JP7238476B2 - Facility management support device, facility management support method, program, and computer-readable recording medium - Google Patents

Description

The present invention relates to a facility management support device, a facility management support method, a program, and a computer-readable recording medium that support state management of a plurality of units constituting a facility used in the manufacturing industry.

Equipment used in the manufacturing industry is regularly maintained so that stable operations can be performed. In addition to regular maintenance, additional maintenance is performed when equipment exhibits abnormal trends.

For example, in a coke oven, which is an example of equipment used in the manufacturing industry, in order to maintain the furnace body, the interior of the oven is inspected using a coking chamber diagnosis and repair device, oven width measurement, etc. according to a maintenance schedule. Exceptionally, if an abnormal extrusion load waveform occurs during coke extrusion, there is a risk that the kiln will be in an abnormal state such as uneven or rough surface of the furnace wall, narrowing of the kiln mouth, etc. Furnace inspection and maintenance will be additionally carried out. A decision as to whether or not to perform an unscheduled furnace inspection or maintenance is made, for example, by focusing on the maximum value of the extrusion load waveform (maximum extrusion load) within a range of at most three cycles.

Here, Patent Literature 1 discloses a method for determining abnormality in the carbonization chamber. In the method described in Patent Document 1, first, when the generated coke is extruded by the extrusion ram of the extruder for each carbonization chamber of the coke oven, the load of the motor that drives the extrusion ram with respect to the extrusion position in the carbonization chamber of the extrusion ram From the load current trend obtained by measuring the current, the ideal load current trend is obtained in advance in consideration of the operating state of the coke oven. Then, the deviation of the load current for each extrusion position between the actual load current trend and the ideal load current trend after the completion of coke extrusion in the coke chamber to be measured is obtained, and the abnormality of the coking chamber is determined from the obtained deviation.

JP 2017-171791 A

Elizaveta Levina; Peter Bickel (2001). "The EarthMover's istance is the Mallows Distance: Some Insights from Statistics". Proceedings of ICCV 2001. Vancouver, Canada: 251‐256.

Immediately after the carbonization chamber is repaired, the load may increase while the carbon is removed, or the load may decrease after the furnace wall is smoothed, so it will take some time for the extrusion load to settle down . However, the period varies depending on the kiln, and it is not easy to select data for setting the ideal load trend as in the method described in Patent Document 1 above. In addition, since the extrudability also changes depending on the state of carbon adhesion, the narrowing of the furnace wall, etc., setting the ideal load trend only once as in the method described in Patent Document 1 above will not increase the abnormality of the carbonization chamber. Accurate detection is not possible.

Therefore, the present invention has been made in view of the above problems, and the object of the present invention is to prevent the occurrence of abnormalities in the units even when the states of the units that make up the facility change unstably. To provide a new and improved equipment management support device, equipment management support method, program, and computer-readable recording medium capable of providing information capable of easily detecting

In order to solve the above problems, according to one aspect of the present invention, one unit out of a plurality of units constituting equipment used in the manufacturing industry is set as an evaluation target, and the evaluation target obtained in a plurality of different periods A histogram conversion processing unit that converts the observed value data group of the unit into a multidimensional histogram with variables of at least the spatio-temporal data of the equipment and the observed values that change in relation to the spatio-temporal data, and a plurality of histograms Provided is a facility management support device comprising: an evaluation index calculation unit that calculates an evaluation index representing a difference; and an information generation unit that generates state information representing changes in the state of a unit to be evaluated based on the evaluation index. be.

The evaluation index calculation unit may calculate the evaluation index using Earth Mover's Distance.

Also, the evaluation index calculation unit may calculate the evaluation index using the χ2 distance.

Alternatively, the evaluation index calculation unit may calculate the evaluation index using a weighted χ2 distance that considers the weight calculated based on the distribution of observation values for spatio-temporal data for a certain period.

In addition, the evaluation index calculation unit combines the Earth Mover's Distance calculated based on the distribution of observed values for spatio-temporal data for a certain period with either the χ2 distance or the weighted χ2 distance considering the weight. may be used to calculate the evaluation index.

The facility management support apparatus may further include an abnormality degree calculation unit that calculates a value obtained by assigning a code representing a change characteristic of the evaluation index to the evaluation index as an abnormality degree representing the degree of abnormality of the unit.

The facility management support device further includes a priority determination unit that determines the priority of units that require inspection in descending order of the degree of abnormality calculated for each of the plurality of units. Instead of or together with the state information, notification information for notifying the operator of the high priority unit determined by the priority determining unit may be generated.

The information generator performs threshold judgment on the information in which the evaluation index is arranged in chronological order or the information in which the degree of abnormality is arranged in chronological order, based on the threshold set in advance for detecting the occurrence of trouble in the unit. Information that predicts the occurrence may be generated.

Further, in order to solve the above problems, according to another aspect of the present invention, one unit out of a plurality of units constituting equipment used in the manufacturing industry is evaluated, and is acquired in a plurality of different periods a histogram conversion processing step of converting the observed value data group of the unit to be evaluated into a multidimensional histogram with variables of at least the spatiotemporal data of the equipment and the observed values that change in relation to the spatiotemporal data; and an information generation step of generating state information representing changes in the state of the unit to be evaluated based on the evaluation index. is provided.

Furthermore, in order to solve the above problems, according to another aspect of the present invention, a computer is evaluated in a plurality of different periods with one unit out of a plurality of units constituting equipment used in the manufacturing industry as an evaluation target. A histogram conversion processing unit that converts the acquired observation value data group of the unit to be evaluated into a multidimensional histogram with variables of at least the spatio-temporal data of the equipment and the observed values that change in relation to the spatio-temporal data. and an evaluation index calculation unit that calculates an evaluation index representing the difference between the plurality of histograms, and an information generation unit that generates state information representing changes in the state of the unit to be evaluated based on the evaluation index. A program that functions as a management support device is provided.

Further, in order to solve the above problems, according to another aspect of the present invention, a computer evaluates one unit out of a plurality of units constituting equipment used in the manufacturing industry, and evaluates it in a plurality of different periods. A histogram conversion processing unit that converts the acquired observation value data group of the unit to be evaluated into a multidimensional histogram with variables of at least the spatio-temporal data of the equipment and the observed values that change in relation to the spatio-temporal data. and an evaluation index calculation unit that calculates an evaluation index representing the difference between the plurality of histograms, and an information generation unit that generates state information representing changes in the state of the unit to be evaluated based on the evaluation index. A computer-readable recording medium recording a program functioning as a management support device is provided.

As described above, according to the present invention, it is possible to provide information that makes it possible to easily detect the occurrence of an abnormality in a unit even when the state of the unit that constitutes the facility changes unstably.

1 is a functional block diagram showing the functional configuration of a facility management support device according to a first embodiment of the present invention; FIG. It is a flowchart which shows the facility management support method which concerns on the same embodiment. FIG. 4 is an explanatory diagram showing data showing the tendency of extrusion load from one month to two months ago and its histogram; FIG. 4 is an explanatory diagram showing data showing the tendency of extrusion load from the latest to one month ago and its histogram. It is an explanatory view explaining Earth Mover's Distance (EMD). It is explanatory drawing explaining the abnormality degree calculated by the abnormality degree calculation part. FIG. 5 is a diagram for explaining a case of focusing on the maximum value of the pushing load and a case of focusing on the peak position of the pushing load in how to assign a sign to the evaluation index. FIG. 10 is an explanatory diagram for explaining the χ2 distance; It is explanatory drawing explaining the abnormality degree calculated by the abnormality degree calculation part. FIG. 4 is an explanatory diagram showing an example of a histogram; It is a block diagram which shows the hardware configuration example of the facility management support apparatus which concerns on the same embodiment. As an example, it is a graph showing information in which EMDs are arranged in chronological order. As an example, it is a graph showing information in which the degrees of abnormality are arranged in chronological order. As an example, it is a graph showing temporal changes in index values for the EMD calculated by the facility management support method according to the first embodiment and the χ2 distance calculated based on the above equation (4). FIG. 15 is a graph showing temporal changes in index values for the χ2 distance and the weighted χ2 distance shown in FIG. 14 as an example.

Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. In the present specification and drawings, constituent elements having substantially the same functional configuration are denoted by the same reference numerals, thereby omitting redundant description.

In the following, as an example, a case where the facility management support device of the present invention is applied to manage the states of a plurality of kilns constituting a coke oven for the maintenance of the coke oven body will be described. The equipment management support device of the present invention can also be applied to equipment for managing the operation, quality, equipment status, etc. described below, for example.

(operation management)
・Coke oven: Detection of deterioration of combustion state using the surface temperature of coke cake, flue temperature of combustion chamber, and furnace wall temperature chart of coking chamber ・Continuous casting equipment: Deterioration of poor solidification state using thermocouple temperature chart in continuous casting mold detection (quality control)
・Hot rolling equipment, cold rolling equipment: Detection of quality deterioration tendency using data on the number of occurrences of defects in coil pieces Detection of deterioration in quality and plating equipment: Detection of deterioration in quality using a data chart of the degree of alloying for each coil position in a continuous hot-dip galvanizing line (CGL) (equipment status management)
・Raw materials: equipment abnormality detection using conveyor motor current in iron ore coal yard

<1. First Embodiment>
[1-1. Facility management support device]
First, referring to FIG. 1, the functional configuration of a facility management support device 100 according to the first embodiment of the present invention will be described. FIG. 1 is a functional block diagram showing the functional configuration of a facility management support device 100 according to this embodiment.

As shown in FIG. 1, the equipment management support device 100 according to the present embodiment includes a histogram conversion processing unit 110, an evaluation index calculation unit 120, an abnormality calculation unit 130, a priority determination unit 140, and an information generation unit. 150 and an output unit 160 .

The histogram conversion processing unit 110 sets one unit of a plurality of units constituting a facility as an evaluation target, and converts observation value data groups of the evaluation target unit acquired in a plurality of different periods into at least a spatio-temporal Data and spatio-temporal data are converted into multi-dimensional histograms with variables of observed values. The spatio-temporal data is data indicating at least one of position and time, and may be one-dimensional information (linear position information) or two-dimensional information (planar position information). Moreover, the observed value that changes in relation to the spatio-temporal data is not limited to one observed value, and may be a plurality of observed values.

For example, the histogram conversion processing unit 110 converts the extrusion load data including the extrusion load for each extrusion position acquired at the time of coke extrusion for each kiln constituting the coke oven into a plurality of axes including at least the extrusion position and the extrusion load. Convert each to a multi-dimensional histogram expressed in a coordinate system. Extrusion position is spatio-temporal data, and extrusion load is one of the observations that varies in relation to the spatio-temporal data. The extrusion load data is accumulated in the operation performance data storage unit 200 as operation performance data. The histogram conversion processing unit 110 converts the waveform data of the pushing load for each pushing position into a histogram using a plurality of pieces of pushing load data acquired in a predetermined period to obtain a feature quantity. Such histograms are created for each of a plurality of different time periods. The histogram conversion processing section 110 outputs the created histogram to the evaluation index calculation section 120 .

The evaluation index calculator 120 calculates an evaluation index representing the difference between the histograms of two different periods from the histograms created by the histogram conversion processor 110 . This evaluation index makes it possible to capture changes in the extrusion load distribution at each extrusion position in the kiln to be evaluated. In this embodiment, Earth Mover's Distance (EMD) is used as an evaluation index for evaluating the difference between histograms in two different periods. The evaluation index calculator 120 outputs the calculated evaluation index representing the difference between the histograms of the two different periods to at least one of the abnormality calculator 130 and the information generator 150 .

The degree-of-abnormality calculator 130 calculates the degree of abnormality representing the degree of abnormality of a unit that constitutes the facility. For example, the information generator 150 calculates the degree of abnormality representing the degree of abnormality of each kiln of the coke oven. In this embodiment, the degree of anomaly is represented by assigning a code indicating whether the condition of the unit (for example, kiln) has deteriorated or improved to the evaluation index calculated by the evaluation index calculation unit 120. This is due to the fact that it may not be possible to determine whether the kiln condition has deteriorated or improved only from changes in the waveform characteristics of the evaluation index. Therefore, the evaluation index calculation unit 120 calculates an index that takes into consideration the maximum value of the extrusion load (i.e., evaluation of the coke cake movement start) or the change in the extrusion position when the extrusion load takes the maximum value (i.e., evaluation of the peak position). The degree of anomaly is calculated by using as a code given to the evaluation index calculated by. Abnormality degree calculation section 130 outputs the calculated abnormality degree to at least one of priority determination section 140 and information generation section 150 .

The priority determination unit 140 determines the priority of the units requiring inspection based on the degrees of abnormality calculated for each of the plurality of units. For example, the priority determining unit 140 determines the priority of kilns that require inspection based on the degree of abnormality calculated for each of the multiple kilns of the coke oven. Priorities may be set, for example, in multiple kilns that make up one furnace bank. The priority determining unit 140 determines the priority of kiln inspection in descending order of the degree of abnormality, assuming that the higher the degree of abnormality, the higher the possibility of trouble occurrence. Priority determining section 140 outputs the determined priority to information generating section 150 .

The information generation unit 150 generates state information representing changes in the state of the evaluation target unit. The state information represents, for example, a change in at least one of the state of the facility, the state of operation in the facility, or the state of the quality of products manufactured using the facility.

For example, the information generation unit 150 generates kiln state information representing the state of the kiln based on the evaluation index as the state information. The kiln state information includes, for example, information in which evaluation indices are arranged in chronological order, information in which degrees of abnormality are arranged in chronological order, and the like. These pieces of information represent how the condition of the kiln changes over time. In addition, the information generation unit 150 generates information or the degree of abnormality in which the evaluation indices are arranged in time series based on a preset threshold value for detecting that the possibility of trouble such as rupture or clogging has increased. are arranged in chronological order, threshold determination may be performed to generate information predicting trouble occurrence.

Furthermore, the information generation unit 150 generates notification information for notifying the operator of a unit with a high priority based on the inspection priority of the unit (for example, the kiln) determined by the priority determination unit 140. good. The information generation unit 150 may generate, for example, notification information for notifying a predetermined number of kilns (for example, top five kilns) in descending order of priority. The notification information includes at least information that can identify the kiln (for example, kiln number), and may also include kiln status information of the notified kiln. Information generated by the information generator 150 is output to the output unit 160 .

The output unit 160 is a functional unit for notifying the operator of information generated by the information generation unit 150 . The output unit 160 is, for example, a display that visually presents information, and may include a speaker that outputs audio. Based on the information presented via the output unit 160, the operator can grasp the state of the units and recognize the units that require inspection or maintenance.

[1-2. Facility management support method]
A facility management support method by the facility management support device 100 according to the present embodiment will be described with reference to FIGS. 2 to 7. FIG. FIG. 2 is a flow chart showing the facility management support method according to this embodiment. 3 and 4 are explanatory diagrams showing data showing trends in extrusion load at different times and their histograms. FIG. 5 is an explanatory diagram for explaining the Earth Mover's Distance (EMD). FIG. 6 is an explanatory diagram illustrating the degree of abnormality calculated by the degree-of-abnormality calculation unit 130. As shown in FIG. FIG. 7 is a diagram for explaining a case of focusing on the maximum value of the pushing load and a case of focusing on the peak position of the pushing load in how to assign a sign to the evaluation index.

(Data acquisition: S100, histogram conversion processing: S110)
When the operation result data for a predetermined period is input as the observed value data group from the operation result data storage unit 200 (S100), the facility management support device 100 converts the pushing load data included in the operation result data by the histogram conversion processing unit 110. is converted into a histogram (S110).

The extrusion load data converted into a histogram is arranged in chronological order for each kiln, which is a unit that constitutes the facility, and is divided into predetermined periods. It is desirable that the length of the period for dividing the extrusion load data should be the same, and the number of data should be substantially the same. Although the periods of each push load data group are set so as not to overlap, some overlap is allowed. For example, when handling the extrusion load data of the operation performance data for the last two months, the extrusion load data for the period from the latest to one month ago and the extrusion load data for the period from one month to two months ago and two extrusion load data groups are created. The histogram conversion processing unit 110 generates a two-dimensional histogram using the push position and the push load as variables from the push load data group for each period.

Extrusion load data groups and histograms generated by converting from the extrusion load data groups are exemplified in FIGS. 3 and 4. FIG. FIG. 3 shows information on extrusion load data for the period from one month to two months ago, and FIG. 4 shows information on extrusion load data for the period from the latest to one month ago. 3 and 4, the horizontal axis represents the position in the longitudinal direction of the kiln, and the vertical axis represents the time. The lighter the color, the higher the extrusion load. 3 and 4 show histograms generated by converting the extrusion load data group. A histogram represents the frequency of occurrence (data distribution) according to the extrusion position and the extrusion load.

From FIGS. 3 and 4, by representing the pushing load data group for a predetermined period with a histogram, it becomes easier to grasp the tendency of the pushing position and the pushing load in each period. For example, as shown in the lower part of FIG. 3, during the period from 1 month to 2 months ago, there is no significant variation in the value of the extrusion load at each extrusion position. However, as shown in the lower part of FIG. 4, in the period from the latest to the previous month, there is a tendency for the extrusion load to increase after the start of extrusion.

(Evaluation Index Calculation Processing: S120)
After the histogram of each period is generated by the histogram conversion processing unit 110, the evaluation index calculation unit 120 evaluates the difference between the two histograms (S120). When kiln anomalies begin to occur, variations in the extrusion load may appear at specific positions in the extrusion load waveform. By looking at the difference between the histograms for two different periods, it is possible to grasp such a variation phenomenon of the extrusion load.

In this embodiment, Earth Mover's Distance (EMD) is used as an evaluation index for evaluating the difference between histograms in two different periods (see Non-Patent Document 1). Earth Mover's Distance represents the distance between a plurality of distributions given by a set of "features" and "weights", and the greater the distance, the greater the difference between distributions. In this embodiment, the histogram generated in step S110 is used as the distribution to be evaluated, and the extrusion position and extrusion load, which are variables of each histogram, are used as the "feature amount", and the bins indicating the frequency of occurrence (frequency) of each are set to " used as a weight. Earth Mover's Distance is an index suitable for comparison of high-dimensional information, and can appropriately evaluate differences in histograms against outliers.

In a little more detail, Earth Mover's Distance is based on the idea of one optimization problem, the "transportation problem." For example, when evaluating the difference between histogram P and histogram Q shown in FIG. Consider transshipment of luggage so that That is, in FIG. 5, at each location j of histogram Q, the amount of packages with a determined weight (i.e., bin frequency of histogram Q when compared; dashed histogram) is stored from histogram P into the warehouse. I think. At this time, in order to transport all the packages in the histogram P to the histogram Q, which packages should be transported to where is most efficient. It is an index for evaluating the difference between P and histogram Q.

Therefore, first, the work Work (P, Q) required for the transportation is defined as in the following formula (1), and the transportation amount of the cargo (location i the amount of each package transported from j to location j). Note that the transportation cost for moving a package (bin) at location i in histogram P to location j in histogram Q is denoted by d _ij , and the transportation amount (bin frequency) is denoted by f _ij .

As for the transportation cost d _ij , Euclidean distance is used in many cases, and the Euclidean distance is used in this embodiment as well. Here, it is assumed that the transportation cost d _ij is given in advance. Then, a linear programming problem with the following equation (2) as the objective function is solved to find the transportation amount f _*ij when the work amount Work(P, Q) is minimum.

Then, using the obtained f _*ij , the value EMD(P, Q) of the Earth Mover's Distance can be obtained from the following equation (3).

The EMD(P, Q) obtained here is considered to be the optimal value for the transport problem when transporting packages (bins) of histogram P to histogram Q, as described above. This EMD(P, Q) can be regarded as the degree of similarity between the two histograms P, Q, and the difference between the two histograms P, Q can be evaluated from the value of EMD(P, Q). It can be said that the smaller the value of EMD(P, Q) is, the more the histogram P and the histogram Q have similar distributions, and the less the distribution changes.

The evaluation index calculation unit 120 calculates an evaluation index (that is, EMD (P, Q)) representing the difference between the two histograms from the above equation (3), and at least one of the abnormality calculation unit 130 and the information generation unit 150 output to one or the other.

(Abnormality degree calculation process: S130)
Next, the degree-of-abnormality calculator 130 calculates the degree of abnormality representing the degree of abnormality of the unit (for example, the kiln) (S130). In this embodiment, the degree of abnormality is represented by adding a code indicating whether the state of the unit has deteriorated or improved to the evaluation index calculated by the evaluation index calculation unit 120 . This is due to the fact that it may not be possible to determine whether the condition of the unit has deteriorated or improved based only on changes in the waveform characteristics of the evaluation index. Therefore, the degree-of-abnormality calculation unit 130 determines the maximum value of the pushing load, which is one of the observed values (that is, the evaluation of the start of coke cake movement) or the pushing position when the pushing load takes the maximum value (that is, the peak position). evaluation) is used as a code given to the evaluation index calculated in step S120 to calculate the degree of abnormality. That is, as shown in FIG. 6, the degree of anomaly can be said to be the EMD (P, Q) calculated in step S120 with a sign representing the trend of change in the state of the unit. In the following, a positive (+) sign indicates that the condition of the unit is deteriorating, and a negative (-) sign indicates that the condition of the unit is improving. do.

As a method of assigning a sign to the evaluation index, for example, when focusing on the maximum value of the extrusion load, as shown in FIG. 7, the maximum value of the extrusion load (peak The median value for value A) may be compared over two different time periods and the sign of the metric determined based on the results. For example, consider extrusion load data for a period from one month to two months ago (period T2 in FIG. 7) and extrusion load data for a period from the latest to one month ago (period T1 in FIG. 7). . In this case, first, the abnormality degree calculation unit 130 extracts the maximum value for each pushing load data in the period from the latest to one month ago, calculates the median value of those values, and from one month ago The maximum value is extracted for each extrusion load data in the period up to two months ago, and the median value of those values is calculated. Then, the degree-of-abnormality calculation unit 130 determines the magnitude of these median values.

A positive sign is given to the evaluation index when the median value in the period from the latest to one month ago is larger than the median value in the period from one month to two months ago. On the other hand, if the median value for the period from the latest to 1 month ago is smaller than the median value for the period from 1 month to 2 months ago, a negative sign is given to the evaluation index. . In this embodiment, data on the extrusion load is obtained for each day, and the maximum value of the extrusion load is obtained and accumulated for each day. It can be calculated using the data accumulated in this way.

When focusing on the peak position of the extrusion load as a method of assigning a sign to the evaluation index, the peak position of the extrusion load in each histogram obtained for each extrusion ( The median value for the peak position value B) in FIG. 7 may be compared over two different time periods and the sign of the metric determined based on the results. For example, consider extrusion load data for a period from one month to two months ago (period T2 in FIG. 7) and extrusion load data for a period from the latest to one month ago (period T1 in FIG. 7). . In this case, first, the abnormality degree calculation unit 130 extracts the peak position for each pushing load data in the period from the latest to one month ago, calculates the median value of those values, and from one month ago The peak position is extracted for each extrusion load data two months before, and the median value of those values is calculated. Then, the degree-of-abnormality calculation unit 130 determines changes in these median values.

If the median peak position in the period from the latest to 1 month ago is moving to the kiln outlet side (i.e., the median peak position in the period from 1 month ago to 2 months ago is greater than ), the metric is given a positive sign. On the other hand, if the median peak position in the period from the latest to 1 month ago is moving to the extruder side (i.e., the median peak position in the period from 1 month to 2 months ago is less than ), a negative sign is given to the evaluation index. In the present embodiment, data on the extrusion load is obtained for each day, and the peak position of the extrusion load is specified and accumulated for each day. can be calculated using the data accumulated in this way.

In this way, by assigning a code indicating the tendency of change in the state of the unit to the evaluation index, it becomes possible to more appropriately detect the occurrence of an abnormality in the unit.

(Confirmation process: S140)
After finishing the processing of step S130, the equipment management support device 100 determines whether or not the processing of steps S110 to S130 has been performed for all units to be evaluated (S140). For example, in the example of coke ovens, the kilns to be evaluated may be all kilns that make up one furnace bank. If it is determined in step S140 that there is an unprocessed unit, the processes of steps S110 to S130 are repeatedly executed until all units to be evaluated are processed (step S140; No). On the other hand, if it is determined in step S140 that all the units have been processed (step S140; Yes), the processing from step S150 onwards is executed.

(Priority determination process: S150)
When the processing of steps S110 to S130 is completed for all the units to be evaluated, the priority determining unit 140 selects the units requiring inspection based on the degree of abnormality calculated for each of the plurality of units in step S130. is determined (S150). For example, in the example of a coke oven, priorities may be set for multiple kilns, eg, forming a furnace bank. The priority determining unit 140 determines the priority of inspection of the units in descending order of the degree of abnormality, assuming that the higher the degree of abnormality, the higher the possibility of trouble occurrence.

(Output processing: S160)
When the priority of unit inspection is determined in step S150, the information generator 150 generates notification information for notifying the operator of the unit with the higher priority. The output unit 160 notifies the worker of the notification information generated by the information generation unit 150 . For example, in the example of the coke oven, the notification information notifies the operator of the kiln number of the kiln with high priority for kiln inspection. Based on the notification information, the operator can grasp the kilns that should be preferentially inspected or maintained, and can take necessary actions at an early stage.

The facility management support method according to the present embodiment has been described above. By using the facility management support method according to the present embodiment, it is possible to perform analysis while sequentially changing the observation value data of a plurality of different periods as the evaluation range. In other words, instead of evaluating against a preset trend, by changing the observation value data for a predetermined period to be evaluated and evaluating it, the units that make up the facility may change unstably. However, it is possible to catch an abnormality of the unit. In the example of a coke oven, this allows for a highly accurate prediction of kiln anomalies such as clogs or holes. As a result, it becomes possible to take appropriate countermeasures against kiln abnormalities at an early stage, thereby preventing the occurrence of out-of-operation kilns and stabilizing operations.

<2. Second Embodiment>
Next, a facility management support device according to a second embodiment of the present invention will be described with reference to FIGS. 8 to 10. FIG. Compared with the facility management support apparatus 100 according to the first embodiment, the facility management support apparatus according to the present embodiment uses Earth Mover's Distance (EMD) as an evaluation index for evaluating the difference between histograms in two different periods. ) is replaced by the χ2 distance.

The configuration of the equipment management support device according to this embodiment is the same as the functional configuration of the equipment management support device 100 shown in FIG. Therefore, the equipment management support device according to the present embodiment will also be described using the same reference numerals as the equipment management support device 100 of the first embodiment shown in FIG. omitted. Also, the flow of the facility management support method is the same as the flow chart shown in FIG. The facility management support method according to this embodiment will be described below with reference to FIG.

[2-1. Facility management support method]
(Data acquisition: S100, histogram conversion processing: S110)
In the facility management support method according to the present embodiment, first, when operation performance data for a predetermined period is input as an observed value data group from the operation performance data storage unit 200 to the facility management support device 100 (S100), the histogram conversion processing unit 110 converts the extrusion load data included in the operational performance data into a histogram (S110). Since steps S100 and S110 may be performed in the same manner as in the first embodiment, detailed description is omitted here. Histograms as shown in FIGS. 3 and 4 are obtained by the processing in step S110.

(Evaluation Index Calculation Processing: S120)
After the histogram of each period is generated by the histogram conversion processing unit 110, the evaluation index calculation unit 120 evaluates the difference between the two histograms (S120). When kiln anomalies begin to occur, variations in the extrusion load may appear at specific positions in the extrusion load waveform. By looking at the difference between the histograms for two different periods, it is possible to grasp such a variation phenomenon of the extrusion load.

In this embodiment, the χ2 distance is used as an evaluation index for evaluating the difference between histograms for two different periods. The χ2 distance is an index similar to the χ2 statistic used in the test of independence and the like, and is used when similarity comparison of histograms is performed, like Earth Mover's Distance. The χ2 distance is represented by the following formula (4). Also, FIG. 8 shows an explanatory diagram for explaining the χ2 distance. Note that i represents the location in histogram P and histogram Q.

In the χ2 distance, for two histograms P and Q to be compared, if the frequency of each bin is 0, the difference between the bins is not calculated, and as shown in FIG. If at least one of the frequencies is not 0, the square value of the bin difference is calculated as shown in the above formula (4), and the square value is divided by the average value of the bin numbers of P and Q Let the sum of the values be the χ2 distance. The evaluation index calculation unit 120 calculates the evaluation index (that is, the χ2 distance) representing the difference between the two histograms from the above equation (4), and outputs it to at least one of the abnormality calculation unit 130 and the information generation unit 150. do.

(Abnormality degree calculation process: S130)
Next, the degree-of-abnormality calculator 130 calculates the degree of abnormality representing the degree of abnormality of the unit (for example, the kiln) (S130). In the present embodiment, as in the first embodiment, the degree of anomaly is given to the evaluation index calculated by the evaluation index calculation unit 120 by adding a code indicating whether the state of the unit has deteriorated or improved. show. This is due to the fact that it may not be possible to determine whether the condition of the unit has deteriorated or improved based only on changes in the waveform characteristics of the evaluation index. Therefore, the degree-of-abnormality calculation unit 130 determines the maximum value of the pushing load, which is one of the observed values (that is, the evaluation of the start of coke cake movement) or the pushing position when the pushing load takes the maximum value (that is, the peak position). evaluation) is used as a code given to the evaluation index calculated in step S120 to calculate the degree of abnormality. That is, as shown in FIG. 9, the degree of anomaly can be said to be the evaluation index (χ2 distance) calculated in step S120 with a sign representing the tendency of change in the state of the unit. In the following, a positive (+) sign indicates that the condition of the unit is deteriorating, and a negative (-) sign indicates that the condition of the unit is improving. do.

As for how to give a sign to the evaluation index, for example, when focusing on the maximum value of the extrusion load, in histograms of two different periods, the evaluation index is based on the results of comparing the median value of the extrusion load in each histogram. may determine the sign of Alternatively, when focusing on the peak position of the extrusion load as a way of assigning a sign to the evaluation index, in histograms of two different periods, based on the result of comparing the median value of the peak position of the extrusion load in each histogram , may determine the sign of the evaluation index. The method of giving such an evaluation index may be performed in the same manner as in the first embodiment. In this way, by assigning a code indicating the tendency of change in the state of the unit to the evaluation index, it becomes possible to more appropriately detect the occurrence of an abnormality in the unit.

(Confirmation process: S140)
After finishing the processing of step S130, the equipment management support device 100 determines whether or not the processing of steps S110 to S130 has been performed for all units to be evaluated (S140). The process of step S140 may be performed in the same manner as in the first embodiment. For example, in the example of coke ovens, the kilns to be evaluated may be all kilns that make up one furnace bank. If it is determined in step S140 that there is an unprocessed unit, the processes of steps S110 to S130 are repeatedly executed until all units to be evaluated are processed (step S140; No). On the other hand, if it is determined in step S140 that all the units have been processed (step S140; Yes), the processing from step S150 onwards is executed.

(Priority determination process: S150)
When the processing of steps S110 to S130 is completed for all the units to be evaluated, the priority determining unit 140 selects the units requiring inspection based on the degree of abnormality calculated for each of the plurality of units in step S130. is determined (S150). The process of step S150 may be performed in the same manner as in the first embodiment. For example, in the example of a coke oven, priorities may be set within multiple kilns, eg, forming a furnace bank. The priority determining unit 140 determines the priority of inspection of the units in descending order of the degree of abnormality, assuming that the higher the degree of abnormality, the higher the possibility of trouble occurrence.

When the priority of unit inspection is determined in step S150, the information generator 150 generates notification information for notifying the operator of the unit with the higher priority. The output unit 160 notifies the worker of the notification information generated by the information generation unit 150 . For example, in the example of the coke oven, the notification information notifies the operator of the kiln number of the kiln with high priority for kiln inspection. Based on the notification information, the operator can grasp the kilns that should be preferentially inspected or maintained, and can take necessary actions at an early stage.

[2-2. Modification]
For example, in the coke oven example, the extrusion load waveform is characterized by the possible distribution of extrusion load values, as shown in FIG. The tendency is that the load distribution varies in a large value range on the extruder side (PS; Pusher Side), and the load distribution varies in a small value range on the coke discharge side (CS; Coke Side). changes, and the possible range of the extrusion load varies depending on the extrusion position.

Therefore, in the calculation of the χ2 distance, the influence of changes in bins that can be taken as extrusion load values with low frequency is greatly evaluated, and the influence of changes in bins that can be taken with high frequency is underestimated. Make changes more sensitive. As a result, for example, in FIG. 10, it is important to see whether the behavior of coke cake at the start of extrusion is good or bad, and it is possible to sensitively grasp the tendency of variation in the extrusion load near the peak of the extrusion load (region C). can be done. In addition, in Fig. 10, it is important to understand whether the behavior of the coke cake in the middle stage of extrusion is good or bad, and the tendency of the extrusion load when the peak position of the extrusion load moves to the coke discharge side can be grasped with good sensitivity. You can also Specifically, it can be seen that as the extrusion load in region D in FIG.

Specifically, the weighted .chi.2-distance is obtained in which the weight _wi for each bin is taken into consideration in the above formula (4) for calculating the .chi.2-distance. The weighted χ2 distance is represented by the following formula (5).

Here, as shown in the following formula (6), the weight _wi is obtained by accumulating a two-dimensional histogram of the extrusion load during a certain period (for example, when the extrusion load is stable after repair, etc.). It may be set by taking the reciprocal of the bin number _Xi for each bin position. If the bin number _Xi is 0, 1 is given.

Alternatively, as in the following equation (7), the value obtained by dividing the number of bins X _i by the maximum number of bins X _Max of the entire histogram may be subtracted from 1 and used as the weight _wi .

In this way, by using the weighted χ2 distance, the impact of changes in bins that can be taken as observed values with low frequency is greatly evaluated, and the impact of changes in bins that can be taken with high frequency is evaluated less. , it is possible to more sensitively capture changes in the distribution of observed values.

The facility management support method according to the present embodiment has been described above. By using the facility management support method according to the present embodiment, it is possible to perform analysis while sequentially changing the observation value data of a plurality of different periods as the evaluation range. In other words, instead of evaluating against a preset trend, by changing the observation value data for a predetermined period to be evaluated and evaluating it, the units that make up the facility may change unstably. However, it is possible to catch an abnormality of the unit. In the example of a coke oven, this allows for a highly accurate prediction of kiln anomalies such as clogs or holes. As a result, it becomes possible to take appropriate countermeasures against kiln abnormalities at an early stage, thereby preventing the occurrence of out-of-operation kilns and stabilizing operations.

In addition, in this embodiment, by using the χ2 distance as an evaluation index for evaluating the difference between histograms in two different periods, it is possible to capture changes in observed values with good sensitivity.

As an evaluation index for evaluating the difference between the histograms of two different periods, two values, the Earth Mover's Distance and either the χ2 distance or the weighted χ2 distance considering the weight, are combined. values may be used. For example, two average values of the χ2 distance or weighted χ2 distance used in this embodiment and the Earth Mover's Distance (EMD) may be used. Alternatively, it is conceivable to switch between the χ2 distance or the weighted χ2 distance and the EMD as an evaluation index. In this case, for example, based on using the χ2 distance as an evaluation index, it may be determined whether to continue to use the χ2 distance as an evaluation index or to use EMD as an evaluation index based on the evaluation of the difference in histograms. . Specifically, when the χ2 distance increases sharply, the evaluation index is switched to the EMD value, and it is confirmed whether the EMD value has a similar increasing trend, and the validity of the variation in the distribution difference is confirmed. By evaluating the

In this way, by using a combination of the χ2 distance or weighted χ2 distance, which captures changes in the distribution difference with high sensitivity, and the highly robust Earth Mover's Distance (EMD), changes in the situation of the unit can be detected more effectively. It can be captured accurately.

<3. Hardware configuration example>
The hardware configuration of the equipment management support device 100 according to this embodiment will be described in detail below with reference to FIG. 11 . FIG. 11 is a block diagram showing a hardware configuration example of the equipment management support device 100 according to the embodiment of the present invention.

The equipment management support device 100 mainly includes a CPU 901 , a ROM 903 and a RAM 905 . The equipment management 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 part of the operations in the facility management support device 100 according to various programs recorded in the ROM 903, RAM 905, storage device 913, or removable recording medium 921. . A ROM 903 stores programs, calculation parameters, and the like used by the CPU 901 . The RAM 905 temporarily stores programs used by the CPU 901, parameters that change as appropriate during execution of the programs, and the like. These are interconnected by a bus 907 comprising 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 operation means operated by a user, such as a mouse, keyboard, touch panel, button, switch, and lever. The input device 909 may be, for example, remote control means (so-called remote controller) using infrared rays or other radio waves, or an external connection device 923 such as a PDA corresponding to the operation of the equipment management support device 100. There may be. Further, the input device 909 is composed of, for example, an input control circuit that generates an input signal based on information input by the user using the operation means described above and outputs the signal to the CPU 901 . By operating the input device 909, the user of the facility management support apparatus 100 can input various data to the facility management support apparatus 100 and instruct processing operations.

The output device 911 is configured by a device capable of visually or audibly notifying the user of the acquired information. Such devices include display devices such as CRT display devices, liquid crystal display devices, plasma display devices, EL display devices and lamps, audio output devices such as speakers and headphones, printer devices, mobile phones, and facsimiles. The output device 911 outputs, for example, results obtained by various processes performed by the facility management support device 100 . Specifically, the display device displays the results obtained by various processes performed by the facility management support device 100 in text or image. On the other hand, the audio output device converts an audio signal including reproduced audio data, acoustic data, etc. into an analog signal and outputs the analog signal.

The storage device 913 is a data storage device configured as an example of a storage unit of the facility management support device 100 . The storage device 913 is configured by, for example, a magnetic storage device such as a 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, and various data obtained from the outside.

The drive 915 is a recording medium reader/writer and is built in or externally attached to the equipment management 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 is also capable of writing records to a removable recording medium 921 such as a mounted magnetic disk, optical disk, magneto-optical disk, or semiconductor memory. The removable recording medium 921 is, for example, a CD medium, a DVD medium, a Blu-ray (registered trademark) medium, or the like. Also, 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. Also, the removable recording medium 921 may be, for example, an IC card (Integrated Circuit card) equipped with a contactless IC chip, an electronic device, or the like.

A connection port 917 is a port for directly connecting a device to the facility management support device 100 . Examples of the connection port 917 include a USB (Universal Serial Bus) port, IEEE1394 port, SCSI (Small Computer System Interface) port, RS-232C port, and the like. By connecting the external connection device 923 to the connection port 917 , the facility management support device 100 directly acquires various data from the external connection device 923 and provides various data to the external connection device 923 .

The communication device 919 is, for example, a communication interface configured with a communication device or the like for connecting to the communication network 925 . 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). Further, the communication device 919 may be a router for optical communication, a router for ADSL (Asymmetric Digital Subscriber Line), a modem for various types of communication, or the like. This communication device 919 can, for example, transmit and receive signals and the like to and from the Internet and other communication devices in accordance with a predetermined protocol such as TCP/IP. A communication network 925 connected to the communication device 919 is configured by a wired or wireless network or the like, and may be, for example, the Internet, home LAN, infrared communication, radio wave communication, satellite communication, or the like. .

An example of the hardware configuration capable of realizing the functions of the facility management support device 100 according to the embodiment of the present invention has been described above. Each component described above may be configured using general-purpose members, or may be configured by hardware specialized for the function of each component. Therefore, it is possible to appropriately change the hardware configuration to be used according to the technical level at which the present embodiment is implemented.

Regarding the Earth Mover's Distance and abnormal values calculated by the facility management support method according to the first embodiment of the present invention, it was confirmed whether there was a relationship with the kiln state of the coke oven. FIG. 12 is information in which the Earth Mover's Distance is arranged in chronological order, and FIG. 13 is information in which the degree of abnormality is arranged in chronological order. Once a day, the operation performance data (extrusion load data) for the last two months is acquired. Histograms generated from extrusion load data up to 1 month prior were compared. Then, the Earth Mover's Distance was calculated from the above equation (2), a sign was further assigned to the Earth Mover's Distance, and an abnormal value was calculated. The sign was given based on the maximum extrusion load.

In the example of FIG. 12, rupture occurred after the Earth Mover's Distance increased. That is, it can be said that rupture prediction is possible by observing an increasing tendency of Earth Mover's Distance. In addition, in the example of FIG. 13, clogging of coke occurred after the abnormal value increased. Similarly, in the case of abnormal values, it can be said that the stagnation can be predicted by observing the increasing trend of abnormal values. Thus, by monitoring changes in Earth Mover's Distance or abnormal values and making threshold determinations, it is possible to prevent the kiln from going out of operation due to troubles such as rupture or clogging.

In addition, whether or not the χ2 distance or the weighted χ2 distance and the abnormal value calculated by the facility management support method according to the second embodiment of the present invention are related to the kiln state of the coke oven was confirmed. FIG. 14 shows temporal changes in index values for the EMD calculated by the facility management support method according to the first embodiment and the χ2 distance calculated based on the above equation (4). FIG. 15 shows temporal changes in index values for the .chi.2 distance shown in FIG. 14 and the weighted .chi.2 distance calculated based on the above equation (5). The index values in FIGS. 14 and 15 are values obtained by dividing the value of each evaluation index (ie, EMD, χ2 distance, weighted χ2 distance) by the maximum possible value of each. If the index value changes by about 0.1 on a daily basis, the change can be said to be steep. Note that the weight was calculated using period data assumed to be in a normal state immediately after repairing the furnace body.

It can be seen from FIG. 14 that the EMD index value increases gently, while the χ2 distance index value tends to rise faster than the EMD index value. By using the χ2 distance as the evaluation index in this way, the index value increases before the engine becomes stuck, and the occurrence of trouble can be detected at an earlier stage by threshold determination, as in the case of using the EMD as the evaluation index. .

Also, FIG. 15 shows that the index value increases at an earlier stage when the weighted .chi.2 distance is used than when the .chi.2 distance is used. In addition, after the index value of the weighted χ2 distance peaked and then decreased slightly, stagnation occurred. Since the weighted χ2 distance can capture changes in observed values with higher sensitivity than the χ2 distance, it is considered that such a tendency of the index value appeared. Based on this tendency, it can be detected that the possibility of trouble occurrence has increased.

From the results of FIGS. 14 and 15, for example, based on using the χ2 distance as an evaluation index, when the χ2 distance sharply increases, the evaluation index is switched to a highly robust EMD value, and the EMD By confirming whether there is a similar increasing trend in

Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, 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 belongs can conceive of various modifications or modifications within the scope of the technical idea described in the claims. It is understood that these also naturally belong to the technical scope of the present invention.

For example, in the above embodiment, Earth Mover's Distance (EMD) or χ2 distance was used as an evaluation index for evaluating the difference between histograms in two different periods, but the present invention is not limited to such examples. For example, a KL information amount, a JS information amount, or the like may be used as an evaluation index.

Further, in the above embodiment, an example of notifying a unit with a high inspection priority determined based on the degree of abnormality of the unit in the output process (S160) has been taken up, but the present invention is not limited to such an example. Instead of or together with the notification information, the operator may be notified of status information indicating changes in the status of the unit to be evaluated. In the example of a coke oven, kiln state information such as information in which evaluation indices are arranged in time series and information in which degrees of abnormality are arranged in time series is notified as the state information. Since this information shows how the kiln condition changes over time, it can be said to be useful information for equipment management support.

Furthermore, in the above embodiment, the information generation unit 150 according to the present embodiment uses a preset threshold value for detecting that the possibility of trouble such as hole breakage or clogging has increased, based on the evaluation index information arranged in chronological order or information arranged in chronological order of the degree of anomaly can be subjected to threshold determination to generate information predicting the occurrence of a trouble. Therefore, in the output process, a unit in which trouble is predicted to occur may be notified based on the result of threshold determination. By performing the threshold determination, in the case of the coke oven, it is possible to prevent the unit from going out of operation due to troubles such as rupture or clogging.

Further, in the above embodiment, the difference between the two histograms is used as an evaluation index representing changes in the state of the evaluation target unit, but the present invention is not limited to such an example. For example, a difference between these histograms calculated by comparing three or more histograms may be used as an evaluation index.

REFERENCE SIGNS LIST 100 Facility management support device 110 Histogram conversion processing unit 120 Evaluation index calculation unit 130 Abnormality degree calculation unit 140 Priority determination unit 150 Information generation unit 160 Output unit 200 Operation performance data storage unit

Claims (9)

One kiln out of a plurality of kilns constituting a coke oven is evaluated, and extrusion load data including the extrusion load for each extrusion position of the evaluation target kiln acquired in a plurality of different periods is used as extrusion load data in the coke oven. a histogram conversion processing unit that converts into a multi-dimensional histogram with position and extrusion load as variables;
an evaluation index calculation unit that calculates an evaluation index representing a difference between the plurality of histograms;
A value given to the evaluation index, which indicates whether the condition of the kiln to be evaluated, which is determined based on the maximum value of the extrusion load or the peak position of the extrusion load, has deteriorated or improved, is defined as the degree of abnormality. An anomaly degree calculation unit that calculates as
a priority determination unit that determines the priority of the kilns that require inspection in descending order of the degree of abnormality calculated for each of the plurality of kilns;
an information generating unit that generates notification information for notifying the operator of the high-priority kiln determined by the priority determination unit;
A facility management support device comprising: 2. The facility management support device according to claim 1, wherein said evaluation index calculation unit calculates said evaluation index using Earth Mover's Distance. 2. The equipment management support device according to claim 1, wherein said evaluation index calculation unit calculates said evaluation index using a χ2 distance. 2. The facility management according to claim 1, wherein said evaluation index calculation unit calculates said evaluation index using a weighted χ2 distance in consideration of a weight calculated based on the distribution of said pushing load for said pushing position for a certain period of time. support equipment. The evaluation index calculation unit combines the Earth Mover's Distance, which is calculated based on the distribution of the pushing load for the pushing position for a certain period, and either the χ2 distance or the weighted χ2 distance considering the weight. 2. The facility management support device according to claim 1, wherein the evaluation index is calculated by The information generation unit performs threshold determination on the information in which the evaluation index is arranged in time series or the information in which the degree of abnormality is arranged in time series, based on a threshold set in advance for detecting the occurrence of trouble in the kiln . 2. The facility management support device according to claim 1 , which performs the above-mentioned operations to generate information predicting trouble occurrence. One kiln out of a plurality of kilns constituting a coke oven is evaluated, and extrusion load data including the extrusion load for each extrusion position of the evaluation target kiln acquired in a plurality of different periods is used as extrusion load data in the coke oven. A histogram conversion processing step for converting the position and the extrusion load into a multi-dimensional histogram with variables;
an evaluation index calculation step of calculating an evaluation index representing a difference between the plurality of histograms;
A value given to the evaluation index, which indicates whether the condition of the kiln to be evaluated, which is determined based on the maximum value of the extrusion load or the peak position of the extrusion load, has deteriorated or improved, is defined as the degree of abnormality. An anomaly degree calculation step calculated as
a priority determination step of determining the priority of the kilns that require inspection in descending order of the degree of abnormality calculated for each of the plurality of kilns;
an information generation step for generating notification information for notifying the operator of the high-priority kiln determined in the priority determination step;
facility management support method. the computer,
One kiln out of a plurality of kilns constituting a coke oven is evaluated, and extrusion load data including the extrusion load for each extrusion position of the evaluation target kiln acquired in a plurality of different periods is used as extrusion load data in the coke oven. a histogram conversion processing unit that converts into a multi-dimensional histogram with position and extrusion load as variables ;
an evaluation index calculation unit that calculates an evaluation index representing a difference between the plurality of histograms;
A value given to the evaluation index, which indicates whether the condition of the kiln to be evaluated, which is determined based on the maximum value of the extrusion load or the peak position of the extrusion load, has deteriorated or improved, is defined as the degree of abnormality. An anomaly degree calculation unit that calculates as
a priority determination unit that determines the priority of the kilns that require inspection in descending order of the degree of abnormality calculated for each of the plurality of kilns;
an information generating unit that generates notification information for notifying the operator of the high-priority kiln determined by the priority determination unit;
A program that functions as a facility management support device. to the computer,
One kiln out of a plurality of kilns constituting a coke oven is evaluated, and extrusion load data including the extrusion load for each extrusion position of the evaluation target kiln acquired in a plurality of different periods is used as extrusion load data in the coke oven. a histogram conversion processing unit that converts into a multi-dimensional histogram with position and extrusion load as variables;
an evaluation index calculation unit that calculates an evaluation index representing a difference between the plurality of histograms;
A value given to the evaluation index, which indicates whether the condition of the kiln to be evaluated, which is determined based on the maximum value of the extrusion load or the peak position of the extrusion load, has deteriorated or improved, is defined as the degree of abnormality. An anomaly degree calculation unit that calculates as
a priority determination unit that determines the priority of the kilns that require inspection in descending order of the degree of abnormality calculated for each of the plurality of kilns;
an information generating unit that generates notification information for notifying the operator of the high-priority kiln determined by the priority determination unit;
A computer-readable recording medium recording a program for functioning as a facility management support device.

Images