1ms and the underlying Hierarchy level 2, a time savings of 5ms by the watchdog 702, so that with a residual time propagation at time 65ms, the accumulated remaining time is 6ms.

Claims

claims

1. real-time environment, in which at least one task is executed with a predetermined task run time, wherein at least one additional function with indeterminate function runtime is to be processed within the specified task runtime with the aid of a time monitoring function,

with the steps:

Starting the time monitoring function, which defines a termination time for the additional function within the specified task runtime,

Executing the additional function, wherein the time monitoring function monitors the function runtime and a function abort is initiated when the predetermined abort time is exceeded, and

End the time monitoring function.

2. Real-time environment according to claim 1, wherein the time monitoring function is configured as a wrapper function that surrounds the program code of the additional function so that the Pro ^¬ program code of the additional function takes place within the program code of the time monitoring function.

3. Real-time environment according to claim 1 or 2, wherein an abort function is provided, which is called when the predetermined abort time is exceeded by the functional run time to perform the abort function.

4. real-time environment according to claim 1 or 2, wherein the additional function comprises an abort condition, which terminates the execution of the additional function when the predetermined abort time is exceeded by the functional run time and reports a processing result.

5. Real-time environment according to one of claims 1 to 4, wherein the time monitoring function determines the predetermined abort time when called as the sum of the current time and a maximum allowable time.

6. Real-time environment according to one of claims 1 to 5, wherein the time monitoring function outputs a characteristic at the end, indicating the proportion of the performed function execution.

7. Real-time environment according to claim 6, wherein the additional function has a plurality of functional elements and wherein the output when terminating the time monitoring function characteristic indicates the accumulated portion of the executed execution of the functional elements and / or the number of accumulated functional elements.

8. Real-time environment according to one of claims 1 to 7, wherein the time monitoring function outputs a time value at the end, indicating the time difference between the current time and the predetermined abort time.

9. Real-time environment according to one of claims 1 to 8, wherein the time-monitoring function emits an error code when terminating, indicating an error condition in the execution of the time ^¬ monitoring function.

10. Real-time environment according to one of claims 1 to 9, wherein the time-monitoring function has at least one subordinate time monitoring function element, the within ^¬ break-off time for an associated additional function within determines the given task run time before the abort time of the time monitoring function.

11. Real-time environment according to claim 10, wherein the time monitoring function is managed using a stack.

12. Programmable logic controller (3), which is connected via a fieldbus (4) with actuators (2) and sensors (1) of a production plant, wherein the programmable logic controller (3) comprises a real-time environment according to one of claims 1 to 11 whose task is used to control actuators (2) and sensors (1), wherein the execution of the additional function is synchronized by the time monitoring function with the controller.

13. A programmable logic controller (3) according to claim 12, which is connected to a function unit (6) for image acquisition to transmit their image data in the real-time environment, wherein the additional function is a vision function for processing and / or analysis of the image data.