Diagnosis Method and Diagnosis System for a Processing Engineering Plant and Training Method

Abstract

A diagnosis method, a diagnosis system, a process-engineering plant and a training method for the diagnosis system, wherein course over time of plant data, which at least partially characterizes the plant status, is provided and a plant status is classified with the aid of a plurality of models based on the course over time of the plant data, where each model of the plurality of models differs with respect to a time window from which the plant data are based, a confidence is allocated to each classification that result from the at least two models, and where diagnosis information based on the classifications of the plant status and the confidences allocated thereto is output.

Claims

1. A diagnosis method for a process-engineering plant, the method comprising: providing a course over time of plant data, which at least partially characterizes a status of the process-engineering plant; classifying the status of the process-engineering plant aided by a plurality of models based on the course over time of the plant data, the plurality of models differing with respect to a time window, from which the plant data are based; allocating in each case one confidence to the classifications which result from the at plurality of models; and outputting diagnosis information which is based on the classifications the status of the process-engineering plant and a confidence allocated thereto.

2. The diagnosis method as claimed in claim 1, wherein time windows differ with respect to their length of time.

3. The diagnosis method as claimed in claim 2, wherein each respective length of time of the time windows is logarithmically distributed with respect to each other.

4. The diagnosis method as claimed in claim 1, wherein time windows differ with respect to metrics.

5. The diagnosis method as claimed in claim 1, wherein at least one time window has logarithmic metrics.

6. The diagnosis method as claimed in claim 1, wherein the plant data is temporally, logarithmically spaced-apart as the course over time.

7. The diagnosis method as claimed in claim 1, wherein an input signal relating to the status of the process-engineering plant is detected and forms a basis for an adjustment of the confidences.

8. The diagnosis method as claimed in claim 1, wherein an input signal relating to the plant status is detected and forms a basis for an adjustment of at least one model of the plurality of models.

9. The diagnosis method as claimed in claim 1, wherein a status analysis of the status of the process-engineering plant is performed based on at least one classification.

10. The diagnosis method as claimed in claim 1, wherein the diagnosis information comprises an overall classification of the plant status; and wherein the overall classification is determined on the basis of the classifications, which result from the at least two models, and the confidences allocated thereto.

11. The diagnosis method as claimed in claim 10, wherein the overall classification is determined as a function of a sequence of classifications.

12. A diagnosis system for a process-engineering plant, comprising: a processor; memory; and a storage device having a plurality of models, and confidences to be allocated to classifications stored therein; wherein the processor is configured to: provide a course over time of plant data, which at least partially characterizes a status of the process-engineering plant; classify the status of the process-engineering plant aided by the plurality of models based on the course over time of the plant data, the plurality of models differing with respect to a time window, from which the plant data are based; allocate, in each case, one confidence to the classifications which result from the at plurality of models; and output diagnosis information which is based on the classifications the status of the process-engineering plant and a confidence allocated thereto.

13. A training method for a diagnosis system comprising a processor, memory, and a storage device having a plurality of models, and confidences to be allocated to classifications stored therein, the processor being configured to provide a course over time of plant data which at least partially characterizes a status of a process-engineering plant, classify the status of the process-engineering plant aided by the plurality of models based on the course over time of the plant data, the plurality of models differing with respect to a time window, from which the plant data are based, allocate, in each case, one confidence to the classifications which result from the at plurality of models, and output diagnosis information which is based on the classifications the status of the process-engineering plant and a confidence allocated thereto, the method comprising: determining the plurality of models via machine learning; wherein the plant data of a first quantity of a plurality of courses over time from at least two different time windows and information with respect to a plurality of process-engineering plant statuses corresponding to the plurality of courses over time form a basis for the machine learning.

14. The training method as claimed in claim 13, wherein the confidences are determined based on a statistical evaluation of the classifications which result in accordance with the plurality of models for plant data from a second quantity of a plurality of courses over time.

15. The training method as claimed in claim 13, wherein a selection of the models is additionally stored in the storage device based on the classifications which result from the plurality of models for plant data from a second quantity of a plurality of courses over time.

16. The training method as claimed in claim 14, wherein a selection of the models is additionally stored in the storage device based on the classifications which result from the plurality of models for plant data from a second quantity of a plurality of courses over time.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The above-described properties, features and advantages of this invention and the manner in which these are achieved will now become clearer and more intelligible in conjunction with the following description of the exemplary embodiment, which will be explained in detail making reference to the drawings, in which:

[0037] FIG. 1 shows an exemplary graphical plot of a course over time of plant data, which is divided into time windows in accordance with the invention;

[0038] FIG. 2 shows an exemplary flow chart of a diagnosis method in accordance with the invention;

[0039] FIG. 3 shows an exemplary schematic block diagram of a diagnosis system in accordance with the invention; and

[0040] FIG. 4 shows an exemplary diagram illustrating a training method in accordance with the invention.

DETAILED DESCRIPTION OF THE EXEMPLARY EMBODIMENTS

[0041] FIG. 1 shows an exemplary graphical plot of a course over time V of plant data D, which is divided into time windows T.sub.1, T.sub.2, T.sub.3 of different length. The plant data D preferably corresponds at least to one measured and/or manipulated variable of a process-engineering plant, which is plotted over time. The plant data D characterizes a status of the plant, such as normal operation or one of possibly several malfunctions. The course over time V of the plant data D can be characteristic of the plant status in which the plant is, for example, at instant t. In particular, the course V can characterize a dynamic, on the basis of which the plant changes from one plant status to another one or else remains in the same status.

[0042] The course over time V of the plant data D can be used accordingly to implement a classification of the plant status with the aid of models. Preferably, in each case one of the time windows T.sub.1, T.sub.2, T.sub.3 is allocated to the models, i.e., the plant data D within the respectively allocated time window T.sub.1, T.sub.2, T.sub.3 is processed by the models. The time windows T.sub.1, T.sub.2, T.sub.3 differ in the illustrated example with respect to their length of time. The first time window T.sub.1 has, for example, a length 1, the second time window T.sub.2 a length 2 and the third time window T.sub.3 a length 3. Consequently, the models can possibly be sensitive to different dynamics in the course of time V. As an alternative or in addition, the time windows T.sub.1, T.sub.2, T.sub.3 can also differ with respect to their metrics, however.

[0043] In continuous operation of the plant, the time windows T.sub.1, T.sub.2, T.sub.3 are preferably selected such that they all reach up to an end instant E. The end instant E corresponds in this connection preferably with the present t, in other words, lie at the end instant E, in particular currently up-to-date plant data D.

[0044] If the plant continues to operate, the end instant E corresponding with the present shifts further accordingly as do the time windows T.sub.1, T.sub.2, T.sub.3 as well, therefore. At the instant t+1 the shifted time windows T.sub.1, T.sub.2, T.sub.3 extend up to the shifted end instant E, therefore. Consequently, it is possible to ensure that the diagnosis of the plant, in particular the classification of the current plant status, is always based on current plant data D.

[0045] FIG. 2 shows an exemplary flowchart of the diagnosis method 1 for a process-engineering plant in accordance with the invention. In a method step S1, a course over time of plant data, which at least partially characterizes the plant status, is provided (see FIG. 1). In a further method step S2a, the plant data of the plant status is classified with the aid of at least two models based on the course over time. The models are preferably applied to time series, which are defined by differing time windows and in each case contain an extract of the provided course over time of the plant data. In a further method step S2b, the classifications obtained from the at least two models can each be allocated a confidence, which indicates, for example, the probability with which the corresponding model has correctly classified the plant status.

[0046] Preferably, the models classify the plant status in method step S2a in a specified sequence, such that a sequence of classifications results. Based on the resulting sequence, an overall classification can then be determined in a further method step S3, and this classifies the current plant status correctly with particularly high probability. In particular, a(n) (overall)confidence can be allocated to the overall classification or the resulting sequence which, for example, can be a measure of the probability that the plant status is correctly classified by the overall classification. The overall classification and/or the confidence allocated to it can be determined, for example, in training runs and/or on repeated execution of the diagnosis method 1 by way of a statistical evaluation of all sequences obtained during training runs and/or on repeated execution of the diagnosis method 1 (see FIG. 4).

[0047] Using the overall classification determined in method step S3 an evaluation can then be made to determine whether normal operation is present, in other words, the plant is running substantially fault-free.

[0048] If normal operation is present, in other words, then the plant is running substantially fault-free, in a further method step S7, corresponding diagnosis information can be output. Here, the diagnosis information preferably contains the overall classification as well as the confidence allocated to it. The diagnosis information can be output, for example, to a plant user or to a control system of the plant, which can continue to control the plant on the basis of this information.

[0049] If, on the other hand, a malfunction is present, i.e., the plant is running defectively or the plant status deviates from normal operation, then in a further method step S4 as check can be performed to determine whether the malfunction can be assessed by the plant user or a further monitoring system. For example, it can be checked whether a cause of the malfunction can be identified and/or which measures should be taken to avert the malfunction or transfer the plant back to normal operation again.

[0050] If this is not the case, then an extensive fault analysis can be peformed in a further method step S5, for example, to characterize the malfunction more accurately.

[0051] In a further method step S6, it is preferably checked whether the malfunction is already known. In particular, the check can be performed to determine whether the malfunction has already occurred. This can be performed in particular independently of the assessment of the malfunction in method step S4 and/or of the extensive fault analysis in method step S5.

[0052] In method step S7, corresponding diagnosis information is then preferably output. In the case of a malfunction, in addition to the overall classification and the confidence allocated to it the diagnosis information can also contain the information determined in method steps S4, S5 and/or S6.

[0053] In particular it is possible that a distinction is made between three cases based on the diagnosis information output in method step S7: (i) normal operation is present, (ii) a known malfunction is present and (iii) an unknown operation is present.

[0054] In a further method step S8, a data set, which is stored, for example, in a storage device of a control system, can be updated in particular based on the sequence of classifications determined in method step S2a. The data set can contain, for example, counter readings that indicate the frequency of the sequences that have occurred. Accordingly, preferably the counter reading, of the sequence determined in method step S2a, is increased. Preferably, the actual plant status determined, for example, by the plant user or the further monitoring system, i.e., the correct classification, is noted in the data set. The data set updated in this way can be used, as described in more detail in connection with FIG. 4, to increase the reliability of the allocation of overall classification to the sequence and the corresponding confidence, for example, by statistically evaluating the content of the data set.

[0055] In a further method step S9, an assessment can be made to determine whether the classification that has occurred via the models in method step S2a and the confidence allocation made in method step S2b is satisfactory. For example, a check can be performed to determine which models were incorrectly classified and/or whether a high confidence value was allocated to such incorrect classifications. If this is the case, an adjustment of the models or the confidences can be made in a further method step S10.

[0056] FIG. 3 shows an exemplary diagnosis system 50 for a process-engineering plant 10, where the diagnosis system 50 is configured to perform a diagnosis method, as described, for example, in connection with FIG. 2. The process-engineering plant 10 has a control system 11 and plant components 12, where the control system 11 and the plant components 12 are connected, for example, over a network. The plant components 12 can be formed, for example, as actuators and/or sensors to control or monitor a process of the plant 10.

[0057] The diagnosis system 50 preferably has a first module 51, a second module 52, a third module 53 and a fourth module 54 and a storage device 55. The first module 51 is preferably configured to provide a course over time of plant data, which at least partially characterizes the status of the plant. For this purpose, the first module 51 can be adapted in particular to access, during operation of the plant 10, measured variables provided by the plant components 12 and/or manipulated variables provided by the control system 11.

[0058] The second module 52 is preferably configured to classify the plant status with the aid of at least two models based on the provided course over time of the plant data. For this, the second module 52 can access, for example, the storage device 55 in which the at least two models are preferably stored. The models differ preferably with respect to a time window from which the plant data of the course over time forms the basis of the models. In other words, the models are adapted to process different time series of the plant data from the provided course over time.

[0059] The third module 53 is preferably configured to allocate one confidence respectively to the classifications resulting from the at least two models. The confidences can disclose, for example, a probability with which the classification determined by the second module 52 applies. The confidences can likewise be stored in the storage device 55.

[0060] The fourth module 54 is preferably configured to disclose diagnosis information based on the classifications of the plant status and the confidences allocated to them. The fourth module 54 can be formed for this purpose, for example, as an interface by which the diagnosis information can be output, for instance, to a plant user.

[0061] The first, second and third modules 51, 52, 53 can be formed in terms of hardware and/or software engineering. In particular, the first, second and third modules 51, 52, 53 can have a processing unit, preferably data- or signal-connected to a storage and/or bus system, in particular a digital processing unit, in particular microprocessor unit (CPU), or a module of such and/or one or more program(s) or program module(s). The CPU can be configured to execute commands, which are implemented as a program stored in a storage system, to detect input signals from a data bus and/or emit output signals to a data bus. A storage system can have one or more, in particular different, storage media, in particular optical, magnetic, solid state and/or other non-volatile media. The program can be of such a nature that it embodies or is capable of implementing the disclosed embodiments of the method in accordance with the invention, such that the CPU can execute the steps of such methods.

[0062] It is also conceivable that the plant data provided by the first module 51 is also stored in the storage device 55 in addition to the at least two models and the confidence. The first module 51 can be configured, in particular, to write the provided plant data substantially continuously, i.e., substantially in real time during operation of the plant 10, into a memory of the storage device 55. Consequently, the diagnosis system 50 can likewise perform the diagnosis method in real time.

[0063] FIG. 4 shows an exemplary training method 100 for a diagnosis system, as is shown, for example, in connection with FIG. 3. In a method step V1, at least two models are determined based on a first quantity of a plurality of courses over time of plant data by machine learning. The plant data of an individual course over time preferably at least partially characterizes the status of a process-engineering plant. Machine learning is based, moreover, on information with respect to plant statuses that correspond with precisely those plurality of courses over time. In other words, for the purpose of learning, information is provided about which plant status is actually characterized by the plant data of an individual course over time from the first quantity or which is the correct or true classification of the plant status.

[0064] Each individual course over time from the first quantity is preferably divided into at least two time segments, which correspond to different time windows, where it is possible for the time windows to also overlap. Each of the at least two time windows thereby define a time series. Based on a plurality of such time series from different courses over time, each defined by the same time window, and the information with respect to the corresponding plant statuses, one of the models respectively is then learned, such as by determining a pattern in these time series.

[0065] Preferably, the at least two learned models are applied in a further method step V2 to plant data from a second quantity of courses over time. The classifications can be performed with the aid of the models in a specified sequence. Different sequences of classifications can result in the process. The number of sequences that occur can be stored in a storage device, for instance in the form of a data set.

[0066] In a first sub-step V2a, for example the plant data from a first time window within the courses over time from the second quantity forms the basis of a first model. FIG. 4 illustrates, by way of example, a quantity G.sub.v for three possible classifications. The index v can assume, for example, the values 0, 1 or 2, with the quantity G.sub.0 indicating, for instance, the number of classifications as normal operation N, the quantity G.sub.1 the number of classifications as a first malfunction F1 and the quantity G.sub.2 the number of classifications as a second malfunction F2.

[0067] In a second sub-step V2b, the plant data from a second time window within the courses over time from the second quantity can then form the basis of a second model. In the present example, it is assumed that the second model can again classify normal operation N, the first malfunction F1 or the second malfunction F2. By considering the classifications of the first model, quantities G.sub.vw result for nine possible sequences, where the indices vw can again assume the values 0, 1 or 2, respectively. The quantity Goo therefore indicates, for example, the number of classifications as normal operation by two models, while the quantity G.sub.12 indicates the number of classifications as the first malfunction F1 by the first model and as the second malfunction F2 by the second model.

[0068] In a further sub-step V2c, the sequences are also supplemented by information with respect to the plant status corresponding with the respective courses over time. The quantity G.sub.002 represents, for example, the number of cases in which the first and second models have each classified normal operation N, while the underlying plant data from the course over time actually corresponds with the second malfunction F2.

[0069] Here, an additional quantity G.sub.003 is also stated, which represents the case of unknown time series. If the considered time series corresponds with an unknown plant status, then it is added to the quantity G.sub.003. What is not illustrated is the case where the models can also classify a time series as unknown. However, it is conceivable here to also allow further values for the indices vwx, such that, for example, a quantity G.sub.303 can be formed.

[0070] In a further method step V3, the quantities G.sub.vwx obtained in sub-step V2c are statistically evaluated to obtain a confidence for the different possible classifications by the at least two models.

[0071] For example, all quantities G.sub.vwx in which the classification by the first model applies are added together and divided by the total of all courses over time from the first quantity. If, overall, for example, the sequence 000 is counted one hundred times, the sequence 011 twelve times and the sequence 001 three times, then this results in a probability of 100/115 that the classification by the first model applies.

[0072] The confidences for classifications by the second and optionally further models can also represent conditional confidences in which the classification that has already occurred or preceding classification is considered by at least one different model. If the first model classifies the plant status as normal operation N, for example, when determining the confidence for the classification by the second model, all quantities G.sub.vwx, in which the classifications by the first and second models apply, can be added together and be divided by the total of all cases in which the classification by the first model applies.

[0073] Thus, while there have been shown, described and pointed out fundamental novel features of the invention as applied to a preferred embodiment thereof, it will be understood that various omissions and substitutions and changes in the form and details of the methods described and the devices illustrated, and in their operation, may be made by those skilled in the art without departing from the spirit of the invention. For example, it is expressly intended that all combinations of those elements and/or method steps which perform substantially the same function in substantially the same way to achieve the same results are within the scope of the invention. Moreover, it should be recognized that structures and/or elements and/or method steps shown and/or described in connection with any disclosed form or embodiment of the invention may be incorporated in any other disclosed or described or suggested form or embodiment as a general matter of design choice. It is the intention, therefore, to be limited only as indicated by the scope of the claims appended hereto.