JP2013222259A - Data analysis support device, data analysis support method, computer program, and computer readable storage medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a data analysis support device which generates an operation analysis map in which shape feature quantities calculated from a plurality of pieces of chart data are mapped, to provide data for analyzing which of equipment and an operation condition a trouble has been caused by.SOLUTION: The data analysis support device includes: a shape feature quantity extraction unit which extracts shape feature quantities of a plurality of pieces of chart data where operation data relating to processing extracted from a plurality of facilities are arranged in time sequence, from the chart data in a manufacturing process where materials of the same specifications are distributed to the plurality of facilities of the same specifications and the same processing is performed in the facilities; and a map generation unit which generates an operation analysis map relating to shape feature quantities, where the shape feature quantities are visually represented and plotted on two-dimensional coordinates with a first axis relating to time passage of processing in each facility and a second axis indicative of sequences set between respective facilities.

Description

  The present invention relates to a data analysis support apparatus, a data analysis support method, a computer program, and a computer-readable storage medium that analyze chart data in a manufacturing process, and more particularly, to analyze a cause of a trouble that has occurred in the manufacturing process. Therefore, the present invention relates to a data analysis support device, a data analysis support method, a computer program, and a computer-readable storage medium that generate an operation analysis map that visualizes the operation state of the manufacturing process from a plurality of chart data to be analyzed.

  Conventionally, when an abnormality occurs in an operation of a manufacturing process, an operation improvement response has been performed using knowledge of past cases. At this time, since the accumulated past case data has been utilized by human memory or manual search, the correspondence taken based on the past case data may differ depending on the experience and subjectivity of the worker.

  For such problems, a method for analyzing past case data has been proposed. In order to improve operational stability and quality, we analyze daily operational data and operational quality data, which are quality data, and operate quality troubles (operating quality troubles are at least one of operational troubles and quality troubles. It is important to elucidate the cause of the problem and to formulate countermeasures. For this reason, data analysis technology is indispensable. Conventionally, data analysis is performed by a separate approach for each problem or each person in charge. For example, the sheet thickness, width, and temperature history are analyzed from the chart data in the longitudinal direction of the product, the motor current value is analyzed from the equipment chart data, and the thread and roll wrinkles are analyzed from the quality data such as wrinkles. be able to. If these data are time-series, the amount of data will be enormous, and time-series data analysis techniques will be required in complex and diverse steel processes.

  As a basic idea of time-series data analysis, first, time-series data is analyzed to select effective operation quality data, and feature quantities are extracted from the selected operation quality data. Then, a discrimination model for classifying the extracted feature quantity and discriminating the factor of the operation quality trouble is created. From this discrimination model, it becomes possible to predict operational quality troubles.

  As a technique for analyzing time series data, for example, Patent Document 1 discloses an independent component analysis (ICA) to analyze the correlation between the strength corresponding to the waveform component of the time series data and the operation result. Thus, an operation analysis device that constructs a model and uses it for operation prediction is disclosed. Patent Document 2 discloses an operation result analysis apparatus for an operation process using wavelet analysis as a similar method of independent component analysis. Further, Patent Document 3 discloses a method of searching for past process state similar cases from a process time-series database using independent variable values of process variable values calculated using high-speed ICA.

  Further, Patent Document 4 incorporates feature quantities of principal component analysis (PCA), independent component analysis, or PLS (Partial Last Square) into a Just In Time (JIT) model as a model variable. A quality prediction apparatus that performs prediction is disclosed. Patent Document 5 discloses a design support apparatus that searches for materials including keywords as design-related information and provides the search results to the designer as knowledge information. In such a design support apparatus, correspondence analysis is used for analyzing the relationship between keywords and materials.

JP 2002-31430 A JP 2004-288144 A JP 2005-135010 A JP 2009-70227 A JP 2010-198259 A

  However, as described above, many methods using independent component analysis have been proposed, but a method for specifying a focused base waveform and an independent component (also referred to as an independent signal) has not been established. In addition, there is no method for using independent component analysis for a plurality of correspondence charts and a method for selecting the best independent component. For this reason, it is not easy to select an independent component that is effective for seeing signs of operation trouble and quality trouble from a large number of independent components. In addition, the shape characteristics and time-series changes of the chart data are different for each facility, and it is not easy to select independent components to be noted for each facility. Finding the cause of quality problems is not easy.

  Therefore, the present invention has been made in view of the above problems, and an object of the present invention is to generate an operation analysis map in which shape feature amounts calculated from a plurality of chart data are mapped, and cause of trouble A new and improved data analysis support apparatus, data analysis support method, computer program, and computer-readable storage medium capable of providing data for analyzing whether the data is due to equipment or operating conditions It is to provide.

  In order to solve the above-described problem, according to one aspect of the present invention, a material with the same specification is distributed to a plurality of equipment with the same specification, and in a manufacturing process in which the same processing is performed, the processing extracted from the plurality of equipment A shape feature quantity extraction unit that extracts a shape feature quantity of the chart data from a plurality of chart data in which operation data is arranged in time series, and a shape feature quantity, a first axis relating to the time lapse of processing in each equipment, and each equipment A map creation unit for creating an operation analysis map related to the shape feature amount, which is visually represented and arranged in a two-dimensional coordinate composed of a second axis indicating the order set in between, A data analysis support apparatus is provided.

  The map creation unit indicates the order in which the values of the plurality of operation condition variables representing the operation conditions of the operation process associated with the chart data are set between the first axis and each facility regarding the time passage of the process in each facility. You may further create the operation analysis map regarding the operation condition variable visually arranged in the two-dimensional coordinates composed of the second axis.

  Here, the order set between the facilities may be the use order of the facilities or the physical arrangement order of the facilities.

  The shape feature quantity extraction unit may extract the shape feature quantity using independent component analysis.

  In order to solve the above-mentioned problem, according to another aspect of the present invention, materials having the same specification are distributed to a plurality of facilities having the same specification and extracted from the plurality of facilities in a manufacturing process in which the same processing is performed. A shape feature amount extraction step for extracting shape feature amounts of the chart data from a plurality of chart data in which operation data related to the processed processing is arranged in time series; And a map creation step for creating an operation analysis map related to the shape feature amount, which is visually represented and arranged in a two-dimensional coordinate consisting of a second axis indicating the order set between each facility. A data analysis support method is provided.

  Furthermore, in order to solve the above-described problem, according to another aspect of the present invention, in a manufacturing process in which a computer is assigned to a plurality of facilities having the same specification and the same processing is performed, a plurality of facilities are provided. A shape feature amount extraction unit for extracting shape feature amounts of the chart data from a plurality of chart data in which operation data related to the processing extracted from the time series are arranged in time series; A map creation unit that creates an operation analysis map related to the shape feature amount, which is visually represented and arranged in two-dimensional coordinates composed of one axis and a second axis indicating the order set between the facilities. There is provided a computer program characterized by functioning as a data analysis support apparatus characterized by the above.

  In order to solve the above problems, according to another aspect of the present invention, in a manufacturing process in which a material having the same specification is distributed to a plurality of facilities having the same specification to a computer, A shape feature amount extraction unit for extracting shape feature amounts of the chart data from a plurality of chart data in which operation data related to the processing extracted from the time series are arranged in time series; A map creation unit for creating an operation analysis map related to the shape feature amount, which is visually represented and arranged in two-dimensional coordinates composed of one axis and a second axis indicating the order set between the facilities; A computer-readable storage medium storing a program for functioning as a data analysis support device is provided.

  As described above, according to the present invention, in order to generate an operation analysis map in which shape feature amounts calculated from a plurality of chart data are mapped, it is possible to analyze whether the cause of the trouble is due to the equipment or the operation conditions. It is possible to provide a data analysis support apparatus, a data analysis support method, a computer program, and a computer-readable storage medium that can provide the data.

It is chart data which shows the pushing force at the time of extruding the coke manufactured from the carbonization chamber of the coke oven at the time of normal operation with an extruder. It is chart data which shows the pushing force at the time of extruding the coke manufactured from the carbonization chamber of the coke oven at the time of operation trouble generation | occurrence | production with an extruder. It is explanatory drawing which shows the outline | summary of the data analysis process by the data analysis assistance apparatus which concerns on embodiment of this invention. It is a functional block diagram which shows the function structure of the data analysis assistance apparatus which concerns on the same embodiment. It is a flowchart which shows the data analysis process by the data analysis assistance apparatus which concerns on the same embodiment. It is explanatory drawing which shows an example of the operation chart data group accumulate | stored in the data storage part. It is explanatory drawing which shows the example of a change pattern of the chart data containing an operation trouble omen. It is explanatory drawing for demonstrating extraction of the base waveform which is a shape feature-value by an independent component analysis, and the weight with respect to the base waveform. It is explanatory drawing explaining calculation of the base waveform and the independent component showing the characteristic of chart data, and calculation of independent components other than the teacher data estimated based on the base waveform. It is explanatory drawing explaining the structure of an operation analysis map. It is explanatory drawing which shows an example of the operation analysis map regarding the intensity | strength of a certain base waveform. It is explanatory drawing explaining the relationship of the operation analysis map regarding the intensity | strength of a certain base waveform, and the operation analysis map regarding a certain operation condition variable. It is a block diagram which shows the hardware structural example of the data analysis assistance apparatus which concerns on the same embodiment.

  Exemplary embodiments of the present invention will be described below in detail with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, duplication description is abbreviate | omitted by attaching | subjecting the same code | symbol.

<1. Analysis of coke oven pushing force chart data>
First, referring to FIG. 1 and FIG. 2, coke which is a target for identifying the cause of the operation trouble among the operation quality troubles using the data analysis support apparatus according to the embodiment of the present invention and identifying the cause thereof An example of the operation of the furnace and the operation trouble that occurs in the coke oven will be described. In addition, FIG. 1 is chart data which shows the pushing force at the time of extruding the coke manufactured from the carbonization chamber of the coke oven at the time of normal operation with an extruder. FIG. 2 is chart data showing the pushing force when coke produced from a coking chamber of a coke oven is pushed out by an extruder when an operation trouble occurs.

  The coke oven is a high-temperature furnace that produces coke by dry distillation of coal, and a combustion chamber for heating the furnace and a carbonization chamber for generating coke (hereinafter also referred to as “kiln”) are alternately arranged horizontally. It constitutes a furnace group. When the coal put in the carbonization chamber is dry-distilled into coke, it is extruded from one side of the carbonization chamber toward the other side of the discharge destination by an extruder. At this time, if it is in a normal state, as shown in FIG. 1, after the coke is compressed by the pushing force of the extruder, the coke moves to the discharge destination. As the extruder moves in the direction of coke extrusion, the coke in the carbonization chamber decreases, so the pushing force of the extruder gradually decreases.

  On the other hand, when an operation trouble occurs in the coke oven, the coke in the carbonization chamber is clogged, and there is a clogged state where the coke cannot be pushed out normally. When such a clogged state occurs, it is necessary to stop the operation of the coke oven and deal with it manually, and productivity is reduced due to time loss and increased work load.

  As shown in FIG. 2, the pushing force of the extruder when pushing out coke in the clogged state does not move as the coke in the carbonization chamber moves, so the pushing force gradually increases as the coke is pushed out by the extruder. Thereafter, the extruder stops without pushing out the coke. The clogged state occurs when the brick furnace wall in the carbonization chamber, which was smooth during normal operation, is reduced in thickness, or when carbon is attached to the brick furnace wall, the non-smooth part expands and the extrusion load increases. To do.

  Therefore, in the present embodiment, using the data analysis support device, an operation trouble map in the coke oven is found and an operation analysis map used for specifying the cause is generated. The user uses the operation analysis map to identify a portion where the extrusion load of the coke oven kiln tends to increase, and further specifies whether the factor is in the facility or the operation condition. Below, the structure of the data analysis support apparatus which produces | generates an operation analysis map and the data analysis process which produces the operation analysis map by this are demonstrated.

<2. Data analysis processing by data analysis support device>
[2-1. Analysis flow overview]
First, based on FIG. 3, the outline | summary of the data analysis process which produces the operation analysis map by the data analysis assistance apparatus which concerns on this embodiment is demonstrated. FIG. 3 is an explanatory diagram showing an overview of data analysis processing by the data analysis support apparatus according to the present embodiment.

  The data analysis support apparatus according to the present embodiment is an apparatus that extracts a shape feature amount from operation data and creates an operation analysis map for specifying a cause of an operation trouble. Specifically, as shown in FIG. 3, the data analysis processing by the data analysis support apparatus includes the following STEP1 to STEP4. The outline of the processing of STEP1 to STEP4 is as follows. Details of each process will be described later.

STEP 1: Selection of Operation Data Teacher data for extracting the shape feature amount of the chart data is selected from the extruded chart data.
STEP 2: Feature amount extraction Independent component analysis is applied to the teacher data to calculate a base waveform and an independent component representing the strength of the base waveform, which are shape feature amounts indicating the characteristics of the chart shape.
STEP 3: Mapping of feature quantity / operating condition variables For each of the shape feature quantity and operating condition variables relating to each chart data, the time axis (first axis) and the axis relating to the order set between each facility of the manufacturing process (second An operation analysis map in which data is arranged in two-dimensional coordinates consisting of axes) is generated.
STEP4: Analysis of the operation analysis map Analyzing the operation analysis map related to the feature quantity, finding the location where the operation trouble and quality trouble occurred, and whether the cause is due to changes in the operation conditions common to all facilities, or the state of each equipment Analyze whether it is due to. In addition, an operation analysis map related to the feature value and an operation analysis map related to the operation condition variable are compared to find an operation condition related to the trouble.

  By using the data analysis support apparatus according to the present embodiment, shape feature quantities are extracted from a plurality of chart data to be analyzed, and an operation analysis map relating to the shape feature quantities is created. It is possible to analyze whether it is due to the change of the equipment or the state of each facility. Further, by comparing the operation analysis map related to the feature quantity and the operation analysis map related to the operation condition variable, it is possible to find the operation condition related to the trouble. In addition, by analyzing the chart data and creating an easy-to-understand operation analysis map, users can analyze it intuitively, making it easier to capture the status of all facilities and the overall feeling of operation over the long term. Become. Hereinafter, the functional configuration of the data analysis support apparatus and the data analysis processing performed thereby will be described in detail.

[2-2. Functional configuration of data analysis support device]
FIG. 4 shows a functional configuration of the data analysis support apparatus 100 according to the present embodiment. As shown in FIG. 4, the data analysis support apparatus 100 includes a data acquisition unit 110, a shape feature amount extraction unit 120, a map creation unit 130, and an output unit 140.

  The data acquisition unit 110 acquires operation data used as teacher data from the data storage unit 200 that stores the history of operation data. The data storage unit 200 is a storage unit that stores operation chart data for a predetermined period (for example, the latest three months or the latest one year). As shown in FIG. 4, the data storage unit 200 may be provided in a server different from the data analysis support apparatus 100 or may be provided in the data analysis support apparatus 100. The data acquisition unit 110 acquires corresponding operation data from the data storage unit 200 based on data selection information that is specified by the user and specifies operation data to be used as teacher data. The operation data acquired from the data storage unit 200 is output to the shape feature amount extraction unit 120.

  The shape feature amount extraction unit 120 is a functional unit that extracts shape feature amounts representing data features from the teacher data, and applies independent component analysis (ICA) to the teacher data to indicate the shape of the chart shape. An independent component representing the contribution of the base waveform and the base waveform in the chart, which is a feature amount, is calculated. By using independent component analysis for the extraction technique of the shape feature value of the operation chart data, the operation chart data can be expressed as a linear sum of a plurality of base waveforms and a product of weights (independent components) for the base waveforms. .

  The map creation unit 130 creates an operation analysis map that visually represents the magnitude of the data value by the shade of color for the feature amount and the operation condition variable regarding each base waveform. The operation analysis map is a map in which data such as feature quantities and operation condition variables related to each base waveform are arranged in two-dimensional coordinates including a time axis and an axis related to the order set between each facility in the manufacturing process. By arranging data in such two-dimensional coordinates, it is possible to analyze the operation state of each facility alone and to analyze the change in operation state common to all facilities. A detailed description of the method for creating and analyzing the operation analysis map will be given later. The map creation unit 130 outputs the created operation analysis map to the output unit 140.

  The output unit 140 outputs the operation analysis map created by the map creation unit 130. As the output unit 140, for example, a display device capable of displaying an operation analysis map can be used. The user analyzes the operation analysis map output from the output unit 140, finds the change in the operation state of the entire equipment or the equipment alone, and identifies the cause of the change.

[2-3. Data analysis processing]
Next, taking the diagnosis of the clogged state of the coke oven as an example, the data analysis processing by the data analysis support apparatus 100 according to the present embodiment will be described along FIGS. 3 and 5 with reference to FIGS. To do.

(STEP1: Selection of operation data)
As shown in FIG. 5, the data analysis processing by the data analysis support apparatus 100 starts by first obtaining operation chart data serving as teacher data from the data storage unit 200 by the data acquisition unit 110 (S100). The teacher data is data including a sign of an operation trouble, and is selected from the extrusion history (operation chart data) stored in the data storage unit 200 by the user.

  The operation chart data is data obtained from each kiln once or twice a day. Hereinafter, a case where operation chart data is obtained from each kiln once a day will be described as an example. For example, as shown in FIG. 6, the data storage unit 200 stores operation chart data indicating the relationship between the extrusion position of the extruder and the pushing force for each kiln for a predetermined period (for example, the latest three months or the last year). Has been. Focusing on the occurrence of clogging in a certain kiln, the user selects chart data that may contain a sign immediately before clogging in a certain kiln as teacher data. For example, when one chart data is obtained per day, six chart data from one week before the occurrence of clogging can be selected and used as teacher data.

  Immediately before clogging of the coke oven, a change as shown in FIG. 7 appears in the chart shape of the operation chart data. FIG. 7 is an explanatory diagram illustrating an example of a change pattern of chart data including an operation trouble sign. For example, as pattern A, a clogged state may occur when the peak point (the point when changing from static friction to dynamic friction in the coke cake) increases every time the coke is extruded by the extruder. In the pattern A, as shown in FIG. 7, when the operation chart data from the operation chart data n times before the clogging state is reached until the clogging state is reached, the peak point gradually increases.

  Further, for example, as pattern B, a clogged state may occur when the pushing force increases in the second half of the extrusion position every time the coke is extruded by the extruder. In the pattern B, as shown in FIG. 7, when the operation chart data from the operation chart data n times before the clogged state to the clogged state is viewed, the pushing force that has decreased as the pushing position increases. However, the pressure output does not decrease gradually, and the pressing force increases when it becomes clogged.

  Further, the pattern C may be in a clogged state when vibration appears in the middle of the chart waveform just before the clogged state is reached. In pattern C, as shown in FIG. 7, when the operation chart data from the operation chart data n times before the clogged state to the clogged state is viewed, the vibration of the chart waveform in the middle of the operation chart data is It is getting bigger gradually.

  As described above, the chart shape of the operation chart data often changes immediately before the operation trouble occurs. By selecting and analyzing such operation chart data as teacher data, it is possible to extract independent components effective for predicting operation troubles.

  From the operation chart data stored in the data storage unit 200, the user selects a plurality of cases (for example, 50 cases) for each kiln of the coke oven as teacher data. One teacher data consists of n operation chart data immediately before an operation trouble such as a clogged state occurs. The operation chart data number n is plural, and can be set to 6 when analyzing the operation chart data for one week, for example. The teacher data includes the three patterns as shown in FIG. 7 and chart data (data groups a to c shown by dotted line frames in FIG. 7) until each block in FIG. 7 reaches clogging. Use it.

  Although FIG. 7 describes the teacher data when clogging occurs, chart data that has not reached the clogged state may be included as teacher data. For example, when a rising pattern (pattern B) with a high pushing force far from the normal chart shape appears, maintenance of the furnace wall may be performed at the operator's judgment to prevent clogging. Therefore, such a pattern that requires repair of the furnace wall is defined as an abnormal waveform pattern (a waveform like the chart data one time before the occurrence of clogging trouble in FIG. 7), and the abnormal waveform pattern is reached. The chart data up to may be included in the teacher data.

  The user inputs data selection information for specifying operation chart data to be used as teacher data by an operation input device (not shown) for operating the data analysis support device 100. The data acquisition unit 110 of the data analysis support apparatus 100 that has received the data selection information acquires the corresponding operation chart data based on the data selection information, and outputs the operation chart data to the shape feature amount extraction unit 120.

(STEP2: feature extraction)
When the teacher data is selected in STEP 1 (S100) and acquired from the data storage unit 200, the shape feature amount is extracted from the operation chart data which is the teacher data by the shape feature amount extraction unit 120 (S110).

  In the present embodiment, independent component analysis (ICA) is used as a technique for extracting shape feature values of operation chart data. By using the independent component analysis, the operation chart data relating to the pushing force is obtained by multiplying the product of a plurality of base waveforms (A) and weights (independent components s (t) and extrusion times t) with respect to the base waveforms as shown in FIG. It can be expressed as a linear sum. FIG. 8 is an explanatory diagram for explaining a base waveform that is a shape feature amount by independent component analysis and extraction of weights for the base waveform. Note that FIG. 8 shows a case where it is divided into three independent components for the sake of simplicity of explanation, but an arbitrary number of components can be set and divided into base waveforms according to the number of components.

Specifically, the teacher data x of n operational chart data as the following equation 1 (t) = [x1 ( t) x2 (t) ··· xn (t)] T the base waveform (n × p mixing matrix) A and p independent components s (t) = [s1 (t) s2 (t)... Sp (t)] that are statistically independent corresponding to the weights corresponding to the base waveform. Assume a linear combination of ^T (ie, x (t) = As (t)). Note that t is the number of extrusions, and p is the number of components set by the user.

  The column elements of the matrix A correspond to the base waveform of the operation chart data, and each operation chart data as the teacher data is approximately expressed by the linear sum of the products of the respective base waveforms and independent components as described above. (The value of s (t) is specified for x (t) of each extrusion count t). From the result of this linear combination, the shape feature quantity extraction unit 120 acquires the weight for the base waveform A, that is, the independent component s (t) as the shape feature quantity for each teacher data.

  In step S110, using the operation chart data for a predetermined period, the independent component s (t) for this period is acquired. At this time, the shape feature amount extraction unit 120 is based on the base waveform (A). Independent components are also calculated for operation chart data other than teacher data for independent component analysis. For example, as shown in the upper diagram of FIG. 9, only the independent component s1 of the period used as the teacher data is acquired from the operation chart data that is the teacher data. Therefore, the shape feature quantity extraction unit 120 multiplies the chart data other than the period used as the teacher data (that is, the chart data other than the teacher data) by the inverse matrix of the base waveform (A) as shown in the lower diagram of FIG. The independent component s1 for the period for which the operation status is to be confirmed is estimated. Independent components s2 to sp other than the independent component s1 are estimated in the same manner.

(STEP3: Mapping of features and operating condition variables)
When the shape feature amount is extracted for each operation chart data in STEP 2 (S110), the map creation unit 120 creates an operation analysis map (S120). The operation analysis map expresses the magnitude of the data value with the shading of the color for the feature value or the operation condition variable regarding each base waveform. Information obtained by visualizing the magnitudes of these data values with color shading is defined as visual data. The map creation unit 120 arranges visual data on two-dimensional coordinates including a time axis and an axis related to the order set between each facility in the manufacturing process. The time axis of the operation analysis map indicates the time passage for each facility, and the change of the operation state with the passage of time can be seen for each facility. On the other hand, the axis related to the order set between the facilities in the operation analysis map indicates the predetermined order set between the facilities performing the same operation, and the change in the operation state common to the entire facility is observed. Can do.

  For example, in the case of coke oven extrusion chart data, for example, an operation analysis map as shown in FIG. 10 can be created. In FIG. 10, the vertical axis of the operation analysis map is a time axis, and the horizontal axis is an axis related to the order set between the facilities. For the time axis (vertical axis, first axis), for example, a coke extrusion cycle in each kiln can be used as the time axis of each kiln in the coke oven. Looking at the kiln having the kiln number 330, data (1, 2) for the first coke extrusion (1 cycle), data (2, 2) for the second coke extrusion (2 cycles), the third time When the coke is extruded (3 cycles), the data value changes as shown by data (3, 2). In this way, by looking at the change in the data value for each number of extrusions of the kiln, it is possible to see the effect on the coke pushing force due to the state change in the kiln (for example, the influence of the carbon adhesion amount in the kiln) The characteristics of each kiln can be grasped.

  On the other hand, for the axes (horizontal axis, second axis) related to the order set between the facilities, as a predetermined order set between the kilns of the coke oven, for example, the entire coke oven as shown in FIG. The order of extrusion between the kilns that extrude the coke can be taken. In the example of FIG. 10, the coke extrusion in each cycle is performed in the order of the kiln number 325, the kiln number 330, and the kiln number 335. For example, in the second cycle, the kiln number 325 includes data (2, 1), kiln The data value changes like data (2, 2) for the number 330 and data (2, 3) for the kiln number 335. From this change in the data value, it is possible to see the effect common to all kilns when the operating condition variables such as the amount of coke charged and the placing time are changed.

  The axis related to the order set between the facilities may be, for example, the physical arrangement order of the kilns constituting the coke oven, in addition to the order of extruding the coke. In this case, it is possible to find out the influence between physically adjacent kilns from the operation analysis map.

  The data value arranged in the operation analysis map is an independent component s (t) that is a shape feature amount or an operation condition variable. First, the operation analysis map related to the shape feature amount represents the shape feature amount, that is, the intensity of the base waveform as visual data, and is arranged in two-dimensional coordinates composed of a time axis and an axis related to the order set between the facilities. Is. For example, if the data value (independent component s (t)) representing the intensity of a certain base waveform is represented as visual data that is black as the value is high and white as the value is low, it is in a grid pattern as shown in FIG. An operation analysis map composed of a plurality of arranged visual data is generated. The visual data represents data values continuously, and the magnitude of the data values is represented by, for example, 256 types of shading. By creating an operation analysis map related to shape features in this way, the overall trend of changes in the shape of the operation chart data can be visualized with the density of visual data, which can lead to operational troubles, quality troubles, or predictors thereof. It will be possible to easily identify the equipment and operation period.

  On the other hand, the operation analysis map related to the operation condition variable represents, for example, the magnitude of data values such as the amount of coke charged and the carbonization time as visual data, and is a two-dimensional model composed of a time axis and an axis related to the order set between the facilities. It is arranged at the coordinates. The operation analysis map related to the operation condition variable can be used to identify the operation condition variable linked to the operation trouble or the quality trouble as compared with the operation analysis map related to the shape feature amount. The operation analysis map related to the operation condition variable is visualized in the same manner as the operation analysis map related to the shape feature quantity, and is as shown in the right figure of FIG. 12, for example. At this time, it is possible to compare the two operation analysis maps by creating the operation analysis map for the shape feature quantity and the operation analysis map for the operation condition variable in the same format, and the relationship between the shape feature quantity and the operation variable is easy. It is possible to find out.

(STEP4: Analysis of operation analysis map by user)
Returning to the description of FIG. 5, when the operation analysis map related to the shape feature amount and the operation analysis map related to the operation condition variable are created in step S <b> 120, the operation analysis map created from the output unit 140 is output. Using the output operation analysis map, the user specifies the operation trouble and quality trouble, or the facility and operation time in which the sign is generated, and narrows down the cause (S130). The data analysis support apparatus 100 according to the present embodiment provides an operation analysis map, and assists the user in easily specifying operation troubles, quality troubles, facilities in which a sign of the trouble occurs, and the operation time. It is a device to do.

  First, the user finds a portion where a high value of the shape feature amount is concentrated from the operation analysis map related to the shape feature amount created by the data analysis support apparatus 100, and identifies the location where the operation trouble or the quality trouble occurs. Identify. The user can determine whether the cause of the trouble depends on whether the high value of the shape feature amount is continuous in the time axis (vertical axis) direction or in the axis (horizontal axis) direction related to the order set between the facilities. Specify whether it is in an individual facility or is in the setting of operating conditions that do not depend on an individual facility.

  In the example of the analysis of the extrusion chart data of the coke oven, as described based on FIG. 10, the change for each extrusion cycle can be seen for each kiln in the time axis direction. For example, as shown in FIG. 11, when high values of shape feature values are concentrated in the time axis (vertical axis) direction representing the order of extrusion cycles, kilns having high values of shape feature values are concentrated. It can be assumed that there is a factor that causes some trouble such as deterioration of the furnace wall.

  In addition, in the direction of the axis (horizontal axis) related to the order set between the facilities, it is possible to see the influence due to the change in operating conditions common to all the kilns. For example, as shown in the left diagram of FIG. 12, the intensity of a certain base waveform, that is, an operation analysis map related to a certain shape feature amount, has a high shape feature amount in the axis (horizontal axis) direction related to the order set between the facilities. When the values are concentrated, it is considered that the deterioration of coke extrusion has occurred in a plurality of kilns in an extrusion cycle in which high values of the shape feature amount are concentrated. In this case, it can be inferred that there is a factor that causes trouble in the operating conditions changed in common to each kiln.

  In this way, the user can see in which direction the high value of the shape feature amount is concentrated in the operation analysis map related to the shape feature amount created by the data analysis support device 100, so that the kiln itself It is possible to easily identify whether there is a cause of trouble or whether there is a cause of trouble in the operating conditions common to all kilns.

  When the location of the trouble is specified by the operation analysis map related to the shape feature value, the user further compares the operation analysis map related to the shape feature value and the operation analysis map related to the operation condition variable to specify the operation condition variable related to this trouble. can do. For example, the right diagram in FIG. 12 is an operation analysis map related to the variable a, which is one of the operation condition variables. Like the operation analysis map related to the shape feature amount, the vertical axis represents the coke extrusion cycle, and the horizontal axis represents the coke. The extrusion order is shown.

  For example, when high values of shape feature values are concentrated in the extrusion order direction (horizontal axis) in the broken line frame A of the operation analysis map related to the shape feature values shown in the left diagram of FIG. In the vicinity of the extrusion cycle in the broken line frame A, an operation condition variable that is significantly different (increased or decreased) is extracted. For example, in the operation analysis map regarding the operation condition variable a in the right diagram of FIG. 12, high data values are concentrated in the vicinity of the extrusion cycle indicated by the broken line frame A (in the broken line frame B). From this, it is estimated that there is a relationship between the operation condition variable and the shape feature quantity that the value of a certain shape feature quantity increases as the data value of the operation condition variable a rises. In this way, by comparing the operation analysis map related to the shape feature quantity and the operation analysis map related to the operation condition variable, it becomes possible to estimate the operation condition related to the trouble.

  As described above, the operation analysis map creation by the data analysis support apparatus 100 according to the present embodiment and the cause analysis method of the trouble occurring in the manufacturing process using the operation analysis map have been described. With such an operation analysis map, it is possible to easily analyze whether a trouble that has occurred in the manufacturing process is caused by a malfunction of equipment or a change in operating conditions. And it becomes possible to analyze the influence related to the state of each equipment and the influence related to the change of the operation condition, and it becomes easy to find information leading to the operation improvement. In addition, by creating a visually understandable map as shown in FIGS. 11 and 12 from the shape feature amount of the chart data and the operation condition variable, the user can intuitively grasp the operation status of the manufacturing process. It becomes possible.

[2-4. Application example]
In the above description, the case where the coke oven extrusion chart data is analyzed by the data analysis support apparatus 100 according to the present embodiment has been described as an example. However, the same processing is performed by distributing the material having the same specification to a plurality of equipment having the same specification. The data analysis support apparatus 100 can also be used for analysis of manufacturing processes.

  For example, application to a manufacturing process of a semiconductor polycrystalline ingot is conceivable. In such a manufacturing process, silicon as a raw material is charged into a plurality of furnaces and melted at a high temperature, and an ingot that is a source of a wafer is generated in each furnace. The generated ingot is considered to change according to operating conditions such as the temperature of each furnace and the type of silicon used as a raw material. Therefore, based on the chart data of the ingot manufacturing process, the data analysis support apparatus 100 according to the present embodiment extracts the shape feature amount using independent component analysis with the data having a sign of the occurrence of trouble as teacher data, An operation analysis map is created that includes visual data representing the magnitude of the shape feature amount, including a time axis and an axis related to the order set between the facilities.

  The user finds facilities and periods in which high values of the shape feature amount are concentrated from the operation analysis map. Then, referring to the operation analysis map related to the operation condition variable, if the value of the operation condition variable changes greatly in the vicinity of the part where the high value of the shape feature value is concentrated, the value of the shape feature value is high. It is likely that this is a factor. In this way, the operation condition that is considered to be a factor that increases the value of the shape feature value can be found using the operation analysis map related to the operation condition variable.

  At this time, if high values of shape feature values are concentrated in the time axis direction representing the time change of each facility (here, each furnace) in the operation analysis map, operation trouble and quality trouble occur in the specific equipment. it seems to do. On the other hand, when high values of shape features are concentrated in the direction (in this case, the physical arrangement order of the furnace) related to the order set between the facilities, operational troubles and quality troubles occur between the facilities. it seems to do. In this way, depending on whether the high value of the shape feature amount appears in any axial direction in the operation analysis map, it is analyzed whether the trouble is caused by the factor of equipment failure or the factor of operation conditions It becomes possible to do.

  In addition to the manufacturing process of a semiconductor polycrystalline ingot, for example, the present invention can be applied to a process of a food manufacturing process. Specifically, it can be applied to a ripening step of aging beer in a plurality of storage tanks in a beer manufacturing process, a baking step of baking bread dough fermented in a plurality of ovens in a bread manufacturing process, and the like. it can.

<3. Hardware configuration example of data analysis support device>
Next, the hardware configuration of the data analysis support apparatus 100 according to the embodiment of the present invention will be described in detail with reference to FIG. FIG. 13 is a block diagram illustrating a hardware configuration example of the data analysis support apparatus 100 according to the embodiment of the present invention.

  The data analysis support apparatus 100 mainly includes a CPU 901, a ROM 903, and a RAM 905. The data analysis support apparatus 100 further includes a bus 907, an input device 909, an output device 911, a storage device 913, a drive 915, a connection port 917, and a communication device 919.

  The CPU 901 functions as an arithmetic processing device and a control device, and controls all or a part of the operation in the data analysis support device 100 according to various programs recorded in the ROM 903, the RAM 905, the storage device 913, or the removable recording medium 921. . The ROM 903 stores programs used by the CPU 901, calculation parameters, and the like. The RAM 905 primarily stores programs used by the CPU 901, parameters that change as appropriate during execution of the programs, and the like. These are connected to each other by a bus 907 constituted by an internal bus such as a CPU bus.

  The bus 907 is connected to an external bus such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge.

  The input device 909 is an operation unit operated by the user, such as a mouse, a keyboard, a touch panel, a button, a switch, and a lever. Further, the input device 909 may be, for example, remote control means (so-called remote control) using infrared rays or other radio waves, or may be an external connection device 923 such as a PDA corresponding to the operation of the data analysis support device 100. There may be. Furthermore, the input device 909 includes, for example, an input control circuit that generates an input signal based on information input by a user using the operation unit and outputs the input signal to the CPU 901. The user of the data analysis support apparatus 100 can input various data and instruct processing operations to the data analysis support apparatus 100 by operating the input device 909.

  The output device 911 is configured by a device that can notify the user of the acquired information visually or audibly. Examples of such devices include CRT display devices, liquid crystal display devices, plasma display devices, EL display devices and display devices such as lamps, audio output devices such as speakers and headphones, printer devices, mobile phones, and facsimiles. For example, the output device 911 outputs results obtained by various processes performed by the data analysis support device 100. Specifically, the display device displays the results obtained by the various processes performed by the data analysis support device 100 as text or images. On the other hand, the audio output device converts an audio signal composed of reproduced audio data, acoustic data, and the like into an analog signal and outputs the analog signal. In the embodiment of the present invention, the output device 911 is provided as a display device 40 separate from the data analysis support device 100.

  The storage device 913 is a data storage device configured as an example of a storage unit of the data analysis support device 100. The storage device 913 includes, for example, a magnetic storage device such as an HDD (Hard Disk Drive), a semiconductor storage device, an optical storage device, or a magneto-optical storage device. The storage device 913 stores programs executed by the CPU 901, various data, various data acquired from the outside, and the like.

  The drive 915 is a recording medium reader / writer, and is built in or externally attached to the data analysis support apparatus 100. The drive 915 reads information recorded on a removable recording medium 921 such as a mounted magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs the information to the RAM 905. The drive 915 can also write a record on a removable recording medium 921 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory. The removable recording medium 921 is, for example, a CD medium, a DVD medium, a Blu-ray medium, or the like. The removable recording medium 921 may be a CompactFlash (registered trademark) (CompactFlash: CF), a flash memory, an SD memory card (Secure Digital memory card), or the like. Further, the removable recording medium 921 may be, for example, an IC card (Integrated Circuit card) on which a non-contact IC chip is mounted, an electronic device, or the like.

  The connection port 917 is a port for directly connecting a device to the data analysis support apparatus 100. Examples of the connection port 917 include a USB (Universal Serial Bus) port, an IEEE 1394 port, a SCSI (Small Computer System Interface) port, and an RS-232C port. By connecting the external connection device 923 to the connection port 917, the data analysis support apparatus 100 acquires various data directly from the external connection device 923 or provides various data to the external connection device 923.

  The communication device 919 is a communication interface including a communication device for connecting to the communication network 925, for example. The communication device 919 is, for example, a communication card for wired or wireless LAN (Local Area Network), Bluetooth (registered trademark), or WUSB (Wireless USB). The communication device 919 may be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various communication. The communication device 919 can transmit and receive signals and the like according to a predetermined protocol such as TCP / IP, for example, with the Internet and other communication devices. The communication network 925 connected to the communication device 919 is configured by a wired or wireless network, and may be, for example, the Internet, a home LAN, infrared communication, radio wave communication, satellite communication, or the like. .

  Heretofore, an example of the hardware configuration capable of realizing the function of the data analysis support apparatus 100 according to the embodiment of the present invention has been shown. Each component described above may be configured using a general-purpose member, or may be configured by hardware specialized for the function of each component. Therefore, it is possible to change the hardware configuration to be used as appropriate according to the technical level at the time of carrying out this embodiment.

  The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention pertains can come up with various changes or modifications within the scope of the technical idea described in the claims. Of course, it is understood that these also belong to the technical scope of the present invention.

  For example, in the above embodiment, the independent feature analysis is used for the extraction of the shape feature amount by the shape feature amount extraction unit 120, but the present invention is not limited to such an example. For example, the shape feature amount may be extracted using principal component analysis, wavelet, PLS, or the like.

  In the above embodiment, the map creation unit 130 creates an operation analysis map based on visual data representing the magnitude of data values in 256 different shades. However, the present invention is not limited to this example. The operation analysis map may be created by representing the size by color data.

DESCRIPTION OF SYMBOLS 100 Data analysis support apparatus 110 Data acquisition part 120 Shape feature-value extraction part 130 Map preparation part 140 Output part 200 Data storage part

Claims (8)

In a manufacturing process in which materials of the same specification are distributed to a plurality of equipment of the same specification and the same processing is performed, the chart is obtained from a plurality of chart data in which operation data related to the processing extracted from the plurality of equipment is arranged in time series A shape feature amount extraction unit for extracting shape feature amounts of data;
The shape feature amount is visually represented and arranged in two-dimensional coordinates composed of a first axis relating to the time elapse of processing in each facility and a second axis indicating the order set between the facilities, A map creation unit for creating an operation analysis map for the shape feature amount;
A data analysis support apparatus comprising:   The map creation unit is configured to obtain a value of a plurality of operation condition variables representing an operation condition of the operation process associated with the chart data between the first axis and the facilities regarding the time passage of the process in each facility. 2. The data according to claim 1, further comprising creating an operation analysis map relating to an operation condition variable, which is visually represented and arranged in a two-dimensional coordinate including the second axis indicating a set order. 3. Analysis support device.   The data analysis support apparatus according to claim 2, wherein the order set between the facilities is a use order of the facilities.   The data analysis support apparatus according to claim 2, wherein the order set between the facilities is a physical arrangement order of the facilities.   5. The data analysis support apparatus according to claim 1, wherein the shape feature amount extraction unit extracts the shape feature amount by using independent component analysis. In a manufacturing process in which materials of the same specification are distributed to a plurality of equipment of the same specification and the same processing is performed, the chart is obtained from a plurality of chart data in which operation data related to the processing extracted from the plurality of equipment is arranged in time series A shape feature extraction step for extracting the shape feature of the data;
The shape feature amount is visually represented and arranged in two-dimensional coordinates composed of a first axis relating to the time elapse of processing in each facility and a second axis indicating the order set between the facilities, A map creation step for creating an operation analysis map for the shape feature,
A data analysis support method characterized by comprising: Computer
In a manufacturing process in which materials of the same specification are distributed to a plurality of equipment of the same specification and the same processing is performed, the chart is obtained from a plurality of chart data in which operation data related to the processing extracted from the plurality of equipment is arranged in time series A shape feature amount extraction unit for extracting shape feature amounts of data;
The shape feature amount is visually represented and arranged in two-dimensional coordinates composed of a first axis relating to the time elapse of processing in each facility and a second axis indicating the order set between the facilities, A map creation unit for creating an operation analysis map for the shape feature amount;
A computer program for causing a data analysis support apparatus to function. On the computer,
In a manufacturing process in which materials of the same specification are distributed to a plurality of equipment of the same specification and the same processing is performed, the chart is obtained from a plurality of chart data in which operation data related to the processing extracted from the plurality of equipment is arranged in time series A shape feature amount extraction unit for extracting shape feature amounts of data;
The shape feature amount is visually represented and arranged in two-dimensional coordinates composed of a first axis relating to the time elapse of processing in each facility and a second axis indicating the order set between the facilities, A map creation unit for creating an operation analysis map for the shape feature amount;
A computer-readable storage medium storing a program for functioning as a data analysis support device.