KR102484916B1 - User setting-based plant predictive maintenance device and method - Google Patents

Abstract

The present invention relates to an apparatus for preforming predictive maintenance of a plant based on user settings. The apparatus for performing predictive maintenance of a plant based on user settings according to the present invention comprises: a collection unit collecting a plurality of facility data for a plant from a plurality of facility sensors; a preprocessing unit performing preprocessing on the multiple facility data based on an external preprocessing file imported according to user settings; a learning unit training an internal artificial intelligence model by inputting the plurality of facility data preprocessed in the preprocessing unit; a management unit managing model data for the internal artificial intelligence model trained in the learning unit or the external artificial intelligence model imported according to user settings; and an operation unit calculating predictive data for maintenance of the plant by using at least one of the artificial intelligence models stored in the management unit and at least one of the plurality of facility data collected by the collection unit.

Description

User setting-based plant predictive maintenance device and method {User setting-based plant predictive maintenance device and method}

The present disclosure relates to an apparatus and method for predictive maintenance of a plant based on user settings. More specifically, the present disclosure relates to a plant predictive maintenance apparatus and method applicable to plant predictive maintenance by importing a preprocessing process (or preprocessing module) and an artificial intelligence model based on user settings.

In plant equipment, predictive maintenance is essential to preserve productivity by foreseeing and taking measures against various risks according to the state of the equipment in advance.

In general, the method of servicing facilities determines whether the conditions for facility maintenance are satisfied by using TBM (Time Based Maintenance) method, which maintains facilities after a certain period of time, and facility condition inspection data, measurement data, and diagnostic data. Therefore, there is a CBM (Condition Based Maintenance) method in which equipment is maintained according to the judgment result.

At this time, in the case of predictive maintenance that utilizes a monitoring system to track raw data such as temperature, displacement, current, and acceleration of the facility in real time, It can be said to be a CBM method that detects abnormalities and takes maintenance measures only in situations where maintenance is required.

On the other hand, when artificial intelligence is applied to the predictive maintenance system, the artificial intelligence model or preprocessing model used has a dependent relationship with the predictive maintenance system, making it impossible to select an artificial intelligence model or preprocessing model according to plant or user preferences. There is an inconvenience that only the use of a designated artificial intelligence model is possible.

The background technology of the present application is disclosed in Korean Patent Registration No. 10-1282244.

The present invention is to solve the above-mentioned problems of the prior art, and a user setting-based plant predictive maintenance device that can learn an artificial intelligence model using a plurality of facility data collected from a plant and perform predictive maintenance for the plant at the same time and to provide a method.

The present application is to solve the above-mentioned problems of the prior art, and to provide a user setting-based plant predictive maintenance device and method that can be selectively applied according to the plant or user preference by importing an external preprocessing file and an external artificial intelligence model. The purpose.

However, the technical problem to be achieved by the embodiments of the present application is not limited to the technical problems described above, and other technical problems may exist.

As a technical means for achieving the above technical problem, a user setting-based plant predictive maintenance device according to an embodiment of the present invention includes a collection unit that collects a plurality of facility data for a plant from a plurality of facility sensors, according to user settings. A pre-processing unit that performs pre-processing on the plurality of facility data based on an imported external pre-processing file, a learning unit that learns an internal artificial intelligence model by inputting the plurality of facility data pre-processed by the pre-processing unit, A management unit that manages model data for the internal AI model learned in the learning unit or an external AI model imported according to user settings, and at least one of the artificial intelligence models stored in the management unit and a plurality of collected data from the collection unit. It may include an operation unit that calculates prediction data for the maintenance of the plant using at least one of the facility data of the plant.

According to an embodiment of the present application, a storage unit for periodically storing the plurality of facility data collected by the collection unit in real time or according to a predetermined period is further included, and the pre-processing unit includes a plurality of data stored in the storage unit. It may be to perform pre-processing by loading at least some of the facility data.

According to an embodiment of the present application, the pre-processing unit performs pre-processing on the plurality of facility data using the external pre-processing file or pre-processes the plurality of facility data using an internal pre-processing function provided in the device. may be performing

According to an embodiment of the present application, the management unit may import an external artificial intelligence model existing outside the device in the form of a file, standardize it into a usable form, and upload it.

According to an embodiment of the present application, the management unit, the model name, used algorithm, characteristics, verification method, hyper parameter value, applied preprocessing method and internal / external artificial intelligence model for the internal artificial intelligence model or the external artificial intelligence model It may be to store and provide the model data for at least one of external models.

According to an embodiment of the present disclosure, the prediction data may include at least one of abnormal detection of the plant, equipment failure life prediction, failure probability prediction, and maintenance time prediction.

According to an embodiment of the present application, the operation unit inputs at least one of a plurality of facility data stored in the storage unit to at least one artificial intelligence model among the artificial intelligence models stored in the management unit, and the predicted data It may be so that is calculated.

According to an embodiment of the present application, a visualization unit for visualizing the predicted data calculated by the operation unit to be monitored may be further included.

As a technical means for achieving the above technical problem, a user setting-based plant predictive maintenance method includes a step of collecting a plurality of equipment data for a plant from a plurality of equipment sensors, an external preprocessing file imported according to user settings Based on the above, the step of performing pre-processing on the plurality of facility data, the step of learning the internal artificial intelligence model with the plurality of facility data pre-processed in the step of performing the pre-processing as an input, the step of learning the At least one of the artificial intelligence models stored and managed in the step of managing model data for an internal artificial intelligence model or an external artificial intelligence model imported according to user settings, and in the step of managing the model data, and the plurality of facility data It may include calculating predicted data for maintenance of the plant using at least one of a plurality of facility data collected in the collecting step.

According to one embodiment of the present application, the step of periodically storing the plurality of facility data collected in the step of collecting the plurality of facility data in real time or according to a predetermined period is further included, and the performing of the preprocessing , It may be to perform preprocessing by loading at least some of the plurality of equipment data stored in the storing step.

According to an embodiment of the present application, the performing of the preprocessing may include performing preprocessing on the plurality of facility data using the external preprocessing file or using an internal preprocessing function provided in the device to perform the preprocessing of the plurality of facilities. It may be to perform pre-processing on the data.

According to an embodiment of the present application, the step of managing the model data may include importing an external artificial intelligence model existing outside the device in the form of a file, standardizing it into a usable form, and uploading it.

According to an embodiment of the present application, the step of managing the model data includes the model name, used algorithm, characteristics, verification method, hyper parameter value, applied data for the internal artificial intelligence model or the external artificial intelligence model. The model data for at least one of a preprocessing method and internal/external model may be stored and provided.

According to an embodiment of the present disclosure, the prediction data may include at least one of abnormal detection of the plant, equipment failure life prediction, failure probability prediction, and maintenance time prediction.

According to an embodiment of the present application, the step of calculating the predicted data for maintenance of the plant includes storing the model data in at least one artificial intelligence model among the artificial intelligence models stored in the managing step. It may be that the prediction data is calculated by inputting at least one of a plurality of equipment data stored in .

According to one embodiment of the present application, the step of visualizing the predicted data calculated in the step of calculating the predicted data for maintenance of the plant may be further included so that monitoring is possible.

The above-described problem solving means are merely exemplary and should not be construed as intended to limit the present disclosure. In addition to the exemplary embodiments described above, additional embodiments may exist in the drawings and detailed description of the invention.

According to the above-described problem solving means of the present application, downtime is reduced by learning an artificial intelligence model using a plurality of facility data collected from the plant and at the same time performing predictive maintenance for the plant, thereby reducing plant operation. efficiency can be improved.

According to the above-described problem solving means of the present application, an external preprocessing file and an external artificial intelligence model can be imported and selectively applied according to plant or user preference, in preparation for using only the existing internal preprocessing function and internal artificial intelligence model. It can expand the function of predictive maintenance and improve performance.

However, the effects obtainable herein are not limited to the effects described above, and other effects may exist.

1 is a schematic configuration diagram of a plant predictive maintenance system based on user settings according to an embodiment of the present invention.
2 is a schematic configuration diagram of a plant predictive maintenance device based on user settings according to an embodiment of the present invention.
3 is a diagram illustrating an autoencoder model, which is a deep learning-based unsupervised learning model that can be provided by a learning unit according to an embodiment of the present invention.
4 is a diagram illustrating model data managed by a manager according to an embodiment of the present disclosure.
5 is a diagram illustrating a process of importing an external artificial intelligence model in a management unit according to an embodiment of the present disclosure.
6 is a diagram illustrating prediction data provided by a visualization unit according to an embodiment of the present disclosure.
7 is an operation flowchart for a method for predictive maintenance of a plant based on user settings according to an embodiment of the present invention.

Hereinafter, embodiments of the present application will be described in detail so that those skilled in the art can easily practice with reference to the accompanying drawings. However, the present disclosure may be implemented in many different forms and is not limited to the embodiments described herein. And in order to clearly describe the present application in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the present specification, when a part is said to be “connected” to another part, it is not only “directly connected”, but also “electrically connected” or “indirectly connected” with another element in between. "Including cases where

Throughout the present specification, when a member is referred to as being “on,” “above,” “on top of,” “below,” “below,” or “below” another member, this means that a member is located in relation to another member. This includes not only the case of contact but also the case of another member between the two members.

Throughout the present specification, when a certain component is said to "include", it means that it may further include other components without excluding other components unless otherwise stated.

Throughout the present specification, 'user setting' refers to a user input received through a user terminal 30 described below, a wired communication device for a user setting-based plant predictive maintenance device 100 according to an embodiment of the present application. Alternatively, it may be interpreted as meaning a setting value according to a user input directly input through a wireless communication device. In other words, throughout the present specification, 'user setting' refers to a setting value input by a user, and an input method thereof is not limited in detail.

The present disclosure relates to an apparatus and method for predictive maintenance of a plant based on user settings. More specifically, the present disclosure relates to a plant predictive maintenance apparatus and method applicable to plant predictive maintenance by importing a preprocessing process (or preprocessing module) and an artificial intelligence model based on user settings.

1 is a schematic configuration diagram of a plant predictive maintenance system based on user settings according to an embodiment of the present invention.

Referring to FIG. 1 , a user setting based plant predictive maintenance system 10 may include a user setting based plant predictive maintenance device 100 , a plant 20 and a user terminal 30 .

Hereinafter, for convenience of explanation, the 'user setting-based plant predictive maintenance system 10' according to an embodiment of the present application is specified as the 'predictive maintenance system 10', and the 'user setting based plant predictive maintenance system 10' according to an embodiment of the present application The plant predictive maintenance device 100 will be specified as the 'predictive maintenance device 100'.

Referring to FIG. 1 , the predictive maintenance device 100 may communicate with a plant 20 and a user terminal 30 through a network. Specifically, according to one embodiment of the present application. The predictive maintenance device 100 may receive a plurality of equipment data from a plurality of equipment sensors included in the plant 20 through a network, and import an external preprocessing file or an external artificial intelligence model from the user terminal 30. A user input for can be received, and prediction data for predictive maintenance calculated using an internal artificial intelligence model or an external artificial intelligence model can be transmitted to the user terminal 30 .

At this time, the network includes a 3rd Generation Partnership Project (3GPP) network, a Long Term Evolution (LTE) network, a 5G network, a World Interoperability for Microwave Access (WIMAX) network, the Internet, a local area network (LAN), and a wireless LAN ( Wireless Local Area Network), WAN(Wide Area Network), PAN(Personal Area Network), Bluetooth Network, Wifi Network, NFC(Near Field Communication) Network, Satellite Broadcasting Network, Analog Broadcasting Network, DMB(Digital Multimedia Broadcasting) ) may include a network, etc., but is not limited thereto.

In addition, the predictive maintenance device 100 detects an abnormality in the plant 20 as a result of calculating the predicted data, or when an issue occurs including a case where it is determined that a situation requiring immediate maintenance has occurred, the predictive maintenance device 100 reports to the user terminal 30. An alarm signal can be sent for an issue that has occurred. At this time, the alarm signal may include information about the type of abnormality (problem), the location of the abnormality, the time of occurrence of the abnormality, the degree of urgency of maintenance, and the reason why it is determined that maintenance is necessary, but is not limited thereto.

The user terminal 30 is, for example, a smart phone (Smartphone), a smart pad (Smart Pad), a tablet PC, a wearable device, and the like, a Personal Communication System (PCS), a Global System for Mobile communication (GSM), and a Personal Digital Cellular (PDC). ), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless It may be all types of wireless communication devices such as Broadband Internet) terminals and stationary terminals such as desktop computers and smart TVs.

2 is a schematic configuration diagram of a plant predictive maintenance device based on user settings according to an embodiment of the present invention.

Referring to FIG. 2 , the predictive maintenance device 100 includes a collection unit 110, a storage unit 120, a pre-processing unit 130, a learning unit 140, a management unit 150, an operation unit 160, and a visualization unit ( 170) may be included.

Referring to FIG. 2 , the collection unit 110 may receive and collect a plurality of equipment data of the plant 20 from a plurality of equipment sensors included in the plant 20 .

According to an embodiment of the present application, the plurality of facility data may be data on at least one of temperature, displacement, acceleration, pressure, vibration, and flow rate, and the plurality of facility sensors are contact sensors attached to the plant 20. Alternatively, it may include a non-contact sensor capable of measuring and sensing facility data for at least one of the component equipment of the plant 20 . At this time, if the equipment data to be collected (received) is vibration data, the collection unit 110 may collect (receive) a value converted to a frequency domain or a value converted to a time domain according to each of a plurality of equipment sensors.

In other words, the collection unit 110 may receive a plurality of facility data in real time from each of a plurality of facility sensors that monitor conditions of a plurality of component equipment included in the plant 20 .

Referring to FIG. 2 , the collection unit 110 may transmit a plurality of collected facility data to the storage unit 120, and the storage unit 120 may receive a plurality of facility data from the collection unit 110. . At this time, the storage unit 120 may receive a plurality of facility data from the collection unit 110 in real time and store the received facility data in real time or periodically according to a preset period. However, it is not limited thereto, and when the collection unit 110 periodically transmits a plurality of facility data to the storage unit 120 according to a preset period, the storage unit 120 receives a plurality of facility data from the collection unit 110. It may be to store a plurality of equipment data received each time a is received. In other words, the storage unit 120 may periodically store the plurality of facility data collected by the collection unit 110 in real time or according to a preset period.

In this case, the preset period may mean a time period according to a user setting, and may be set and modified by a user before or during operation of the predictive maintenance device 100 . For example, the predictive maintenance device 100 receives a time period for collecting or storing a plurality of facility data through the user terminal 30, and collects and stores the plurality of facility data according to the received time period. can

In addition, the storage unit 120 may store (separately) a plurality of facility data in detail in consideration of at least one of plant type, plant scale, data type, and data collection size per unit time. For example, the storage unit 120 may classify and store a plurality of facility data into structured data, unstructured data, and semi-structured data in consideration of data types.

In this case, the structured data corresponds to relational data (Relational Database), and may include, for example, temperature, pressure, and flow rate collected from the plant 20 . In addition, the unstructured data may include, for example, noise data generated in the plant 20, facility images, CCTV images, facility-related documents such as PDF files, and plant drawing files, and the semi-structured data, Data including a description of the structure within the data content, for example, may include data in the form of a file such as Hyper Text Markup Language (HTML), eXtensible Markup Language (XML), and JavaScript Object Notation (JSON), More specifically, it may include a CAD shape information file, web log data, signal data generated from a sensor, and the like. However, it is not limited thereto.

Referring to FIG. 2 , the preprocessing unit 130 may read at least some of a plurality of facility data stored in the storage unit 120 and perform preprocessing. Specifically, the pre-processing unit 130 selectively selects data required for learning an artificial intelligence model to be described later among a plurality of facility data stored separately according to plant type, plant size, data type, data collection size per unit time, and the like. can be pretreated.

In addition, the pre-processing unit 130 may include a built-in pre-processing unit 131 and a user pre-processing unit 132. The built-in pre-processing unit 131 performs pre-processing of a plurality of facility data using the built-in internal pre-processing function provided in the predictive maintenance device 100 according to an embodiment of the present invention, and the user pre-processing unit ( 130) may perform pre-processing on a plurality of equipment data based on an external pre-processing file imported according to user settings.

Specifically, the internal preprocessing function provides preprocessing functions such as data merging, missing or outlier processing, interpolation (linear interpolation and multi polynomal interpolation, etc.), column addition, creation, and conversion. It may include, and the built-in pre-processing unit 131 may pre-process (refine) a plurality of facility data using such an internal pre-processing function.

The preprocessing method for handling missing values is multi-polynomal interpolation, which is a method of interpolating using m values near missing values, not methods such as general interpolation methods such as Replace or Linear Interpolation. Interpolation) method may exist. Since the polynomial interpolation method is a well-known technique for those skilled in the art, a detailed description thereof will be omitted.

As described above, the user pre-processing unit 132 uses functions other than the pre-processing function built in the predictive maintenance device 100 to perform pre-processing according to rules set by the user. (100) An external pre-processing file that exists outside may be imported, the external pre-processing file may be standardized and uploaded, and a plurality of facility data may be pre-processed using the uploaded external pre-processing file. In other words, the user pre-processing unit 132 may be provided so that the user can utilize an external pre-processing function as needed.

For example, the user pre-processing unit 132 may perform an external pre-processing file by uploading an external pre-processing file through Python modularization and extension form. For another example, if a unit conversion for data processing is required and a specific conversion expression is required rather than a simple operation such as a constant multiplication function, the user pre-processing unit 132 imports and uploads an external pre-processing file for this to be utilized. can Specifically, when it is necessary to convert the temperature unit from Celsius scale temperature to Fahrenheit scale temperature, the user preprocessor 132 displays a relationship between Celsius temperature and Fahrenheit temperature according to the user's setting. You can convert units of temperature by importing and uploading the relationship (°F = 1.8°C + 32).

Although not shown in the drawings, the plurality of facility data preprocessed by the preprocessing unit 130 may be stored again in the storage unit 120 and may be utilized in the operation of an artificial intelligence model by the operating unit 160 to be described later. In addition, the plurality of facility data preprocessed by the pre-processing unit 130 may be transferred to the learning unit 140 and used for learning of the internal artificial intelligence model.

Therefore, the pre-processing unit 130 imports and uploads an external pre-processing file according to user settings, and performs pre-processing of a plurality of facility data using the external pre-processing file, thereby predicting the type and type of artificial intelligence model to be learned by the user and foresight. It can help perform preprocessing by considering various cases (situations) such as input values or input value types required for the artificial intelligence model to be used for maintenance.

Referring to FIG. 2 , the learning unit 140 may learn an internal artificial intelligence model by inputting a plurality of facility data preprocessed by the preprocessing unit 130 . The learning unit 140 may create an artificial intelligence model using a plurality of preprocessed facility data. At this time, the artificial intelligence model generated or learned by the learning unit 140 may be disclosed as an 'internal artificial intelligence model' in the following description, and should be interpreted as a concept distinct from an 'external artificial intelligence model'.

Artificial intelligence models include supervised learning-based models, unsupervised learning-based models, machine learning-based models (random forest, SVM (Support Vector Machine), etc.) and deep learning. It may include a base model and the like.

The learning unit 140 may provide, for example, an autoencoder model that is an unsupervised learning model among deep learning-based models. 3 is a diagram illustrating an autoencoder model, which is a deep learning-based unsupervised learning model that can be provided by a learning unit according to an embodiment of the present invention.

In addition, the learning unit 140 not only creates or learns an internal artificial intelligence model using a plurality of facility data stored in the storage unit 120 or data preprocessed through the pre-processing unit 130, but also already created And it may be to perform verification on the learned internal artificial intelligence model.

Specifically, the learning unit 140 classifies a plurality of facility data (including preprocessed data) into learning data necessary for generating and learning an artificial intelligence model and verification data necessary for verifying an already created and learned artificial intelligence model, An artificial intelligence model can be created or learned using training data, and the performance of an artificial intelligence model that has already been created and learned can be evaluated using verification data. The learning unit 140 may store the generated, learned, and verified artificial intelligence models by transferring them to the management unit 150 .

Referring back to FIG. 2 , the management unit 150 receives and stores the generated, learned, and verified artificial intelligence model from the learning unit 140, that is, the internal artificial intelligence model, and stores internal model data for the stored internal artificial intelligence model. can be stored and managed. In addition, the management unit 150 may import and store external artificial intelligence models according to user settings, and store and manage external model data for the stored external artificial intelligence models. In other words, the management unit 150 may manage model data for an internal artificial intelligence model learned by the learning unit 140 or an external artificial intelligence model imported according to user settings.

Specifically, the model data managed by the management unit 150 includes the model name, model type, used algorithm, characteristic, scaler, verification method, hyper parameter value, and applied preprocessing method for the artificial intelligence model. and whether it is an internal/external model (model registrant).

4 is a diagram illustrating model data managed by a management unit according to an embodiment of the present disclosure. Referring to FIG. 4 , it can be seen that two or more artificial intelligence models are stored and managed together with a plurality of model data. However, it is not limited thereto, and FIG. 4 is preferably interpreted as showing an embodiment of the management unit 150 .

According to one embodiment of the present application, the management unit 150 may include an internal model management unit 151 and an external model management unit 152 . Specifically, the internal model management unit 151 may store the internal artificial intelligence model generated, learned, and verified by the learning unit 140 as described above, and manage internal model data for the stored internal artificial intelligence model. .

In addition, the external model management unit 152 imports an external artificial intelligence model that exists outside the predictive maintenance device 100, that is, that is not generated or learned in the learning unit 140 in the form of a file, formalizes it into a usable form, and uploads it. It may be to store and manage external model data for the stored external AI model.

5 is a diagram illustrating a process of importing an external artificial intelligence model in a management unit according to an embodiment of the present disclosure. Referring again to FIG. 5 , the external model management unit 152 may call various external artificial intelligence models that already exist, standardize them into a form usable for predictive maintenance, and upload and store them.

According to one embodiment of the present application, the predictive maintenance device 100, as described above, the plant 20 or the plant 20 to selectively apply an external preprocessing file and an external artificial intelligence model according to the user's preference. Or you can import and upload according to your preference. Accordingly, the predictive maintenance apparatus 100 may expand the function of predictive maintenance and improve performance in contrast to using only the existing internal preprocessing function and the internal artificial intelligence model.

Referring back to FIG. 2 , the operation unit 160 may include at least one of the artificial intelligence models stored in the management unit 150 and at least one of a plurality of equipment data collected by the collection unit 110 and stored in the storage unit 120. One may be received, and prediction data for maintenance of the plant 20 may be calculated using the received artificial intelligence model and equipment data.

Specifically, the operation unit 160 receives, from the management unit 150, at least one artificial intelligence model to be used for predictive maintenance among a plurality of internal artificial intelligence models or external artificial intelligence models stored in the management unit 150. , A plurality of facility data stored in the storage unit 120 to be used as data to be applied (input) to the received artificial intelligence model, or preprocessing through the preprocessing unit 130, although not shown in FIG. It is possible to receive the data of a plurality of facilities that have been configured.

In addition, the operation unit 160 may apply the received facility data as an input to the received artificial intelligence model so that predicted data is calculated. In other words, the operation unit 160 inputs at least one of a plurality of facility data stored in the storage unit 120 to at least one artificial intelligence model among the artificial intelligence models stored in the management unit 150 to calculate predicted data. can be made

For example, when performing predictive maintenance on problems that may occur due to temperature changes in the plant 20, the operation unit 160 may use an artificial intelligence model and plant capable of predicting temperature changes and problems that may occur due to temperature changes ( 20) may receive temperature data for each component equipment, and predictive data may be calculated from the artificial intelligence model by inputting the received temperature data into the received artificial intelligence model.

In this case, the prediction data may include at least one of abnormal detection of the plant 20, equipment failure life prediction, failure probability prediction, and maintenance time prediction.

According to one embodiment of the present application, the operation unit 160 transmits at least one of the artificial intelligence models already stored and managed by the management unit 150, rather than the internal artificial intelligence model being created and learned by the learning unit 140. Since it is received and used, at least one artificial intelligence among a plurality of internal artificial intelligence models and a plurality of external artificial intelligence models stored and managed by the management unit 150 while learning the internal artificial intelligence model in the learning unit 140 Using the model, predictive data can be calculated, that is, predictive maintenance can be performed.

In other words, the predictive maintenance device 100 may learn an artificial intelligence model using a plurality of facility data collected from the plant 20 and perform predictive maintenance for the plant 20 at the same time. It can have the effect of reducing downtime and improving the efficiency of plant operation.

Referring to FIG. 2 , the visualization unit 170 may receive predicted data calculated from the operation unit 160 . The visualization unit 170 may visualize the predicted data calculated by the operation unit 160 so as to be monitored.

6 is a diagram illustrating prediction data provided by a visualization unit according to an embodiment of the present disclosure. As shown in FIG. 6 , the visualization unit 170 may express and visualize in various forms such as a line graph or a bar chart according to an artificial intelligence model using prediction data or a type of facility data. In addition, the visualization unit 170 may transmit the visualized prediction data to the user terminal 30 or a PC including a display that the user can directly monitor with his/her eyes. In addition, the visualized prediction data may be provided to be downloadable or editable as an image file according to user settings.

Hereinafter, based on the details described above, the operation flow of the present application will be briefly reviewed.

7 is an operation flowchart for a method for predictive maintenance of a plant based on user settings according to an embodiment of the present invention.

The plant predictive maintenance method based on user settings shown in FIG. 7 may be performed by the previously described plant predictive maintenance device 100 based on user settings. Therefore, even if omitted below, the description of the user setting-based plant predictive maintenance apparatus 100 can be equally applied to the description of the user setting-based plant predictive maintenance method.

Referring to FIG. 7 , in step S210, the collection unit 110 may collect a plurality of facility data for the plant 20 from a plurality of facility sensors.

Next, in step S220, the storage unit 120 may periodically store the plurality of facility data collected by the collection unit 110 in real time or according to a preset period.

Next, in step S230, the pre-processing unit 130 may read at least some of the plurality of facility data stored in the storage unit 120 and perform pre-processing. Specifically, the pre-processing unit 130 includes a built-in pre-processing unit 131 and a user pre-processing unit 132, and in step S231, the built-in pre-processing unit 131 provides an internal pre-processing function within the predictive maintenance device 100. It is possible to perform pre-processing on a plurality of facility data using , and in step S232, the user pre-processing unit 132 pre-processes a plurality of facility data based on an external pre-processing file imported according to user settings. can be performed.

Next, in step S240, the learning unit 140 may learn the internal artificial intelligence model by inputting the plurality of facility data preprocessed by the preprocessing unit 130.

Next, in step S250, the management unit 150 may manage model data for the internal artificial intelligence model learned in the learning unit 140 or the external artificial intelligence model imported according to user settings. Specifically, in step S250, the management unit 150 determines the model name, used algorithm, characteristics, verification method, hyper parameter value, applied preprocessing method, and internal/external model for the internal artificial intelligence model or the external artificial intelligence model. Model data for at least one of them may be stored and provided. In addition, the management unit 150 includes an internal model management unit 151 and an external model management unit 152, and in step S251, the internal model management unit 151 controls the internal artificial intelligence model generated and learned in the learning unit 140. Internal model data is managed, and in step S252, the external model management unit 152 imports an external AI model that exists outside the predictive maintenance device 100 in the form of a file, formalizes it into a usable form, uploads it, and imports and uploads it. It could be managing external model data for an external AI model.

Next, in step S260, the operation unit 160 uses at least one of the artificial intelligence models stored and managed by the management unit 150 and at least one of a plurality of facility data collected by the collection unit 110 to control the plant 20 ), predictive data for maintenance can be calculated. Specifically, in step S260, the operation unit 160 predicts by inputting at least one of a plurality of facility data stored in the storage unit 120 into at least one artificial intelligence model among the artificial intelligence models stored in the management unit 150. It may be to allow data to be calculated. In this case, the prediction data may include at least one of abnormal detection of the plant 20, equipment failure life prediction, failure probability prediction, and maintenance time prediction.

Next, in step S270, the visualization unit 170 may visualize the predicted data calculated by the operation unit 160 to be monitored.

In the foregoing description, steps S210 to S270 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present application. Also, some steps may be omitted if necessary, and the order of steps may be changed.

The plant predictive maintenance method based on user settings according to an embodiment of the present disclosure may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program instructions recorded on the medium may be those specially designed and configured for the present invention or those known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to act as one or more software modules to perform the operations of the present invention, and vice versa.

In addition, the above-described method for plant predictive maintenance based on user settings may be implemented in the form of a computer program or application stored in a recording medium and executed by a computer.

The above description of the present application is for illustrative purposes, and those skilled in the art will understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present application. Therefore, the embodiments described above should be understood as illustrative in all respects and not limiting. For example, each component described as a single type may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined form.

The scope of the present application is indicated by the following claims rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be construed as being included in the scope of the present application.

10: Plant predictive maintenance system based on user settings
20: plant
30: user terminal
100: plant predictive maintenance device based on user settings
110: collection unit
120: storage unit
130: pre-processing unit
131: built-in pre-processing unit
132: user pre-processing unit
140: learning unit
150: management unit
151: internal model management unit
152: external model management unit
160: operation department
170: visualization unit

Claims (16)

In the user setting-based plant predictive maintenance device,
a collection unit that collects a plurality of facility data for a plant from a plurality of facility sensors;
a pre-processing unit that performs pre-processing on the plurality of equipment data based on an external pre-processing file imported according to user settings;
a learning unit that learns an internal artificial intelligence model by inputting a plurality of facility data pre-processed by the pre-processing unit;
a management unit that manages model data for the internal artificial intelligence model learned in the learning unit or an external artificial intelligence model imported according to user settings; and
An operation unit that calculates predictive data for maintenance of the plant using at least one of the artificial intelligence models stored in the management unit and at least one of a plurality of facility data collected by the collection unit;
Including,
The pre-processing unit,
a built-in preprocessing unit provided in the plant predictive maintenance device and performing preprocessing on the plurality of equipment data using an internal preprocessing function built into the plant predictive maintenance device; and
A user pre-processing unit that performs pre-processing on the plurality of facility data according to a rule according to the user setting using the external pre-processing file;
including,
The plant predictive maintenance apparatus of claim 1 , wherein the plurality of facility data is pre-processed by selectively applying one of the built-in pre-processing unit using the internal pre-processing function and the user pre-processing unit using the external pre-processing file. According to claim 1,
A storage unit that periodically stores the plurality of facility data collected by the collection unit in real time or according to a preset period;
Including more,
The pre-processing unit,
Loading at least some of the plurality of equipment data stored in the storage unit and performing preprocessing,
Plant predictive maintenance device. delete According to claim 1,
the management department,
Importing an external artificial intelligence model that exists outside the device in the form of a file, standardizing it in a usable form and uploading it,
Plant predictive maintenance device. According to claim 1,
the management department,
The model data for at least one of the model name, used algorithm, characteristics, verification method, hyper parameter value, applied preprocessing method, and internal/external model for the internal artificial intelligence model or the external artificial intelligence model to store and provide;
Plant predictive maintenance device. According to claim 1,
The prediction data,
Including at least one of abnormality detection for the plant, equipment failure life prediction, failure probability prediction, and maintenance timing prediction,
Plant predictive maintenance device. According to claim 2,
The operating department,
inputting at least one of a plurality of facility data stored in the storage unit into at least one artificial intelligence model among the artificial intelligence models stored in the management unit to calculate the predicted data;
Plant predictive maintenance device. According to claim 1,
A visualization unit that visualizes the predicted data calculated by the operation unit so as to be able to be monitored;
Plant predictive maintenance device further comprising a. In the plant predictive maintenance method based on user settings,
collecting a plurality of facility data for the plant from a plurality of facility sensors;
performing pre-processing on the plurality of equipment data based on an external pre-processing file imported according to user settings;
Learning an internal artificial intelligence model using the plurality of facility data preprocessed in the preprocessing step as input;
Managing model data for the internal artificial intelligence model learned in the learning step or an external artificial intelligence model imported according to user settings; and
Prediction data for the maintenance of the plant using at least one of the artificial intelligence models stored and managed in the step of managing the model data and at least one of the plurality of facility data collected in the step of collecting the plurality of facility data. A step of allowing to be calculated,
Including,
Performing the preprocessing step,
(a) performing pre-processing on the plurality of equipment data using an internal pre-processing function provided in the plant predictive maintenance device and built into the plant predictive maintenance device; and
(b) performing pre-processing on the plurality of equipment data according to a rule according to the user setting using the external pre-processing file;
including,
The plant predictive maintenance method of claim 1 , wherein the plurality of facility data is preprocessed by selectively applying one of the steps (a) or (b). According to claim 9,
Periodically storing the plurality of facility data collected in the step of collecting the plurality of facility data in real time or according to a preset period;
Including more,
Performing the preprocessing step,
Loading at least some of the plurality of equipment data stored in the storing step to perform preprocessing,
Plant predictive maintenance method. delete According to claim 9,
The step of managing the model data,
Importing an external artificial intelligence model that exists outside the device in the form of a file, standardizing it in a usable form and uploading it,
Plant predictive maintenance method. According to claim 9,
The step of managing the model data,
The model data for at least one of the model name, used algorithm, characteristics, verification method, hyper parameter value, applied preprocessing method, and internal/external model for the internal artificial intelligence model or the external artificial intelligence model to store and provide;
Plant predictive maintenance method. According to claim 9,
The prediction data,
Including at least one of abnormality detection for the plant, equipment failure life prediction, failure probability prediction, and maintenance timing prediction,
Plant predictive maintenance method. According to claim 10,
The step of calculating the predicted data for the maintenance of the plant,
Inputting at least one of the plurality of facility data stored in the storing step to at least one artificial intelligence model among the artificial intelligence models stored in the step of managing the model data so that the predicted data is calculated ,
Plant predictive maintenance method. According to claim 9,
Visualizing the predicted data calculated in the step of calculating the predicted data for maintenance of the plant to be monitored;
Plant predictive maintenance method further comprising a.

Images