WO2021165428A2

WO2021165428A2 - Method and device for operating a production facility

Info

Publication number: WO2021165428A2
Application number: PCT/EP2021/054076
Authority: WO
Inventors: Jürgen WOLL; Jan BÄR; Manuel STEGER; Patrick STÖRNER; Florian SCHLEISSINGER
Original assignee: Dieffenbacher GmbH Maschinen- und Anlagenbau
Priority date: 2020-02-18
Filing date: 2021-02-18
Publication date: 2021-08-26
Also published as: EP4106966A2; WO2021165428A3; DE102020104287A1

Abstract

The invention relates to a method and a device for operating a production facility for producing material panels, said production facility having at least devices for shaping a nonwoven from a material and pressing same in order to form material panels. In order to produce a material panel, product parameters of the material panel to be manufactured and facility parameters of the production facility are set, wherein the production facility and/or devices thereof have sensor systems for ascertaining measurement values and computers which are operatively connected thereto for controlling and/or regulating purposes. It is essential to the invention that at least one virtual sensor transmits measurement values to the computer for controlling and/or regulating the production facility or the devices thereof.

Description

METHOD AND DEVICE FOR OPERATING A PRODUCTION PLANT

The invention relates to a method for operating a production plant according to the preamble of patent claim 1. The invention also relates to a device for operating a production plant according to the preamble of patent claim 29.

Intermittent presses or continuously operating single or double belt presses are generally used for the production of material panels made of plastics and / or raw materials based on biological raw materials (wood, plants). For this purpose, the raw material is prepared, usually dried and, if necessary, mixed with a binding agent, for example with a liquid or dry glue, in a predetermined mixing ratio. Subsequently, in such a production plant, the material is poured or scattered in a scattering device, optionally in predetermined layers and / or area weight ratios, to form a material fleece and fed to a press. For continuous production, the material fleece is preferably produced on an endlessly revolving molding belt and introduced into a continuously operating press, where it is pressed under pressure and with the supply of heat to form a material plate.

Afterwards, after a press, there is the final production, in which various devices are arranged based on the products, such as trimming or diagonal saws, grinding devices, transport devices, cooling devices, stacking systems and mostly also measuring devices Testing the quality. Post-processing can also influence the quality of the product, for example through the type and manner of storage, and in particular through the temperature profile until the ambient temperature is reached.

It is known to establish a control room in large production plants in which the entire production plant is graphically displayed by means of monitors. In addition to the individual parts or devices, there are general status values and status data from sensors and controls. Complex evaluations and control and regulation algorithms can be implemented without problems if all the necessary measured values are available.

With all known technical measuring methods, however, it is possible that there are areas in a production plant in which no measuring devices can be installed, measuring devices are not cost-effective compared to measuring success, or physical measuring limits cannot be grasped in transition areas.

The object of the present invention is to create a production plant and a method for operating a production plant with which it is possible to optimize the control and regulation of the production plant in a generic production plant by increasing or improving the usable measurement results.

In particular, it should be possible to enable predictive production and quality control in a complex system with one or more material flows through various devices for carrying out the production process. For example, product changes can lead to changes in the material, the amount of material per unit of time and the surcharges (additives, binders), which in turn influence the energy input for pressure and / or heat. Here, load changes should be proactive in a complex system can be implemented in such a way that rejects are minimized and production changes can be carried out as smoothly as possible.

In an extension of the task, it should be made possible to ensure the safe and optimal operation of a production plant, even if essential sensors for determining measured values fail or deliver incorrect values. At the same time, it should be possible to regularly check and maintain the entire range of sensors in a production system and to take preventive action by replacing foreseeable failures of the sensors during maintenance shutdowns in the production system.

In addition, in the course of the modernization of systems, it should be possible to carry out virtual test runs for changes to the system, in particular the measurement and control technology, but also through the implementation of additional machines.

The method is preferably used for operating a production plant for the production of material panels, the production system having at least devices for forming a fleece from the material and pressing it into material panels and for producing a material panel, product parameters of the material panel to be produced and system parameters of the production system are set, with the production plant and / or its devices have sensors for determining measured values and computers that are operatively connected to them for control and / or regulation.

The object for the method is achieved in that at least one virtual sensor transmits measured values to the computers for controlling and / or regulating the production plant or its devices. By integrating virtual sensors and displaying these values as measured values, the following advantages are achieved:

- Deviations from the regular behavior are quickly apparent and help diagnose errors.

- Process controls and regulations receive an additional value for the calculation of their control or regulation systems and can thus proceed more finely or with higher resolution.

- By using machine learning methods, the simulation parameters can automatically adapt to the aging of the machine and / or the replacement of components.

- For parameters without in-situ measurement, it is possible to use external data sources and to correlate the offline measurement results for the training with the respective input variables using the time stamp.

In this context, deviations can also be detected so that the system can be retrained manually or automatically; as a result, more precise values result for the virtual sensor.

- When the system is running, virtual sensors can be used for testing in parallel to sensors that are actually present, in order to test whether sensor savings are possible through virtual sensors or to carry out a test operation with virtual sensors. The virtual signal can temporarily be generated parallel to the real measurement signal and after successful test operation, this or future production systems can do without the real sensors at this tried and tested location.

- Virtual sensors, especially if they have been trained, can continue to produce with the virtual signal in the event of a sensor failure until a replacement sensor has been delivered.

Particularly preferably, the measured values of the virtual sensor are created from a measured value of a different type with a correction factor and / or from several correlated non-type measured values from actual value sensors. This has the advantage that measured values can be generated and used for the control and / or regulation of the production system, which are otherwise only available via very expensive measuring devices or measuring devices that often fail and thus cannot be brought into proportion to cost-effective production. It may also be that no measuring devices can be attached at certain locations in a complex production plant or that measuring devices for this application do not exist. Here, a virtual sensor, which receives measured values from neighboring or other (unrelated) actual value sensors, can create or deliver measured values that can be sensibly used in a control or regulation system.

The input data, the output data and / or the measured values of the virtual sensor are preferably provided with a, preferably system-synchronous, time stamp, or they are already there. This means that the measured values can always be assigned to a current event or a specific production time in a simple manner.

Alternatively or cumulatively, the measured values of the virtual sensor can be taken from a database or current production data with measured values from earlier production cycles, preferably taking into account predetermined marginal and / or time data. This can be used, for example, to train a virtual sensor or to support the creation of a neural network as part of the virtual sensor.

In a preferred embodiment, an actual value sensor can be accompanied by a virtual sensor and, in the event of deviations outside of a predetermined range, trigger a reaction, preferably a notification function, to an operator and / or allow a corresponding notification entry to be made in a database. This means that the documentation requirement and the notification requirement can be sufficiently fulfilled. Particularly preferably, selected actual value sensors in the production plant could be accompanied by a virtual sensor and thus checked at predetermined intervals. By regularly checking the real sensor system, measurement errors due to mechanical defects (cables, sensors or the like) can be detected at an early stage, especially in the course of predictive maintenance.

To avoid production downtimes, if an actual value sensor fails or there is an obvious incorrect measurement, a virtual sensor could take over the generation of the measured values; this generation of the measured values could preferably start automatically, and in particular take place accompanied by alarm information to the operator.

In an advanced embodiment, the production plant could be optimized step by step to the extent that, after appropriate test runs with virtual sensors, the actual value sensors are step by step reduced or switched off. This is preferably used to minimize errors caused by sensor systems that often fail and to make production safer and more optimized.

In connection with one or more of the above-mentioned advantageous embodiments, a database with correct measured values can be created during regular production and, in the event of a failure, one or more actual value sensors can be used to generate the missing measured data from the virtual sensor.

In a particularly preferred and optimized embodiment, selected actual value sensors could be simulated as virtual sensors with the aid of a neural network. Using simple or advanced algorithms, as described in more detail later, these neural networks can be implemented advantageously. It may also be advantageous to generate product parameters and / or system parameters, preferably which are without current or existing actual value sensors, with the help of a virtual sensor, supported by an artificial neural network.

Alternatively or cumulatively, the measured values of the virtual sensor can be transmitted as product parameters and / or system parameters to the computer for controlling and / or regulating the production system or its devices.

Alternatively or cumulatively, the input parameters for the neural network can be normalized and / or aggregated, in particular for the use of the input parameters also for other production systems or their controls / regulators.

It would be advantageous if the results of the neural network and / or the virtual sensor are normalized and / or aggregated before being used on the local production facility or being passed on to other production facilities.

Particularly preferably, a virtual sensor can be checked and / or trained in an ongoing production, preferably using actual value sensors from a local or other production facility.

A neural network is understood here to be an algorithm based on artificial intelligence. In this invention, this is understood to mean process-based algorithms that are used in the development of artificial intelligence. An algorithm based on artificial intelligence advantageously comprises or is based on at least one method or a modification thereof from the following groups: simple methods such as linear regression, polynomial regression, functional regression; and / or classification-based methods such as,

K Nearest Neighbors Classification, Decision Trees, Random Forests, Naive Bayes, Support Vector Machines; and / or advanced methods such as, for example, Random Forest Regression, Support Vector Regression, K Nearest Neural Networks, Neural Networks, Recurrent Neural Networks, Convolutional Neural Networks, Residual Networks, Bayesian Networks. In particular, in addition to a mathematical method, in particular with mapping functions and / or neighboring functions, limits are preferably given to the algorithm for certain parameters in which the algorithm can move freely. For a method based on neural networks, for example, one or more mapping layers and weighting factors are specified, with the weightings in particular being optimized by training with the database.

Alternatively or cumulatively, the measured values of the virtual sensor or sensors can be written into a database, preferably with a time stamp, or visualized together with the actual values of the production system.

Alternatively or cumulatively, the program code of the virtual sensor can be set to a specific interface description, but it can be executed independently of the actual value sensor to be replaced.

Alternatively or cumulatively, a virtual sensor can be used, in particular in the course of a comparison with an actual value sensor, for status monitoring and / or predictive maintenance and / or failure detection.

Alternatively or cumulatively, in the course of the automated use of the production plant, an optimization of the production or the quality and / or a reduction of material input or scrap can be carried out, particularly preferably using an optimization computer which, with the help of one or more virtual sensors, a program for Predicts production quality and visualizes its results. The operating personnel thus receives information about the probable production quality and, if this is desired, the results generated by the virtual sensor are enabled and used for controlling and / or regulating the production system. This can even take place automatically within specified limits.

Alternatively or cumulatively, the optimization computer that is in operative connection with the production system can receive measured material, product and / or system parameters from the production system and / or its devices.

In such a production plant, devices for shredding, sorting, setting the mixing ratios of the material, providing the binding agent, gluing, storage, air conditioning of the material, for weighing, for monitoring and / or testing the material or the material fleece, for pre-pressing, for setting the humidity, temperature, width and / or height of the material fleece, for measuring parameters of the educts and material panels, for temperature control of the material panel and the like. Be provided. .

A corresponding device, preferably for implementing the aforementioned method, has the generic features.

The object is achieved for such a device in that at least one virtual sensor is operated using a computer and this computer for transmitting the virtual measured values is arranged in operative connection with the computers for controlling and / or regulating the production plant or its devices. A computer is not necessarily to be understood as an independent computer, but rather a device on which a program code runs, whereby it is now common to run several program codes on a computer at the same time, which communicate with one another and are thus in operative connection with one another.

Alternatively or cumulatively, to operate the virtual sensor, the computer can be connected to actual value sensors of the same and / or a different type, preferably with the option of using their measured values with a correction factor and / or from several correlated non-specific measured values to create the virtual sensor map.

Alternatively or cumulatively, the virtual sensor can be in operative connection with a device for issuing a, preferably system-synchronous, time stamp

Alternatively or cumulatively, a database or current production data with measured values from earlier production cycles, preferably taking into account predetermined marginal and / or time data, can be arranged for the transmission of measured values to the virtual sensor.

Alternatively or cumulatively, a neural network is arranged to form the virtual sensor.

Alternatively or cumulatively, a device for normalizing and / or aggregating the values can be arranged upstream and / or downstream of the virtual sensor, as well as alternatively integrated.

Devices for comminution, sorting, setting the mixing ratios of the material, provision of the binding agent, gluing, storage, air conditioning of the material, for weighing, for monitoring and / or testing the material or the material fleece, are preferred in the production plant Pre-pressing, for setting the humidity, temperature, width and / or height of the material fleece, for measuring parameters of the starting materials and material panels, for tempering the material panel and the like. Provided. Product parameters are variables with which the characteristics of the material plate to be produced are recorded. For the necessary optimization and control purposes, no exact analytical determination of all product properties, including laboratory values, is necessary, but only essential product parameters are sufficient to be included. These could be: product name, mixing ratio of material or material / binder, basic moisture content of the starting material or mixed material, compression factor, heat input, temperature, production speed, geometric features of the cross-section (layer structure), compressibility, quality index, ... pointed out that the individual conveying devices or other system components belonging to a system, which are necessary for the production process but have no effect in terms of process economy, are not specifically mentioned, but are included in the control process. For example, depending on the production speed of the press, the necessary conveying and transport systems are adapted and controlled accordingly so that the starting materials or the products are conveyed in or out accordingly.

The invention understands glued material not only as liquid gluing, in which the binder is sprayed, for example, and applied to the material, but also the production of mixing ratios of material / binder in the dry process.

Even if the use of the invention is adapted to a production plant for the production of material plates, the teaching and the knowledge of the invention can also be implemented in a hydraulic injection molding press, metal forming machines, recycling plants and / or other production plants. The invention can particularly preferably be used in special machine construction if the values are standardized and / or aggregated and thus can be easily ported to other production systems, preferably of the same type.

It is advantageously possible to reduce the product parameters to a few essential parameters (aggregation), in particular if they are correlated with one another.

Finally, the algorithm based on artificial intelligence is used to perform an iterative optimization on the specification of one or several product parameters (quality, thickness, width of the material panel). For example, the automatic iterative optimization is implemented in that a higher-level optimization computer is separated from the system control or the controls of the individual system components (device for gluing, device for forming the mat fleece, press, ...) with the help of a neural network, measured value sets and processes the process variables of past, theoretical or in individual cases specified values are calculated and the process is iteratively transferred to the optimal operating point. For this purpose, the higher-level optimization computer will output key figures for controlling and / or regulating the production plant after the optimization has been completed. It is checked at specified intervals whether the process parameters are within the specified tolerance limits and whether the pressing time is shorter or the pressing speed is greater than the previous one.

The use of an algorithm based on artificial intelligence, a neural network, means, among other things, the use of machine learning, in which no model is coherently specified based on mathematical and / or physical values and the model parameters are then adjusted, but rather the use of preferably artificial neural networks in which parts or the complete algorithm are adapted through training processes. Mathematical or physical Models can be used to generate training data / methods. One or more layers of a network can thus be defined and / or created, as well as starting values for the weighting parameters from previous experience.

If neural networks are used, these can also be multilayered and can have different structures. What they have in common is that in the design step, there is no modeling in the actual sense, but only a framework structure is specified for how the network is constructed and then an optimization algorithm optimizes the parameters. This optimization algorithm does not need or has any information about the process that is being simulated and only adapts all network parameters so that the output variables in the training data matched the specified target variables as closely as possible. An example of a neural network from another industry is e.g. AlexNet which is used for face recognition.

If it is recognized that the algorithm is no longer working optimally, independent retraining can take place or the operator can be requested to initiate the automated adjustment manually.

The virtual sensor will preferably be freely configurable, so that configuration files or computer program products can be created for the production system in which the input and output parameters and the algorithm used for the simulation are specified. A virtual sensor defines a sensor that does not actually exist for creating a measured value in the production plant, which computer program product tries to approximate a current actual value from other known values (possibly also historical values), states and changes in state and outputs this accordingly. For example, you can travel, pressure, or e.g. also replace humidity sensors with a virtual sensor. Alternatively, you can try to optimize or correct real results with the help of a virtual sensor.

It is particularly advantageous that the production plant can be tested and compared during operation as to which algorithms are used to obtain which quality of the estimate of a certain sensor value and whether sensor savings / compensation for a temporary failure of the signal is possible without complex software adjustments to have to make in the computers or their software of the production plant.

Another important application is the estimation of values that cannot be determined or can only be determined with great effort during production.

An example of this would be the determination of the plastic content of a recycled raw material. The proportion of the "non-wood material" has previously been determined manually by employees. B. can enter together with the time of sampling in a table of a database. In a virtual training session, these manually recorded measured values are then linked to process data and / or camera images so that a continuous inline plastic proportion measurement can then be carried out and this information (e.g. also strong fluctuations in this value) can be used for improvement can flow into the production process.

A similar application example would be the chip size distribution after comminution. This is carried out manually for the training on the basis of one or more material samples, stored in a database and the virtual sensor can use the Shredding systems and density measurement of the material before gluing, shaping or the press estimate which chip size distribution is currently being processed. With a corresponding sensor quality of the virtual sensor, samples can be taken much less frequently in order to still be able to guarantee the same (measurement) information for the setting of the production system or process changes / damage in system components can be detected at an early stage.

External data sources are any data sources that exist apart from the installed measurement data acquisition system and provide data together with time information about their acquisition.

In order to further deepen and explain the above individual features and the advantages associated therewith, further exemplary embodiments are described below which, independently or in combination with the preceding features, offer advantages over the prior art.

In particular, forward-looking production and quality control should be emphasized. It should preferably also be possible to carry out a quality assessment or prediction for the product as a function of the characteristics / states of the production plant and / or the reactants present. In this context, it should finally be possible to optimize the operation of the production plant as a function of the product, in particular from previous experience.

Here, one or more virtual sensors can, for example, map quality-forming properties of the product (product parameters), which set a reference variable as fictitious / virtual measured values, on the basis of which the production system is controlled and / or regulated in order to supply this product obtain. For this purpose, the computer, or a computer program product on this computer, will fall back on previous empirical values from previous production processes in order to adjust the production plant according to the reference variable or to regulate it during operation.

Particularly preferred is an algorithm based on artificial intelligence, iteratively revising an initial assessment of the parameters to be set until the result is that all the necessary parameters in the production plant are optimized in such a way that a product will be manufactured with an almost certain probability that reflects the quality-forming properties of the reference variable .

For this purpose, the fluctuating input variables that occur in complex production systems should be briefly referred to. Different types of materials, their mixtures, proportions of aggregates, ambient temperatures, operating temperatures of the devices in the production plant, their wear and much more lead to volatile fluctuations in the basic parameters in the production of products. In the case of material flows that take several minutes from the starting material to the product, marginal changes can lead to serious defects in production quality or cause a difference between A and B goods. This also applies, for example, to maintenance intervals at which wear parts affecting the material are replaced, to changes in the aggregates (binding agent or the like) due to batch changes or to changes in temperature (day / night operation). By referring to such changes in the overall system, it is possible when using virtual sensors, thus virtual measured values, to run through and optimize calculation algorithms in order to obtain specifications for individual machines for optimized production. In particular, when using an algorithm based on artificial intelligence, which receives specifications or framework conditions from virtual sensors, it is now possible to generate a self-optimizing control for a production plant.

Particularly preferably, a data source is used as a table from previous production processes including production results, which the neural network can access in order to self-optimize to determine a predictive scenario for production and for setting a large number of parameters in the production plant. Calculation structures are not specified on the basis of mathematical or physical models, but a single or multi-layer neural network can independently select a currently suitable set from the data source (table) of previous production values, which preferably also contain the product parameters or the quality features of the products Determine production values. The algorithm for artificial intelligence can therefore take previous production values, but preferably also the product values, from the data source. This can be presented to an operator or a controlling computer program product before it enables production.

Particularly preferably, the algorithm will carry out its own weighting of the parameters on the basis of artificial intelligence and the previously usual weighting by technologists or mathematical preset algorithms is dispensed with and only data sets from previous and / or current productions are used.

It is now possible to control or regulate a complex production system through the virtual parameterization of variables. It is no longer necessary to use the product, which is expensive and with a corresponding waiting time, all in one Laboratory to analyze quality features that cannot be directly determined, but statements on quality can be made in advance.

These statements on quality can in turn be the basis for new iterative improvement calculations by the algorithm based on artificial intelligence or request the operator to initiate measures that are not intended for automated activation.

In a particularly preferred alternative or cumulative variant, it is now also possible to use empirical values from other, preferably comparable, production plants as a data source for the algorithm based on artificial intelligence. This data source is preferably revised as a table before it is used and, if necessary, converted to the local production facility with appropriate correction factors.

Due to the large amount of data, it may be necessary to reduce or bundle the amount of data (clustering). This can, for example, be carried out with a large number of press cylinders along a length or an interpolation or extrapolation can be introduced. These aggregated values can also be normalized with regard to physical key data such as length, frequencies, throughput times and others. This also makes it possible to make different presses or differently sized or designed individual devices comparable for alignment. This data could then be used universally.

By comparing the raw data and / or the aggregated data, anomalies can be better identified. In doing so, data errors or incorrect data records can be eliminated in a meaningful way.

The raw data or the aggregated data for use in a computer for controlling and / or regulating a production plant relate to advantageously to real production parameters and / or production plants that are correlated with real quality parameters. These are particularly preferably linked with a time stamp, most preferably with a concurrent or readable time stamp over the production time, so that the associated material or its course through the production system can be assigned to each product.

Depending on the design, a time base is used that assigns a product the previously spaced values with a different time stamp. Especially in systems with a material flow of the educt of several minutes or hours, this can be decisive if parameters could change at this point in time.

With the proposed principle, it is possible to predict and optimize the quality currently being produced in a production plant, which can only be determined later on the basis of laboratory values. These optimizations or predictions can be visualized for the operator and / or used for further optimization.

The virtual quality of a produced product can be "measured" and displayed immediately or this can be specified as a target in the virtual sensor. This opens up the new possibilities of the present invention.

In a preferred embodiment, it should be possible to inform the operator that a certain type of production is currently not possible; it is particularly preferred to carry out and display an analysis that shows how much scrap has to be expected until optimal production is possible again. Promising production alternatives are particularly preferably offered to the operator. In another preferred embodiment, the invention puts a production plant into automatic mode in which it independently optimizes the production plant for the production of a high-quality product during production.

Furthermore, it may be possible for the production plant to automatically determine when maintenance is necessary and to coordinate maintenance intervals in the various production cells in order to generate maintenance downtimes as short as possible. A maintenance plan can particularly preferably be generated and optimized by the method, in particular with regard to pending production orders.

In a possible variant, the storage or the input material (s) will be the subject of optimization processes in order to control the type of material used or the mixing ratios

In a particularly preferred embodiment, productivity can be increased with a virtual sensor in conjunction with an algorithm based on artificial intelligence, if the start-up and cooling times of the machines can be calculated in the event of a production change or start of production and thus the previous system areas (preheating, gluing) and the same can set and, if necessary, adjust to ensure an even or necessary heat input.

For example, you can adapt the preheating of the educt to a press that has not yet been fully heated by slowly converting the preheating in the high load range to continuous operation (normal load), whereas the press adapts to the current load or warms up more and more. It is therefore possible to produce B-goods or even A-goods instead of rejects. Load changes can be proactively calculated and thus also carried out by using virtual sensors to set up the machines and plant components for the changed production in advance.

If, for example, other material or other material mixtures are pressed, system parts can be adjusted accordingly in advance so that they are properly pressed when the new material mixtures arrive.

In a particularly advantageous embodiment, it would now be possible to “virtually” retrofit existing systems using virtual sensors. Thus, without the installation of extended measurement technology, existing systems are virtually able to run through an upgrade and theoretically are able to produce products that they could not previously produce due to a lack of the necessary sensors. In the course of a planned retrofit, the success of such a retrofit can, for example, be forecast. The retrofitting or the necessary retrofitting measures on measuring sensors can be checked for sensibility, so that, for example, only a minimum of real measuring electronics or measuring sensors have to be installed in reality in order to obtain better results or to increase operational reliability in terms of quality and quantity.

In summary, the virtual sensor can display various values virtually, but it can also be used to specify a virtual product parameter. As a result, an algorithm based on artificial intelligence can undertake the further parameters for the system setting and preferably undertake optimizations for the parameterization of the system based on the material and / or its chemical / physical properties.

Claims

1. A method for operating a production plant for the manufacture of material panels, wherein the production system has at least devices for forming a fleece from material and pressing it into material panels and for producing a material panel, product parameters of the material panel to be manufactured and system parameters of the production system are set, with the production system and / or their devices have sensors for determining measured values and computers that are operatively connected to them for control and / or regulation, characterized in that at least one virtual sensor transmits measured values to the computers for controlling and / or regulating the production plant or their devices.

2. The method according to claim 1, characterized in that the measured values of the virtual sensor are created from a measured value of a different type with a correction factor and / or from several correlated non-specific measured values from actual value sensors.

3. The method at least according to one of the preceding claims, characterized in that the measured values of the virtual sensor are or will be provided with a, preferably system-synchronous, time stamp.

4. The method at least according to one of the preceding claims, characterized in that the measured values of the virtual sensor are taken from a database or current production data with measured values from earlier production cycles, preferably taking into account predetermined marginal and / or time data

5. The method at least according to one of the preceding claims, characterized in that an actual value sensor is accompanied by a virtual sensor and, in the event of deviations outside a predetermined range, a reaction, preferably a notification function, is triggered to an operator and / or a corresponding notification entry takes place in a database.

6. The method at least according to one of the preceding claims, characterized in that selected actual value sensors in the production system are accompanied by a virtual sensor and thus checked at predetermined intervals.

7. The method at least according to one of the preceding claims, characterized in that in the event of failure or obvious incorrect measurement of an actual value sensor, a virtual sensor takes over the generation of the measured values and this generation of the measured values preferably starts automatically, in particular accompanied by an alarm information to the Operator.

8. The method at least according to one of the preceding claims, characterized in that step by step the production plant is optimized to the extent that, after corresponding test runs with virtual sensors, the actual value sensors are gradually reduced or switched off.

9. The method at least according to one of the preceding claims, characterized in that a database with correct measured values is created during regular production and, in the event of a failure, one or more sensors are used to create the measured data by the virtual sensor.

10. The method at least according to one of the preceding claims, characterized in that selected actual value sensors are simulated as virtual sensors with the aid of a neural network and / or Product parameters and / or system parameters, preferably which are simulated as virtual sensors without current actual value sensors, with the help of an artificial neural network.

11. The method at least according to one of the preceding claims, characterized in that the measured values of the virtual sensor are transmitted as product parameters and / or system parameters to the computer for controlling and / or regulating the production system or its devices.

12. The method at least according to one of the preceding claims, characterized in that the input parameters for the neural network are normalized and / or aggregated, in particular for the use of the input parameters also for other production systems.

13. The method at least according to one of the preceding claims, characterized in that the results of the neural network and / or the virtual sensor are normalized and / or aggregated before being used on the local production facility or being passed on to other production facilities.

14. The method at least according to one of the preceding claims, characterized in that a virtual sensor is checked and / or trained during an ongoing production, preferably using actual value sensors.

15. The method at least according to one of the preceding claims, characterized in that the measured values of the virtual sensor or sensors, preferably with a time stamp, are written into a database or are visualized together with the actual values of the production plant.

16. The method at least according to one of the preceding claims, characterized in that the program code of the virtual sensor is set to a specific interface description but is executed independently of the actual value sensor to be replaced.

17. The method at least according to one of the preceding claims, characterized in that a virtual sensor, in particular in the course of a comparison with an actual value sensor, is used for status monitoring and / or predictive maintenance and / or failure detection.

18. The method at least according to one of the preceding claims, characterized in that in the course of the automated use of the production system, an optimization of the production or the quality and / or a reduction of material input or rejects is carried out.

19. The method at least according to one of the preceding claims, characterized in that the optimization computer which is in operative connection with the production system receives measured material, product and / or system parameters from the production system and / or its devices.

20. The method at least according to one of the preceding claims, characterized in that in the production plant devices for shredding, sorting, setting the mixing ratios of the material, providing the binding agent, gluing, storage, air conditioning of the material, for weighing, for monitoring and / or testing of the material or the material fleece, for pre-pressing, for setting the humidity, temperature, width and / or height of the material fleece, for measuring parameters of the educts and material panels, for temperature control of the material panel and the like. Are provided.

21. The method at least according to one of the preceding claims, characterized in that at least one virtual sensor maps parameters of the product to be manufactured, in particular quality-defining properties of the product.

22. The method at least according to one of the preceding claims, characterized in that predictions about the product are output or visualized for the decision as a function of characteristics / states of the production plant, and are preferably used to further optimize the parameterization of the production plant.

23. The method at least according to one of the preceding claims, characterized in that a data source, preferably as a table or matrix, consisting of previous production data or the parameterization of the production system in connection with the associated quality features of the manufactured product is made available to the neural network.

24. The method at least according to one of the preceding claims, characterized in that production data sets from other production plants, possibly including aggregated data or correction factors, are used as the data source.

25. The method at least according to one of the preceding claims, characterized in that data records from a production are used as the data source which have reduced or bundled data records or data from a production.

26. The method at least according to one of the preceding claims, characterized in that the data source has a time stamp which preferably depicts the passage of a material through the production plant or at least approximates the passage of the material.

27. The method at least according to one of the preceding claims, characterized in that, in the sense of predictive production, parts of the production plant are controlled or regulated differently over time, in particular in order to avoid deficits in the provision of pressure, heat, speed, or the like balance.

28. The method at least according to one of the preceding claims, characterized in that virtual sensors are used for planning or checking a modernization of a production plant, which map new or parts of the production plant to be changed in order to obtain information about the value of the modernization without real intervention in the production plant.

29. Device for operating a production plant for the production of material panels, the production system having at least devices for forming a fleece from material and pressing it into material panels and for producing a material panel product parameters of the material panel to be manufactured and system parameters of the production system are set, with the production system and / or their devices have sensors for determining measured values and computers operatively connected to them for control and / or regulation, characterized in that at least one virtual sensor is operated using a computer, this computer for transmitting the virtual measured values to the computers for control and / or regulation the production plant or its devices is in operative connection.

30. Device according to the preceding claim, characterized in that, for operating the virtual sensor, the computer is connected to actual value sensors of the same and / or a different type, preferably with the option of using their measured values with a correction factor and / or several in correlation The virtual sensor can be used to map the set foreign measurement values.

31. The device at least according to one of the preceding device claims, characterized in that the virtual sensor is in operative connection with a device for outputting a, preferably system-synchronous, time stamp.

32. The device according to at least one of the preceding device claims, characterized in that a database or current production data with measured values from earlier production cycles, preferably taking into account predetermined marginal and / or time data, is arranged for the transmission of measured values to the virtual sensor.

33. The device according to at least one of the preceding device claims, characterized in that a neural network is arranged to form the virtual sensor.

34. The device according to at least one of the preceding device claims, characterized in that a device for normalization is connected upstream and / or downstream of the virtual sensor and / or aggregation of the values is arranged.

35. The method according to at least one of the preceding claims, characterized in that devices for comminution, sorting, setting the mixing ratios of the material, provision of the binding agent, gluing, storage, air conditioning of the material, for weighing, for monitoring and / or testing of the material or the material fleece, for pre-pressing, for setting the humidity, temperature, width and / or height of the material fleece, for measuring parameters of the educts and material panels, for temperature control of the material panel and the like. Are provided.