JP2009070052A - Monitoring device and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a monitoring device for, even if it is supposed that there are monitor items, assuming a huge number of featured values and measurement data, grasping the tendency (temporal transition) of the monitor item data, such as a bird's-eye view. <P>SOLUTION: This monitoring device is provided with a featured value storage part 1 for storing acquired monitor item data (featured values and measurement data) and time information, by associating them with each other; a reference value calculation part 2 for calculating a reference value, based on the past monitor item data; a deviation degree calculating part 3 for calculating the degree of deviation of the monitor item data, from the calculated reference value; a color stage determining part 4 for deciding a color, corresponding to the deviation degree from the reference value calculated by the degree of deviation calculating part; and a color map display part 6 for creating and outputting a color map, in which the determined colors are arranged at the corresponding positions of a coordinate system that correspond to the monitor item data (ordinate axis) and the time axis (abscissa axis). <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a monitoring device and a program for facility equipment constituting a manufacturing process.

  2. Description of the Related Art Conventionally, there is an equipment failure diagnosis device that uses a PLC input / output signal to diagnose whether there is an abnormality in an equipment whose operation is controlled by the PLC. As an example of this equipment failure diagnosis apparatus, there is an invention disclosed in Patent Document 1. The present invention is premised on a production system in which various equipments start operation at independent timings and repeat a series of operations in various production processes. In such a production system, the equipment failure diagnosis apparatus records state changes of sensors and contacts in time series, and performs abnormality diagnosis (failure diagnosis) based on this. That is, in the conventional failure diagnosis, a reference pattern of time-series state changes at normal time is created in advance, and normality / abnormality of the equipment is determined by comparison with this.

In addition, in manufacturing processes such as the surface mounting process of substrates, by monitoring the quality characteristics (inspection characteristics), intermediate quality characteristics, materials, equipment, and production environment of products manufactured by executing the process, There are also diagnostic methods that detect process abnormalities that affect product quality. This is based on the premise that if the equipment that makes up the manufacturing process operates normally, the product to be manufactured will also be a non-defective product. If a defective product is produced, some abnormality or failure will occur in the equipment. It is estimated that this has occurred.
Japanese Patent No. 3277247

  The conventional failure determination disclosed in Patent Literature 1 and the like is performed by generating a reference pattern of time-series state change by performing feature extraction processing when the production system is operating normally, and at the time of actual abnormality diagnosis, A feature extraction process similar to that at the time of pattern creation is performed, and it is determined that there is a failure (abnormality) when a preset threshold value with respect to the reference pattern is exceeded. As described above, since normality and abnormality are clearly defined and separated, notification is made when an abnormality occurs, and the production system is stopped, the following problems occur.

  That is, when trying to perform the above abnormality diagnosis in an actual production system, a large number of monitoring item data (On / Off signals, etc.) of hundreds to thousands are monitored, and when and where an abnormality has occurred is detected. There is a need to. Similarly, when monitoring for abnormalities based on products, for example, the surface mounting process consists of three processes: “solder printing”, “component mounting”, and “reflow”. There are hundreds of monitoring items, including dozens of inspection items per process.

  Thus, it is necessary to set a threshold value for performing normal / abnormal determination before starting monitoring for monitoring items based on a large amount of monitoring target data, and the setting process is complicated. Furthermore, equipment that has an abnormality / failure not only suddenly (suddenly) breaks down at a certain moment, but in many cases, its state gradually changes to a direction in which an abnormality / failure occurs. However, there are many cases in which the operation is abnormal in the normal range, but at some point, the threshold is exceeded and a complete failure / abnormality occurs. In such cases, by detecting the signs and making adjustments in advance, it is possible to suppress the production of defective products in the event of a failure, so there is a demand to quickly detect changes in the state (condition) of equipment. However, it is practically difficult to monitor a large number of inspection items as described above.

  In the present invention, when monitoring equipment, either directly or indirectly, even if there are a large number of monitoring items such as feature value values and measurement data, the monitoring item data tendencies (temporal changes) are displayed. It is an object of the present invention to provide a monitoring device and a program that can be grasped from a bird's-eye view and can provide information for estimating the occurrence of abnormality or failure of equipment.

  The monitoring apparatus according to the present invention is (1) a monitoring apparatus for equipment constituting a manufacturing process, and is obtained by measuring process data obtained during operation of the manufacturing process and products manufactured by the manufacturing process. Storage means for storing at least one of the measured data and the feature value extracted based on the data as monitoring item data, and storing the acquired monitoring item data in association with time information, and past monitoring Means for obtaining a reference value determined based on item data; a deviation degree calculating means for calculating a deviation degree from the reference value of the monitoring item data stored in the storage means from the reference value; and a deviation degree calculation. Color determining means for determining the color corresponding to the degree of deviation from the reference value obtained by the means, and the color determined by the color determining means for the axis of the monitoring item data Create a colormap disposed in corresponding positions of the coordinate system of the two axes consisting of a time axis, and output means for outputting, and configured with a.

  When storing the feature value in the storage means, the feature value calculation may be performed on the acquired process data or measurement data, or the feature value obtained by another device may be acquired. You may make it do. The means for obtaining the reference value may be calculated based on the monitoring item data accumulated by the accumulation means as shown below, or may be obtained by directly inputting the reference value. In the embodiment, the vertical axis is the monitoring item data and the horizontal axis is the time axis (time axis), but the arrangement may be reversed. The time axis is not limited to date / time information or the like as in the embodiment, and may be arranged in time series. Therefore, for example, in the case of measurement data obtained from a product or a feature amount based on the measurement data, for example, the record numbers are given in the order in which they are manufactured, and the records are arranged in the order of the record numbers. You may do it. In other words, the time information associated with the monitoring item data by the storage means may be information for arranging in time series on the time axis, and includes information for specifying the manufacturing order. The color determination unit corresponds to the color stage determination unit 4 in the embodiment.

  According to the present invention, since one axis is a monitoring item and the other axis is a time series, and a color map in which colors corresponding to the degree of deviation from the reference value of the monitoring item data are arranged is output, the user can By looking at the map, it is possible to intuitively recognize the state of change in the degree of deviation from the past to the present. Therefore, it can be determined that the color map is normal when the color map is configured with a color (in the embodiment, “green”) associated with a degree of deviation from the reference value of 0 or small. In addition, when the color deviation from the initial reference value was 0 or small, when the color corresponding to the color deviation from a certain point started to be output, something abnormal / failure was caused to the equipment from that point. It can be presumed that this occurred (being generated). And since the change of the state of an installation apparatus appears by the change of the color on a color map, it can detect easily and reliably.

  Furthermore, even when the abnormality determination threshold value is not necessarily given from the outside, the present invention can capture a difference in tendency by comparison with past data. That is, since the process of determining the threshold value that has been required in the past and setting the threshold value is not necessary, operability is improved. In particular, the effect becomes more remarkable as the number of monitoring item data increases.

  (2) The monitoring apparatus according to claim 1, further comprising reference value calculation means for calculating the reference value based on past monitoring item data stored in the storage means.

  (3) The color determining means assigns the degree of deviation from the reference value of the monitoring item data to colors divided into n stages. For example, an upper limit and a lower limit are set in a range in which it is apparently abnormal when the monitoring item data exceeds this value. When the degree of deviation from the acquired reference value exceeds the set upper limit value or lower limit value, the end color divided into n stages can be determined. By setting the upper limit value and the lower limit value, it is possible to create a color map by paying attention to the degree of deviation from the reference value between them. Therefore, it is possible to detect without missing the initial stage of abnormality / failure. If the degree of deviation from the reference value is so large that the upper limit value or the lower limit value is exceeded, there is no difference in the occurrence of an abnormality or failure. No problem.

  (4) When displaying a color map, a grouping unit that groups monitoring item data so that the same color is displayed together is provided, and the output unit arranges the monitoring item data on the axis of the monitoring item data. The order may be arranged for each monitoring item data grouped by the grouping means. The grouping means corresponds to the group determination unit 5 in the embodiment.

  By providing the grouping means, the color map output by the output means is displayed together with the same color, so that the user can easily find it and find it without missing the color change.

  (6) The program of the present invention extracts a computer based on process data obtained during operation of a manufacturing process, measurement data obtained by measuring a product manufactured by the manufacturing process, and those data. At least one of the obtained feature value values is set as monitoring item data, storage means for storing the acquired monitoring item data in association with time information, and a reference value determined based on past monitoring item data is acquired Means for calculating the degree of deviation from the reference value of the monitoring item data stored in the storage means from the reference value, and a color corresponding to the degree of deviation from the reference value obtained by the deviation degree calculating means. The color determining means to be determined, and the color determined by the color determining means to the corresponding position in the two-axis coordinate system composed of the monitoring item data axis and the time axis Create a colormap location, and a program for operating an output means for outputting as.

  In the present invention, when directly or indirectly monitoring equipment, even if there are an enormous number of monitoring items such as feature values and measurement data, the monitoring consists of a monitoring item data axis and a time axis. By outputting a color map indicating the degree of deviation of the item data in color, the user can grasp the trend (temporal transition) of the monitoring item data from the color change of the color map.

  FIG. 1 shows a preferred embodiment of the present invention. In the present embodiment, a feature amount accumulation unit 1, a reference value calculation unit 2, a deviation degree calculation unit 3, a color stage determination unit 4, a group determination unit 5, and a color map display unit 6 are provided. .

  The feature amount storage unit 1 stores feature amount values and the like that are acquired monitoring items. In the present embodiment, as the monitoring item, not only the feature amount value (including the normalized value) obtained by extracting the feature amount with respect to various data (measurement values) acquired from the measurement device or the inspection device, The acquired data (process data / measurement value) itself is also included. A feature amount is obtained from data obtained for a certain item within a certain period of time, obtained from data of a plurality of items obtained simultaneously, data of a plurality of related items generated at different times, etc. is there. In addition, there are various feature amounts to be extracted, such as average, maximum value, minimum value, and variance. In addition, as a feature quantity obtained from data of a plurality of related items generated at different times, for example, a certain signal of equipment is turned ON / OFF (exceeding a threshold value), and other related control signals are turned ON. / OFF (time beyond threshold).

  The feature amount value can be obtained by extracting the feature amount using a feature amount calculation formula set in advance based on a measurement value or the like acquired from an external measurement device (not shown). The feature amount accumulating unit 1 may have a function of calculating the feature amount, calculate the feature amount value itself based on the acquired measurement value, etc., and store and hold the feature amount value. The value may be acquired and stored.

  Further, in the present embodiment, the feature amount storage unit 1 registers time information and attribute information in association with the feature amount value as information for specifying the feature amount value. An example of the data structure at the time of registration is as shown in FIG. The time information is time series information indicating the measurement time point, and includes, for example, a combination of date and time. Note that the time information is not limited to the date and time, and may be only the time, or the record number or the like, as long as the monitoring items can be finally displayed in time series. The attribute information defines attributes of data (features), and identifies differences in devices, measurement values, and the like. In the present embodiment, the number is zero or more (preferably at least one). That is, attribute information is not an essential element. In the feature quantity column, a feature quantity value (including a measured value) identified by the attribute information is stored.

  FIG. 3 shows an example of specific data stored in the feature amount accumulation unit 1. In this example, data based on surface state measurement of a product manufactured by a surface mounting process is stored. Here, the solder volume (volume / area) at a preset point is used as a measurement value (inspection value). The attribute information includes information for specifying a measurement point, information for specifying inspection contents (items), and the like.

The reference value calculation unit 2 calculates a reference value based on past data stored in the feature amount accumulation unit 1. For example, as shown in the following equation, the reference value is calculated by obtaining a past average value for a predetermined period (one hour ago, one day ago, one week ago, etc.). Of course, the reference value may be obtained by a calculation method other than the average value, or may be a value given from the outside set by the administrator.

Here, N is the number of data existing during a certain period. The subscript j uniquely identifies the feature amount specified by the attribute information. For example, the subscript j specifies a measurement point on the substrate surface. Therefore, for example, the reference value α _j means the reference value (average value of past data) for the j-th feature quantity, and d _j-past (i) is the past data of the j-th feature quantity. The i-th data during the reference value calculation period is meant.

The deviation degree calculation unit 3 calculates a deviation degree c _j from the current data dj-current reference value. Specifically, it can be calculated based on the following formula.

This arithmetic expression divides a variable by a reference value. (1) If it is not deviated from the reference value, “1” (dj−current = α _j → c _j (i) = 1) is obtained. Also, (2) when the value of the current variable is larger than the reference value (dj-current> α _j ), the deviation degree c _j becomes a value larger than 1, conversely, (3) When the value is smaller than the reference value (dj-current <α _j ), the deviation degree c _j is a value smaller than 1.

As another calculation formula, as shown in the following formula, a reference value may be subtracted from a variable and divided. In this case, all variables are centered on zero.

When this calculation formula is used, (1) When it is not deviated from the reference value, “0” (dj−current = α _j → c _j (i) = 0) is obtained. Also, (2) when the current variable value is larger than the reference value (dj-current> α _j ), the deviation degree c _j is a value (positive) greater than 0, and conversely, (3) the current value Is smaller than the reference value (dj-current <α _j ), the deviation degree c _j is a value smaller than 0 (negative).

  Furthermore, in this embodiment, the deviation degree calculation unit 3 performs processing for calculating upper and lower limits of the degree of deviation from the reference value. That is, as the degree of deviation from the reference value increases, there is a high possibility that an abnormality / failure has occurred. And, if it deviates from a reference value above a certain level, it does not change the phenomenon that an abnormality / failure has occurred, so in this embodiment, upper and lower limit values of the degree of deviation from each reference value are set. I did it.

  Specifically, when an arithmetic expression that is 1 when not deviating from the reference value is used, the upper limit is 2, the lower limit is 0, and the operation is 0 when not deviating from the reference value. When the equation is used, the upper limit can be +1 and the lower limit can be -1. Of course, the present invention is not limited to this, and the administrator may set specific numerical values from outside.

The color stage determination unit 4 determines a color corresponding to the degree of deviation from the reference value displayed on the display device, based on the control signal c _j with the degree of deviation equipment for each acquired monitoring item. That is, in the present embodiment, the acquired current variable values (feature value values, measured values, etc.) are not output as they are, but the deviation degrees from the reference values of the variables obtained by the deviation degree calculation unit 3 are output. In addition, the display mode is displayed as a color map using a color corresponding to the degree of deviation from the reference value.

Therefore, when the deviation degree from the reference value is displayed separately in N colors, as shown in the legend of FIG. 4, dj-current = α corresponding to the case classification (1) for obtaining the deviation degree described above. _If there is no variation that includes _j (including a certain range), the middle color (the color that corresponds to (or is assigned to) Color ₈ because it is color-coded in 17 levels in FIG. 4). If c _j corresponds to the above (2), it is assigned to any color from Color ₉ to Color _{16 in} FIG. 4 according to the degree of deviation. Further, when c _j corresponds to the above (3), it is assigned to any color from Color ₇ to Color _{0 in} FIG. 4 according to the degree of deviation.

The color assigned to Color _{0 to} Color ₁₆ can be adjusted to a change in hue, for example. As an example, Color _{8 at} the center is green, and Color ₉ to Color ₁₆ is a warm-colored array, and Color ₁₆ having the largest degree of deviation from the reference value is red. Further, Color ₀ Color ₀ is made larger off degree since most reference value as an array of cold colors from Color ₇ is blue. This is preferable because the degree of deviation can be intuitively understood from the color. Instead of using the hue in this way, the lightness may be used, and Color ₀ may be white (black), Color ₁₆ may be black (white), and an appropriate gray may be assigned between them. Alternatively, the saturation may be used to sequentially change the saturation for a certain color, and further, it can be combined as appropriate, and assignment of other colors is not prevented.

In the color stage determination unit 4, a specific algorithm for determining the color stage shown on the color map based on the deviation degree c _j from the reference value obtained by the deviation degree calculation unit 3 is as follows. Can do. Here, as shown in FIG. 4, it is assumed that the color is divided into 17 stages.

As a first method, a value of “degree of deviation from the reference value” exceeding the upper and lower limits is set in the colors Color ₀ and Color ₁₆ at both ends, and the degree of deviation between the upper and lower limits is assigned from Color ₁ to Color _15. There is. Specifically, if the lower limit value is Clw and the upper limit value is Cup,
When C _j is greater than or equal to Cup, the display color is Color ₁₆
When C _j is less than or equal to Clw, the display color is Color ₀
age,
Further, when the interval from Clw to Cup is divided into 15 equal parts and C _j is within the 15th divided range, the display color is the nth stage color (n is an integer from 1 to 15). Color _n
And

Further, as a second method, there is a color calculation method starting from the lower limit of the value of “degree of deviation from the reference value”. First,
When Cj is greater than or equal to Cup, the display color is Color ₁₆
When Cj is less than or equal to Clw, the display color is Color ₀
Is the same as above. Then, the following equation is used to determine Color _n (n is an integer of 1 to 15).

Furthermore, Color ₁ to Color ₁₅ may be set to an arbitrary width instead of being equally divided. In that case, a table or the like that associates the degree of deviation corresponding to each color is created, and the color stage determination unit 4 can determine the color by referring to the table when the degree of deviation is obtained.

  The color map display unit 6 displays a color map composed of an orthogonal coordinate system in which the vertical axis indicates monitoring items (features and the like) and the horizontal axis indicates time. In other words, the color map display unit 6 acquires color information (for example, the value of n) corresponding to the degree of deviation from the reference value for each variable (feature amount or the like) determined by the color stage determination unit 4 to obtain the color The color of the cell M at the corresponding intersection on the map (orthogonal coordinate system) is displayed in the acquired color. An example of this color map is as shown in FIG.

  In FIG. 5, for convenience of explanation, the case of 10 variables and 15 hours is displayed, and the color stages are also 5 stages (red: high deviation degree, yellow: + little deviation degree, green: no deviation, light blue: -out. Small degree, blue: minus degree of deviation). And the color map display part 6 displays the legend H for grasping | ascertaining a color step on the margin of the color map which consists of a rectangular coordinate system. From the relationship shown in the drawing, each color is drawn in an appropriate pattern in each square M and legend on the color map.

  As is clear from FIG. 5, the displayed color map displays the degree of deviation from the reference value for each monitoring item in chronological order. Therefore, the color map display unit 6 also has a function of storing and holding the time-series data. In the present embodiment, the current state is compared with the past state and displayed in a color corresponding to the obtained degree of loss, so the current state tendency (change in degree from the reference value) can be intuitively determined. Understandable. For example, in the example shown in FIG. 5, it can be estimated that the manufacturing process was also operating normally without any deviation from the reference value (less) at the beginning. Since the degree of deviation of C1, C3, and C5 has gradually increased from time “12” onward, it can be estimated that an abnormality has occurred (is occurring) somewhere in the equipment constituting the manufacturing process. Then, the location where an abnormality has occurred can be predicted to some extent from the variables C1, C3, and C5 whose degree of loss has increased, and it is possible to quickly perform maintenance and adjustment.

  In FIG. 5, for convenience of explanation, the color stage is set to five stages. However, in actuality, it is preferable to classify the color stages more finely and to make a number of color stages. By doing so, it is possible to extract a variable whose degree of deviation from the reference value (the amount of deviation) gradually increases before it becomes too large, and before a complete abnormality occurs, that is, normal It is possible to detect a variable that is within the range but becomes abnormal in the near future if left as it is.

Furthermore, since the degree of deviation from the reference value is recognized by color coding, even if the vertical width (thickness) of the cell M for displaying one variable C _j is reduced, the color change Can be recognized. That is, a large number of variables can be displayed on the color map at a time, and a variable in which an abnormality has occurred (beginning to occur) can be detected reliably.

  Some types of monitoring item data may vary to some extent even in a normal state. In such a case, the color has a large degree of deviation from the beginning of monitoring, or the color changes periodically. In such a case, it is possible to determine whether or not the variation is within a normal range from the color change history information.

  By the way, in the display example of FIG. 5, there are C2, C4 having no color change (still green with almost no degree of deviation) between C1, C3, and C5 whose colors have changed. When viewed in the axial direction, the colors are displayed sparsely. Thus, when there are mixed color squares having different degrees of deviation from the reference value, there are problems that it is difficult to identify the color change and it is difficult to recognize which variable color has changed. In particular, as the number of variables increases, the width of one square in the height direction becomes narrower, so the problem becomes more prominent.

  Therefore, the group determination unit 5 selects a group that is best grouped so that the same color is displayed together from a predefined grouping method (arrangement order). The color map display unit 6 displays a color map according to the selected arrangement order.

  In this grouping method, for example, grouping can be performed according to the number of colors of cells M on the color map. The determination target at this time is, for example, one column (the column at time 15 in FIG. 5) indicating the degree of deviation from the latest reference value. Of course, multiple columns may be targeted. Various methods can be employed, such as dividing the same colors into groups, and arranging the different colors in the order of the legend, or increasing the number of groups constituting a smaller number. When arranged in the order of the legend, abnormal variables are gathered at both the upper and lower ends, so that it is only necessary to pay particular attention to that part, so that abnormality detection can be easily performed. In general, there are many cases where the degree of deviation from the reference value is 0 or small, and the larger the absolute value of the degree of deviation, the smaller the number of existence, and the smaller the number constituting the same color. When arranged on the upper side, the more abnormal variables are gathered on the upper side, it is easy to monitor. In this way, the color map shown in FIG. 5 simply arranged in the order of the predetermined variable number (j) is grouped in the same color as shown in FIG.

  In addition, instead of focusing on the latest vertical line in this way, the whole can be determined, focusing on one color, and grouping can be made based on one with more or less colors. In the example of FIG. 5, for example, focusing on green, it is possible to arrange in order from the smallest number of green.

  Furthermore, when an abnormality occurs in the equipment, the degree of deviation of the related variable from the reference value increases. Thus, by displaying the same color as a group as described above, it is easy to estimate which variables are related to each other. For example, if C1 shown in FIGS. 5 and 6 is the squeegee speed of the solder printing machine, C3 is the solder printing volume for the part A, and C5 is the solder printing volume for the part B, the squeegee speed of the C1 printing machine is the part A , B can be assumed to have an influence on the solder printing.

  When there are a plurality of predefined grouping methods, grouping is performed by each method, a method having the best color gathering condition is selected, grouped, and displayed. In addition, when performing this grouping, each variable may be handled as an individual unit. However, some grouping is performed in advance, and grouping (subgrouping) is performed for each group. It can also be done.

  In FIG. 7, it is determined that there is an abnormality / failure at time 15 shown in FIG. 6, and the countermeasures such as maintenance are implemented. After that, the degree of deviation from the reference value is small (0) and the countermeasures are effective. It shows that there was. In this way, by displaying in time series, it is possible to easily and quickly determine whether or not the countermeasure is effective, and it is possible to easily determine whether or not it is necessary to implement the countermeasure again.

It is a block diagram which shows suitable one Embodiment of the equipment diagnostic apparatus of this invention. 3 is a diagram illustrating an example of a data structure of data stored in a feature amount storage unit 1. FIG. It is a figure which shows the specific example of the data structure of the data accumulate | stored in the feature-value accumulation | storage part 1. FIG. It is a figure explaining the color corresponding to the degree of deviation from a standard value. It is a figure which shows an example of a color map. It is a figure which shows an example of a color map. It is a figure which shows an example of a color map.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Feature-value accumulation | storage part 2 Reference value calculation part 3 Deviation degree calculation part 4 Color stage determination part 5 Group determination part 6 Color map display part

Claims (5)

A monitoring device for equipment constituting a manufacturing process,
At least one of process data obtained during operation of the manufacturing process, measurement data obtained by measuring a product manufactured by the manufacturing process, and a feature value extracted based on the data And storage means for storing the acquired monitoring item data in association with time information,
Means for obtaining a reference value determined based on past monitoring item data;
A deviation degree calculating means for calculating a deviation degree from the reference value of the monitoring item data stored in the storage means from the reference value;
Color determining means for determining a color corresponding to the degree of deviation from the reference value obtained by the deviation degree calculating means;
An output unit that creates and outputs a color map in which the color determined by the color determination unit is arranged at a corresponding position in a two-axis coordinate system including an axis of monitoring item data and a time axis;
Monitoring device.   The monitoring apparatus according to claim 1, further comprising reference value calculation means for calculating the reference value based on past monitoring item data stored in the storage means. The color determining means assigns the degree of deviation from the reference value of the monitoring item data to the colors divided into n stages, and the degree of deviation from the acquired reference value exceeds a set upper limit value or lower limit value. In this case, the monitoring apparatus according to claim 1 or 2, wherein the color is determined as an end color divided into n stages. When displaying the color map, it has a grouping means for grouping the monitoring item data so that the same color is displayed together,
The output means arranges the arrangement order of the monitoring item data in the axis of the monitoring item data for each monitoring item data grouped by the grouping means,
The monitoring device according to any one of claims 1 to 3, wherein Computer
At least one of process data obtained during operation of the manufacturing process, measurement data obtained by measuring a product manufactured by the manufacturing process, and a feature value extracted based on the data Storage means for storing monitoring item data in association with time information,
Means for obtaining a reference value determined based on past monitoring item data;
A deviation degree calculating means for calculating a deviation degree from the reference value of the monitoring item data stored in the storage means from the reference value;
Color determining means for determining a color corresponding to the degree of deviation from the reference value obtained by the degree of deviation calculation means;
An output unit that creates and outputs a color map in which the color determined by the color determination unit is arranged at a corresponding position in a two-axis coordinate system including an axis of monitoring item data and a time axis;
Program to function as.

Images