Operation method for Process Operation Support Server

Abstract

The present invention provides a method of operation of a process operation support server comprising the steps of: receiving integrated data including environmental data measured from IoT sensors installed in a factory, process data and configured equipment data from process equipment; performing data interpolation on the integrated data to learn a plurality of algorithms for predicting the operating status of each of the process equipment; determining a specific algorithm having a relatively high prediction result value among the prediction result values ​​learned through each of the plurality of algorithms; and transmitting a prediction model corresponding to the specific algorithm to a monitoring device that monitors the process equipment to predict the operating status of the process equipment.

Description

Technology Field

[0001] The present invention relates to a method of operation of a process operation support server, and more specifically, to a method of operation of a process operation support server for predicting the operating status of each of the process facilities within a factory and supporting the operation and operation of each of the process facilities. Background Technology

[0002] Generally, factories can be described as a root industry, a process technology industry utilized throughout the entire manufacturing sector, primarily in casting, mold making, plastic processing, welding, surface treatment, and heat treatment.

[0003] Most foundational industries are small in scale, and the reality is that systems such as the Manufacturing Execution System (MES), which are primarily utilized by large corporations, have not been properly implemented.

[0004] Consequently, there are many companies that face limitations in establishing automation of the manufacturing process itself or efficiently performing process operations.

[0005] There is a need for a systematic system capable of establishing process automation tailored to the characteristics of manufacturing processes in these foundational industries and increasing the operational efficiency of the manufacturing process.

[0006] Recently, research is being conducted on methods to optimize the operational efficiency of each of the manufacturing process facilities installed within these foundational industries, that is, within factories. The problem to be solved

[0007] The present invention provides a method of operation for a process operation support server to predict the operating status of each of the process facilities within a factory and to support the operation and operation of each of the process facilities.

[0008] The objects of the present invention are not limited to those mentioned above, and other unmentioned objects and advantages of the present invention may be understood from the following description and will be more clearly understood by the embodiments of the present invention. Furthermore, it will be readily apparent that the objects and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims. means of solving the problem

[0009] The method of operation of a process operation support server according to the present invention may include the steps of: receiving integrated data including environmental data measured from IoT sensors installed in a factory, process data and set equipment data for a process from process equipment; performing data interpolation on the integrated data and learning a plurality of algorithms for predicting the operating state of each of the process equipment; determining a specific algorithm having a relatively high prediction result value among the prediction result values ​​learned through each of the plurality of algorithms; and transmitting a prediction model corresponding to the specific algorithm to a monitoring device that monitors the process equipment in order to predict the operating state of the process equipment.

[0010] The above environmental data includes temperature, humidity, and dust concentration within the factory, the above process data includes operation information and raw material information for each of the above process equipment, and the above equipment data may include specifications for each of the above process equipment.

[0011] The above plurality of algorithms may be Decision Tree, Random Forest, CNN, DNN, Long-Short Term Memory, XGBoost, STL, FFT, Autoencorder, ROI, YOLO for predicting the operating state of each of the process facilities.

[0012] The step of learning with the plurality of algorithms may include the step of interpolating data of the integrated data and deleting missing data, the step of converting the integrated data into pattern information values ​​to generate integrated information values ​​classified by time intervals, and the step of applying the integrated information values ​​to the plurality of algorithms for learning.

[0013] The step of transmitting the above prediction model may transmit prediction result information corresponding to the above prediction result value to the monitoring device.

[0014] After the step of transmitting the above prediction model, the method may further include the step of transmitting equipment operation information for the optimal operation of each of the above process equipment based on the above prediction result value to the monitoring device.

[0015] The above facility operation information may represent control information related to the operation and function of each of the above process facilities. Effects of the invention

[0016] The method of operation of a process operation support server according to the present invention has the advantage of being able to provide prediction models for predicting the optimal operation efficiency of process equipment within a factory.

[0017] In addition, the method of operation of the process operation support server according to the present invention has the advantage of reducing the amount of data of integrated data applied to multiple algorithms by data interpolation and classification by time interval of integrated data acquired within the factory.

[0018] In addition, the method of operation of the process operation support server according to the present invention has the advantage of being able to guide process equipment to increase operational efficiency by providing a specific algorithm having a relatively high prediction result value among the prediction result values ​​predicted by a plurality of algorithms to the process equipment.

[0019] Meanwhile, the effects of the present invention are not limited to those mentioned above, and various effects may be included within the scope obvious to a person skilled in the art from the contents described below. Brief explanation of the drawing

[0020] FIG. 1 is a system diagram showing a process operation support system according to the present invention. Figure 2 is a control block diagram showing the control configuration of the process operation support server shown in Figure 1. Figures 3 and 4 are flowcharts illustrating the operation method of the process operation support server shown in Figure 1. Specific details for implementing the invention

[0021] The present invention is susceptible to various modifications and may have various embodiments, and specific embodiments are illustrated in the drawings and described in detail. However, this is not intended to limit the invention to specific embodiments, and it should be understood that the invention includes all modifications, equivalents, and substitutions that fall within the spirit and scope of the invention. Similar reference numerals have been used for similar components in the description of each drawing.

[0022] Terms such as first, second, A, B, etc., may be used to describe various components, but said components should not be limited by said terms. These terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component. The term "and / or" includes a combination of multiple related described items or any of the multiple related described items.

[0023] When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. On the other hand, when it is stated that one component is "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between.

[0024] The terms used in this application are used merely to describe specific embodiments and are not intended to limit the invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, terms such as "comprising" or "having" are intended to indicate the presence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0025] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the present invention pertains. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0026] Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings.

[0027] FIG. 1 is a system diagram showing a process operation support system according to the present invention.

[0028] Referring to FIG. 1, the process operation support system (1) may include IoT sensors (10), process equipment (20), a monitoring device (30), and a process operation support server (40).

[0029] IoT sensors (10) and process equipment (20) are installed in the factory and can transmit factory environment data (d1), process data (d2) and equipment data (d3) to the process operation support server (40).

[0030] First, the IoT sensors (10) are sensors capable of measuring environmental data (d1), including temperature, humidity, and odor within the factory, and can transmit the environmental data (d1) to the monitoring device (10) and the process operation support server (40).

[0031] Process equipment (20) represents a manufacturing device for manufacturing any product within a factory, and may be, for example, an injection / mold device, a press / mold device, a welding device, a heat treatment device, a casting device and a plasticizing device, but is not limited thereto.

[0032] Additionally, the process equipment (20) may include a separate device installed in the factory.

[0033] Process equipment (20) can transmit process data (d2) and equipment data (d3) for the manufacturing process to a monitoring device (30) and a process operation support server (40).

[0034] In an embodiment, environmental data (d1), process data (d2), and equipment data (d3) are transmitted to a monitoring device (30), and the monitoring device (30) transmits integrated data (d) including environmental data (d1), process data (d2), and equipment data (d3) to a process operation support server (40).

[0035] Environmental data (d1) includes temperature, humidity, and dust concentration within the factory, process data (d2) includes operation information and raw material information for each of the process equipment (20), and equipment data (d3) may include specifications for each of the process equipment (20), but is not limited thereto.

[0036] The monitoring device (30) can monitor the operation and operating status of the IoT sensors (10) and process equipment (20), and can control the operation of at least one of the IoT sensors (10) and process equipment (20) according to the input of a manager.

[0037] In addition, the monitoring device (30) can predict the current operating status of the process equipment (20) according to the prediction model transmitted from the process operation support server (40).

[0038] The monitoring device (30) can separately control the operation and operation of each of the process equipment (20) according to the equipment operation information transmitted from the process operation support server (40).

[0039] The process operation support server (40) can receive integrated data (d) from the monitoring device (30).

[0040] At this time, the process operation support server (40) can receive integrated data (d) from the monitoring device (30), but can also receive each of the environment data (d1), process data (d2), and equipment data (d3) included in the integrated data (d) from the IoT sensors (10) and process equipment (20), respectively.

[0041] The process operation support server (40) can learn multiple algorithms to predict the operating status of each process facility (20) by performing data interpolation on the integrated data (d).

[0042] Here, the process operation support server (40) can reduce the amount of data by interpolating the data of the integrated data (d) and deleting missing data.

[0043] Afterwards, the process operation support server (40) can convert the integrated data (d) into a pattern information value in a learnable format and generate an integrated information value classified by time interval.

[0044] Here, the integrated information value may be a value obtained by sorting and classifying the pattern information value by time interval, but is not limited thereto.

[0045] The process operation support server (40) can learn by applying the integrated information value to a plurality of set algorithms.

[0046] The above multiple algorithms may be Decision Tree, Random Forest, CNN, DNN, Long-Short Term Memory, XGBoost, STL, FFT, Autoencorder, ROI, YOLO for predicting the operating state of each of the process equipment (20), and other learning algorithms may be applied.

[0047] The process operation support server (40) can determine a specific algorithm that has a relatively high prediction result value among the prediction result values ​​learned through each of the plurality of algorithms.

[0048] That is, the process operation support server (40) can determine a specific algorithm that has a relatively high prediction result value among the prediction result values ​​for any process equipment among the process equipment (20) and apply it to relearn the next input integrated information value.

[0049] The process operation support server (40) can transmit a prediction model corresponding to the specific algorithm to a monitoring device (30) that monitors the process equipment (20) in order to predict the operating status of the process equipment (20).

[0050] As described above, the monitoring device (30) can predict the operating status of the process equipment (20) based on the prediction model.

[0051] Additionally, the process operation support server (40) can transmit equipment operation information for the optimal operation of each of the process equipment (20) to the monitoring device (30) based on the predicted result value. The equipment operation information may represent control information related to the operation and operation of each of the process equipment (20).

[0052] Additionally, the process operation support server (40) may transmit the analysis results learned from the specific algorithm to the monitoring device (30) so that the manager can recognize them, but is not limited thereto.

[0053] Figure 2 is a control block diagram showing the control configuration of the process operation support server shown in Figure 1.

[0054] Referring to FIG. 2, the process operation support server (40) may include a storage module (110), a communication module (120), and a processor module (130).

[0055] The storage module (110) may store prediction models for multiple algorithms, and may store integrated data (d) transmitted from the monitoring device (30), integrated information values ​​and prediction result values ​​corresponding to the integrated data (d), but is not limited thereto.

[0056] Additionally, the storage module (110) may provide stored information under the control of the processor module (130), and is not limited thereto.

[0057] The communication module (120) can communicate with at least one of the IoT sensors (10), process equipment (20), and monitoring device (30).

[0058] The processor module (130) may include a preprocessing unit (132), a learning unit (134), and a decision unit (136).

[0059] The preprocessing unit (132) can reduce the amount of data by interpolating the data of the integrated data (d) received from the monitoring device (30) and deleting missing data.

[0060] The preprocessing unit (132) can convert the integrated data (d) into a pattern information value in a learnable format and generate an integrated information value classified by time interval.

[0061] Here, the integrated information value may be a value obtained by sorting and classifying the pattern information value by time interval, but is not limited thereto.

[0062] The learning unit (134) can learn by applying the integrated information value to multiple algorithms.

[0063] The above multiple algorithms may be Decision Tree, Random Forest, CNN, DNN, Long-Short Term Memory, XGBoost, STL, FFT, Autoencorder, ROI, YOLO for predicting the operating state of each of the process equipment (20), and other learning algorithms may be applied.

[0064] The decision unit (136) can determine a specific algorithm that has a relatively high prediction result value among the prediction result values ​​learned through each of the plurality of algorithms.

[0065] That is, the decision unit (136) can determine a specific algorithm that has a relatively high prediction result value among the prediction result values ​​for any process equipment among the process equipment (20) and apply it to relearn the next input integrated information value.

[0066] The decision unit (136) can transmit a prediction model corresponding to the specific algorithm to a monitoring device (30) that monitors the process equipment (20) in order to predict the operating status of the process equipment (20).

[0067] The decision unit (136) can transmit equipment operation information for the optimal operation of each of the process equipment (20) to the monitoring device (30) based on the predicted result value. The equipment operation information may represent control information related to the operation and operation of each of the process equipment (20).

[0068] Additionally, the decision unit (136) may transmit the analysis results learned from the specific algorithm to the monitoring device (30) so that the manager can recognize them, and is not limited thereto.

[0069] FIGS. 3 and FIGS. 4 are flowcharts illustrating the operation method of a process operation support system according to the present invention.

[0070] Referring to FIGS. 3 and 4, the process operation support server (40) of the process operation support system (1) can receive integrated data (d) including environmental data (d1) measured from IoT sensors (10) installed in the factory, process data (d2) and set equipment data (d3) for the process from process equipment (20) (S110).

[0071] That is, the process operation support server (40) can receive integrated data (d) including environment data (d1), process data (d2) and equipment data (d3) from the monitoring device (30).

[0072] Environmental data (d1) includes temperature, humidity, and dust concentration within the factory, process data (d2) includes operation information and raw material information for each of the process equipment (20), and equipment data (d3) may include specifications for each of the process equipment (20), but is not limited thereto.

[0073] The process operation support server (40) can perform data interpolation on the integrated data (d) and learn with a plurality of algorithms to predict the operating status of each of the process equipment (20) (S120).

[0074] Here, Fig. 4 may represent step (S120) of Fig. 3.

[0075] Referring to FIG. 4, the process operation support server (40) interpolates data of the integrated data (d) and deletes missing data (S210), converts the integrated data (d) into pattern information values ​​to generate integrated information values ​​classified by time intervals (S220), and applies the integrated information values ​​to the plurality of algorithms to learn (S230).

[0076] That is, the process operation support server (40) can learn multiple algorithms to predict the operating status of each process facility (20) by performing data interpolation on the integrated data (d).

[0077] Here, the process operation support server (40) can reduce the amount of data by interpolating the data of the integrated data (d) and deleting missing data.

[0078] Afterwards, the process operation support server (40) can convert the integrated data (d) into a pattern information value in a learnable format and generate an integrated information value classified by time interval.

[0079] Here, the integrated information value may be a value obtained by sorting and classifying the pattern information value by time interval, but is not limited thereto.

[0080] The process operation support server (40) can learn by applying the integrated information value to a plurality of set algorithms.

[0081] The above multiple algorithms may be Decision Tree, Random Forest, CNN, DNN, Long-Short Term Memory, XGBoost, STL, FFT, Autoencorder, ROI, YOLO for predicting the operating state of each of the process equipment (20), and other learning algorithms may be applied.

[0082] The process operation support server (40) can determine a specific algorithm that has a relatively high prediction result value among the prediction result values ​​learned through each of the plurality of algorithms (S130).

[0083] That is, the process operation support server (40) can determine a specific algorithm that has a relatively high prediction result value among the prediction result values ​​learned through each of the plurality of algorithms.

[0084] That is, the process operation support server (40) can determine a specific algorithm that has a relatively high prediction result value among the prediction result values ​​for any process equipment among the process equipment (20) and apply it to relearn the next input integrated information value.

[0085] The process operation support server (40) can transmit a prediction model corresponding to the specific algorithm to a monitoring device (30) that monitors the process equipment (20) in order to predict the operating status of the process equipment (S140).

[0086] The process operation support server (40) can transmit facility operation information for optimal operation of each of the process facilities (20) based on the above prediction result value to the monitoring device (30) (S150).

[0087] That is, the process operation support server (40) can transmit a prediction model corresponding to the specific algorithm to a monitoring device (30) that monitors the process equipment (20) in order to predict the operating status of the process equipment (20).

[0088] As described above, the monitoring device (30) can predict the operating status of the process equipment (20) based on the prediction model.

[0089] Additionally, the process operation support server (40) can transmit equipment operation information for the optimal operation of each of the process equipment (20) to the monitoring device (30) based on the predicted result value. The equipment operation information may represent control information related to the operation and operation of each of the process equipment (20).

[0090] Additionally, the process operation support server (40) may transmit the analysis results learned from the specific algorithm to the monitoring device (30) so that the manager can recognize them, but is not limited thereto.

[0091] The features, structures, effects, etc. described in the embodiments above are included in at least one embodiment of the present invention and are not necessarily limited to only one embodiment. Furthermore, the features, structures, effects, etc. exemplified in each embodiment may be combined or modified and implemented in other embodiments by a person skilled in the art to which the embodiments belong. Therefore, details regarding such combinations and modifications should be interpreted as being included within the scope of the present invention.

[0092] Furthermore, although the above description has focused on exemplary embodiments, this is merely illustrative and does not limit the invention. Those skilled in the art will understand that various modifications and applications not exemplified above are possible within the scope of the essential characteristics of the exemplary embodiments. For instance, each component specifically shown in the exemplary embodiments may be modified. Furthermore, differences related to such modifications and applications should be interpreted as being included within the scope of the invention as defined in the appended claims.

Claims

Claim 1 A method of operation of a process operation support server comprising: receiving integrated data including environmental data measured from IoT sensors installed in a factory, process data and set equipment data for a process from process equipment; performing data interpolation on the integrated data and learning a plurality of algorithms for predicting the operating state of each of the process equipment; determining a specific algorithm having a relatively high prediction result value among the prediction result values ​​learned through each of the plurality of algorithms; and transmitting a prediction model corresponding to the specific algorithm to a monitoring device that monitors the process equipment to predict the operating state of the process equipment. Claim 2 A method of operation of a process operation support server according to claim 1, wherein the environment data includes temperature, humidity, and dust concentration within the factory, the process data includes operation information and raw material information for each of the process equipment, and the equipment data includes specifications for each of the process equipment. Claim 3 A method of operation of a process operation support server, wherein the plurality of algorithms are Decision Tree, Random Forest, CNN, DNN, Long-Short Term Memory, XGBoost, STL, FFT, Autoencorder, ROI, and YOLO for predicting the operating state of each of the process facilities. Claim 4 In claim 3, the step of learning with the plurality of algorithms comprises: a step of interpolating data of the integrated data and deleting missing data; a step of converting the integrated data into pattern information values ​​to generate integrated information values ​​classified by time intervals; and a step of applying the integrated information values ​​to the plurality of algorithms to learn, a method of operation of a process operation support server. Claim 5 In claim 1, the step of transmitting the prediction model is to transmit prediction result information corresponding to the prediction result value to the monitoring device, a method of operation of a process operation support server. Claim 6 A method of operation of a process operation support server according to claim 1, further comprising, after the step of transmitting the prediction model, the step of transmitting facility operation information for the optimal operation of each of the process facilities based on the prediction result value to the monitoring device. Claim 7 In claim 6, the method of operation of a process operation support server, wherein the facility operation information represents control information related to the operation and operation of each of the process facilities.

Images