Analytical method and device therefor

Abstract

To provide a method for analyzing errors in a methodological and technical installation, such as a coating installation, for simply and surely analyzing an error situation.SOLUTION: A method for predicting process deviation in a methodological and technical installation, such as a coating installation, for simply and surely predicting a process deviation includes: automatically forming a prediction model; and predicting the process deviation in an operation of the methodological and technical installation using the prediction model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a method for analyzing errors in process engineering plants, for example in painting plants. Summary of the Invention [Problem to be solved by the invention]

[0002] The object of the invention is to provide a method for error analysis in a process technology installation, for example a painting installation, which allows error situations to be analyzed simply and reliably. [Means for solving the problem]

[0003] This object is achieved by a method for analyzing errors in a process technology plant, for example in a painting plant.

[0004] Methods for error analysis in technical installations, for example in painting installations, include: - the method for automatically recognizing error situations in technical equipment; storing an error situation data set for each recognized error situation in an error database; - automatically determining the error cause for an error situation and / or automatically determining the process value associated with the error situation based on the error data set of the respective recognized error situation.

[0005] The term "process value causing an error situation" means, within the framework of this description and the appended claims, in particular a process value causing and / or associated with an error situation.

[0006] The term "particularly" is used only to describe possible optional and / or alternative features within the framework of this description and the appended claims.

[0007] It may be advantageous if the error situation is automatically recognized by the reporting system.

[0008] In the form of a method for error analysis in a technical installation, one or more process values ​​are combined with an error situation on the basis of one or more of the following combination criteria in order to automatically determine an error cause for the error situation and / or a process value associated with the error situation: -Pre-binding from reporting systems; - associating the process values ​​with the same part of the process technical installation in which the error situation occurred; -Combining process values ​​with historical error situations based on the user's active selection; - Active selection of process values ​​by the user.

[0009] In the form of a method for error analysis in a technical installation, an automatic prioritization of process values ​​associated with an error situation is automatically performed based on one or more of the following prioritization criteria in order to automatically determine the error causes for the error situation and / or the process values ​​associated with the error situation: -Process relevance of process values; - the location of the process value or the sensor for determining the process value inside the method-technical installation; - the magnitude of the deviation of the process value from the defined process window and / or from the normal state; -Prioritization of historical process values ​​in historical error situations; -By adopting a prioritization of error causes and / or process values ​​from the reporting system; -Prioritization by users.

[0010] The prioritization performed based on the process relevance of the process values ​​is preferably done in such a way that process critical process values ​​have a higher priority.

[0011] The term "process-critical process value" refers within the framework of this specification and the appended claims to a process value that is stored as process-critical in a reporting system and / or that is defined by a user as being process-critical.

[0012] The prioritization, which is performed based on the location of the process values ​​or sensors determining the process values ​​within the method technology installation, is preferably performed in such a way that process values ​​that are associated with identical, nearby and / or comparable parts of the installation have a higher priority.

[0013] The term "comparable equipment parts" means, within the framework of this description and the appended claims, in particular equipment parts having a similar or equal construction.

[0014] Comparable installation parts are, for example, industrial air supply installations of equal or similar construction, regulation modules of equal or similar construction of industrial air supply installations, or pumps or motors of equal or similar construction.

[0015] The positions of the sensors for determining the process values ​​are preferably identified using a scheme from the numbering system within the process technology installation (the so-called "plant numbering system").

[0016] The process values ​​are preferably designated unambiguously using a numbering system.

[0017] Preferably, the process values ​​are prioritized according to their representation within the numbering system.

[0018] The numbering system preferably comprises a designation of the functional unit, a designation of the functional group of each functional unit and / or a designation of each functional component to which the respective sensor and / or process value is assigned, in order to unambiguously designate the sensor and / or process value.

[0019] Furthermore, it may be advantageous if the clear representation of the process values ​​by the numbering system includes a designation of the type of measured variable, for example temperature, flow rate, pressure.

[0020] For example, the air supply of a painting installation is a functional unit, in which case the regulating module of the air supply is a functional group, and in which case the pump of the air supply is a functional member.

[0021] The normal state of the process value is preferably determined using an anomaly and / or error recognition method.

[0022] The prioritization that is performed based on the priorities of the historical process values ​​within the historical error situations is preferably performed in such a way that the process values ​​are prioritized in the same way as the historical error situations.

[0023] In the form of a method for error analysis in a technical installation, further error causes and / or process values ​​are suggested in order to automatically determine an error cause for an error situation and / or a process value associated with the error situation, the suggestion being carried out automatically using one or more of the following suggestion criteria: -Process relevance of process values; - the location of the process value or the sensor from which the process value is determined within the technical installation; - the magnitude of deviation of the process value from the defined process window and / or from the normal state; -Priority of historical process values ​​in historical error situations; -Physical dependency of the process value.

[0024] Process-critical process values ​​are preferably proposed with priority.

[0025] The proposal, which is based on the location of the process values ​​or sensors determining the process values ​​within the method technology installation, is preferably carried out in such a way that process values ​​associated with identical, nearby and / or comparable parts of the installation are proposed earlier.

[0026] Preferably, the process values ​​are proposed according to their representation within the numbering system.

[0027] The proposal, which is carried out based on the priority of the historical process values ​​in the historical error situation, is preferably carried out in such a way that process values ​​with higher priority are proposed first within the historical error situation.

[0028] To obtain suggestions based on physical dependencies of process values, the physical dependencies are preferably defined by the user as expert rules.

[0029] Preferably, the priorities of the suggested error causes and / or process values ​​are changeable by the user.

[0030] In the form of a method for error analysis in a technical installation, historical error situations are determined from an error database using one or more of the following similarity criteria: -Error classification for historical error situations; -Historical error situations on the same or comparable pieces of equipment; - Process values ​​with historical error conditions that are equal to or similar to the process value with the recognized error condition.

[0031] Historical error situations that have the same error classification as the recognized error situation are preferably determined with priority.

[0032] The identity or similarity of the process values ​​of the historical error situations to the process values ​​of the recognized error situations is determined by a comparison algorithm.

[0033] In the form of a method for error analysis in a method-technical installation, historical process values ​​that are identical or similar to a recognized error situation are determined from a process database.

[0034] Preferably, a process database is searched through to determine historical process values. It may be advantageous to use a comparison algorithm to determine identity or similarity of process values.

[0035] The determination of the historical process values ​​is preferably done automatically.

[0036] In the form of a method for error analysis in a method-technical installation, determined historical process values ​​are characterized as belonging to historical error situations.

[0037] In the form of a method for error analysis in a method-technical installation, for recognized error situations, error situation data sets are stored in an error database.

[0038] In the form of a method for analyzing errors in a technical installation, each error identification data set comprises one or more of the following error situation data: -Error classification of error situations; - Process values ​​combined with error situations based on previous combinations from the reporting system; - information about the time of occurrence of the respective error situation; - information about the duration of the occurrence of each error situation; - Information about the location of occurrence of each error situation; -alarm; -Status reporting.

[0039] In the form of a method for error analysis in a method-technical installation, the error situation data set for each error situation contains error identification data for unambiguously identifying the recognized error situation.

[0040] The error identification data is preferably usable to unambiguously specify the error situation.

[0041] In the form of a method for error analysis in a method-technical installation, documentation data and error elimination data are stored in an error situation data set for each error situation.

[0042] The documentation data preferably includes operating guidelines, handbooks, circuit diagrams, method diagrams and / or data sheets of the equipment parts that are relevant to the respective error situation.

[0043] The error elimination data preferably includes data for eliminating the error situation, in particular operational instructions for eliminating the error situation.

[0044] In particular, documentation data and error removal data can be added by the user to the error situation dataset.

[0045] In the form of a method for error analysis in a process technology installation, process values ​​are stored during operation of the process technology installation in time synchronism with recognized error situations.

[0046] In the form of a method for error analysis in a method technology installation, the process values ​​are provided with time stamps, by means of which the process values ​​can be unambiguously associated with a point in time.

[0047] The invention further relates to an error analysis system for error analysis in a process technology installation, for example in a painting installation, which error analysis system is designed and arranged to carry out the method according to the invention for error analysis in a process technology installation, for example in a painting installation.

[0048] The invention further relates to an industrial control system comprising an error analysis system according to the invention.

[0049] The invention further relates to a method for predicting process deviations in a process technology installation, for example in a painting installation.

[0050] Another object of the invention is to provide a method for predicting process deviations in a process technology installation, for example in a painting installation, which allows process deviations to be predicted simply and reliably.

[0051] This problem is solved by a method for predicting process deviations in a process technology plant, for example in a painting plant.

[0052] A method for predicting process deviations in a technical installation, for example in a painting installation, comprises: - Automatic generation of forecast models; - predicting process deviations during operation of the process technical equipment using predictive models;

[0053] Preferably, a predictive model can be used to predict process deviations of manufacturing critical process values.

[0054] In the form of a method for predicting process deviations, the method for predicting process deviations is performed in an industrial air supply facility, in a pre-treatment station, in a cathodic dip coating station, and / or in a drying station.

[0055] Industrial air supply installations, pre-treatment stations and / or cathodic dip coating stations are particularly highly inertial process technology installations.

[0056] The production-critical process values ​​of such process technology installations therefore change only very slowly during their operation.

[0057] Due to the high inertia of such process technology installations, it is possible to predict process deviations during operation of the process technology installations at an early stage using predictive models.

[0058] Advantageously, time can therefore be gained for repairs and / or maintenance of such process technology equipment before process deviations occur.

[0059] Therefore, the industrial air supply installation preferably comprises a number of conditioning modules, such as preheating modules, cooling modules, additional heat modules and / or humidifying modules.

[0060] Preferably, the predictive model formed is transferable to similar process and technical equipment.

[0061] For example, it is contemplated that a predictive model developed for a pretreatment station can be used for a cathodic dip coating station.

[0062] In the form of a method for predicting process deviations, process deviations of production-critical process values ​​in a process technology plant are predicted using a prediction model, in particular on the basis of process values ​​that change during operation of the process technology plant.

[0063] The term "production-critical process value" in the context of this description and the appended claims means in particular a process value whose deviation from a predetermined process window leads to quality deviations, in particular quality defects.

[0064] Production-critical process values ​​of industrial air supply installations are, for example, the temperature and relative air humidity of the air conditioned by means of the industrial air supply installation, in particular in the outlet section of the industrial air supply installation.

[0065] The air conditioned using the industrial air supply system is supplied to the painting system, preferably to the painting cabin, and thus preferably directly affects the processing quality of the workpieces in the painting cabin, in particular the vehicle bodies processed in the painting cabin.

[0066] For example, the predictive model can be used to predict process deviations of manufacturing-critical process values ​​over a prediction horizon of at least about 10 minutes, such as at least about 15 minutes, and preferably at least about 20 minutes.

[0067] In the form of a method for predicting process deviations, process values ​​and / or status variables are stored during operation of the process technology installation over a predetermined period of time in order to automatically generate a prediction model.

[0068] If the process technology installation is an industrial air supply installation, the process values ​​and / or status variables that are stored are preferably: - target variables of the industrial air supply system, in particular the temperature and relative humidity of the air conditioned by the industrial air supply system, in particular at the outlet of the industrial air supply system; - manipulated variables, in particular valve positions of valves of heating and / or cooling modules of industrial air supply installations, rotational frequencies of pumps, in particular wetting pumps and / or rotational frequencies of ventilators; - internal variables, in particular the forward and / or return temperatures in heating and / or cooling modules of industrial air supply installations and / or the air condition between regulation modules; -measured variables, in particular the external temperature and / or relative external humidity in the blowing section of the industrial air supply system; - Unmeasured disability variables; and / or - Status variables, especially the wet pump (on / off), manual mode for the pump (on / off), supply valve (open / closed), ventilator (on / off).

[0069] The term "process value" means within the framework of this description and the appended claims, in particular a time-dependent, continuous signal.

[0070] The term "status variable" means, within the framework of this description and the appended claims, in particular a discrete event that is time-dependent.

[0071] In the form of a method for predicting process deviations, the predetermined time period during which process values ​​and / or status variables are stored during operation of the method technology installation is set according to one or more of the following criteria: - the process technology equipment is in a state of readiness of at least about 60%, preferably at least about 80%, in particular for production runs, within a predetermined period of time; - the process technology facilities are in a state of production readiness for at least about 60%, preferably at least about 80%, within a predetermined period of time; -Method: the technical installation is driven within a predetermined time period, in particular by all possible drive strategies; - A predetermined number of process deviations and / or failures within a predetermined period of time.

[0072] If the process technical installation is an industrial air supply installation, this installation preferably comprises: - if the ventilator of the industrial air supply system is activated (ventilator status variable "ON"); - if the regulation module of the industrial air supply installation is operated in automatic mode; - at least one regulating valve is open; and / or - if the wetting pump is activated (wetting pump status variable "On"), It is ready for production driving.

[0073] The term "production-ready state of the process technology installation" means, in particular, within the scope of this description and the appended claims, that the target variables of the process technology installation are within a predetermined process window.

[0074] If the process technology installation is an industrial air supply installation, this installation is ready for production when the target variables of the industrial air supply installation, in particular the temperature and relative humidity of the air conditioned by means of the industrial air supply installation, in particular at the outlet part of the industrial air supply installation, are within a predetermined process window.

[0075] The pretreatment station or the cathodic dip coating station can in particular be driven by only one drive strategy.

[0076] The industrial air supply installation can be driven in particular by a number of drive strategies, in particular according to the ambient conditions.

[0077] Industrial air supply plants can be driven, for example, by the following driving strategies: heat-humid, cool-heat, cool-humid, cool, heat, moist.

[0078] If the process technology installation is an industrial air supply installation, it is particularly conceivable that the process values ​​and / or status variables for automatically forming the predictive model are stored, for example, for a period of at least 6 months, in particular for a period of at least approximately 9 months, preferably for a period of at least approximately 12 months.

[0079] If the process technology installation is a pretreatment station or a cathodic dip coating station, it is particularly conceivable that the process values ​​and / or status variables for automatically generating a predictive model are stored, for example, for a period of at least about two weeks, in particular for a period of at least about four weeks, preferably for a period of at least about six weeks.

[0080] For example, it is contemplated that at least about 30, and preferably at least about 50, process deviation and / or fault cases will occur within a predetermined period of time.

[0081] In particular, it is also conceivable that the predetermined time period in which process values ​​and / or status variables are stored during operation of the process technology installation comprises several unconnected sub-time periods.

[0082] If the time period in which process values ​​and / or status variables are stored during operation of the method technology installation comprises several disconnected sub-time periods, the sub-time periods preferably each have one or more of the following criteria: - a minimum length of the subperiod, for example at least about 30 minutes; - at the beginning of the partial period, the operation of the process technology installation is in a state of production readiness and / or a defined state of overshoot; The drive of the method technical installation is in a defined state of overshoot at the end of the partial period.

[0083] In the form of a method for predicting process deviations, a machine learning method is implemented to form a predictive model, in which process values ​​and / or status variables stored over a predetermined period of time are used to form the predictive model.

[0084] The learning methods implemented to automatically form the predictive model preferably comprise one or more of the following: gradient boosting, random forests, support vector machines.

[0085] In the form of a method for predicting process deviations, machine learning is performed based on features extracted from process values ​​and / or status variables stored over a predetermined period of time.

[0086] In the form of a method for predicting process deviations, one or more of the following are used to extract features: - statistical index; - coefficients from main component analysis; -linear regression coefficients; - Dominant frequencies and / or amplitudes based on the Fourier spectrum.

[0087] The statistical indices may include, for example, a minimum, a maximum, a median, a mean, and / or a standard deviation.

[0088] In one form of a method for predicting process deviations, a selected number of predictive data sets with process deviations and a selected number of predictive data sets without process deviations are used to train a predictive model.

[0089] In particular, it is conceivable that a selected number of predicted data sets with process deviations correspond at least approximately to a selected number of predicted data sets without process deviations.

[0090] In particular, it is conceivable that the selected number of predicted data sets with process deviations and the selected number of predicted data sets without process deviations are identical.

[0091] In the embodiment of the method for predicting a process deviation, the selection of the number of prediction data sets having the process deviation is based on one or more of the following criteria: - minimum time interval between two forecast data sets; -Automatic selection using defined rules; -User selection.

[0092] The minimum time interval between two forecast data sets is, for example, at least about two hours.

[0093] In one embodiment of the method for predicting a process deviation, a predictive data set having a process deviation is characterized as such if the process deviation occurs within a predetermined time interval.

[0094] The predetermined time interval preferably comprises the duration of the forecast data set and the selected forecast horizon.

[0095] For example, the forecast data set may have a duration of 30 minutes and the selected forecast horizon may be 15 minutes.

[0096] A predicted data set free of process deviations is characterized as such when no process deviations are present within a predetermined time interval.

[0097] In a form of a method for predicting process deviations, process values ​​and / or status variables stored over a predetermined period of time are compiled into a predictive data set by pre-processing.

[0098] In the form of a method for predicting process deviations, the pre-processing comprises: - Regularization of stored process values ​​over a predetermined period of time; - Combining process values ​​and / or status variables into a forecast data set by dividing the process values ​​and / or status variables in a time window with a time shift.

[0099] Preferably, the duration of the time window is greater than the time shift.

[0100] The duration of the time window is, for example, 30 minutes.

[0101] The time shift is, for example, 5 minutes.

[0102] In that case, preferably, the time-successive forecast data sets each comprise process values ​​and / or status variables with a time overlap of, for example, 5 minutes.

[0103] The invention further relates to a forecasting system for forecasting process deviations in a process technology installation, which forecasting system is configured and arranged to carry out the method according to the invention for forecasting process deviations in a process technology installation, for example in a painting installation.

[0104] The present invention further relates to an industrial control system, which includes a prognostic system according to the present invention.

[0105] The method according to the present invention for predicting process deviations preferably includes one or more of the features and / or advantages discussed above in relation to the method according to the present invention for error analysis.

[0106] The method for error analysis according to the present invention preferably further includes one or more of the features and / or advantages discussed above in relation to the method for predicting process deviations according to the present invention.

[0107] The invention further relates to a method for anomaly and / or error recognition in a process technical installation, for example in a painting installation.

[0108] Another object of the invention is to provide a method for recognizing anomalies and / or errors in a process technology installation, for example a painting installation, which allows for simple and reliable recognition of anomalies and / or error situations.

[0109] This object is achieved by a method for detecting anomalies and / or errors in a process technology installation, for example in a painting installation.

[0110] The method for recognizing anomalies and / or errors in a process-technical installation, for example in a painting installation, preferably comprises: - the method automatically generates an anomaly and / or error model of the technical installation, which model contains information about the probability of occurrence of process values; -Method for automatically reading process values ​​of technical equipment during its operation; - Automatic recognition of anomaly and / or error situations by determining the probability of occurrence using anomaly and / or error models based on the process values ​​of the loaded method-technical installation and by checking the probability of occurrence against limit values.

[0111] Preferably, an anomaly and / or error recognition method is used to identify error situations, i.e. failures and / or malfunctions of components, sensors and / or actors.

[0112] Preferably, the normal state of the process technology installation can be determined automatically by a method for anomaly and / or error recognition within the process technology installation.

[0113] Anomaly and / or error models can be used to describe static and / or dynamic relationships, especially within process technical installations.

[0114] The term "anomaly" in the context of this description and the appended claims means in particular the deviation of a process value from its normal state.

[0115] The anomaly and / or error model preferably comprises a structure graph.

[0116] The structural graph in particular comprises a plurality of cliques, where the relationships between the knots of each clique are preferably described by a probability density function.

[0117] By means of cliques of the structure graph, respectively, relationships are preferably described for sensors and / or actors of the method technical installation.

[0118] Preferably, an anomaly is recognized if a threshold value for the probability of occurrence of a process value falls below a clique of the structure graph of the anomaly and / or error model.

[0119] It may be beneficial for the user to be able to graphically display the identified anomalies with abnormal process variables.

[0120] In the form of a method for anomaly and / or error recognition, the anomaly and / or error model comprises structure data containing information about the process structure in the process technical installation, and / or The anomaly and / or error model comprises parameter setting data containing information about the relationships between process values ​​of the method technology installation.

[0121] The structural data includes in particular information about the relationships between sensors and / or actors within the process technical installation.

[0122] The parameter setting data contains, inter alia, information about the probability of occurrence of the process values.

[0123] In particular, the structural data and / or parameter setting data are utilized to form an anomaly and / or error model.

[0124] In the form of a method for anomaly and / or error recognition, one or more of the following steps are performed to form an anomaly and / or error model: -Method of structural identification for determining the process structure of technological equipment; -Determine causal relationships within the process structure of the sought-after methodological equipment; -Setting of structural parameters of the relationships within the process structure of the desired method-technical equipment.

[0125] The anomaly and / or error model preferably includes structural information, causality information and / or structural parameter setting information.

[0126] Preferably, structure identification data can be used to facilitate structure parameter setting.

[0127] In particular, the structure identification data can be used to reduce the parameter setting effort and the associated calculation effort for setting the structure parameters.

[0128] In the case of a structure identification in the form of a method for anomaly and / or error recognition in order to determine the process structure of a process technology installation, a structure graph is determined, which structure graph in particular simulates the relationships within the process technology installation.

[0129] The structural graph preferably includes a plurality of knots and a plurality of edges connecting the knots to each other in pairs.

[0130] The structural graph preferably includes multiple cliques.

[0131] It may be advantageous if the relationships within the determined structural graph are determined using structural identification.

[0132] In the form of a method for anomaly and / or error recognition, a structure graph is determined using one or more of the following: -Mechanistic learning methods; -Expert Knowledge -Recognized circuit diagrams and / or method diagrams; -Method of designation within the numbering system of technical equipment.

[0133] For the structure identification, in particular for determining the structure graph, it can be advantageous if a scheme from the numbering system within the process technical installation (the so-called "plant numbering system") is used, for example by means of semantic analysis.

[0134] The numbering system contains information in particular about the functional units, for example about the equipment type of the process technical equipment, about the functional groups of the respective functional units, about the functional members of the respective functional groups and / or about the data types.

[0135] Preferably, the numbering system has multiple levels.

[0136] The first level of the numbering system contains, for example, information about each functional unit.

[0137] The second level of the numbering system contains, for example, information about each functional group.

[0138] The third level of the numbering system contains, for example, information about each functional component.

[0139] The fourth level of the numbering system contains, for example, information about each data type.

[0140] Preferably, the numbering system data set contains an unambiguous designation of the functional components of the process technical installation.

[0141] For example, the explicit designation of a functional member may include information about the first, second, third and / or fourth level.

[0142] Preferably, in the case of a semantic analysis, the extraction of information from the numbering system data set is carried out on the basis of an explicit designation of the functional components of the method-technical installation, for example.

[0143] Preferably, when performing the semantic analysis, one or more string searches are performed within the numbering system dataset.

[0144] In that case, in particular, information can be extracted from the numbering system data set.

[0145] When extracting information, a first string search is performed in the particular numbering system data set, resulting in the particular extracted data set.

[0146] The information extracted from the numbering system dataset is preferably categorized for semantic analysis.

[0147] When categorizing, a second string search is performed within the extracted data set, for example obtained during information extraction.

[0148] For example, it is conceivable that in the case of a semantic analysis, in particular in one or more string searches, it is possible to identify which physical variables are measured by the sensor element.

[0149] Physical variables that can be identified using semantic analysis are, for example: thermodynamic variables (temperature and / or humidity); hydraulic variables (pressure, volume and / or state of fill); mechanical variables (rotational speed, torque and / or rotational position); electrical variables (frequency, voltage, current strength and / or electrical power).

[0150] Furthermore, for semantic analysis, it may be advantageous if the status variable is identifiable, especially in one or more string searches.

[0151] Status variables that can be identified in semantic analysis include, for example, the following information: information about the operating state of the wet pump (on / off); information about the manual mode for the pump (on / off); information about the opening status of the supply valve (open / closed); information about the operating state of the ventilator (on / off).

[0152] Determining the structural graph using machine learning methods is preferably performed using correlation coefficients, which allow non-linear relationships to be reproduced, for example by mutual information.

[0153] The term "expert knowledge" means within the framework of this description and the appended claims, for example, knowledge about the relationships between sensors in a process.

[0154] Preferably, edges between knots of the structure graph can be eliminated by pre-constructing the structure graph using expert knowledge, information from known circuit diagrams and / or method diagrams, in which case the computational effort for determining the structure graph can be reduced in particular.

[0155] The process values ​​are preferably clearly indicated using a numbering system ("plant numbering system").

[0156] Therefore, it may be advantageous if the structure graph is determined using explicit specifications of each of the process values.

[0157] In particular, it is conceivable that the structural graphs determined using machine learning methods are checked for their validity using expert knowledge, using known circuit diagrams and / or method diagrams and / or using designations within the numbering system of the method technical equipment.

[0158] In the form of a method for anomaly and / or error recognition, the method technical equipment is stimulated by test signals in order to identify structures, in particular to determine structure graphs.

[0159] Preferably, when stimulated by the test signal, desired anomalies and / or error situations are generated.

[0160] The test signal is generated taking into account, in particular, design data, on the basis of which limit values ​​for the test signal can be set, for example, the maximum amplitude of the manipulated variable jump when setting a jump function.

[0161] The term "design data" means, within the framework of this description and / or the appended claims, in particular one or more of the following pieces of information: - sensor type (temperature sensor, flow sensor, valve position sensor, pressure sensor, etc.) and / or actor type (valve, ventilator, flap, E-motor); - the allowed value domain of the sensor and / or actor; -Sensor and / or actor signal type (float, integer).

[0162] In particular, the method technical installation is dynamically stimulated with test signals.

[0163] Test signals are in particular signals which can change manipulated variables in the process technology installation, for example by means of which manipulated variables of valves and / or pumps of the process technology installation are changed.

[0164] In the form of a method for anomaly and / or error recognition, the determination of the causal relationships of the process structure of the determined method-technical installation is carried out using one or more of the following: - system input signals and system output signals generated when stimulating the technical equipment with a test signal; -Expert knowledge; - known circuit diagrams and / or method diagrams; -Method of designation within the numbering system of technical equipment.

[0165] The determined causal relationships within the process structure are derived, for example, from the system input signals and system output signals of the process technology equipment determined when the process technology equipment is stimulated by a test signal, for example by using the respective time courses of the system input signals and system output signals.

[0166] Alternatively or additionally, it is conceivable to derive causal relationships from the system input and output signals determined when the method technical installation is stimulated by a test signal using causal inference methods.

[0167] The term "causality" in the context of this specification and / or the appended claims refers in particular to the causality directions, ie "arrows", in the determined structure graph.

[0168] Preferably, the determined causal relationships within the determined process structure or within the determined structure graph can be used to find the process values ​​responsible for the recognized anomaly.

[0169] In the form of a method for anomaly and / or error recognition, one or more of the following are used to determine the relationships within the process structure of the process technology installation: -Methods for determining probability density functions, especially Gaussian mixture models; -Known relationships between process values; Physical maps of functional components of the method technical installation, for example maps of valves.

[0170] Preferably, the structural parameter setting is performed using a method for determining probability density functions, in particular using a Gaussian mixture model.

[0171] It may be advantageous if, by means of a physical map of the functional components of the process technical installation, the relationships between the variables of the functional components can be described.

[0172] Using a known valve map of the valve, for example, the relationship between valve position and volumetric flow rate can be described.

[0173] In the form of a method for anomaly and / or error recognition, data from regular operation of the process technology equipment and / or data obtained by stimulating the process technology equipment with test signals are used for setting structural parameters using methods for determining probability density functions, in particular using Gaussian mixture models.

[0174] For example, using a method for determining probability density functions, position variables, measurement variables and / or adjustment variables, which are stored in particular in a database, are used for setting the structural parameters.

[0175] Preferably, for the structural parameter setting using the method for determining the probability density function, data from the ongoing operation of the process technical installation is used, which data is stored for a period of at least 2 weeks, preferably at least 4 weeks, for example at least 8 weeks.

[0176] In the form of a method for anomaly and / or error recognition, the data used for setting the structural parameters is pre-processed before setting the structural parameters using a method for determining probability density functions, in particular using a Gaussian mixture model.

[0177] When preprocessing, data from the regular operation of the process technology equipment that is not associated with the ready-to-operate or ready-to-production operating state of the process technology equipment (e.g. equipment off, maintenance phase, etc.) is preferably filtered out using alarm and status bits that describe the state of the process technology equipment.

[0178] Furthermore, it may be advantageous if the data from the regular operation of the installation is pre-processed by filtering, for example with a low-pass filter and / or with a Butterworth filter.

[0179] Data from the regular drive is interpolated to a uniform time step width.

[0180] In the form of a method for recognizing an anomaly and / or error, when forming an anomaly and / or error model, a limit value for the occurrence probability of a process value is defined, and if the limit value is exceeded, an anomaly is recognized.

[0181] The determination of the limits is preferably done automatically.

[0182] The limiting is preferably done using a non-linear optimization method, for example the Nelder-Mead method.

[0183] Alternatively or additionally, it is conceivable that the limiting is done using quantiles.

[0184] The limit value for the probability of occurrence of the process value can preferably be optimized, for example by setting a "false positive rate".

[0185] Preferably, the limit values ​​are adapted after the initial setting of the anomaly and / or error model, especially if the occurrence of error alarms is too high.

[0186] In the form of a method for anomaly and / or error recognition, the method for anomaly and / or error recognition is used to identify an error cause of a recognized anomaly and / or a recognized error situation.

[0187] In particular, error causes can be identified using the structure graph of the anomaly and / or error model.

[0188] Preferably, the structure graph is visualized for a user to identify anomalies and / or error situations and / or to identify error causes.

[0189] Using the structure graph, in particular a "root cause analysis" can be carried out, in particular abnormal process values ​​within the process structure of a process technology installation can be identified.

[0190] Preferably, a recognized abnormality can be characterized by the user as an error condition or an error alarm.

[0191] The error conditions are stored in particular in an error database.

[0192] In the form of a method for anomaly and / or error recognition, the method technical installation comprises or is formed by one or more of the following operating stations of a painting installation: -Pre-treatment station; -Cathode immersion coating station; - Drying station; -Industrial air supply equipment; -Painting robot.

[0193] The invention further relates to an anomaly and / or error recognition system for recognizing anomalies and / or errors, which system is configured and arranged to carry out the method according to the invention for recognizing anomalies and / or errors in a process technical installation, for example in a painting installation.

[0194] Anomaly and / or error recognition systems are in particular reporting systems, by means of which error situations in process technical installations can be recognized in an automated manner.

[0195] The invention further relates to an industrial control system, which includes an anomaly and / or error recognition system according to the invention.

[0196] The method according to the present invention for recognizing anomalies and / or errors preferably comprises one or more of the features and / or advantages described in relation to the method according to the present invention for analyzing errors and / or the method according to the present invention for predicting process deviations.

[0197] The method for analyzing errors according to the present invention and / or the method for predicting process deviations according to the present invention preferably comprises one or more of the features and / or advantages described in relation to the method for recognizing anomalies and / or errors according to the present invention.

[0198] Further features and / or advantages of the invention are the subject of the following description of exemplary embodiments and the accompanying drawings. [Brief explanation of the drawings]

[0199] [Figure 1] 1 is a diagrammatic representation of a methodological installation and an industrial control system. [Figure 2] 1 is a diagrammatic representation of a process technology installation, in particular a painting installation. [Figure 3] 1 is a diagrammatic representation of an industrial air supply system. [Figure 4] 4 is a diagrammatic representation of the industrial air supply installation shown in FIG. 3 when an error condition occurs. [Figure 5] 4 is a schematic representation of the industrial air supply system shown in FIG. 3 when another error condition occurs. [Figure 6] 4 is a schematic representation of the industrial air supply system shown in FIG. 3 when another error condition occurs. [Figure 7] 1 is another schematic representation of an industrial air supply system. [Figure 8] 8 is a diagrammatic representation of the industrial air supply installation shown in FIG. 7 in an operating state without process deviations. [Figure 9] 8 is a diagrammatic representation of the industrial air supply installation shown in FIG. 7 in an operating state with process deviations due to changes in ambient conditions. [Figure 10] 8 is a diagrammatic representation of the industrial air supply installation shown in FIG. 7 in an operating state with a process deviation due to the heat recovery system being switched on. [Figure 11] 8 is a diagrammatic representation of the industrial air supply installation shown in FIG. 7 in an operating state with a process deviation due to a valve malfunction. [Figure 12] 1 is a graphical representation of process values ​​compiled into a forecast data set. [Figure 13] 13 is a graphical representation of a predictive data set according to FIG. 12 characterized as a predictive data set with a process deviation and a predictive data set without a process deviation. [Figure 14] 1 is a diagrammatic representation of a pre-treatment station. [Figure 15] 4 is a diagrammatic representation of method steps for forming an anomaly model and / or an error model of a pre-processing station. [Figure 16] 5 is a diagrammatic representation of a graph with a process structure derived from the pretreatment station according to FIG. 4. [Figure 17] 1 shows the cliques in the factor graph. [Figure 18] A model of functional relationships within a clique based on Figure 7. [Figure 19] It shows a clique equivalent to the one shown in 17, expanded by one knot due to the assignment of error causes. DETAILED DESCRIPTION OF THE INVENTION

[0200] In all figures, identical or functionally equivalent parts are provided with the same reference numerals.

[0201] FIG. 1 shows an industrial control system, generally designated 10 , for a process technology installation 101 .

[0202] The process technical installation 101 is, for example, a painting installation 104, which is particularly shown in FIG.

[0203] 1 to 6, a method for error analysis in particular in a process-technical installation 101, in particular in a painting installation 102, is explained.

[0204] 1, 2 and 7 to 13, a method for predicting process deviations in particular in a process-technical installation 101, in particular in a painting installation 102, is explained.

[0205] 1, 2 and 14 to 19, a method for anomaly and / or error recognition in particular in a process-technical installation 101, in particular in a painting installation 102, is explained.

[0206] The process-technical installation 101, in particular a painting installation 102, shown in FIG. 2, preferably comprises a number of processing stations 104 for processing workpieces 106, in particular for processing vehicle bodies 108.

[0207] The processing stations 104 are in particular connected to one another in the embodiment of the painting installation 102 shown in FIG. 2, thus forming a painting line 110 .

[0208] To process the workpiece 106, in particular to paint a vehicle body 108, the workpiece 106 preferably passes through the processing stations 104 one after the other.

[0209] For example, it is contemplated that the workpiece 106 passes through successive processing stations 104 in the order described.

[0210] The workpiece 106 is pre-treated in a pre-treatment station 112 and transferred from the pre-treatment station 112 to a station 114 for cathodic dip coating.

[0211] The workpiece 106 is then subjected to cathodic dip coating at a station 114. After the coating is applied, the substrate is transported to a station 114 for cathode dip coating followed by a drying station 116.

[0212] After the coating applied to the workpiece 106 in the cathodic dip coating station 114 has been dried in the drying station 116, the workpiece 106 is preferably transported into a base coat cabin 118, in which a coating is again applied to the workpiece 106.

[0213] After the coating is applied in the basecoat cabin 118 , the workpiece 106 is preferably transferred into a basecoat drying station 120 .

[0214] After the coating applied to the workpiece 106 in the basecoat cabin 118 is dried in the basecoat drying station 120, the workpiece 106 is preferably transferred into a clearcoat cabin 122, where another coating is applied onto the workpiece 106.

[0215] After the coating is applied in the clear coat cabin 122 , the workpiece 106 is preferably fed to a clear coat drying station 204 .

[0216] The coating applied to the workpiece 106 in the clear coat cabin 122 After being dried in the clear coat drying station 203, the workpiece 106 is preferably fed to the control station 126 at the end of the manufacturing process.

[0217] Within the control station 126, quality control is preferably performed by a quality inspector, for example using visual control.

[0218] The process-technical installation 101, in particular the painting installation 102, preferably further comprises an industrial air supply installation 128, for example for conditioning the air supplied to the basecoat cabin 118 and / or the clearcoat cabin 122.

[0219] The temperature and / or relative air humidity of the air supplied to the basecoat cabin 118 and / or the clearcoat cabin 122 can preferably be adjusted using the industrial air supply system 128 .

[0220] By means of the industrial control system 100 it is possible to control preferably the manufacturing process, in particular the painting process, in a process station 104 of a process-technical installation 101, in particular a painting installation 102.

[0221] To that end, the industrial control system 100 preferably includes a process control system 130 .

[0222] The industrial control system 100 shown in FIG. 1 preferably further includes a database 132 .

[0223] The databases 132 of the industrial control system 100 preferably include a process database 134 and an error database 136 .

[0224] Additionally, the industrial control system 100 advantageously includes a reporting system 138 and an analysis system 140 .

[0225] The industrial control system 100 preferably further includes a visualization system 142 that can be used to visualize information for a user.

[0226] In that case, the visualization system 142 preferably comprises one or more displays on which the information can be displayed.

[0227] The analysis system 140 preferably includes or is formed by an error analysis system 144 .

[0228] It may be advantageous if the reporting system 138 comprises or is formed by a forecasting system 146 for predicting process deviations within the process engineering installation 101 .

[0229] Alternatively, or in addition, it is conceivable that the reporting system 138 comprises an anomaly and / or error recognition system 148 .

[0230] The error analysis system 144 is especially arranged and configured to carry out the method for error analysis described with the aid of FIGS. 1 to 6 in the method technical installation 101 .

[0231] The forecasting system 146 is arranged and configured to implement in the process technology installation 101 the method for forecasting process deviations, which is described in particular with the aid of FIGS.

[0232] The anomaly and / or error recognition system 148 is especially designed to implement the method for anomaly and / or error recognition described in FIGS. 1, 2 and 14 to 19 in the method technical installation 101 .

[0233] The industrial air supply plant 128 shown in FIGS. 3 to 6 preferably includes a number of conditioning modules 150, in particular a preheating module 154, a cooling module 156, an additional heat module 158 and / or a humidifying module 160.

[0234] For example, the industrial air supply system 128 of the painting system 102 is a functional unit, in which case the regulation module 150 of the air supply system 128 is a functional group, and in which case the circulation pump 152 of the air supply system is a functional member (see Figures 3 to 6).

[0235] In addition to the circulation pumps 152 of the preheat module, the cooling module 156 and the additional heat module 158 , the industrial air supply facility 128 preferably further includes a wetting pump 153 of the wetting module 160 .

[0236] Additionally, it may be advantageous if the air supply system 128 includes a ventilator 162 .

[0237] The air supply facility 128 preferably further includes a heat recovery system 164 for recovering heat.

[0238] The air supply facility 128 may be supplied with an air flow 165, preferably from its surroundings.

[0239] A conditioned air flow 167 using the air supply system 128 can preferably be supplied to the basecoat cabin 118 and / or the clearcoat cabin 122 .

[0240] The air supply installation preferably has sensors, not shown in the figures, by means of which process values ​​can be determined.

[0241] For example, the following process values ​​can be detected using sensors, which are preferably indicated with respective reference numerals in Figures 3 to 6: -external temperature 166; - external humidity 168; - Temperature of conditioned air using industrial air supply equipment 170; - Humidity of air conditioned using industrial air supply equipment 172; volumetric flow rates 174, 176, 178 in the regulation module 150; Valve positions 180, 182, 184 of valves 181, 183, 185 in the regulation module 150.

[0242] Furthermore, it may be advantageous if the rotation frequency 193 of the wet pump 153 and the rotation frequency 195 of the ventilator 194 are detected.

[0243] Preferably, the process values ​​166 to 184 are stored in the process database 134 .

[0244] Furthermore, the following status variables can be detected and are preferably respectively indicated with the same reference numerals in FIGS. 3 to 6: - pump status 186, 188, 190 of the circulation pump 152 and pump status 192 (on / off) of the wetting pump 153 of the regulation module 150; -Ventilator status 194 (on / off); - valve status 196, 198, 200 (closed / open) of the regulation module 150; - Status 202 (on / off) of heat recovery system 164.

[0245] These status variables 186 - 202 are preferably also stored in the process database 134 .

[0246] The method for error analysis in the method-technical installation 101 will now be described, preferably with reference to FIGS.

[0247] In that case, the industrial air supply installation 128 forms in particular the process technical installation 101 .

[0248] In the following, various example situations will be described, based on which the way in which the error analysis system 144 functions will become clear.

[0249] Example scenario 1 (see Figure 4): (Valve leakage)

[0250] A valve leak occurs in the preheat module 154. A volumetric flow rate 174 > 0 is measured. The pump status 186 is "off" and the valve status 196 of the regulator valve is "closed."

[0251] The error condition is stored as logic in the reporting system (pump status 186="off", volumetric flow rate 174>0 and valve status 196 "closed"). The reporting system therefore stores the process and status values ​​preferably pre-coupled.

[0252] The error analysis steps in the event of a valve leak based report are preferably the following: 1) The report is displayed to the user using the visualization system 142, for example using the monitor of the visualization system 142. 2) The user opens a diagnostic window in an attempt to analyze the situation. 3) In the diagnostic window, the user is presented with the process values ​​174 and status variables 186-196 pre-combined with the report. The error analysis system 144 preferably obtains this information directly from the reporting system 138. 4) Prioritization of process values ​​combined with error conditions is preferably not performed since error conditions are associated with process values ​​174 only. 5) The user stores the error condition along with the binding in the error database 136. 6) In the event of a new occurrence of the error condition "valve leak" on the same or a comparable valve, the user is preferably informed of the comparable error condition.

[0253] Example scenario 2 (see Figure 5): (Exceeding the temperature 170 of the air conditioned using the industrial air supply 128 due to an excessively high external temperature 166)

[0254] The outside temperature 166 was outside the design window of the industrial air supply system 128 and therefore exceeded the temperature 170 of the air conditioned using the industrial air supply system 128 .

[0255] If the temperature 170 of the air conditioned using the industrial air supply 128 falls outside a predetermined process window, a report is generated and reported from the reporting system 138 to the visualization system 142.

[0256] This report is coupled with the value of the temperature 170 of the air conditioned using the industrial air supply 128. However, this report is not coupled with the outside temperature 166.

[0257] The error analysis steps when a temperature change based report occurs are preferably as follows: 1) The report is displayed to the user using the visualization system 142, for example using the monitor of the visualization system 142. 2) The user opens a diagnostic window in an attempt to analyze the situation. 3) In the diagnostic window, the user is presented with the process values ​​170 associated with the report. 4) Prioritization of process values ​​associated with error conditions is not performed because only process value 166 is associated with an error condition. 5) In addition, the following process values ​​are preferably proposed to the user: - Humidity of air conditioned using industrial air supply systems 172 (process critical variable, indicates abnormalities in behavior); -External temperature 166 (indicating abnormalities in behavior); -External humidity 168 (indicating abnormal behavior). 6) The user selects the suggested process values ​​and attaches them to the error condition. 7) The user is provided with important process values ​​so that the causes of temperature variations can be understood directly from the analysis system 140, and in particular from the error analysis system 144. 8) The user adds documentation to the error situation with suggestions for eliminating the error. 9) The user stores the error situation in an error database along with the binding and documentation. 10) The error analysis system 144 preferably captures the error ID, error classification (temperature rise), error location (128 outlet of the industrial air supply system), as well as the reference (ID) and characteristic amount (e.g., mean value, minimum value, maximum value, variability of the process variable during the error condition) of the process variables 170, 172, 166, 168 in order of priority, and the duration of the error condition until the time of storage or the end of the error condition.

[0258] Example scenario 3 (see Figure 5): (Exceeding 170°C of conditioned air from industrial air supply equipment due to excessively high external temperatures)

[0259] The temperature of the conditioned air using the industrial air supply system 170 is now exceeded based on the outside temperature. This error image is similar to situation example 2.

[0260] When a temperature change based report occurs, the analysis steps are preferably as follows: 1) The report is displayed to the user using the visualization system 142, for example using the monitor of the visualization system 142. 2) The user opens a diagnostic window in an attempt to analyze the error situation. 3) In the diagnostic window the user is presented with the reports and associated process values: 170, 172, 166, 168 in the order listed. 4) A list of processes and their priorities are derived from similar error situations. Similarities to error situations based on Example Situation 2 are determined by the error analysis system 144 via numerical adjustment of process values. 5) A similar error condition is displayed to the user. 6) The user can use the graphical progression of process values ​​in prioritized columns and the record of similar error situations shown to him to find a solution. 7) The user stores the error condition.

[0261] Example scenario 4 (see Figure 6): (Disruptions in the supply system)

[0262] Too little combustion gas is being supplied to the burners in the preheat module 154. The volumetric flow rate 174 drops.

[0263] To obtain more combustion gases, the valve 181 of the preheat module 154 opens more and the valve position 180 changes.

[0264] To compensate for the failure of the preheat module 154, the valve 185 of the supplemental heat module 158 is also opened. The valve position 184 changes.

[0265] This disturbance cannot be compensated for based on the low external temperature 166, causing the temperature 170 of the conditioned air using the industrial air supply to drop.

[0266] When a report occurs based on a fault in the supply system, the analysis steps are preferably the following: 1) The report is displayed to the user using the visualization system 142, for example using the monitor of the visualization system 142. 2) The user opens a diagnostic window in an attempt to analyze the error situation. 3) Within the diagnostic window, the user is presented with the process values ​​170 associated with the reports based on pre-prioritization within the reporting system 138 . 4) No prioritization is done. 5) The following process values ​​are suggested: - Humidity of air conditioned using industrial air supply systems 172 (process critical variable, indicates abnormalities in behavior); - volumetric flow rate 174, valve position 180, valve position 186 (depending on deviation from normal state); 6) The error situations based on example situations 2 and 3 cannot be classified as similar (signal behavior is different due to large numerical intervals between process values); 7) The proposed process value is added to the error condition and stored in the error database.

[0267] Method A method for predicting process deviations in a technical installation 101 will now be described, preferably with reference to FIGS.

[0268] If the process technology installation 101 is an industrial air supply installation 128, the stored process values ​​and / or status variables preferably comprise (see FIG. 7): target variables 204 of the industrial air supply system 128, in particular the temperature 170 and relative air humidity 172 of the air conditioned by the industrial air supply system, in particular at the outlet of the air supply system 128; manipulated variables 206, in particular valve positions 180, 182, 184 of the valves of the heating and / or cooling modules 154, 156, 168 of the industrial air supply installation 128, the rotation frequency 193 of the pump 152, in particular the wetting pump 153, and / or the rotation frequency 195 of the ventilator 162; internal variables 208, in particular the forward and / or return temperatures 210 in the heating and / or cooling modules 154, 156, 158 of the industrial air supply installation 128, and / or the air conditions during the conditioning module 150; - measured disturbance variables 210, in particular the external temperature 166 and / or the relative external humidity 168 in the blowing section of the industrial air supply installation 128; - unmeasured disability variables 212; and / or - Status variables 214, in particular the wet pump 153 (on / off); manual mode for the pumps 152, 153 (on / off); supply valves 181, 183, 185, ventilator 162 (on / off).

[0269] Next, examples of various operating conditions will be described that will clarify how the anticipation system 146 functions.

[0270] Drive state example 1; (No deviation)

[0271] 8 shows an example of a first operating state of the industrial air supply installation 128 without process deviations. The first operating state example therefore preferably represents a positive case.

[0272] The external temperature 166 and external humidity 168 are not constant. The preheat module 154 and the moistening module 160 are active.

[0273] The conditioning system of the industrial air supply 128 maintains the temperature 170 and relative air humidity 172 of the air conditioned using the industrial air supply 128 at constant values.

[0274] According to status variable 214 (ventilator 162 = on and valve and pump mode = "auto"), industrial air supply 128 is ready to run.

[0275] Based on the constant temperature 170 and relative air humidity 172 of the air conditioned using the industrial air supply system 128, the industrial air supply system 128 is preferably further production-ready.

[0276] Driving state example 2: (Decreasing relative humidity 168 above design parameters and increasing external temperature 166; impact of measured disturbance variable 210 on target variable 204)

[0277] FIG. 9 illustrates an example of a second operating state of the industrial air supply plant 128 when a sudden change in weather causes a decrease in relative external humidity 168 and an increase in external temperature.

[0278] The process value exhibits the following behavior: a) The external temperature 166 that rose after the sudden change in weather is outside the design parameters. b) The power output of the previously active preheat module 154 is reduced by closed loop control. c) Because the reduction in heating power is not sufficient, the closed loop control opens valve 183 of cooling module 156, thereby increasing the cooling power. d) The rotational frequency 193 of the wet pump 153 is increased by closed loop control to compensate for the decreasing external humidity 168. e) Insufficient cooling output due to too low a design of the cooling module 156 leads to deviations in the temperature 170 of the air conditioned by the industrial air supply plant 128.

[0279] Going outside the predetermined process window for temperature 170 is delayed based on the inertia of the industrial air supply plant 128 and the compensation of the closed loop control.

[0280] Driving state example 3: (Switching to winter drive with heat recovery; influence of unmeasured disturbance variables 212 on target variables 204)

[0281] FIG. 10 shows an example of a third operating state of the industrial air supply plant 128 when the heat recovery system 164 is turned on, which heats up the air flow 165 in cold weather conditions based on the waste heat.

[0282] Turning on the heat recovery system 164 is done by a manual valve, so the impact of heat recovery by the heat recovery system 164 is not measurable (unmeasured fault variable 212).

[0283] The process value exhibits the following behavior: a) The heating output of the heat recovery system 164 is increased and the value cannot be measured. b) Valve 181 of preheat module 154 closes based on the increase in heating power. c) Valve 183 opens in cooling module 156 to maintain temperature with additional cooling power. d) The rotation frequency 193 of the wetting pump 153 is adapted so that the air humidity 172 of the air conditioned by means of the industrial air supply plant 128 is maintained by closed loop control. e) Deviations in the temperature 170 of the air conditioned using the industrial air supply system 128 occur because the cooling module 156 cannot compensate for the heat supply quickly enough. The deviations are delayed based on the inertia of the industrial air supply system 128 and the compensation of the closed-loop control.

[0284] Driving state example 4: (Valve 181 of preheating module 154 malfunction)

[0285] FIG. 11 illustrates a fourth example operating state of the industrial air supply system 128 having a malfunction of the valve 181 of the preheat module 154 .

[0286] The process value exhibits the following behavior: a) Valve 181 of preheat module 154 closes based on an appliance error, thereby reducing heating output. b) To compensate for the missing heating power, the valve 185 of the additional heat module 158 opens. c) The heating output of the additional heat module 158 is insufficient, resulting in deviations in the temperature 170 of the air conditioned by the industrial air supply plant 128 .

[0287] Method A method for predicting process deviations in a technical installation 101, in particular in an industrial air supply installation, is explained below with reference to the operating states 1 to 4 described above.

[0288] Preferably, operating states 2 to 4 having process deviations during operation of the industrial air supply system 128 can be predicted using a method for predicting process deviations with a prediction horizon 216 of, for example, about 15 minutes.

[0289] As a database for training the predictive model, periods during which the industrial air supply plant 128 operates in a normal (>80%) ready operating state (see, for example, operating state 1) are considered.

[0290] The described data includes, for example, actuation states 2 to 4, preferably multiple times each, which may occur during the course of actuation, for example by closure of valves 181, 183, 185, or alternatively may be brought about intentionally.

[0291] These data are preferably then pre-processed and normalized, as can be seen for example in Figure 12, which shows for example the valve position 180 of the valve 181 of the pre-heating module 154 and the temperature 170 and relative air humidity 172 of the air conditioned using the industrial air supply plant 128.

[0292] The regularized data is divided into time windows 218 of, for example, 30 minutes each with a time shift of, for example, 5 minutes.

[0293] The regularized data within the time window 218 forms predictive data sets, particularly a predictive data set without a process deviation 220 and a predictive data set with a process deviation (see FIG. 7).

[0294] For a forecast data set 222 with process deviations, the status variable 214 is used to check whether the process technical installation 101 is ready to be activated (for example, the ventilator 162 is "on", the regulation module 150 is automatically activated). - If negative: The corresponding forecast data set with the process deviation is discarded and not used to train the forecast model. - In the positive case: the corresponding prediction data set with process deviations is considered for training the prediction module.

[0295] Based on a minimum time interval of, for example, one hour, only one forecast data set 222 with process deviations is selected in FIG.

[0296] The selection of the predicted data set 220 without process deviations is preferably performed similarly to the selection of the predicted data set 222 with process deviations.

[0297] In a minimum time interval, for example, one hour, only one forecast data set without process deviations is selected for training the forecast model.

[0298] Features are then preferably extracted from the predicted data set 220 without the selected process deviation and from the predicted data set 222 with the selected process deviation.

[0299] For example, statistical indices such as minimum, maximum, median, mean and / or standard deviation are used to extract the features. Furthermore, it may be advantageous to use linear regression coefficients to extract the features.

[0300] The predictive model is trained based on a predictive data set 220 without the selected process deviations and based on a predictive data set 222 with the selected process deviations, in particular using machine learning methods, for example gradient boosting.

[0301] Using the trained predictive model, process deviations from production-critical process values ​​within the industrial air supply system 128 are preferably predicted based on process values ​​that change during operation of the industrial air supply system 128.

[0302] The prediction model is explained using the example of driving states 2 to 4 in particular:

[0303] Driving state example 2:

[0304] The predictive model predicts process deviations after the appearance of a temperature rise, based on the course of measured disturbance variables 210, in particular the external temperature 166 and external humidity 168, the reaction of the conditioning module 150 and the temperature 170 at the outlet of the air conditioned by the industrial air supply system 128.

[0305] Driving state example 3:

[0306] The predictive model predicts the temperature increase 170 of the air conditioned using the industrial air supply 128 after the heat recovery system is turned on. The basis is the response of the conditioning module 150 and the temperature 170 evolution at the outlet of the air conditioned using the industrial air supply 128.

[0307] Driving state example 4:

[0308] The predictive model predicts the temperature rise of the temperature 170 of the air conditioned using the industrial air supply system 128 based on weather conditions and the valve position 180 of the valve 181 of the preheat module 156 .

[0309] A method for anomaly and / or error recognition in a method-technical installation 101 will now be described, preferably with reference to FIGS.

[0310] By means of the method for anomaly and / or error recognition, preferably error situations, in particular faults and / or malfunctions in components, sensors and / or actors, can be identified.

[0311] In that case, the pretreatment station 112 forms, for example, the process technical installation 101 .

[0312] The pre-treatment station 112 preferably includes a pre-treatment vessel 224 in which the workpiece 105, preferably a vehicle body 108, is pre-treated.

[0313] Pre-treatment station 112 preferably further includes a first pump 226 , a second pump 228 , a heat exchanger 230 , and a valve 232 .

[0314] The process value V62 points, S86, T95, T85, T15 and T05 are named according to their distinct designations within the method technical installation 101 numbering system.

[0315] The process values ​​T95, T85, T15 and T05 represent in particular the temperature inside the process technical installation 101, in particular inside the pre-treatment station 112.

[0316] The process value S86 is the valve position of the valve 232.

[0317] The process value V62 point is a volumetric flow rate.

[0318] Preferably, in order to implement the method for anomaly and / or error recognition, an anomaly and / or error model 233 is formed of the method technical installation 101, in particular of the pre-processing station 112, which contains information about the probability of occurrence of the process values ​​listed above (see Figure 15).

[0319] The formation of the anomaly and / or error model 233 is preferably performed as follows:

[0320] First, in particular within the framework of test signal generation 236, test signals are generated taking into account design data 234.

[0321] In particular, based on the design data 234, limits for the test signals are set, for example the maximum amplitude of the manipulated variable jump when setting a jump function.

[0322] Design data 234 may include, for example, one or more of the following information: - sensor type (temperature sensor, flow sensor, valve position, pressure sensor, etc.) and / or actor type (valve, ventilator, flap, E-motor); - the allowed value domain of the sensor and / or actor; -Sensor and / or actor signal type (float, integer).

[0323] The process technology installation 101, in particular the pre-processing station 112, is preferably dynamically stimulated with a test signal, as shown in Fig. 15 with reference number 238. In this case, it is conceivable that when stimulated by the test signal, anomalies and / or error situations are formed as desired.

[0324] When the method technical installation 101, in particular the pre-treatment station 112, is stimulated by a test signal, preferably a system input signal 240 and a system output signal 242 are formed.

[0325] These system input signals 240 and system output signals 242 are preferably stored in a test signal database 244 .

[0326] A structure identification 246 is then preferably carried out of the process technology installation 101, in particular of the pre-treatment station 112. A structure graph 247 of the process technology installation 101, in particular of the pre-treatment station 112, is then determined (see FIG. 16).

[0327] Structural identification 246, and in particular the determination of the structural graph, is preferably performed using machine learning methods, preferably using correlation, whereby non-linear relationships can be reproduced, for example using "mutual information".

[0328] Furthermore, it may be advantageous to utilize expert knowledge 248 for structure identification 246, ie, knowledge specifically about relationships within processes.

[0329] In that case, for example, edges between knots of the structure graph to be determined can be excluded by pre-configuring the structure graph using expert knowledge, information from known circuit diagrams and / or method diagrams 250. In that case, in particular, the computational effort for determining the structure graph can be reduced.

[0330] Furthermore, it may be advantageous if the structural graph is determined using a numbering system of the method technical installation 101, in particular of the pre-processing station 112, using respectively clear designations of the process values, i.e., using the semantics 252 of the designation of the process values.

[0331] In particular, it is conceivable that the structural graphs determined using machine learning methods are checked for validity using expert knowledge 248, using known circuit diagrams and / or method diagrams 250 and / or using designations (semantics 252) within the numbering system of the method technical equipment 101.

[0332] Preferably, the causal relationships 254 within the determined process structure, and in particular the "arrow directions" within the determined structure graph, are then determined.

[0333] The causal relationships 254 within the determined process structure are derived, for example, from the system input signals 240 and the system output signals 242 of the method technical equipment 101 determined when the method technical equipment 101 is stimulated by a test signal, for example using the respective time progressions of the system input signals 240 and the system output signals 242.

[0334] Alternatively or additionally, it is conceivable that the causal relationship 254 is derived using a causal inference method from the system input signals 240 and the system output signals 242 determined when the method technical equipment 101 is stimulated by a test signal.

[0335] To determine the causal relationships 254, preferably furthermore the expert knowledge 248, the method diagram 250 and / or the designation in the numbering system (semantics 252) of the method technical installation 101 are used.

[0336] Preferably, the causal relationships 254 determined within the determined process structure or within the determined structure graph can be used to find the process values ​​responsible for the identified anomaly.

[0337] After determining structure identification 246 and / or causality 254, structure parameter setting 256 is preferably performed.

[0338] The structure identification 246 can preferably be used to facilitate the structure parameter setting 256. The computational effort for the structure parameter setting 256 can preferably be reduced using the structure identification 246.

[0339] The structural parameter setting 256 is preferably performed using a method for determining probability density functions, in particular using a Gaussian mixture model.

[0340] The structural parameter setting 256 is performed using a Gaussian mixture model (see FIG. 18), for example, for the common probability density function f1 of the clique 258 shown in FIG. 17.

[0341] Preferably, expert knowledge 248 is utilized for the structural parameter settings 256 as well.

[0342] For example, known physical relationships between process values ​​and / or physical maps of functional components of the process technical installation 101, in particular of the pre-treatment station, are used for the construction parameter setting 256. For example, a map of the valve 232 is used.

[0343] Additionally, expert knowledge 248 regarding error conditions can be advantageously utilized in the configuration parameter settings 256 .

[0344] Using a known valve map of the valve 232, for example, the relationship between the valve position S86 and the volumetric flow V62 point can be described.

[0345] For the structural parameter setting 256 using a method for determining probability density functions, in particular using a Gaussian mixture model, data from the regular driving of the method technical equipment 101, in particular the pre-treatment station 112, and / or data from the test signal database 244, which are preferably stored in the driving database 260, are used.

[0346] The manipulated variables, measured variables and / or adjustment variables stored in the databases 244, 260 are used to determine the structural parameter settings 256 using a method for determining probability density functions.

[0347] For the structural parameter setting 256, preferably using a method for determining a probability density function, data from the ongoing operation of the method technical equipment 101, in particular the pre-treatment station 10, is used, which data is stored for a period of at least two weeks, preferably at least four weeks, for example at least eight weeks.

[0348] These data are preferably pre-processed before the structural parameter setting 256 .

[0349] When preprocessing, data of the process technical equipment 101 that does not correspond to the operating or production-ready operating state of the process technical equipment 101 (e.g. equipment switched off, maintenance phase, etc.) is preferably excluded, in particular using alarms and status bits that describe the state of the process technical equipment 10, in particular the preprocessing station 112.

[0350] Furthermore, it may be advantageous if the data of the methodological equipment 101 is pre-processed by filtering, for example with a low-pass filter and / or with a Butterworth filter.

[0351] Preferably, the data is further interpolated to a uniform time step width.

[0352] When forming the anomaly and / or error model 233, preferably within the framework of a limit value optimization 264, limit values ​​for the occurrence probability of the process values ​​are defined.

[0353] A threshold value for the probability of occurrence is preferably established such that an anomaly is recognized if the threshold value is not exceeded.

[0354] The determination of the limit value is preferably performed using a non-linear optimization method, for example using the Nelder-Mead method.

[0355] Alternatively or additionally, it is also conceivable that the determination of the limit values ​​is carried out using quantiles.

[0356] The limit value for the probability of occurrence of the process value can preferably be optimized, for example by setting a "false positive rate".

[0357] Furthermore, it is conceivable that limit values ​​are adapted after the initial formation of the anomaly and / or error model 233, especially if the number of error alarms is too high.

[0358] Anomaly and / or error recognition using the anomaly and / or error model 233 is performed as follows:

[0359] For example, a valve malfunction of valve 232 results in a deviation of the sensor values ​​from the normal state represented in each clique.

[0360] Anomalies detected in various cliques result when the probability of occurrence of sensor values ​​in a clique falls below a limit value that is evaluated and calculated in the operation of the method technical equipment 101, in particular in the operation of the pre-treatment station 112.

[0361] A valve failure of valve 232 will first result in an anomaly in clique 258 of valve position S86, which will then be reported by anomaly and / or error recognition system 148.

[0362] Over further time, the error propagation causes other anomalies that subsequently affect process critical variables, particularly the bath temperature T35 of bath 224.

[0363] Preferably, the report by the anomaly and / or error recognition system 148 includes one or more of the following information; - Time of anomaly detection; - The clique or cliques where the anomaly occurred, along with the sensors involved.

[0364] By early recognition of anomalies and reporting them to the user, deviations of a process-critical variable, namely the bath temperature T35 of bath 224, can preferably be prevented if timely intervention is performed.

[0365] The user can then define the error cause, i.e. the valve failure that caused the anomaly.

[0366] By specifying the error source, the clique 258 is expanded by one knot 266 and the probability density function of the abnormal data is integrated in the functional relationship (see FIG. 19).

[0367] After integrating the error causes, anomaly and / or error recognition is performed as before. In case of anomaly occurrence, the probability of the determined error cause is additionally output.

[0368] The user obtains one or more of the following information from the anomaly and / or error recognition system 148 report: - Time of anomaly detection; -The clique of anomaly occurrence and the sensors involved; -Probability of a given error cause

[0369] Particular embodiments are the following:

[0370] Embodiment 1: A method for error analysis in a technical installation (101), for example in a painting installation (102), comprising: - the method of automatically recognizing error situations in the technical equipment (101); - storing an error situation data set for each recognized error situation in an error database (136); - automatically determining an error cause for the error situation and / or automatically determining a process value associated with the error situation based on the error data set of each recognized error situation.

[0371] Example 2: In order to automatically determine the error cause for an error situation and / or to automatically determine a process value associated with the error situation, one or more process values ​​are determined based on the following combined criteria: -Pre-binding from reporting systems; - associating the process values ​​with the part of the process technical installation (101) in which the error situation occurs; - combining process values ​​with historical error conditions based on the user's active selection; - Active selection of process values ​​by the user; 2. The method of claim 1, wherein the error condition is combined with the error condition based on one or more of:

[0372] Embodiment 3: To automatically determine the error cause for an error situation and / or to automatically determine the process value associated with the error situation, the following priority criteria are used: -Process relevance of process values; - the location of the process value or the sensor for determining the process value inside the method-technical installation (101); - the magnitude of deviation of the process value from the defined process window and / or from the normal state; -Prioritization of historical process values ​​in historical error situations; - by adopting a prioritization of error causes and / or process values ​​from the reporting system (138); -Prioritization by user; 3. The method of embodiment 2, wherein an automatic prioritization of process values ​​associated with error conditions is performed based on one or more of:

[0373] Embodiment 4: In order to automatically determine an error cause for an error situation and / or to automatically determine a process value related to the error situation, further error causes and / or process values ​​are proposed, the proposal being based on the following proposal criteria: -Process relevance of process values; - the location of the process value or the sensor for determining the process value inside the method-technical installation (101); - the magnitude of deviation of the process value from the defined process window and / or normal state: -Prioritization of historical process values ​​in historical error situations; -Physical dependence of process values; 4. The method of any one of embodiments 1 to 3, wherein the method is automatically performed based on one or more of:

[0374] Embodiment 5: Historical error situations are identified from the error database (136) according to the following similarity criteria: -Error classification for historical error situations; -Historical error situations on the same or comparable pieces of equipment; - Process values ​​with historical error conditions that are equal to or similar to the process value with a known error condition; 5. The method of any one of embodiments 1 to 4, wherein the method is determined using one or more of:

[0375] Embodiment 6: historical process values ​​are determined from a process database (134), and the process values ​​are equal to or similar to process values ​​of known error conditions; 6. The method according to any one of embodiments 1 to 5, wherein

[0376] Embodiment 7: 7. The method according to embodiment 6, wherein the determined historical process values ​​are characterized as belonging to a historical error situation.

[0377] Embodiment 8: 8. The method according to any one of embodiments 1 to 7, wherein for a recognized error situation, an error information data set is stored in an error database (136).

[0378] Embodiment 9: Each error identification data set contains the following error condition data: -Error classification of error situations; - Process values ​​combined with error situations based on previous combinations from the reporting system; - information about the time of occurrence of each error situation; - information about the duration of the occurrence of each error situation; - Information about the location of each error situation; -alarm; -Status reports; 9. The method of embodiment 8, comprising one or more of:

[0379] Embodiment 10: 10. The method according to embodiment 8 or 9, wherein the error situation data set for each error situation comprises error identification data for unambiguously identifying the recognized error situation.

[0380] Embodiment 11: 11. The method according to any one of embodiments 8 to 10, wherein for each error situation, documentation data and error removal data are stored in the error situation data set.

[0381] Embodiment 12: 12. The method according to any one of embodiments 8 to 11, characterized in that process values ​​in the operation of the method technical installation (101) are stored synchronously in time with the recognized error situation.

[0382] Embodiment 13: 13. The method according to any one of embodiments 8 to 12, wherein the process values ​​are provided with time stamps, by means of which the process values ​​can be unambiguously associated with a point in time.

[0383] Embodiment 14: 14. An error analysis system (144) for analyzing errors in a process-technical installation (101), for example in a painting installation (102), the error analysis system being configured and arranged to perform a method for analyzing errors in a process-technical installation (101), for example in a painting installation (102), according to any one of embodiments 1 to 13.

[0384] Embodiment 15: 15. An industrial control system (100), wherein the control system comprises an error analysis system (144) according to embodiment 14.

[0385] Embodiment 16: 1. A method for predicting process deviations in a technical installation (101), for example in a painting installation (102), comprising: - Automatic generation of predictive models; - predicting process deviations in the operation of the process technology equipment (101) using said prediction model, A method comprising:

[0386] Embodiment 17: 17. The method according to embodiment 16, wherein the method for predicting process deviations is performed in an industrial air supply plant (128), in a pre-treatment station (112), in a cathodic dip coating station (114), and / or in a drying station (116, 120, 124).

[0387] Embodiment 18: 18. The method according to embodiment 16 or 17, characterized in that within the process technology plant (101) a predictive model is used to predict process deviations of production-critical process values ​​based on process values ​​that change during operation of the process technology plant (101).

[0388] Embodiment 19: 19. The method according to any one of embodiments 16 to 18, characterized in that, in order to automatically form a predictive model, process values ​​and / or status variables in the operation of the method technical installation (101) are stored for a predetermined period of time.

[0389] Embodiment 20: The method is characterized in that the process values ​​and / or status variables are stored during the operation of the technical installation (101) for a predetermined period of time, and the storage period is determined based on the following criteria: - the process technology installation (101) is in a ready-to-run state for a predetermined period of time, at least approximately 60%, preferably at least approximately 80%, in particular for production runs; - the process technology installation (101) is in a production-ready state for at least about 60%, preferably at least about 80%, for a predetermined period of time; - the method technical installation (101) is driven for a predetermined period of time, in particular with all possible drive strategies; - a predetermined number of process deviations and / or failures within a predetermined period of time; 20. The method of embodiment 19, wherein the method is configured according to one or more of:

[0390] Embodiment 21: 21. The method according to embodiment 19 or 20, wherein to form the predictive model, a machine learning method is implemented, and process values ​​and / or status variables stored over a predetermined period of time are used to form the predictive model.

[0391] Embodiment 22: 22. The method of embodiment 21, wherein the machine learning method is performed based on features, the features being extracted from process values ​​and / or status variables stored over a predetermined period of time.

[0392] Embodiment 23: To extract features: -Statistical indices; - Coefficients based on main component analysis; -linear regression coefficients; - Dominant frequencies and / or amplitudes based on the Fourier spectrum; 23. The method of embodiment 22, wherein one or more of the following are used:

[0393] Embodiment 24: 24. The method according to any one of embodiments 16 to 23, wherein a selected number of prediction data sets (222) with process deviations and a selected number of prediction data sets (220) without process deviations are used to train the predictive model.

[0394] Embodiment 25: The selection of the number of prediction data sets with process deviations is based on the following criteria: - minimum time interval between two forecast data sets with process deviations; -Automatic selection using defined rules; -User selection; 25. The method of embodiment 24, wherein the method is performed based on one or more of:

[0395] Embodiment 26: 26. The method of embodiment 24 or 25, wherein the predictive data set having the process deviation is characterized as such if the process deviation occurs during a predetermined time interval.

[0396] Embodiment 27: 27. The method of embodiment 26, wherein the process values ​​and / or status variables stored over a predetermined period of time are compiled into a process data set by pre-processing.

[0397] Embodiment 28: Preprocessing is: - Regularizing the stored process values ​​over a predetermined period of time; -combining the process values ​​and / or status variables into a forecast data set by dividing the process values ​​and / or status variables into time windows with a time shift. 28. The method of embodiment 27.

[0398] Embodiment 29: A forecasting system (146) for forecasting process deviations in a process technology facility, the forecasting system being configured and arranged to implement a method for forecasting process deviations in a process technology facility (101), for example in a painting facility (102), according to any one of embodiments 16 to 29.

[0399] Embodiment 30: 30. An industrial control system (100) comprising a forecasting system (146) according to embodiment 29.

[0400] Embodiment 31: 1. A method for detecting anomalies and / or errors in a technical installation (101), for example in a painting installation (102), said method comprising: - automatically forming an anomaly and / or error model (233) of the process technical installation (101) containing information about the probability of occurrence of process values; - Automatically reading the process values ​​of the technical equipment (101) during its operation; - automatically recognizing anomalies and / or error situations by determining the probability of occurrence using an anomaly and / or error model (233) based on the process values ​​of the loaded method-technical installation (101) and by checking the probability of occurrence against limit values. method.

[0401] Embodiment 32: the anomaly and / or error model (233) comprises structure data, said structure data comprising information about the process structure in the process technical installation (101), and / or the anomaly and / or error model (233) comprises parameter setting data, the parameter setting data comprising information about the relationships between process values ​​of the process technical installation (101), 32. The method of embodiment 31,

[0402] Embodiment 33: To form the anomaly and / or error model (233), the following steps are performed: - method for identifying the structure (246) of a process of technical installation (101) for determining the process structure; - determining causal relationships (254) within a determined process structure of a technical installation (101): - setting (256) structural parameters of the desired process structure of the process-technical equipment (101); 33. The method of embodiment 31 or 32, wherein one or more of the following are performed:

[0403] Embodiment 34: 34. The method according to embodiment 33, characterized in that when performing structure identification (246) to determine the process structure of the process technical equipment (101), a structure graph is determined, said structure graph representing in particular the relationships within the process technical equipment (101).

[0404] Embodiment 35: Obtaining a structure graph involves: -Mechanistic learning methods; -Expert Knowledge (248); - known circuit diagrams and / or method diagrams (250); -designation within the numbering system of method-technical equipment (101); 35. The method of embodiment 34, wherein the method is performed using one or more of:

[0405] Embodiment 36: 36. The method according to embodiments 33 to 35, characterized in that the method technical equipment (101) is stimulated by a test signal for structure identification, in particular for determining a structure graph.

[0406] Embodiment 37: To determine the causal relationships (254) within the determined process structure of a technical installation (101), the following steps are carried out: - system input signals (240) and system output signals (242) generated when stimulating the method technical equipment (101) with test signals; -Expert Knowledge (248); - known circuit diagrams and / or method diagrams (252); -designation within the numbering system of method-technical equipment (101); 37. The method of any one of embodiments 33 to 36, wherein the method is carried out using one or more of:

[0407] Embodiment 38: To set the structural parameters (246) of the desired process structure of the process technical equipment (101), the following are performed: -Methods for determining probability density functions, especially Gaussian mixture models; -Known physical relationships between process values; - physical maps of functional components of the method-technical installation (101), for example maps of valves (232); 38. The method according to any one of embodiments 33 to 37, wherein one or more of the following are used:

[0408] Embodiment 39: 39. The method according to embodiment 38, characterized in that data from regular operation of the method technical equipment (101) and / or data obtained by stimulating the method technical equipment (101) with test signals are used for the structural parameter setting (246) using a method for determining probability density functions, in particular using a Gaussian mixture model.

[0409] Embodiment 40: 40. The method of embodiment 39, wherein the data used for the structural parameter setting (246) is preprocessed before the structural parameter setting (246) using a method for determining a probability density function, in particular using a Gaussian mixture model.

[0410] Embodiment 41: 41. The method according to any one of embodiments 31 to 40, wherein when forming the anomaly and / or error model (233), a limit value for the probability of occurrence of the process value is defined, below which an anomaly is recognized.

[0411] Embodiment 42: 42. The method according to any one of embodiments 31 to 41, wherein a method for anomaly and / or error recognition is used to identify an error cause of a recognized anomaly and / or a recognized error situation.

[0412] Embodiment 43: The process technical installation (101) comprises the following processing stations (104) of a painting installation: - pre-treatment station (112); - a station for cathodic immersion coating (114); - Drying stations (116, 120, 124); -Industrial air supply equipment(128) -Painting robots, comprising or formed by one or more of: 43. The method of any one of embodiments 31 to 42.

[0413] Embodiment 44: An anomaly and / or error recognition system (148) for recognizing anomalies and / or errors, said system being configured and arranged to implement the method for recognizing anomalies and / or errors according to any one of embodiments 31 to 43 in a process-technical installation (101), for example in a painting installation (102).

[0414] Embodiment 45: 45. An industrial control system (100) comprising an anomaly and / or error recognition system (148) according to embodiment 44.

[0415] Embodiment 46: An industrial control system comprising an error analysis system as described in embodiment 14, a prediction system for predicting process deviations in a technical installation as described in embodiment 29, and / or an anomaly and / or error recognition system as described in embodiment 44.

Claims

1. 1. A method for predicting process deviations in a process-technical installation (101), for example in a painting installation (102), said method comprising: - Automatic generation of predictive models; - predicting process deviations in the operation of the process technology installation (101) using said predictive model, A method comprising:

2. 2. The method of claim 1, wherein the method for predicting process deviations is performed in an industrial air supply system (128), in a pre-treatment station (112), in a cathodic dip coating station (114), and / or in a drying station (116, 120, 124).

3. 3. The method according to claim 1, wherein a prediction model is used in the process technology plant (101) to predict process deviations of production-critical process values ​​on the basis of process values ​​that change during operation of the process technology plant (101).

4. 4. The method according to claim 1, wherein process values ​​and / or status variables in the operation of the process technology installation (101) are stored for a predetermined period of time in order to automatically generate a predictive model.

5. The predetermined period during which the process values ​​and / or status variables are stored during the operation of the method technology installation (101) is determined based on the following criteria: - the process technology installation (101) is in a ready-to-run state for a predetermined period of time, at least approximately 60%, preferably at least approximately 80%, in particular for production runs; - the process technical equipment (101) is in a production-ready state for a predetermined period of time, at least about 60%, preferably at least about 80%; - the method technical installation (101) is driven for a predetermined period of time, in particular with all possible drive strategies; - a predetermined number of process deviations and / or fault cases within a predetermined period of time; 5. The method of claim 4, wherein the parameter is set according to one or more of:

6. 6. The method according to claim 4, wherein a machine learning method is implemented to form the predictive model, and stored process values ​​and / or status variables over a predetermined period of time are used to form the predictive model.

7. 7. The method of claim 6, wherein the machine learning method is performed on the basis of features, the features being extracted from process values ​​and / or status variables stored over a predetermined period of time.

8. To extract features: - statistical indices; - coefficients based on main component analysis; - linear regression coefficients; - dominant frequencies and / or amplitudes based on the Fourier spectrum; 8. The method of claim 7, wherein one or more of the following are used:

9. 9. The method according to claim 1, wherein a selected number of prediction data sets (222) with process deviations and a selected number of prediction data sets (220) without process deviations are used to train the predictive model.

10. The selection of the number of prediction data sets with process deviations is based on the following criteria: - the minimum time interval between two forecast data sets with process deviations; - automatic selection using defined rules; - User selection; 10. The method of claim 9, wherein the method is based on one or more of:

11. 11. The method of claim 9 or 10, wherein the predictive data set with the process deviation is characterized as such if the process deviation occurs during a predetermined time interval.

12. 12. The method of claim 11, wherein the process values ​​and / or status variables stored over a predetermined period of time are compiled into a process data set by pre-processing.

13. Pre-processing is as follows: - regularizing the stored process values ​​over a predetermined period of time; - Combining process values ​​and / or status variables into a forecast data set by dividing the process values ​​and / or status variables into time windows with a time shift.

13. The method of claim 12.

14. 1. A forecasting system (146) for forecasting process deviations in a process technology installation, the forecasting system being configured and arranged to implement a method for forecasting process deviations in a process technology installation (101), for example in a painting installation (102), according to any one of claims 1 to 13.

15. An industrial control system (100) comprising the prognostic system (146) of claim 14.

Images