JP5867041B2 - Failure prediction system, failure prediction device, and program - Google Patents

Description

  The present invention relates to a failure prediction system, a failure prediction device, and a program.

  For example, in an image forming apparatus that forms and outputs an image on a recording material such as paper, if a failure (including an abnormality, a failure, and a failure) that hinders the operation occurs, inconvenience is caused to the user of the image forming apparatus. It will be. Therefore, the occurrence of such a failure is predicted, and by making it possible to perform necessary measures such as parts replacement and repair immediately before the occurrence of the failure or after the failure has occurred, the use of the image forming apparatus can be improved. It would be desirable to reduce the time for a limited state.

Here, various inventions have been proposed for failure prediction targeting an apparatus such as an image forming apparatus.
For example, an image forming apparatus capable of determining deterioration of a conveyance mechanism, a timing sensor that detects a sheet, a timing sensor control unit that acquires information on a conveyance time required to convey the sheet, and a conveyed sheet A media sensor control unit that acquires thickness information, an environmental sensor control unit that acquires temperature and humidity information, and a temporal deterioration determination unit that determines deterioration of the transport mechanism based on the acquired transport time information An invention has been proposed in which the aging deterioration determination unit changes the determination result of aging deterioration based on the acquired thickness information and temperature and humidity information (see Patent Document 1).

JP 2010-210801 A

  The present invention relates to failure prediction for an apparatus such as an image forming apparatus, and an object thereof is to propose a technique capable of improving the failure prediction accuracy.

The present invention according to claim 1 is an acquisition means for acquiring a parameter indicating an internal state of a target apparatus, a time measurement means for measuring a plurality of types of time elements indicating an operation status of the target apparatus, and the acquisition means. Predicting means for predicting the occurrence of a failure in the target device using the parameters obtained by the above, a plurality of time elements timed by the time measuring means, and the time element affects each time element type. Correction means for performing correction to reduce the degree of contribution in the prediction of the parameter corresponding to the time element indicating the period in which the operation of the target device is estimated to be unstable based on the correspondence table in which the affected parameter is associated ; A failure prediction system characterized by comprising:

According to a second aspect of the present invention, in the first aspect of the present invention, as the plurality of types of time elements, at least one of an operation time of the apparatus, an elapsed time from replacement of consumables, and an elapsed time from replacement of parts The failure prediction system is characterized in that the shorter the time, the higher the instability of the operation of the target device.

According to a third aspect of the present invention, in the present invention according to the first or second aspect , the predicting unit calculates an index value representing a characteristic of the parameter acquired by the acquiring unit, and the calculated index value The occurrence of a failure in the target device is predicted based on the degree of abnormality of the target, and the correction means uses the index value of the period during which the operation of the target device is estimated to be unstable as the instability of the period. The failure prediction system is characterized in that correction is performed in a direction to suppress anomalies using a correction coefficient corresponding to the degree of.

The present invention according to claim 4 is an acquisition unit that acquires a parameter indicating an internal state of the target device, and a prediction unit that predicts the occurrence of a failure in the target device using the parameter acquired by the acquisition unit. And a timing table of a plurality of types of time elements indicating the operation status of the target device, and a correspondence table in which parameters affected by the time element are associated with each type of time element . A failure prediction apparatus comprising: a correction unit that performs correction to reduce a contribution degree in the prediction of a parameter corresponding to a time element indicating a period in which operation is estimated to be unstable.

The present invention according to claim 5 predicts the occurrence of a failure in the target device using an acquisition function for acquiring a parameter indicating the internal state of the target device in the computer and the parameter acquired by the acquisition function. Based on a prediction function to be performed, a time measurement result of a plurality of types of time elements indicating the operation status of the target device, and a correspondence table in which parameters affected by the time elements are associated with each time element type This is a program for realizing a correction function for performing correction for reducing the contribution in the prediction of the parameter corresponding to the time element indicating the period during which the operation of the apparatus is estimated to be unstable.

According to the present invention according to claims 1, 4 , and 5 , failure prediction for an apparatus such as an image forming apparatus can be performed with higher accuracy than when the present invention is not applied.

According to the present invention according to claims 1, 4 and 5 , it is possible to correct the parameters used for failure prediction in consideration of the influence of various time elements on each parameter.

According to the second aspect of the present invention, the degree of operational instability can be estimated effectively.

According to the third aspect of the present invention, correction of parameters used for failure prediction can be performed according to the degree of instability of operation, and the accuracy of failure prediction can be improved.

It is a figure which shows the example of the functional block of the server apparatus in the failure prediction system which concerns on one Embodiment of this invention. It is a figure which shows the example of the setting table of the conversion value of a failure sign parameter | index. It is a figure which shows the example of the setting table of the correction coefficient used for correction | amendment of the conversion value of a failure predictor parameter | index. It is a figure which shows the example of the setting table of the application aspect of correction | amendment with respect to the converted value of a failure symptom index. It is a figure which shows the example of the processing flow regarding the failure prediction by a server apparatus. FIG. 6 is a diagram illustrating an example of a setting table for conversion values of standard deviation of toner density. It is a figure which shows the example of the setting table of the correction coefficient based on continuous operation time. It is a figure which shows the example of conversion and correction | amendment of a failure predictor parameter | index. It is a figure which shows the example of the setting table of the conversion value of the standard deviation of each operation parameter. It is a figure which shows the example of the setting table of the correction coefficient for every time element. It is a figure which shows the example of the setting table which shows a response | compatibility with an operation parameter and a time element.

A failure prediction system according to an embodiment of the present invention will be described with reference to the drawings.
In the failure prediction system of this example, a server device (an example of a failure prediction device according to the present invention) connected to the image forming apparatus so as to be able to communicate with a wired or wireless communication is based on information collected from the image forming apparatus to be monitored. The occurrence of a failure in the image forming apparatus is predicted.

First, an image forming apparatus to be monitored will be described.
The image forming apparatus is an apparatus having an image forming function for forming and outputting an image on a recording material such as paper. Examples of the image forming apparatus include apparatuses such as a printer (document printing apparatus), a copier (document copying apparatus), a facsimile apparatus (document transfer apparatus), and a multi-function apparatus having a combination of functions of these apparatuses. included.

  Here, the image forming apparatus of the present example has a function of detecting an operation parameter value indicating the internal state. This operation parameter is predetermined as a parameter that can contribute to the prediction of failure. For example, during the operation of image forming processing such as toner density, charging voltage, exposure potential, exposure power amount, grid potential, and magroll potential. Examples include parameters that are detected at any time. As the detected value of the motion parameter, a measurement value measured at a part corresponding to the motion parameter may be used, or a target value (set value) set as a target for controlling each part may be used. Other types of values such as the difference between the value and the target value may be used.

  Further, the image forming apparatus of this example has a function of measuring time elements indicating the operation status. This time element is set in advance as a parameter used for adjusting the contribution of the operation parameter when predicting a failure. For example, the operation time of the image forming apparatus (continuous operation time or operation time within the past T time), consumption, and the like. Time elements such as an elapsed time from replacement of a product (for example, toner) and an elapsed time from replacement of a component (for example, a photoreceptor) can be mentioned.

In the image forming apparatus of this example, when a job command for instructing execution of image forming processing relating to one page or a plurality of pages is received, each time an image is formed and output on a sheet according to the job command (each page) Are detected, and after all the image forming processes related to the job command have been completed, the operation state data storing the detected values of the respective operation parameters is transmitted to the server apparatus. Further, in conjunction with the transmission of the operation state data, the time data storing the results measured for each time element is transmitted to the server device.
Note that the operation state data in this example is data having a structure storing a device ID for identifying the own device, detection values of each operation parameter, detection date and time, and the time data in this example is the own device. Data of a structure storing a device ID for identifying the measurement value, a measurement value of each time element, and the like.

  Here, as described above, instead of the configuration in which the operation state data and the time data are transmitted to the server device every time the image forming process based on the job command is completed, these data are temporarily stored in the memory. A configuration may be adopted in which the accumulated untransmitted data is transmitted when a predetermined transmission condition is satisfied. Specifically, for example, the passage of a predetermined time may be used as a transmission condition, and data may be transmitted every passage of the time (for example, every hour). Data may be sent in response to the request. Further, the operation state data and the time data may be transmitted based on different transmission conditions.

Next, the server device will be described.
In the server apparatus of this example, the occurrence of a failure in the image forming apparatus is roughly predicted based on the operation state data and time data collected (received) from the monitored image forming apparatus. Here, the prediction of failure occurrence is performed for each image forming apparatus by identifying each image forming apparatus by the apparatus ID included in the operation state data and the time data.
As shown in FIG. 1, the server device of this example includes a device operation state acquisition unit 1, a device usage status acquisition unit 2, a failure sign index calculation unit 3, a failure sign index correction unit 4, and a failure sign. It has a determination unit 5 and a notification unit 6.

  The apparatus operation state acquisition unit 1 acquires (receives) operation state data from the image forming apparatus to be monitored. The apparatus usage status acquisition unit 2 acquires (receives) time data from the image forming apparatus to be monitored. The data acquired by the device operating state acquisition unit 1 and the device usage status acquisition unit 2 is stored for a period necessary for predicting a failure. For example, when failure prediction is performed using data of the past three months, it is stored for at least three months from the data acquisition time point.

  The failure sign index calculation unit 3 calculates a failure sign index that represents the characteristic of each operation parameter value based on the operation state data (value of each operation parameter) acquired by the apparatus operation state acquisition unit 1. Examples of the failure predictor index include, for example, a variance value (or standard deviation) of each operation parameter value in a predetermined length period, and a time series of two operation parameter values in a predetermined length period. For example, a correlation value of change.

  The failure sign index correction unit 4 corrects the failure sign index calculated by the failure sign index calculation unit 3 based on the time data (value of each time element) acquired by the device usage status acquisition unit 2. In the correction of the failure predictor index, adjustment is made to suppress the abnormality of the failure predictor index during a period in which the operation of the image forming apparatus to be monitored is estimated to be unstable (for example, a period immediately after the start of the image forming apparatus). To do. As an example, when correction is performed by multiplying a failure predictor index by a correction coefficient (0 to 1), a correction coefficient (0 that is smaller for a period during which the operation of the image forming apparatus to be monitored is estimated to be unstable. A correction coefficient (a value close to 1) is used for a period during which the operation of the image forming apparatus to be monitored is estimated to be stable.

  Here, the degree of instability of the operation of the image forming apparatus to be monitored is determined based on the time data (value of each time element) acquired by the apparatus usage status acquisition unit 2. Specifically, for example, it is determined that the instability is higher as the operation time of the image forming apparatus (continuous operation time or operation time within the past T time) is shorter, and consumables (for example, toner) or components (for example, It is determined that the instability is higher as the elapsed time from the replacement of the photosensitive member is shorter.

The correction of the failure sign index by the failure sign index correction unit 4 will be described with reference to FIGS.
FIG. 2 is an example of a setting table for conversion values of the failure predictor index, and is used when the failure predictor index is converted into a mode that can be easily used for failure prediction processing. In the example of FIG. 2, to be converted into constant x ₂ in the case of failure predictor index parameters X (a type of operation parameter) in terms of constant x ₁ when included in the range X _1, are within the scope X _2, in terms of constant y ₁ when failure predictor index parameter Y (a type of operating parameter) is included in the range Y _1, it is converted to a constant y ₂ when included in the range Y _2, parameter Z (operating parameters It is set to convert to a constant z ₁ when _one kind of failure predictor index is included in the range Z _1, and to convert to a constant z ₂ when included in the range Z ₂ .

FIG. 3 is an example of a correction coefficient setting table used for correcting the converted value of the failure predictor index, and is used when correcting the converted value of the failure predictor index. In the example of FIG. 3, the correction coefficient α ₁ is used when the value of the correction index A (a type of time element) is included in the range A ₁ as the correction coefficient to be multiplied by the converted value of the failure predictor index, and is included in the range A ₂ . using the correction coefficient alpha ₂ in the case that, using the correction coefficient alpha ₃ when included in the range a _3, correction index B correction coefficient beta ₁ if the value of (time a kind of element) is included in the range B ₁ , The correction coefficient β ₂ is used when included in the range B ₂ , and the correction coefficient β ₃ is used when included in the range B ₃ .

  FIG. 4 is an example of a setting table of an application mode of correction for the converted value of the failure predictor index, and is used when determining whether or not to correct the converted value of the failure predictor index. In the example of FIG. 4, the converted value of the failure predictor index of parameter X is corrected using the correction coefficient based on correction index A and the correction coefficient based on correction index B, and the converted value of failure predictor index of parameter Y. On the other hand, it is set to perform correction using a correction coefficient based on the correction index A, not to correct the converted value of the failure sign index of the parameter Z, and the like.

In the failure sign index correction unit 4 of this example, the failure sign index calculated by the failure sign index calculation unit 3 is converted with reference to the setting table illustrated in FIG. 2, and a value obtained as a result (failure sign index) Is converted with reference to the time data (value of each time element) acquired by the apparatus usage status acquisition unit 2 and the setting tables illustrated in FIGS. Specifically, for example, the operation parameter X is the range X ₁ , the operation parameter Y is the range Y ₂ , the operation parameter Z is the range Z ₂ , the correction index A is the range A ₁ , and the correction index B is the range B ₂ . In this case, the corrected failure sign index (converted value) x ′ = x ₁ × α ₁ × β ₂ related to the motion parameter X, and the corrected failure sign index (converted value) y ′ = y ₁ × α ₁ , and the corrected failure predictor index (converted value) z ′ = z ₂ related to the operation parameter Z.

  As described above, the failure sign index correction unit 4 of this example converts the failure sign index calculated by the failure sign index calculation unit 3 into a constant, and converts the time data (of each time element) into the converted value (constant). Correction is performed by multiplying by a correction coefficient determined by (value). Here, the failure indication index that is the correction target is an index that represents the characteristic of the value of the operation parameter that indicates the internal state of the image forming apparatus to be monitored. By performing the correction described above, the image formation of the monitoring target is performed. For a period in which the operation of the apparatus is estimated to be unstable, the contribution of the operation parameter in the subsequent failure prediction is reduced. Note that such a correction method is merely an example, and correction may be performed by other methods.

  The failure sign determination unit 5 predicts the occurrence of a failure in the monitored image forming apparatus based on the failure sign index (converted value) corrected by the failure sign index correction unit 4. In this example, the maximum value for each day of the failure sign index (converted value) corrected by the failure sign index correction unit 4 is summed up, and when the total value exceeds a predetermined threshold, the image forming apparatus to be monitored It is determined that there is a sign that a failure will occur in the near future. Note that such a prediction method is merely an example, and failure prediction may be performed by other methods.

  The notification unit 6 notifies the user of the failure prediction system of the prediction result by the failure sign determination unit 5. The notification method is arbitrary. For example, the configuration is such that the information of the prediction result is transmitted to the image forming apparatus to be monitored and displayed on the operation panel provided in the image forming apparatus, or the terminal of the remote center is addressed. The information of the prediction result is transmitted to the image forming apparatus, and the image forming apparatus to be monitored is identified and displayed on the display panel provided in the terminal.

A series of processing relating to failure prediction by the server device of this example will be described with reference to the processing flow illustrated in FIG.
In the server apparatus of this example, the apparatus operation state acquisition unit 1 acquires operation state data (values of each operation parameter) from the image forming apparatus to be monitored (step S1), and the failure sign indicator calculation unit 3 performs apparatus operation. A failure sign index is calculated based on the operation state data acquired by the state acquisition unit 1 (step S2), and the failure sign index correction unit 4 calculates the converted value of the failure sign index calculated by the device operation state acquisition unit 1. Calculate (step S3), and correct the converted value of the failure sign index using a correction coefficient based on the time data (value of each time element) acquired from the image forming apparatus to be monitored by the apparatus usage status acquisition unit 2 ( Step S4).
Thereafter, the failure sign determination unit 5 sums up the maximum value within the same day for the failure sign index (converted value) for each operation parameter after correction by the failure sign index correction unit 4 (step S5), and the total value is determined in advance. The obtained threshold is compared (step S6). As a result, when it is determined that the total value is larger than the threshold value, the notification unit 6 notifies that there is a sign of failure (step S7). On the other hand, the total value is not determined to be larger than the threshold value. In this case, the notification unit 6 notifies that there is no sign of failure (step S8).

The correction of the failure predictor index by the server device of this example will be described with a specific example.
FIG. 6 shows an example of a setting table for conversion values of standard deviation of toner density. According to the example of FIG. 6, it is set to convert to 0 if the standard deviation of the toner density is less than 0.2, and to 1 if it is 0.2 or more.
FIG. 7 shows an example of a correction coefficient setting table based on the continuous operation time. According to the example of FIG. 7, the correction coefficient 0 is used when the continuous operation time of the image forming apparatus is less than 2 hours, and the correction coefficient 1 is used when the image forming apparatus is 2 hours or longer.
In such a setting, even if the standard deviation of the toner density is 0.2 or more and converted to a constant 1, if the continuous operation time of the image forming apparatus is less than 2 hours, a correction coefficient of 0 is multiplied. The standard deviation (converted value) of the corrected toner density is zero. That is, even if some abnormality is observed when the standard deviation of the toner density is 0.2 or more, the operation of the apparatus is in an unstable state because the time has not passed so much since the operation of the image forming apparatus. In this case, correction is performed to reduce the contribution of the standard deviation (converted value) of the toner density in the failure prediction (in this example, to 0).

FIG. 8 shows an example of conversion and correction of the failure predictor index.
In FIG. 8, a1 is a graph showing a time-series transition of a failure predictor index related to parameter A (a kind of operation parameter) on a certain day, and a2 is a failure predictor index (converted value) related to parameter A. ) Is a graph showing a time-series transition, and a3 is a graph showing a time-series transition of the failure predictor index (converted value) related to the parameter A after correction.
According to the graphs a1 to a3, the failure sign index (converted value) for parameter A is 1 at 9 o'clock, indicating that it is in an abnormal state. As a result of the unstable state, a correction for reducing the value (in this example, 0) is performed. As a result, the maximum value of the daily sign of failure indication (converted value) is zero.

In FIG. 8, b1 is a graph showing a time-series transition of the failure predictor index related to the parameter B (a kind of operation parameter) on a certain day, and b2 is a failure predictor index related to the parameter B ( (Converted value) is a graph showing a time-series transition, and b3 is a graph showing a time-series transition of a failure sign indicator (converted value) related to the parameter B after correction.
According to the graphs b1 to b3, the failure predictor index (converted value) related to the parameter B is 1 at 9 o'clock and 14:00, indicating that it is in an abnormal state. The failure predictor index (converted value) is caused by an unstable state immediately after the start of the image forming apparatus, and the failure predictor index (converted value) is reduced (set to 0 in this example) while correction is performed. The failure sign index (converted value) at 14:00 is in a stable state after a certain amount of time has elapsed since the start of the image forming apparatus, and thus correction for reducing the value is not performed. As a result, the maximum daily failure predictive index (converted value) is 1.

Another example of conversion and correction of the failure predictor index will be described.
FIG. 9 shows an example of a setting table for conversion values of standard deviations of the operation parameters. According to the example of FIG. 9, it is set that the standard deviation σ of the operation parameter is converted to 0 if it is less than the threshold value determined for the operation parameter, and is converted to 1 if it is greater than or equal to the threshold value. .
FIG. 10 shows an example of a correction coefficient setting table for each time element. According to the example of FIG. 10, the time elements of the continuous operation time t1 of the image forming apparatus, the operation time t2 within the past two hours, the elapsed time t3 from the toner replacement, and the elapsed time t4 from the photoconductor replacement are respectively shown. It is set that a correction coefficient close to 0 is used as the time is short, and a correction coefficient close to 1 is used as the time is long.

  FIG. 11 shows an example of a setting table indicating correspondence between operation parameters and time elements. Note that “◯” in the setting table of FIG. 11 means that correction based on the corresponding time element is performed, and “X” means that correction based on the corresponding time element is not performed. For example, the failure predictor index (converted value) relating to the measured value of toner density is affected by the time elements of the continuous operation time t1, the operation time t2 within the past 2 hours, and the elapsed time t3 after toner replacement. Therefore, the correction based on these time elements is performed, but on the other hand, since it is not affected by the elapsed time t4 since the photoconductor replacement, it is set that the correction based on this time element is not performed.

Based on such a setting table (FIGS. 9 to 11), for example, processing is performed as follows.
First, for each color component of M (Magenta) color, Y (Yellow) color, C (Cyan) color, and K (Key Plate) color, a toner density measurement value, a toner density setting value (target value), and a charged potential measurement value For each operation parameter of charging potential setting value (target value), exposure potential measurement value, exposure power amount, grid potential measurement value, and magroll potential measurement value, values are acquired for each job command of the image forming process, and multiple times The standard deviation σ is calculated from the value of as a failure predictor index. Then, according to the setting table of FIG. 9, the failure predictor index of each operation parameter is compared with a threshold value for each operation parameter, and is converted to 0 when it is less than the threshold value and to 1 when it is greater than or equal to the threshold value.

Thereafter, a time element used for correcting the failure predictor index (converted value) is specified for each operation parameter according to the setting table of FIG. 10, and the failure predictor index is determined based on the specified time element according to the setting table of FIG. (Conversion value) is corrected.
In this example, the operation parameters to be corrected based on the continuous operation time t1 of the image forming apparatus and the operation time t2 within the past two hours are the toner density measurement value, the charge potential measurement value, the charge potential setting value, and the exposure potential measurement value. The operation parameter that becomes the grid potential measurement value and corrects based on the elapsed time t3 from the toner replacement is the toner density measurement value, and the operation parameter that corrects based on the elapsed time t4 from the photoconductor replacement is the charged potential. The measured value, charged potential setting value, exposure potential measured value, grid potential measured value, and other operating parameters are not corrected.

  That is, when the time elements such as the continuous operation time t1 of the image forming apparatus, the operation time t2 within the past two hours, the elapsed time t3 from the toner replacement, and the elapsed time t4 from the photoconductor replacement are short, for example, the toner is the toner It is presumed that the operation of the image forming apparatus is unstable due to factors such as being easily mixed and not being mixed in the container, and having a small number of cleanings in the image forming process and a non-uniform photoreceptor surface. By correcting the operation parameter that is likely to take an abnormal value temporarily in a short period, it is possible to prevent the failure prediction accuracy from being lowered due to the abnormal value that temporarily occurs.

  As described above, in the failure prediction system of this example, the server apparatus acquires (receives) the operation state data and the time data from the image forming apparatus to be monitored by the apparatus operation state acquisition unit 1 and the device usage state acquisition unit 2. Then, the failure sign indicator calculation unit 3 calculates a failure sign index representing the characteristic of each operation parameter value based on the operation state data (value of each operation parameter), and the failure sign indicator correction unit 4 calculates the failure sign. After the conversion of the index, correction that reduces the contribution in the failure prediction for the period when the operation of the image forming apparatus to be monitored is estimated to be unstable based on the time data (value of each time element) The failure sign determination unit 5 predicts the occurrence of a failure in the monitored image forming apparatus based on the corrected failure sign index (converted value), and the notification unit 6 And to notify the measurement result to the user.

  In this example, the failure sign index (converted value) calculated based on the value of each operation parameter is corrected. However, the effect of parameter abnormality on failure prediction during a period when the operation of the image forming apparatus is unstable. For example, the operation parameter value itself may be corrected.

  Here, the server device in the failure prediction system of the present example is a CPU (Central Processing Unit) that performs various arithmetic processing, a RAM (Random Access Memory) that is a work area of the CPU, a ROM that records a basic control program, and the like ( Main storage device such as Read Only Memory), auxiliary storage device such as HDD (Hard Disk Drive) that stores various programs and data, display device for displaying and outputting various information, and used for input operations by the operator Consists of a computer having hardware resources such as an input / output I / F that is an interface with an input device such as an operation button or a touch panel, and a communication I / F that is an interface for performing wired or wireless communication with other devices. Been Yes.

Then, the program according to the present invention is read from the auxiliary storage device or the like, loaded into the RAM, and executed by the CPU, thereby realizing the function of the failure prediction device according to the present invention on the computer of the server device.
That is, the function of the acquisition unit according to the present invention is realized by the apparatus operating state acquisition unit 1, and the function of the prediction unit according to the present invention is realized by the failure sign indicator calculation unit 3 and the failure sign determination unit 5. The function of the correction means is realized by the device usage status acquisition unit 2 and the failure sign index correction unit 4. The function of the time measuring means according to the present invention is provided in the image forming apparatus to be monitored.
Here, the functional units 1 to 5 may be provided in the image forming apparatus, and the failure prediction may be performed by the image forming apparatus alone.

  In addition, an apparatus other than the image forming apparatus may be the target of failure prediction. That is, in a configuration in which a failure occurrence prediction in the target device is performed using a parameter indicating the internal state of the device (a parameter that can contribute to the prediction of the failure), a time element indicating the operation status of the device (operation anxiety) (Time element that can estimate qualitative), and based on the result, correction is performed to reduce the contribution of parameters in failure prediction for the period when the operation of the device is estimated to be unstable Thus, it is possible to suppress the failure prediction accuracy from being lowered due to a parameter abnormality caused by the instability of the operation of the device.

Here, the program according to the present invention is set in the computer according to the present example by, for example, a format read from an external storage medium such as a CD-ROM storing the program or a format received via a communication network. The
Note that the present invention is not limited to a mode in which each functional unit is realized by a software configuration as in this example, and each functional unit may be realized by a dedicated hardware module.

  1: device operating state acquisition unit, 2: device usage status acquisition unit, 3: failure sign indicator calculation unit, 4: failure sign indicator correction unit, 5: failure sign determination unit, 6: notification unit

Claims (5)

Acquisition means for acquiring a parameter indicating an internal state of the target device;
Clocking means for clocking a plurality of types of time elements indicating the operation status of the target device;
Predicting means for predicting the occurrence of a failure in the target device, using the parameters acquired by the acquiring means;
Based on a plurality of types of time elements timed by the time measuring means and a correspondence table in which parameters affected by the time elements are associated with each time element type , the operation of the target device is estimated to be unstable. Correction means for performing correction to reduce the contribution in the prediction of the parameter corresponding to the time element representing the period of
A failure prediction system comprising: As the plurality of types of time elements, one or more of the operation time of the apparatus, the elapsed time from replacement of consumables, and the elapsed time from replacement of parts are used. The shorter the time, the more unstable the operation of the target apparatus. Is estimated to be high,
The failure prediction system according to claim 1 . The predicting unit calculates an index value representing the characteristics of the parameter acquired by the acquiring unit, predicts the occurrence of a failure in the target device based on the degree of abnormality of the calculated index value,
The correction means corrects the index value during a period in which the operation of the target device is estimated to be unstable using a correction coefficient corresponding to the degree of instability in the period in a direction to suppress anomalies.
The failure prediction system according to claim 1 or claim 2 , characterized by that. Acquisition means for acquiring a parameter indicating an internal state of the target device;
Predicting means for predicting the occurrence of a failure in the target device, using the parameters acquired by the acquiring means;
Based on the time measurement results of a plurality of types of time elements indicating the operation status of the target device and the correspondence table in which the parameters affected by the time elements are associated with each type of time element, the operation of the target device is Correction means for performing correction to reduce the contribution in the prediction of the parameter corresponding to the time element representing the period estimated to be unstable;
A failure prediction apparatus comprising: On the computer,
An acquisition function for acquiring a parameter indicating the internal state of the target device;
A prediction function that predicts the occurrence of a failure in the target device using the parameters acquired by the acquisition function;
Based on the time measurement results of a plurality of types of time elements indicating the operation status of the target device and the correspondence table in which the parameters affected by the time elements are associated with each type of time element, the operation of the target device is A correction function for performing correction to reduce the contribution in the prediction of the parameter corresponding to the time element representing the period estimated to be unstable;
A program to realize

Images